summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--gcc/ChangeLog549
-rw-r--r--gcc/config.gcc14
-rw-r--r--gcc/config/i386/avx512cdintrin.h219
-rw-r--r--gcc/config/i386/avx512erintrin.h333
-rw-r--r--gcc/config/i386/avx512fintrin.h12147
-rw-r--r--gcc/config/i386/avx512pfintrin.h130
-rw-r--r--gcc/config/i386/i386-builtin-types.def259
-rw-r--r--gcc/config/i386/i386.c1745
-rw-r--r--gcc/config/i386/immintrin.h8
-rw-r--r--gcc/testsuite/ChangeLog30
-rw-r--r--gcc/testsuite/gcc.target/i386/avx-1.c175
-rw-r--r--gcc/testsuite/gcc.target/i386/sse-22.c424
-rw-r--r--gcc/testsuite/gcc.target/i386/sse-23.c175
13 files changed, 16150 insertions, 58 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 1bb86a88fc9..be9476cae0d 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -8,6 +8,555 @@
Kirill Yukhin <kirill.yukhin@intel.com>
Michael Zolotukhin <michael.v.zolotukhin@intel.com>
+ * config.gcc (extra_headers): Add avx512fintrin.h, avx512cdintrin.h,
+ avx512erintrin.h, avx512pfintrin.h.
+ * config/i386/avx512cdintrin.h: New file.
+ * config/i386/avx512erintrin.h: New file.
+ * config/i386/avx512fintrin.h: New file.
+ * config/i386/avx512pfintrin.h: New file.
+ * config/i386/i386-builtin-types.def: Add V16UHI, V32SF, V16SF, V8DF,
+ V8DI, V16SI, V64QI, PV8DF, PV8DI, PV16SI, PV16SF, PCV8DF, PCV16SF,
+ PCV8DI, PCV16SI, V16QI_FTYPE_V16SI, V8DF_FTYPE_V8SI, V8DF_FTYPE_V8DF,
+ V8HI_FTYPE_V8DI, V16SF_FTYPE_V16SF, V8SI_FTYPE_V8DI, V8SF_FTYPE_V8DF,
+ V8SF_FTYPE_V8DF_V8SF_QI, V16HI_FTYPE_V16SI, V16SF_FTYPE_FLOAT,
+ V16SI_FTYPE_INT, V8DF_FTYPE_DOUBLE, V8DI_FTYPE_INT64,
+ V16SF_FTYPE_V4SF, V8DF_FTYPE_V4DF, V8DI_FTYPE_V4DI, V16QI_FTYPE_V8DI,
+ UINT_FTYPE_V4SF, UINT64_FTYPE_V4SF, UINT_FTYPE_V2DF,
+ UINT64_FTYPE_V2DF, V16SI_FTYPE_V16SI, V16SI_FTYPE_V16SI_V16SI_HI,
+ V8DI_FTYPE_V8DI, V8DI_FTYPE_V8DI_V8DI_QI, V16SI_FTYPE_PV4SI,
+ V16SF_FTYPE_PV4SF, V8DI_FTYPE_PV4DI, V8DF_FTYPE_PV4DF,
+ V8UHI_FTYPE_V8UHI, V8USI_FTYPE_V8USI, V2DF_FTYPE_V2DF_UINT,
+ V2DF_FTYPE_V2DF_UINT64, V4DF_FTYPE_V8DF_INT,
+ V4DF_FTYPE_V8DF_INT_V4DF_QI, V8DF_FTYPE_V8DF_V8DI,
+ V4SF_FTYPE_V4SF_UINT, V4SF_FTYPE_V4SF_UINT64,
+ INT_FTYPE_V4SF_V4SF_INT_INT, INT_FTYPE_V2DF_V2DF_INT_INT,
+ V16SF_FTYPE_V16SF_INT, V4SF_FTYPE_V16SF_INT,
+ V4SF_FTYPE_V16SF_INT_V4SF_QI, V16SF_FTYPE_V16SF_V16SF,
+ V16SF_FTYPE_V16SF_V16SI, V8DF_FTYPE_V8DF_V4DF_INT_V8DF_QI,
+ V8DF_FTYPE_V8DF_V8DF_INT_V8DF_QI, V8DF_FTYPE_V8DF_INT_V8DF_QI,
+ V8DF_FTYPE_V8DF_V8DF_V8DI_INT_QI_INT, V8DF_FTYPE_V8DF_V8DF,
+ V16SF_FTYPE_V16SF_V16SF_INT, V16SF_FTYPE_V16SF_V16SF_INT_V16SF_HI,
+ V16SF_FTYPE_V16SF_INT_V16SF_HI, V16SI_FTYPE_V16SI_V4SI_INT_V16SI_HI,
+ V16SF_FTYPE_V16SF_V16SF_V16SI_INT,
+ V16SF_FTYPE_V16SF_V16SF_V16SI_INT_HI,
+ V16SF_FTYPE_V16SF_V16SF_V16SI_INT_HI_INT,
+ V4SF_FTYPE_V4SF_V4SF_V4SI_INT_QI,
+ V4SF_FTYPE_V4SF_V4SF_V4SI_INT_QI_INT,
+ V2DF_FTYPE_V2DF_V2DF_V2DI_INT_QI,
+ V2DF_FTYPE_V2DF_V2DF_V2DI_INT_QI_INT, V16SF_FTYPE_V16SF_V4SF_INT,
+ V16SF_FTYPE_V16SF_V4SF_INT_V16SF_HI, V16HI_FTYPE_V16SF_INT,
+ V16HI_FTYPE_V16SF_INT_V16HI_HI, V16HI_FTYPE_V16HI_V16HI_INT_V16HI_HI,
+ V16SI_FTYPE_V16SI_V4SI, V16SI_FTYPE_V16SI_V4SI_INT,
+ V4SI_FTYPE_V16SI_INT, V4SI_FTYPE_V16SI_INT_V4SI_QI,
+ V16SI_FTYPE_V16SI_V16SI, V16SI_FTYPE_V16SI_V16SI_INT_V16SI_HI,
+ V16SI_FTYPE_V16SI_SI, V16SI_FTYPE_V16SI_INT,
+ V16SI_FTYPE_V16SI_V4SI_V16SI_HI, V16SI_FTYPE_V16SI_INT_V16SI_HI,
+ V8DI_FTYPE_V8DI_V8DI, V16SI_FTYPE_V8DF_V8DF,
+ V8DI_FTYPE_V8DI_V8DI_INT_V8DI_QI, V8DI_FTYPE_V8DI_V4DI_INT_V8DI_QI,
+ V8DI_FTYPE_V8DI_V2DI, V4DI_FTYPE_V8DI_INT,
+ V4DI_FTYPE_V8DI_INT_V4DI_QI, V8DI_FTYPE_V8DI_V2DI_V8DI_QI,
+ V8DI_FTYPE_V8DI_INT_V8DI_QI, VOID_FTYPE_PDOUBLE_V8DF,
+ VOID_FTYPE_PFLOAT_V16SF, VOID_FTYPE_PV8DI_V8DI, HI_FTYPE_HI,
+ HI_FTYPE_HI_HI, HI_FTYPE_HI_INT, QI_FTYPE_V8DI_V8DI,
+ QI_FTYPE_V8DI_V8DI_QI, HI_FTYPE_V16SI_V16SI, HI_FTYPE_V16SI_V16SI_HI,
+ QI_FTYPE_V8DI_V8DI_INT, QI_FTYPE_V8DI_V8DI_INT_QI,
+ HI_FTYPE_V16SI_V16SI_INT, HI_FTYPE_V16SI_V16SI_INT ,HI,
+ QI_FTYPE_V8DF_V8DF_INT, QI_FTYPE_V8DF_V8DF_INT_QI,
+ QI_FTYPE_V8DF_V8DF_INT_QI_INT, HI_FTYPE_V16SF_V16SF_INT,
+ HI_FTYPE_V16SF_V16SF_INT_HI, HI_FTYPE_V16SF_V16SF_INT_HI_INT,
+ QI_FTYPE_V2DF_V2DF_INT, QI_FTYPE_V2DF_V2DF_INT_QI,
+ QI_FTYPE_V2DF_V2DF_INT_QI_INT, QI_FTYPE_V4SF_V4SF_INT,
+ QI_FTYPE_V4SF_V4SF_INT_QI, QI_FTYPE_V4SF_V4SF_INT_QI_INT,
+ V16SI_FTYPE_HI, V8DI_FTYPE_QI, V8DF_FTYPE_V8DF_V8DF_V8DF,
+ V16SF_FTYPE_V16SF_V16SF_V16SF, V8DF_FTYPE_V8DF_V8DF_QI,
+ V8DF_FTYPE_V8SF_V8DF_QI, V8DF_FTYPE_V8SI_V8DF_QI,
+ V8DI_FTYPE_V8SI_V8DI_QI, V8DI_FTYPE_V8HI_V8DI_QI,
+ V8DI_FTYPE_V16QI_V8DI_QI, V8DI_FTYPE_V8DI_V8DI_V8DI_QI,
+ V8DF_FTYPE_V8DI_V8DF_V8DF, V8DF_FTYPE_V8DI_V8DF_V8DF_QI,
+ V8DF_FTYPE_V8DF_V8DI_V8DF_QI, V8DF_FTYPE_V8DF_V8DF_V8DF_QI,
+ V16SI_FTYPE_V16SI_V16SI_V16SI_HI, V2DF_FTYPE_V2DF_V2DF_V2DF_QI,
+ V2DF_FTYPE_V2DF_V4SF_V2DF_QI, V16SF_FTYPE_V16SF_V16SF_HI,
+ V16SF_FTYPE_V16SI_V16SF_HI, V16SF_FTYPE_V16SF_V16SF_V16SF_HI,
+ V16SF_FTYPE_V16SI_V16SF_V16SF, V16SF_FTYPE_V16SI_V16SF_V16SF_HI,
+ V16SF_FTYPE_V16SF_V16SI_V16SF_HI, V4SF_FTYPE_V4SF_V2DF_V4SF_QI,
+ V4SF_FTYPE_V4SF_V4SF_V4SF_QI, V16SF_FTYPE_V4SF_V16SF_HI,
+ V8DF_FTYPE_V4DF_V8DF_QI, V8DF_FTYPE_V2DF_V8DF_QI,
+ V16SI_FTYPE_V4SI_V16SI_HI, V16SI_FTYPE_SI_V16SI_HI,
+ V16SI_FTYPE_V16HI_V16SI_HI, V16SI_FTYPE_V16QI_V16SI_HI,
+ V8SI_FTYPE_V8DF_V8SI_QI, V8DI_FTYPE_V4DI_V8DI_QI,
+ V8DI_FTYPE_V2DI_V8DI_QI, V8DI_FTYPE_DI_V8DI_QI,
+ V16SF_FTYPE_PCV16SF_V16SF_HI, V8DF_FTYPE_PCV8DF_V8DF_QI,
+ V16SI_FTYPE_PCV16SI_V16SI_HI, V8DI_FTYPE_PCV8DI_V8DI_QI,
+ V2DF_FTYPE_PCDOUBLE_V2DF_QI, V4SF_FTYPE_PCFLOAT_V4SF_QI,
+ V16QI_FTYPE_V16SI_V16QI_HI, V16HI_FTYPE_V16SI_V16HI_HI,
+ V8SI_FTYPE_V8DI_V8SI_QI, V8HI_FTYPE_V8DI_V8HI_QI,
+ V16QI_FTYPE_V8DI_V16QI_QI, VOID_FTYPE_PV8DF_V8DF_QI,
+ VOID_FTYPE_PV16SF_V16SF_HI, VOID_FTYPE_PV8DI_V8DI_QI,
+ VOID_FTYPE_PV16SI_V16SI_HI, VOID_FTYPE_PDOUBLE_V2DF_QI,
+ VOID_FTYPE_PFLOAT_V4SF_QI, V16SI_FTYPE_V16SF_V16SI_HI,
+ V8DI_FTYPE_V8DI_V8DI_V8DI_INT_QI,
+ V16SI_FTYPE_V16SI_V16SI_V16SI_INT_HI, V8DI_FTYPE_V8DI_V8DI_V8DI,
+ V16SI_FTYPE_V16SI_V16SI_V16SI, V8DF_FTYPE_V8DF_V8DI_V8DF,
+ V16SF_FTYPE_V16SF_V16SI_V16SF, V4SF_FTYPE_V4SF_V4SF_INT_V4SF_QI,
+ V2DF_FTYPE_V2DF_V2DF_INT_V2DF_QI, V8DI_FTYPE_V16SI_V16SI_V8DI_QI,
+ UINT64_FTYPE_V2DF_INT, UINT64_FTYPE_V4SF_INT, UINT_FTYPE_V2DF_INT,
+ UINT_FTYPE_V4SF_INT, INT64_FTYPE_V2DF_INT, INT64_FTYPE_V4SF_INT,
+ INT_FTYPE_V2DF_INT, INT_FTYPE_V4SF_INT, V2DF_FTYPE_V2DF_UINT64_INT,
+ V4SF_FTYPE_V4SF_UINT64_INT, V4SF_FTYPE_V4SF_UINT_INT,
+ V2DF_FTYPE_V2DF_INT64_INT, V4SF_FTYPE_V4SF_INT64_INT,
+ V4SF_FTYPE_V4SF_INT_INT, V16SI_FTYPE_V16SF_V16SI_HI_INT,
+ V16SF_FTYPE_V16SI_V16SF_HI_INT, V16SF_FTYPE_V16SF_V16SF_HI_INT,
+ V16SF_FTYPE_V16HI_V16SF_HI_INT, V8SI_FTYPE_V8DF_V8SI_QI_INT,
+ V8SF_FTYPE_V8DF_V8SF_QI_INT, V8DF_FTYPE_V8DF_V8DF_QI_INT,
+ V8DF_FTYPE_V8SF_V8DF_QI_INT, V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT,
+ V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT, V4SF_FTYPE_V4SF_V4SF_V4SF_QI_INT,
+ V4SF_FTYPE_V4SF_V2DF_V4SF_QI_INT, V2DF_FTYPE_V2DF_V2DF_V2DF_QI_INT,
+ V2DF_FTYPE_V2DF_V4SF_V2DF_QI_INT, V2DF_FTYPE_V2DF_V2DF_V2DF_INT,
+ V16SF_FTYPE_V16SF_INT_V16SF_HI_INT, V8DF_FTYPE_V8DF_INT_V8DF_QI_INT,
+ V4SF_FTYPE_V4SF_V4SF_INT_V4SF_QI_INT,
+ V2DF_FTYPE_V2DF_V2DF_INT_V2DF_QI_INT, V8DI_FTYPE_V8DI_SI_V8DI_V8DI,
+ V16SF_FTYPE_V16SF_PCFLOAT_V16SI_HI_INT,
+ V16SF_FTYPE_V16SF_PCFLOAT_V8DI_HI_INT,
+ V8DF_FTYPE_V8DF_PCDOUBLE_V8SI_QI_INT,
+ V8DF_FTYPE_V8DF_PCDOUBLE_V16SI_QI_INT,
+ V8SF_FTYPE_V8SF_PCFLOAT_V8DI_QI_INT,
+ V8DF_FTYPE_V8DF_PCDOUBLE_V8DI_QI_INT,
+ V16SI_FTYPE_V16SI_PCINT_V16SI_HI_INT,
+ V16SI_FTYPE_V16SI_PCINT_V8DI_HI_INT,
+ V8DI_FTYPE_V8DI_PCINT64_V8SI_QI_INT,
+ V8DI_FTYPE_V8DI_PCINT64_V16SI_QI_INT,
+ V8SI_FTYPE_V8SI_PCINT_V8DI_QI_INT,
+ V8DI_FTYPE_V8DI_PCINT64_V8DI_QI_INT,
+ VOID_FTYPE_PFLOAT_HI_V16SI_V16SF_INT,
+ VOID_FTYPE_PDOUBLE_QI_V8SI_V8DF_INT,
+ VOID_FTYPE_PFLOAT_QI_V8DI_V8SF_INT,
+ VOID_FTYPE_PDOUBLE_QI_V8DI_V8DF_INT,
+ VOID_FTYPE_PINT_HI_V16SI_V16SI_INT,
+ VOID_FTYPE_PLONGLONG_QI_V8SI_V8DI_INT,
+ VOID_FTYPE_PINT_QI_V8DI_V8SI_INT,
+ VOID_FTYPE_PLONGLONG_QI_V8DI_V8DI_INT,
+ VOID_FTYPE_HI_V16SI_PCINT_INT_INT, VOID_FTYPE_QI_V8DI_PCINT_INT_INT.
+ (ALIAS): Add DEF_FUNCTION_TYPE_ALIAS (V16SI_FTYPE_V8DF_V8DF, ROUND).
+ * config/i386/i386.c (enum ix86_builtins): Add IX86_BUILTIN_ADDPD512,
+ IX86_BUILTIN_ADDPS512, IX86_BUILTIN_ADDSD_MASK,
+ IX86_BUILTIN_ADDSS_MASK, IX86_BUILTIN_ALIGND512,
+ IX86_BUILTIN_ALIGNQ512, IX86_BUILTIN_BLENDMD512,
+ IX86_BUILTIN_BLENDMPD512, IX86_BUILTIN_BLENDMPS512,
+ IX86_BUILTIN_BLENDMQ512, IX86_BUILTIN_BROADCASTF32X4_512,
+ IX86_BUILTIN_BROADCASTF64X4_512, IX86_BUILTIN_BROADCASTI32X4_512,
+ IX86_BUILTIN_BROADCASTI64X4_512, IX86_BUILTIN_BROADCASTSD512,
+ IX86_BUILTIN_BROADCASTSS512, IX86_BUILTIN_CMPD512,
+ IX86_BUILTIN_CMPPD512, IX86_BUILTIN_CMPPS512, IX86_BUILTIN_CMPQ512,
+ IX86_BUILTIN_CMPSD_MASK, IX86_BUILTIN_CMPSS_MASK, IX86_BUILTIN_COMIDF,
+ IX86_BUILTIN_COMISF, IX86_BUILTIN_COMPRESSPD512,
+ IX86_BUILTIN_COMPRESSPDSTORE512, IX86_BUILTIN_COMPRESSPS512,
+ IX86_BUILTIN_COMPRESSPSSTORE512, IX86_BUILTIN_CVTDQ2PD512,
+ IX86_BUILTIN_CVTDQ2PS512, IX86_BUILTIN_CVTPD2DQ512,
+ IX86_BUILTIN_CVTPD2PS512, IX86_BUILTIN_CVTPD2UDQ512,
+ IX86_BUILTIN_CVTPH2PS512, IX86_BUILTIN_CVTPS2DQ512,
+ IX86_BUILTIN_CVTPS2PD512, IX86_BUILTIN_CVTPS2PH512,
+ IX86_BUILTIN_CVTPS2UDQ512, IX86_BUILTIN_CVTSD2SS_MASK,
+ IX86_BUILTIN_CVTSI2SD64, IX86_BUILTIN_CVTSI2SS32,
+ IX86_BUILTIN_CVTSI2SS64, IX86_BUILTIN_CVTSS2SD_MASK,
+ IX86_BUILTIN_CVTTPD2DQ512, IX86_BUILTIN_CVTTPD2UDQ512,
+ IX86_BUILTIN_CVTTPS2DQ512, IX86_BUILTIN_CVTTPS2UDQ512,
+ IX86_BUILTIN_CVTUDQ2PD512, IX86_BUILTIN_CVTUDQ2PS512,
+ IX86_BUILTIN_CVTUSI2SD32, IX86_BUILTIN_CVTUSI2SD64,
+ IX86_BUILTIN_CVTUSI2SS32, IX86_BUILTIN_CVTUSI2SS64,
+ IX86_BUILTIN_DIVPD512, IX86_BUILTIN_DIVPS512, IX86_BUILTIN_DIVSD_MASK,
+ IX86_BUILTIN_DIVSS_MASK, IX86_BUILTIN_EXPANDPD512,
+ IX86_BUILTIN_EXPANDPD512Z, IX86_BUILTIN_EXPANDPDLOAD512,
+ IX86_BUILTIN_EXPANDPDLOAD512Z, IX86_BUILTIN_EXPANDPS512,
+ IX86_BUILTIN_EXPANDPS512Z, IX86_BUILTIN_EXPANDPSLOAD512,
+ IX86_BUILTIN_EXPANDPSLOAD512Z, IX86_BUILTIN_EXTRACTF32X4,
+ IX86_BUILTIN_EXTRACTF64X4, IX86_BUILTIN_EXTRACTI32X4,
+ IX86_BUILTIN_EXTRACTI64X4, IX86_BUILTIN_FIXUPIMMPD512_MASK,
+ IX86_BUILTIN_FIXUPIMMPD512_MASKZ, IX86_BUILTIN_FIXUPIMMPS512_MASK,
+ IX86_BUILTIN_FIXUPIMMPS512_MASKZ, IX86_BUILTIN_FIXUPIMMSD128_MASK,
+ IX86_BUILTIN_FIXUPIMMSD128_MASKZ, IX86_BUILTIN_FIXUPIMMSS128_MASK,
+ IX86_BUILTIN_FIXUPIMMSS128_MASKZ, IX86_BUILTIN_GETEXPPD512,
+ IX86_BUILTIN_GETEXPPS512, IX86_BUILTIN_GETEXPSD128,
+ IX86_BUILTIN_GETEXPSS128, IX86_BUILTIN_GETMANTPD512,
+ IX86_BUILTIN_GETMANTPS512, IX86_BUILTIN_GETMANTSD128,
+ IX86_BUILTIN_GETMANTSS128, IX86_BUILTIN_INSERTF32X4,
+ IX86_BUILTIN_INSERTF64X4, IX86_BUILTIN_INSERTI32X4,
+ IX86_BUILTIN_INSERTI64X4, IX86_BUILTIN_LOADAPD512,
+ IX86_BUILTIN_LOADAPS512, IX86_BUILTIN_LOADDQUDI512,
+ IX86_BUILTIN_LOADDQUSI512, IX86_BUILTIN_LOADSD, IX86_BUILTIN_LOADSS,
+ IX86_BUILTIN_LOADUPD512, IX86_BUILTIN_LOADUPS512,
+ IX86_BUILTIN_MAXPD512, IX86_BUILTIN_MAXPS512, IX86_BUILTIN_MAXSD_MASK,
+ IX86_BUILTIN_MAXSS_MASK, IX86_BUILTIN_MINPD512, IX86_BUILTIN_MINPS512,
+ IX86_BUILTIN_MINSD_MASK, IX86_BUILTIN_MINSS_MASK,
+ IX86_BUILTIN_MOVAPD512, IX86_BUILTIN_MOVAPS512,
+ IX86_BUILTIN_MOVDDUP512, IX86_BUILTIN_MOVDQA32LOAD512,
+ IX86_BUILTIN_MOVDQA32STORE512, IX86_BUILTIN_MOVDQA32_512,
+ IX86_BUILTIN_MOVDQA64LOAD512, IX86_BUILTIN_MOVDQA64STORE512,
+ IX86_BUILTIN_MOVDQA64_512, IX86_BUILTIN_MOVESD, IX86_BUILTIN_MOVESS,
+ IX86_BUILTIN_MOVNTDQ512, IX86_BUILTIN_MOVNTPD512,
+ IX86_BUILTIN_MOVNTPS512, IX86_BUILTIN_MOVSHDUP512,
+ IX86_BUILTIN_MOVSLDUP512, IX86_BUILTIN_MULPD512,
+ IX86_BUILTIN_MULPS512, IX86_BUILTIN_MULSD_MASK,
+ IX86_BUILTIN_MULSS_MASK, IX86_BUILTIN_PABSD512, IX86_BUILTIN_PABSQ512,
+ IX86_BUILTIN_PADDD512, IX86_BUILTIN_PADDQ512, IX86_BUILTIN_PANDD512,
+ IX86_BUILTIN_PANDND512, IX86_BUILTIN_PANDNQ512, IX86_BUILTIN_PANDQ512,
+ IX86_BUILTIN_PBROADCASTD512, IX86_BUILTIN_PBROADCASTD512_GPR,
+ IX86_BUILTIN_PBROADCASTMB512, IX86_BUILTIN_PBROADCASTMW512,
+ IX86_BUILTIN_PBROADCASTQ512, IX86_BUILTIN_PBROADCASTQ512_GPR,
+ IX86_BUILTIN_PBROADCASTQ512_MEM, IX86_BUILTIN_PCMPEQD512_MASK,
+ IX86_BUILTIN_PCMPEQQ512_MASK, IX86_BUILTIN_PCMPGTD512_MASK,
+ IX86_BUILTIN_PCMPGTQ512_MASK, IX86_BUILTIN_PCOMPRESSD512,
+ IX86_BUILTIN_PCOMPRESSDSTORE512, IX86_BUILTIN_PCOMPRESSQ512,
+ IX86_BUILTIN_PCOMPRESSQSTORE512, IX86_BUILTIN_PEXPANDD512,
+ IX86_BUILTIN_PEXPANDD512Z, IX86_BUILTIN_PEXPANDDLOAD512,
+ IX86_BUILTIN_PEXPANDDLOAD512Z, IX86_BUILTIN_PEXPANDQ512,
+ IX86_BUILTIN_PEXPANDQ512Z, IX86_BUILTIN_PEXPANDQLOAD512,
+ IX86_BUILTIN_PEXPANDQLOAD512Z, IX86_BUILTIN_PMAXSD512,
+ IX86_BUILTIN_PMAXSQ512, IX86_BUILTIN_PMAXUD512,
+ IX86_BUILTIN_PMAXUQ512, IX86_BUILTIN_PMINSD512,
+ IX86_BUILTIN_PMINSQ512, IX86_BUILTIN_PMINUD512,
+ IX86_BUILTIN_PMINUQ512, IX86_BUILTIN_PMOVDB512,
+ IX86_BUILTIN_PMOVDW512, IX86_BUILTIN_PMOVQB512,
+ IX86_BUILTIN_PMOVQD512, IX86_BUILTIN_PMOVQW512,
+ IX86_BUILTIN_PMOVSDB512, IX86_BUILTIN_PMOVSDW512,
+ IX86_BUILTIN_PMOVSQB512, IX86_BUILTIN_PMOVSQD512,
+ IX86_BUILTIN_PMOVSQW512, IX86_BUILTIN_PMOVSXBD512,
+ IX86_BUILTIN_PMOVSXBQ512, IX86_BUILTIN_PMOVSXDQ512,
+ IX86_BUILTIN_PMOVSXWD512, IX86_BUILTIN_PMOVSXWQ512,
+ IX86_BUILTIN_PMOVUSDB512, IX86_BUILTIN_PMOVUSDW512,
+ IX86_BUILTIN_PMOVUSQB512, IX86_BUILTIN_PMOVUSQD512,
+ IX86_BUILTIN_PMOVUSQW512, IX86_BUILTIN_PMOVZXBD512,
+ IX86_BUILTIN_PMOVZXBQ512, IX86_BUILTIN_PMOVZXDQ512,
+ IX86_BUILTIN_PMOVZXWD512, IX86_BUILTIN_PMOVZXWQ512,
+ IX86_BUILTIN_PMULDQ512, IX86_BUILTIN_PMULLD512,
+ IX86_BUILTIN_PMULUDQ512, IX86_BUILTIN_PORD512, IX86_BUILTIN_PORQ512,
+ IX86_BUILTIN_PROLD512, IX86_BUILTIN_PROLQ512, IX86_BUILTIN_PROLVD512,
+ IX86_BUILTIN_PROLVQ512, IX86_BUILTIN_PRORD512, IX86_BUILTIN_PRORQ512,
+ IX86_BUILTIN_PRORVD512, IX86_BUILTIN_PRORVQ512,
+ IX86_BUILTIN_PSHUFD512, IX86_BUILTIN_PSLLD512, IX86_BUILTIN_PSLLDI512,
+ IX86_BUILTIN_PSLLQ512, IX86_BUILTIN_PSLLQI512,
+ IX86_BUILTIN_PSLLVV16SI, IX86_BUILTIN_PSLLVV8DI,
+ IX86_BUILTIN_PSRAD512, IX86_BUILTIN_PSRADI512, IX86_BUILTIN_PSRAQ512,
+ IX86_BUILTIN_PSRAQI512, IX86_BUILTIN_PSRAVV16SI,
+ IX86_BUILTIN_PSRAVV8DI, IX86_BUILTIN_PSRLD512, IX86_BUILTIN_PSRLDI512,
+ IX86_BUILTIN_PSRLQ512, IX86_BUILTIN_PSRLQI512,
+ IX86_BUILTIN_PSRLVV16SI, IX86_BUILTIN_PSRLVV8DI,
+ IX86_BUILTIN_PSUBD512, IX86_BUILTIN_PSUBQ512, IX86_BUILTIN_PTESTMD512,
+ IX86_BUILTIN_PTESTMQ512, IX86_BUILTIN_PTESTNMD512,
+ IX86_BUILTIN_PTESTNMQ512, IX86_BUILTIN_PUNPCKHDQ512,
+ IX86_BUILTIN_PUNPCKHQDQ512, IX86_BUILTIN_PUNPCKLDQ512,
+ IX86_BUILTIN_PUNPCKLQDQ512, IX86_BUILTIN_PXORD512,
+ IX86_BUILTIN_PXORQ512, IX86_BUILTIN_RCP14PD512,
+ IX86_BUILTIN_RCP14PS512, IX86_BUILTIN_RCP14SD, IX86_BUILTIN_RCP14SS,
+ IX86_BUILTIN_RNDSCALEPD, IX86_BUILTIN_RNDSCALEPS,
+ IX86_BUILTIN_RNDSCALESD, IX86_BUILTIN_RNDSCALESS,
+ IX86_BUILTIN_RSQRT14PD512, IX86_BUILTIN_RSQRT14PS512,
+ IX86_BUILTIN_RSQRT14SD, IX86_BUILTIN_RSQRT14SS,
+ IX86_BUILTIN_SCALEFPD512, IX86_BUILTIN_SCALEFPS512,
+ IX86_BUILTIN_SCALEFSD, IX86_BUILTIN_SCALEFSS, IX86_BUILTIN_SHUFPD512,
+ IX86_BUILTIN_SHUFPS512, IX86_BUILTIN_SHUF_F32x4,
+ IX86_BUILTIN_SHUF_F64x2, IX86_BUILTIN_SHUF_I32x4,
+ IX86_BUILTIN_SHUF_I64x2,
+ IX86_BUILTIN_SQRTPD512_MASK, IX86_BUILTIN_SQRTPS512_MASK,
+ IX86_BUILTIN_SQRTSD_MASK,
+ IX86_BUILTIN_SQRTSS_MASK, IX86_BUILTIN_STOREAPD512,
+ IX86_BUILTIN_STOREAPS512, IX86_BUILTIN_STOREDQUDI512,
+ IX86_BUILTIN_STOREDQUSI512, IX86_BUILTIN_STORESD,
+ IX86_BUILTIN_STORESS, IX86_BUILTIN_STOREUPD512,
+ IX86_BUILTIN_STOREUPS512, IX86_BUILTIN_SUBPD512,
+ IX86_BUILTIN_SUBPS512, IX86_BUILTIN_SUBSD_MASK,
+ IX86_BUILTIN_SUBSS_MASK, IX86_BUILTIN_UCMPD512, IX86_BUILTIN_UCMPQ512,
+ IX86_BUILTIN_UNPCKHPD512, IX86_BUILTIN_UNPCKHPS512,
+ IX86_BUILTIN_UNPCKLPD512, IX86_BUILTIN_UNPCKLPS512,
+ IX86_BUILTIN_VCVTSD2SI32, IX86_BUILTIN_VCVTSD2SI64,
+ IX86_BUILTIN_VCVTSD2USI32, IX86_BUILTIN_VCVTSD2USI64,
+ IX86_BUILTIN_VCVTSS2SI32, IX86_BUILTIN_VCVTSS2SI64,
+ IX86_BUILTIN_VCVTSS2USI32, IX86_BUILTIN_VCVTSS2USI64,
+ IX86_BUILTIN_VCVTTSD2SI32, IX86_BUILTIN_VCVTTSD2SI64,
+ IX86_BUILTIN_VCVTTSD2USI32, IX86_BUILTIN_VCVTTSD2USI64,
+ IX86_BUILTIN_VCVTTSS2SI32, IX86_BUILTIN_VCVTTSS2SI64,
+ IX86_BUILTIN_VCVTTSS2USI32, IX86_BUILTIN_VCVTTSS2USI64,
+ IX86_BUILTIN_VFMADDPD512_MASK, IX86_BUILTIN_VFMADDPD512_MASK3,
+ IX86_BUILTIN_VFMADDPD512_MASKZ, IX86_BUILTIN_VFMADDPS512_MASK,
+ IX86_BUILTIN_VFMADDPS512_MASK3, IX86_BUILTIN_VFMADDPS512_MASKZ,
+ IX86_BUILTIN_VFMADDSD3_MASK, IX86_BUILTIN_VFMADDSD3_MASK3,
+ IX86_BUILTIN_VFMADDSD3_MASKZ, IX86_BUILTIN_VFMADDSS3_MASK,
+ IX86_BUILTIN_VFMADDSS3_MASK3, IX86_BUILTIN_VFMADDSS3_MASKZ,
+ IX86_BUILTIN_VFMADDSUBPD512_MASK, IX86_BUILTIN_VFMADDSUBPD512_MASK3,
+ IX86_BUILTIN_VFMADDSUBPD512_MASKZ, IX86_BUILTIN_VFMADDSUBPS512_MASK,
+ IX86_BUILTIN_VFMADDSUBPS512_MASK3, IX86_BUILTIN_VFMADDSUBPS512_MASKZ,
+ IX86_BUILTIN_VFMSUBADDPD512_MASK3, IX86_BUILTIN_VFMSUBADDPS512_MASK3,
+ IX86_BUILTIN_VFMSUBPD512_MASK3, IX86_BUILTIN_VFMSUBPS512_MASK3,
+ IX86_BUILTIN_VFMSUBSD3_MASK3, IX86_BUILTIN_VFMSUBSS3_MASK3,
+ IX86_BUILTIN_VFNMADDPD512_MASK, IX86_BUILTIN_VFNMADDPS512_MASK,
+ IX86_BUILTIN_VFNMSUBPD512_MASK, IX86_BUILTIN_VFNMSUBPD512_MASK3,
+ IX86_BUILTIN_VFNMSUBPS512_MASK, IX86_BUILTIN_VFNMSUBPS512_MASK3,
+ IX86_BUILTIN_VPCLZCNTD512, IX86_BUILTIN_VPCLZCNTQ512,
+ IX86_BUILTIN_VPCONFLICTD512, IX86_BUILTIN_VPCONFLICTQ512,
+ IX86_BUILTIN_VPERMDF512, IX86_BUILTIN_VPERMDI512,
+ IX86_BUILTIN_VPERMI2VARD512, IX86_BUILTIN_VPERMI2VARPD512,
+ IX86_BUILTIN_VPERMI2VARPS512, IX86_BUILTIN_VPERMI2VARQ512,
+ IX86_BUILTIN_VPERMILPD512, IX86_BUILTIN_VPERMILPS512,
+ IX86_BUILTIN_VPERMILVARPD512, IX86_BUILTIN_VPERMILVARPS512,
+ IX86_BUILTIN_VPERMT2VARD512, IX86_BUILTIN_VPERMT2VARD512_MASKZ,
+ IX86_BUILTIN_VPERMT2VARPD512, IX86_BUILTIN_VPERMT2VARPD512_MASKZ,
+ IX86_BUILTIN_VPERMT2VARPS512, IX86_BUILTIN_VPERMT2VARPS512_MASKZ,
+ IX86_BUILTIN_VPERMT2VARQ512, IX86_BUILTIN_VPERMT2VARQ512_MASKZ,
+ IX86_BUILTIN_VPERMVARDF512, IX86_BUILTIN_VPERMVARDI512,
+ IX86_BUILTIN_VPERMVARSF512, IX86_BUILTIN_VPERMVARSI512,
+ IX86_BUILTIN_VTERNLOGD512_MASK, IX86_BUILTIN_VTERNLOGD512_MASKZ,
+ IX86_BUILTIN_VTERNLOGQ512_MASK, IX86_BUILTIN_VTERNLOGQ512_MASKZ,
+ IX86_BUILTIN_KAND16, IX86_BUILTIN_KANDN16, IX86_BUILTIN_KNOT16,
+ IX86_BUILTIN_KOR16, IX86_BUILTIN_KORTESTC16, IX86_BUILTIN_KORTESTZ16,
+ IX86_BUILTIN_KUNPCKBW, IX86_BUILTIN_KXNOR16, IX86_BUILTIN_KXOR16,
+ IX86_BUILTIN_GATHER3SIV8DI,
+ IX86_BUILTIN_SCATTERDIV16SF, IX86_BUILTIN_SCATTERDIV16SI,
+ IX86_BUILTIN_SCATTERDIV8DF, IX86_BUILTIN_SCATTERDIV8DI,
+ IX86_BUILTIN_SCATTERSIV16SF, IX86_BUILTIN_SCATTERSIV16SI,
+ IX86_BUILTIN_SCATTERSIV8DF, IX86_BUILTIN_SCATTERSIV8DI,
+ IX86_BUILTIN_GATHERPFDPS, IX86_BUILTIN_GATHERPFQPS,
+ IX86_BUILTIN_SCATTERPFDPS, IX86_BUILTIN_SCATTERPFQPS,
+ IX86_BUILTIN_EXP2PD_MASK, IX86_BUILTIN_EXP2PS_MASK,
+ IX86_BUILTIN_RCP28PD, IX86_BUILTIN_RCP28PS,
+ IX86_BUILTIN_RSQRT28PD, IX86_BUILTIN_RSQRT28PS.
+ (bdesc_special_args): Add __builtin_ia32_compressstoresf512_mask,
+ __builtin_ia32_compressstoresi512_mask,
+ __builtin_ia32_compressstoredf512_mask,
+ __builtin_ia32_compressstoredi512_mask,
+ __builtin_ia32_expandloadsf512_mask,
+ __builtin_ia32_expandloadsf512_maskz,
+ __builtin_ia32_expandloadsi512_mask,
+ __builtin_ia32_expandloadsi512_maskz,
+ __builtin_ia32_expandloaddf512_mask,
+ __builtin_ia32_expandloaddf512_maskz,
+ __builtin_ia32_expandloaddi512_mask,
+ __builtin_ia32_expandloaddi512_maskz,
+ __builtin_ia32_loaddqusi512_mask, __builtin_ia32_loaddqudi512_mask,
+ __builtin_ia32_loadsd_mask, __builtin_ia32_loadss_mask,
+ __builtin_ia32_loadupd512_mask, __builtin_ia32_loadups512_mask,
+ __builtin_ia32_loadaps512_mask, __builtin_ia32_movdqa32load512_mask,
+ __builtin_ia32_loadapd512_mask, __builtin_ia32_movdqa64load512_mask,
+ __builtin_ia32_movntps512, __builtin_ia32_movntpd512,
+ __builtin_ia32_movntdq512, __builtin_ia32_storedqusi512_mask,
+ __builtin_ia32_storedqudi512_mask, __builtin_ia32_storesd_mask,
+ __builtin_ia32_storess_mask, __builtin_ia32_storeupd512_mask,
+ __builtin_ia32_storeups512_mask, __builtin_ia32_storeaps512_mask,
+ __builtin_ia32_movdqa32store512_mask, __builtin_ia32_storeapd512_mask,
+ __builtin_ia32_movdqa64store512_mask, __builtin_ia32_alignd512_mask,
+ __builtin_ia32_alignq512_mask, __builtin_ia32_blendmd_512_mask,
+ __builtin_ia32_blendmpd_512_mask, __builtin_ia32_blendmps_512_mask,
+ __builtin_ia32_blendmq_512_mask, __builtin_ia32_broadcastf32x4_512,
+ __builtin_ia32_broadcastf64x4_512, __builtin_ia32_broadcasti32x4_512,
+ __builtin_ia32_broadcasti64x4_512, __builtin_ia32_broadcastsd512,
+ __builtin_ia32_broadcastss512, __builtin_ia32_cmpd512_mask,
+ __builtin_ia32_cmpq512_mask, __builtin_ia32_compressdf512_mask,
+ __builtin_ia32_compresssf512_mask, __builtin_ia32_cvtdq2pd512_mask,
+ __builtin_ia32_vcvtps2ph512_mask, __builtin_ia32_cvtudq2pd512_mask,
+ __builtin_ia32_cvtusi2sd32, __builtin_ia32_expanddf512_mask,
+ __builtin_ia32_expanddf512_maskz, __builtin_ia32_expandsf512_mask,
+ __builtin_ia32_expandsf512_maskz, __builtin_ia32_extractf32x4_mask,
+ __builtin_ia32_extractf64x4_mask, __builtin_ia32_extracti32x4_mask,
+ __builtin_ia32_extracti64x4_mask, __builtin_ia32_insertf32x4_mask,
+ __builtin_ia32_insertf64x4_mask, __builtin_ia32_inserti32x4_mask,
+ __builtin_ia32_inserti64x4_mask, __builtin_ia32_movapd512_mask,
+ __builtin_ia32_movaps512_mask, __builtin_ia32_movddup512_mask,
+ __builtin_ia32_movdqa32_512_mask, __builtin_ia32_movdqa64_512_mask,
+ __builtin_ia32_movesd_mask, __builtin_ia32_movess_mask,
+ __builtin_ia32_movshdup512_mask, __builtin_ia32_movsldup512_mask,
+ __builtin_ia32_pabsd512_mask, __builtin_ia32_pabsq512_mask,
+ __builtin_ia32_paddd512_mask, __builtin_ia32_paddq512_mask,
+ __builtin_ia32_pandd512_mask, __builtin_ia32_pandnd512_mask,
+ __builtin_ia32_pandnq512_mask, __builtin_ia32_pandq512_mask,
+ __builtin_ia32_pbroadcastd512, __builtin_ia32_pbroadcastd512_gpr_mask,
+ __builtin_ia32_broadcastmb512, __builtin_ia32_broadcastmw512,
+ __builtin_ia32_pbroadcastq512, __builtin_ia32_pbroadcastq512_gpr_mask,
+ __builtin_ia32_pbroadcastq512_mem_mask,
+ __builtin_ia32_pcmpeqd512_mask, __builtin_ia32_pcmpeqq512_mask,
+ __builtin_ia32_pcmpgtd512_mask, __builtin_ia32_pcmpgtq512_mask,
+ __builtin_ia32_compresssi512_mask, __builtin_ia32_compressdi512_mask,
+ __builtin_ia32_expandsi512_mask, __builtin_ia32_expandsi512_maskz,
+ __builtin_ia32_expanddi512_mask, __builtin_ia32_expanddi512_maskz,
+ __builtin_ia32_pmaxsd512_mask, __builtin_ia32_pmaxsq512_mask,
+ __builtin_ia32_pmaxud512_mask, __builtin_ia32_pmaxuq512_mask,
+ __builtin_ia32_pminsd512_mask, __builtin_ia32_pminsq512_mask,
+ __builtin_ia32_pminud512_mask, __builtin_ia32_pminuq512_mask,
+ __builtin_ia32_pmovdb512_mask, __builtin_ia32_pmovdw512_mask,
+ __builtin_ia32_pmovqb512_mask, __builtin_ia32_pmovqd512_mask,
+ __builtin_ia32_pmovqw512_mask, __builtin_ia32_pmovsdb512_mask,
+ __builtin_ia32_pmovsdw512_mask, __builtin_ia32_pmovsqb512_mask,
+ __builtin_ia32_pmovsqd512_mask, __builtin_ia32_pmovsqw512_mask,
+ __builtin_ia32_pmovsxbd512_mask, __builtin_ia32_pmovsxbq512_mask,
+ __builtin_ia32_pmovsxdq512_mask, __builtin_ia32_pmovsxwd512_mask,
+ __builtin_ia32_pmovsxwq512_mask, __builtin_ia32_pmovusdb512_mask,
+ __builtin_ia32_pmovusdw512_mask, __builtin_ia32_pmovusqb512_mask,
+ __builtin_ia32_pmovusqd512_mask, __builtin_ia32_pmovusqw512_mask,
+ __builtin_ia32_pmovzxbd512_mask, __builtin_ia32_pmovzxbq512_mask,
+ __builtin_ia32_pmovzxdq512_mask, __builtin_ia32_pmovzxwd512_mask,
+ __builtin_ia32_pmovzxwq512_mask, __builtin_ia32_pmuldq512_mask,
+ __builtin_ia32_pmulld512_mask, __builtin_ia32_pmuludq512_mask,
+ __builtin_ia32_pord512_mask, __builtin_ia32_porq512_mask,
+ __builtin_ia32_prold512_mask, __builtin_ia32_prolq512_mask,
+ __builtin_ia32_prolvd512_mask, __builtin_ia32_prolvq512_mask,
+ __builtin_ia32_prord512_mask, __builtin_ia32_prorq512_mask,
+ __builtin_ia32_prorvd512_mask, __builtin_ia32_prorvq512_mask,
+ __builtin_ia32_pshufd512_mask, __builtin_ia32_pslld512_mask,
+ __builtin_ia32_pslldi512_mask, __builtin_ia32_psllq512_mask,
+ __builtin_ia32_psllqi512_mask, __builtin_ia32_psllv16si_mask,
+ __builtin_ia32_psllv8di_mask, __builtin_ia32_psrad512_mask,
+ __builtin_ia32_psradi512_mask, __builtin_ia32_psraq512_mask,
+ __builtin_ia32_psraqi512_mask, __builtin_ia32_psrav16si_mask,
+ __builtin_ia32_psrav8di_mask, __builtin_ia32_psrld512_mask,
+ __builtin_ia32_psrldi512_mask, __builtin_ia32_psrlq512_mask,
+ __builtin_ia32_psrlqi512_mask, __builtin_ia32_psrlv16si_mask,
+ __builtin_ia32_psrlv8di_mask, __builtin_ia32_psubd512_mask,
+ __builtin_ia32_psubq512_mask, __builtin_ia32_ptestmd512,
+ __builtin_ia32_ptestmq512, __builtin_ia32_ptestnmd512,
+ __builtin_ia32_ptestnmq512, __builtin_ia32_punpckhdq512_mask,
+ __builtin_ia32_punpckhqdq512_mask, __builtin_ia32_punpckldq512_mask,
+ __builtin_ia32_punpcklqdq512_mask, __builtin_ia32_pxord512_mask,
+ __builtin_ia32_pxorq512_mask, __builtin_ia32_rcp14pd512_mask,
+ __builtin_ia32_rcp14ps512_mask, __builtin_ia32_rcp14sd_mask,
+ __builtin_ia32_rcp14ss_mask, __builtin_ia32_rsqrt14pd512_mask,
+ __builtin_ia32_rsqrt14ps512_mask, __builtin_ia32_rsqrt14sd_mask,
+ __builtin_ia32_rsqrt14ss_mask, __builtin_ia32_shufpd512_mask,
+ __builtin_ia32_shufps512_mask, __builtin_ia32_shuf_f32x4_mask,
+ __builtin_ia32_shuf_f64x2_mask, __builtin_ia32_shuf_i32x4_mask,
+ __builtin_ia32_shuf_i64x2_mask, __builtin_ia32_ucmpd512_mask,
+ __builtin_ia32_ucmpq512_mask, __builtin_ia32_unpckhpd512_mask,
+ __builtin_ia32_unpckhps512_mask, __builtin_ia32_unpcklpd512_mask,
+ __builtin_ia32_unpcklps512_mask, __builtin_ia32_vplzcntd_512_mask,
+ __builtin_ia32_vplzcntq_512_mask,
+ __builtin_ia32_vpconflictsi_512_mask,
+ __builtin_ia32_vpconflictdi_512_mask, __builtin_ia32_permdf512_mask,
+ __builtin_ia32_permdi512_mask, __builtin_ia32_vpermi2vard512_mask,
+ __builtin_ia32_vpermi2varpd512_mask,
+ __builtin_ia32_vpermi2varps512_mask,
+ __builtin_ia32_vpermi2varq512_mask, __builtin_ia32_vpermilpd512_mask,
+ __builtin_ia32_vpermilps512_mask, __builtin_ia32_vpermilvarpd512_mask,
+ __builtin_ia32_vpermilvarps512_mask,
+ __builtin_ia32_vpermt2vard512_mask,
+ __builtin_ia32_vpermt2vard512_maskz,
+ __builtin_ia32_vpermt2varpd512_mask,
+ __builtin_ia32_vpermt2varpd512_maskz,
+ __builtin_ia32_vpermt2varps512_mask,
+ __builtin_ia32_vpermt2varps512_maskz,
+ __builtin_ia32_vpermt2varq512_mask,
+ __builtin_ia32_vpermt2varq512_maskz, __builtin_ia32_permvardf512_mask,
+ __builtin_ia32_permvardi512_mask, __builtin_ia32_permvarsf512_mask,
+ __builtin_ia32_permvarsi512_mask, __builtin_ia32_pternlogd512_mask,
+ __builtin_ia32_pternlogd512_maskz, __builtin_ia32_pternlogq512_mask,
+ __builtin_ia32_pternlogq512_maskz, __builtin_ia32_copysignps512,
+ __builtin_ia32_copysignpd512, __builtin_ia32_sqrtpd512,
+ __builtin_ia32_sqrtps512, __builtin_ia32_exp2ps,
+ __builtin_ia32_roundpd_az_vec_pack_sfix512,
+ __builtin_ia32_floorpd_vec_pack_sfix512,
+ __builtin_ia32_ceilpd_vec_pack_sfix512, __builtin_ia32_kandhi,
+ __builtin_ia32_kandnhi, __builtin_ia32_knothi, __builtin_ia32_korhi,
+ __builtin_ia32_kortestchi, __builtin_ia32_kortestzhi,
+ __builtin_ia32_kunpckhi, __builtin_ia32_kxnorhi,
+ __builtin_ia32_kxorhi, __builtin_ia32_addpd512_mask,
+ __builtin_ia32_addps512_mask, __builtin_ia32_addsd_mask,
+ __builtin_ia32_addss_mask, __builtin_ia32_cmppd512_mask,
+ __builtin_ia32_cmpps512_mask, __builtin_ia32_cmpsd_mask,
+ __builtin_ia32_cmpss_mask, __builtin_ia32_vcomisd,
+ __builtin_ia32_vcomiss, __builtin_ia32_cvtdq2ps512_mask,
+ __builtin_ia32_cvtpd2dq512_mask, __builtin_ia32_cvtpd2ps512_mask,
+ __builtin_ia32_cvtpd2udq512_mask, __builtin_ia32_vcvtph2ps512_mask,
+ __builtin_ia32_cvtps2dq512_mask, __builtin_ia32_cvtps2pd512_mask,
+ __builtin_ia32_cvtps2udq512_mask, __builtin_ia32_cvtsd2ss_mask,
+ __builtin_ia32_cvtsi2sd64, __builtin_ia32_cvtsi2ss32,
+ __builtin_ia32_cvtsi2ss64, __builtin_ia32_cvtss2sd_mask,
+ __builtin_ia32_cvttpd2dq512_mask, __builtin_ia32_cvttpd2udq512_mask,
+ __builtin_ia32_cvttps2dq512_mask, __builtin_ia32_cvttps2udq512_mask,
+ __builtin_ia32_cvtudq2ps512_mask, __builtin_ia32_cvtusi2sd64,
+ __builtin_ia32_cvtusi2ss32, __builtin_ia32_cvtusi2ss64,
+ __builtin_ia32_divpd512_mask, __builtin_ia32_divps512_mask,
+ __builtin_ia32_divsd_mask, __builtin_ia32_divss_mask,
+ __builtin_ia32_fixupimmpd512_mask, __builtin_ia32_fixupimmpd512_maskz,
+ __builtin_ia32_fixupimmps512_mask, __builtin_ia32_fixupimmps512_maskz,
+ __builtin_ia32_fixupimmsd_mask, __builtin_ia32_fixupimmsd_maskz,
+ __builtin_ia32_fixupimmss_mask, __builtin_ia32_fixupimmss_maskz,
+ __builtin_ia32_getexppd512_mask, __builtin_ia32_getexpps512_mask,
+ __builtin_ia32_getexpsd128_mask, __builtin_ia32_getexpss128_mask,
+ __builtin_ia32_getmantpd512_mask, __builtin_ia32_getmantps512_mask,
+ __builtin_ia32_getmantsd_mask, __builtin_ia32_getmantss_mask,
+ __builtin_ia32_maxpd512_mask, __builtin_ia32_maxps512_mask,
+ __builtin_ia32_maxsd_mask, __builtin_ia32_maxss_mask,
+ __builtin_ia32_minpd512_mask, __builtin_ia32_minps512_mask,
+ __builtin_ia32_minsd_mask, __builtin_ia32_minss_mask,
+ __builtin_ia32_mulpd512_mask, __builtin_ia32_mulps512_mask,
+ __builtin_ia32_mulsd_mask, __builtin_ia32_mulss_mask,
+ __builtin_ia32_rndscalepd_mask, __builtin_ia32_rndscaleps_mask,
+ __builtin_ia32_rndscalesd_mask, __builtin_ia32_rndscaless_mask,
+ __builtin_ia32_scalefpd512_mask, __builtin_ia32_scalefps512_mask,
+ __builtin_ia32_scalefsd_mask, __builtin_ia32_scalefss_mask,
+ __builtin_ia32_sqrtpd512_mask, __builtin_ia32_sqrtps512_mask,
+ __builtin_ia32_sqrtsd_mask, __builtin_ia32_sqrtss_mask,
+ __builtin_ia32_subpd512_mask, __builtin_ia32_subps512_mask,
+ __builtin_ia32_subsd_mask, __builtin_ia32_subss_mask,
+ __builtin_ia32_vcvtsd2si32, __builtin_ia32_vcvtsd2si64,
+ __builtin_ia32_vcvtsd2usi32, __builtin_ia32_vcvtsd2usi64,
+ __builtin_ia32_vcvtss2si32, __builtin_ia32_vcvtss2si64,
+ __builtin_ia32_vcvtss2usi32, __builtin_ia32_vcvtss2usi64,
+ __builtin_ia32_vcvttsd2si32, __builtin_ia32_vcvttsd2si64,
+ __builtin_ia32_vcvttsd2usi32, __builtin_ia32_vcvttsd2usi64,
+ __builtin_ia32_vcvttss2si32, __builtin_ia32_vcvttss2si64,
+ __builtin_ia32_vcvttss2usi32, __builtin_ia32_vcvttss2usi64,
+ __builtin_ia32_vfmaddpd512_mask, __builtin_ia32_vfmaddpd512_mask3,
+ __builtin_ia32_vfmaddpd512_maskz, __builtin_ia32_vfmaddps512_mask,
+ __builtin_ia32_vfmaddps512_mask3, __builtin_ia32_vfmaddps512_maskz,
+ __builtin_ia32_vfmaddsd3_mask, __builtin_ia32_vfmaddsd3_mask3,
+ __builtin_ia32_vfmaddsd3_maskz, __builtin_ia32_vfmaddss3_mask,
+ __builtin_ia32_vfmaddss3_mask3, __builtin_ia32_vfmaddss3_maskz,
+ __builtin_ia32_vfmaddsubpd512_mask,
+ __builtin_ia32_vfmaddsubpd512_mask3,
+ __builtin_ia32_vfmaddsubpd512_maskz,
+ __builtin_ia32_vfmaddsubps512_mask,
+ __builtin_ia32_vfmaddsubps512_mask3,
+ __builtin_ia32_vfmaddsubps512_maskz,
+ __builtin_ia32_vfmsubaddpd512_mask3,
+ __builtin_ia32_vfmsubaddps512_mask3, __builtin_ia32_vfmsubpd512_mask3,
+ __builtin_ia32_vfmsubps512_mask3, __builtin_ia32_vfmsubsd3_mask3,
+ __builtin_ia32_vfmsubss3_mask3, __builtin_ia32_vfnmaddpd512_mask,
+ __builtin_ia32_vfnmaddps512_mask, __builtin_ia32_vfnmsubpd512_mask,
+ __builtin_ia32_vfnmsubpd512_mask3, __builtin_ia32_vfnmsubps512_mask,
+ __builtin_ia32_vfnmsubps512_mask3, __builtin_ia32_exp2pd_mask,
+ __builtin_ia32_exp2ps_mask, __builtin_ia32_rcp28pd_mask,
+ __builtin_ia32_rcp28ps_mask, __builtin_ia32_rsqrt28pd_mask,
+ __builtin_ia32_rsqrt28ps_mask, __builtin_ia32_gathersiv16sf,
+ __builtin_ia32_gathersiv8df, __builtin_ia32_gatherdiv16sf,
+ __builtin_ia32_gatherdiv8df, __builtin_ia32_gathersiv16si,
+ __builtin_ia32_gathersiv8di, __builtin_ia32_gatherdiv16si,
+ __builtin_ia32_gatherdiv8di, __builtin_ia32_gatheraltsiv8df ,
+ __builtin_ia32_gatheraltdiv8sf , __builtin_ia32_gatheraltsiv8di ,
+ __builtin_ia32_gatheraltdiv8si , __builtin_ia32_scattersiv16sf,
+ __builtin_ia32_scattersiv8df, __builtin_ia32_scatterdiv16sf,
+ __builtin_ia32_scatterdiv8df, __builtin_ia32_scattersiv16si,
+ __builtin_ia32_scattersiv8di, __builtin_ia32_scatterdiv16si,
+ __builtin_ia32_scatterdiv8di, __builtin_ia32_gatherpfdps,
+ __builtin_ia32_gatherpfqps, __builtin_ia32_scatterpfdps,
+ __builtin_ia32_scatterpfqps.
+ (ix86_init_mmx_sse_builtins): Handle builtins with AVX512 embeded
+ rounding, builtins for AVX512 gathers/scatters.
+ (ix86_expand_args_builtin): Handle new functions types, add warnings
+ for masked builtins.
+ (ix86_erase_embedded_rounding): Handle patterns with embedded rounding.
+ (ix86_expand_sse_comi_round): Ditto.
+ (ix86_expand_round_builtin): Ditto.
+ (ix86_expand_builtin): Handle AVX512's gathers/scatters and kortest{z}.
+ Call ix86_expand_round_builtin.
+ * config/i386/immintrin.h: Add avx512fintrin.h, avx512erintrin.h,
+ avx512pfintrin.h, avx512cdintrin.h.
+
+2013-12-31 Alexander Ivchenko <alexander.ivchenko@intel.com>
+ Maxim Kuznetsov <maxim.kuznetsov@intel.com>
+ Sergey Lega <sergey.s.lega@intel.com>
+ Anna Tikhonova <anna.tikhonova@intel.com>
+ Ilya Tocar <ilya.tocar@intel.com>
+ Andrey Turetskiy <andrey.turetskiy@intel.com>
+ Ilya Verbin <ilya.verbin@intel.com>
+ Kirill Yukhin <kirill.yukhin@intel.com>
+ Michael Zolotukhin <michael.v.zolotukhin@intel.com>
+
* config/i386/i386.c (MAX_CLASSES): Increase number of classes.
(classify_argument): Extend for 512 bit vectors.
(construct_container): Ditto.
diff --git a/gcc/config.gcc b/gcc/config.gcc
index 99f11e5561a..9ce29901f6e 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -372,9 +372,10 @@ i[34567]86-*-*)
immintrin.h x86intrin.h avxintrin.h xopintrin.h
ia32intrin.h cross-stdarg.h lwpintrin.h popcntintrin.h
lzcntintrin.h bmiintrin.h bmi2intrin.h tbmintrin.h
- avx2intrin.h fmaintrin.h f16cintrin.h rtmintrin.h
- xtestintrin.h rdseedintrin.h prfchwintrin.h adxintrin.h
- fxsrintrin.h xsaveintrin.h xsaveoptintrin.h"
+ avx2intrin.h avx512fintrin.h fmaintrin.h f16cintrin.h
+ rtmintrin.h xtestintrin.h rdseedintrin.h prfchwintrin.h
+ adxintrin.h fxsrintrin.h xsaveintrin.h xsaveoptintrin.h
+ avx512cdintrin.h avx512erintrin.h avx512pfintrin.h"
;;
x86_64-*-*)
cpu_type=i386
@@ -387,9 +388,10 @@ x86_64-*-*)
immintrin.h x86intrin.h avxintrin.h xopintrin.h
ia32intrin.h cross-stdarg.h lwpintrin.h popcntintrin.h
lzcntintrin.h bmiintrin.h tbmintrin.h bmi2intrin.h
- avx2intrin.h fmaintrin.h f16cintrin.h rtmintrin.h
- xtestintrin.h rdseedintrin.h prfchwintrin.h adxintrin.h
- fxsrintrin.h xsaveintrin.h xsaveoptintrin.h"
+ avx2intrin.h avx512fintrin.h fmaintrin.h f16cintrin.h
+ rtmintrin.h xtestintrin.h rdseedintrin.h prfchwintrin.h
+ adxintrin.h fxsrintrin.h xsaveintrin.h xsaveoptintrin.h
+ avx512cdintrin.h avx512erintrin.h avx512pfintrin.h"
need_64bit_hwint=yes
;;
ia64-*-*)
diff --git a/gcc/config/i386/avx512cdintrin.h b/gcc/config/i386/avx512cdintrin.h
new file mode 100644
index 00000000000..6186e06bdbe
--- /dev/null
+++ b/gcc/config/i386/avx512cdintrin.h
@@ -0,0 +1,219 @@
+/* Copyright (C) 2013
+ Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#ifndef _IMMINTRIN_H_INCLUDED
+#error "Never use <avx512cdintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX512CDINTRIN_H_INCLUDED
+#define _AVX512CDINTRIN_H_INCLUDED
+
+#ifndef __AVX512CD__
+#pragma GCC push_options
+#pragma GCC target("avx512cd")
+#define __DISABLE_AVX512CD__
+#endif /* __AVX512CD__ */
+
+/* Internal data types for implementing the intrinsics. */
+typedef long long __v8di __attribute__ ((__vector_size__ (64)));
+typedef int __v16si __attribute__ ((__vector_size__ (64)));
+
+/* The Intel API is flexible enough that we must allow aliasing with other
+ vector types, and their scalar components. */
+typedef long long __m512i __attribute__ ((__vector_size__ (64), __may_alias__));
+typedef double __m512d __attribute__ ((__vector_size__ (64), __may_alias__));
+
+typedef unsigned char __mmask8;
+typedef unsigned short __mmask16;
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_conflict_epi32 (__m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vpconflictsi_512_mask ((__v16si) __A,
+ (__v16si) _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_conflict_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_vpconflictsi_512_mask ((__v16si) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_conflict_epi32 (__mmask16 __U, __m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vpconflictsi_512_mask ((__v16si) __A,
+ (__v16si) _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_conflict_epi64 (__m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vpconflictdi_512_mask ((__v8di) __A,
+ (__v8di) _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_conflict_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_vpconflictdi_512_mask ((__v8di) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_conflict_epi64 (__mmask8 __U, __m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vpconflictdi_512_mask ((__v8di) __A,
+ (__v8di) _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_lzcnt_epi64 (__m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vplzcntq_512_mask ((__v8di) __A,
+ (__v8di) _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_lzcnt_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_vplzcntq_512_mask ((__v8di) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_lzcnt_epi64 (__mmask8 __U, __m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vplzcntq_512_mask ((__v8di) __A,
+ (__v8di) _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_lzcnt_epi32 (__m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vplzcntd_512_mask ((__v16si) __A,
+ (__v16si) _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_lzcnt_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_vplzcntd_512_mask ((__v16si) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_lzcnt_epi32 (__mmask16 __U, __m512i __A)
+{
+ return (__m512i)
+ __builtin_ia32_vplzcntd_512_mask ((__v16si) __A,
+ (__v16si) _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcastmb_epi64 (__mmask8 __A)
+{
+ return (__m512i) __builtin_ia32_broadcastmb512 (__A);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcastmw_epi32 (__mmask16 __A)
+{
+ return (__m512i) __builtin_ia32_broadcastmw512 (__A);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_testn_epi32_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_ptestnmd512 ((__v16si) __A,
+ (__v16si) __B,
+ (__mmask16) -1);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_testn_epi32_mask (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_ptestnmd512 ((__v16si) __A,
+ (__v16si) __B, __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_testn_epi64_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_ptestnmq512 ((__v8di) __A,
+ (__v8di) __B,
+ (__mmask8) -1);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_testn_epi64_mask (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_ptestnmq512 ((__v8di) __A,
+ (__v8di) __B, __U);
+}
+
+#ifdef __DISABLE_AVX512CD__
+#undef __DISABLE_AVX512CD__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX512CD__ */
+
+#endif /* _AVX512CDINTRIN_H_INCLUDED */
diff --git a/gcc/config/i386/avx512erintrin.h b/gcc/config/i386/avx512erintrin.h
new file mode 100644
index 00000000000..4583d690378
--- /dev/null
+++ b/gcc/config/i386/avx512erintrin.h
@@ -0,0 +1,333 @@
+/* Copyright (C) 2013
+ Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#ifndef _IMMINTRIN_H_INCLUDED
+#error "Never use <avx512erintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX512ERINTRIN_H_INCLUDED
+#define _AVX512ERINTRIN_H_INCLUDED
+
+#ifndef __AVX512ER__
+#pragma GCC push_options
+#pragma GCC target("avx512er")
+#define __DISABLE_AVX512ER__
+#endif /* __AVX512ER__ */
+
+/* Internal data types for implementing the intrinsics. */
+typedef double __v8df __attribute__ ((__vector_size__ (64)));
+typedef float __v16sf __attribute__ ((__vector_size__ (64)));
+
+/* The Intel API is flexible enough that we must allow aliasing with other
+ vector types, and their scalar components. */
+typedef float __m512 __attribute__ ((__vector_size__ (64), __may_alias__));
+typedef double __m512d __attribute__ ((__vector_size__ (64), __may_alias__));
+
+typedef unsigned char __mmask8;
+typedef unsigned short __mmask16;
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_exp2a23_round_pd (__m512d __A, int __R)
+{
+ __m512d __W;
+ return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_exp2a23_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
+{
+ return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_exp2a23_round_pd (__mmask8 __U, __m512d __A, int __R)
+{
+ return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
+ (__v8df) _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_exp2a23_round_ps (__m512 __A, int __R)
+{
+ __m512 __W;
+ return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_exp2a23_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
+{
+ return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_exp2a23_round_ps (__mmask16 __U, __m512 __A, int __R)
+{
+ return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
+ (__v16sf) _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rcp28_round_pd (__m512d __A, int __R)
+{
+ __m512d __W;
+ return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rcp28_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
+{
+ return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rcp28_round_pd (__mmask8 __U, __m512d __A, int __R)
+{
+ return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
+ (__v8df) _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rcp28_round_ps (__m512 __A, int __R)
+{
+ __m512 __W;
+ return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rcp28_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
+{
+ return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rcp28_round_ps (__mmask16 __U, __m512 __A, int __R)
+{
+ return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
+ (__v16sf) _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rsqrt28_round_pd (__m512d __A, int __R)
+{
+ __m512d __W;
+ return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rsqrt28_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
+{
+ return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rsqrt28_round_pd (__mmask8 __U, __m512d __A, int __R)
+{
+ return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
+ (__v8df) _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rsqrt28_round_ps (__m512 __A, int __R)
+{
+ __m512 __W;
+ return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rsqrt28_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
+{
+ return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rsqrt28_round_ps (__mmask16 __U, __m512 __A, int __R)
+{
+ return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
+ (__v16sf) _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+#else
+#define _mm512_exp2a23_round_pd(A, C) \
+ __builtin_ia32_exp2pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_exp2a23_round_pd(W, U, A, C) \
+ __builtin_ia32_exp2pd_mask(A, W, U, C)
+
+#define _mm512_maskz_exp2a23_round_pd(U, A, C) \
+ __builtin_ia32_exp2pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_exp2a23_round_ps(A, C) \
+ __builtin_ia32_exp2ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_exp2a23_round_ps(W, U, A, C) \
+ __builtin_ia32_exp2ps_mask(A, W, U, C)
+
+#define _mm512_maskz_exp2a23_round_ps(U, A, C) \
+ __builtin_ia32_exp2ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
+
+#define _mm512_rcp28_round_pd(A, C) \
+ __builtin_ia32_rcp28pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_rcp28_round_pd(W, U, A, C) \
+ __builtin_ia32_rcp28pd_mask(A, W, U, C)
+
+#define _mm512_maskz_rcp28_round_pd(U, A, C) \
+ __builtin_ia32_rcp28pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_rcp28_round_ps(A, C) \
+ __builtin_ia32_rcp28ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_rcp28_round_ps(W, U, A, C) \
+ __builtin_ia32_rcp28ps_mask(A, W, U, C)
+
+#define _mm512_maskz_rcp28_round_ps(U, A, C) \
+ __builtin_ia32_rcp28ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
+
+#define _mm512_rsqrt28_round_pd(A, C) \
+ __builtin_ia32_rsqrt28pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_rsqrt28_round_pd(W, U, A, C) \
+ __builtin_ia32_rsqrt28pd_mask(A, W, U, C)
+
+#define _mm512_maskz_rsqrt28_round_pd(U, A, C) \
+ __builtin_ia32_rsqrt28pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_rsqrt28_round_ps(A, C) \
+ __builtin_ia32_rsqrt28ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_rsqrt28_round_ps(W, U, A, C) \
+ __builtin_ia32_rsqrt28ps_mask(A, W, U, C)
+
+#define _mm512_maskz_rsqrt28_round_ps(U, A, C) \
+ __builtin_ia32_rsqrt28ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
+#endif
+
+#define _mm512_exp2a23_pd(A) \
+ _mm512_exp2a23_round_pd(A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_mask_exp2a23_pd(W, U, A) \
+ _mm512_mask_exp2a23_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_maskz_exp2a23_pd(U, A) \
+ _mm512_maskz_exp2a23_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_exp2a23_ps(A) \
+ _mm512_exp2a23_round_ps(A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_mask_exp2a23_ps(W, U, A) \
+ _mm512_mask_exp2a23_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_maskz_exp2a23_ps(U, A) \
+ _mm512_maskz_exp2a23_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_rcp28_pd(A) \
+ _mm512_rcp28_round_pd(A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_mask_rcp28_pd(W, U, A) \
+ _mm512_mask_rcp28_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_maskz_rcp28_pd(U, A) \
+ _mm512_maskz_rcp28_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_rcp28_ps(A) \
+ _mm512_rcp28_round_ps(A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_mask_rcp28_ps(W, U, A) \
+ _mm512_mask_rcp28_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_maskz_rcp28_ps(U, A) \
+ _mm512_maskz_rcp28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_rsqrt28_pd(A) \
+ _mm512_rsqrt28_round_pd(A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_mask_rsqrt28_pd(W, U, A) \
+ _mm512_mask_rsqrt28_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_maskz_rsqrt28_pd(U, A) \
+ _mm512_maskz_rsqrt28_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_rsqrt28_ps(A) \
+ _mm512_rsqrt28_round_ps(A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_mask_rsqrt28_ps(W, U, A) \
+ _mm512_mask_rsqrt28_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm512_maskz_rsqrt28_ps(U, A) \
+ _mm512_maskz_rsqrt28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
+
+#ifdef __DISABLE_AVX512ER__
+#undef __DISABLE_AVX512ER__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX512ER__ */
+
+#endif /* _AVX512ERINTRIN_H_INCLUDED */
diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h
new file mode 100644
index 00000000000..f717d4601fc
--- /dev/null
+++ b/gcc/config/i386/avx512fintrin.h
@@ -0,0 +1,12147 @@
+/* Copyright (C) 2013
+ Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#ifndef _IMMINTRIN_H_INCLUDED
+#error "Never use <avx512fintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX512FINTRIN_H_INCLUDED
+#define _AVX512FINTRIN_H_INCLUDED
+
+#ifndef __AVX512F__
+#pragma GCC push_options
+#pragma GCC target("avx512f")
+#define __DISABLE_AVX512F__
+#endif /* __AVX512F__ */
+
+/* Internal data types for implementing the intrinsics. */
+typedef double __v8df __attribute__ ((__vector_size__ (64)));
+typedef float __v16sf __attribute__ ((__vector_size__ (64)));
+typedef long long __v8di __attribute__ ((__vector_size__ (64)));
+typedef int __v16si __attribute__ ((__vector_size__ (64)));
+
+/* The Intel API is flexible enough that we must allow aliasing with other
+ vector types, and their scalar components. */
+typedef float __m512 __attribute__ ((__vector_size__ (64), __may_alias__));
+typedef long long __m512i __attribute__ ((__vector_size__ (64), __may_alias__));
+typedef double __m512d __attribute__ ((__vector_size__ (64), __may_alias__));
+
+typedef unsigned char __mmask8;
+typedef unsigned short __mmask16;
+
+/* Rounding mode macros. */
+#define _MM_FROUND_TO_NEAREST_INT 0x00
+#define _MM_FROUND_TO_NEG_INF 0x01
+#define _MM_FROUND_TO_POS_INF 0x02
+#define _MM_FROUND_TO_ZERO 0x03
+#define _MM_FROUND_CUR_DIRECTION 0x04
+#define _MM_FROUND_NO_EXC 0x05
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set_epi64 (long long __A, long long __B, long long __C,
+ long long __D, long long __E, long long __F,
+ long long __G, long long __H)
+{
+ return __extension__ (__m512i) (__v8di)
+ { __H, __G, __F, __E, __D, __C, __B, __A };
+}
+
+/* Create the vector [A B C D E F G H I J K L M N O P]. */
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set_epi32 (int __A, int __B, int __C, int __D,
+ int __E, int __F, int __G, int __H,
+ int __I, int __J, int __K, int __L,
+ int __M, int __N, int __O, int __P)
+{
+ return __extension__ (__m512i)(__v16si)
+ { __P, __O, __N, __M, __L, __K, __J, __I,
+ __H, __G, __F, __E, __D, __C, __B, __A };
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set_pd (double __A, double __B, double __C, double __D,
+ double __E, double __F, double __G, double __H)
+{
+ return __extension__ (__m512d)
+ { __H, __G, __F, __E, __D, __C, __B, __A };
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set_ps (float __A, float __B, float __C, float __D,
+ float __E, float __F, float __G, float __H,
+ float __I, float __J, float __K, float __L,
+ float __M, float __N, float __O, float __P)
+{
+ return __extension__ (__m512)
+ { __P, __O, __N, __M, __L, __K, __J, __I,
+ __H, __G, __F, __E, __D, __C, __B, __A };
+}
+
+#define _mm512_setr_epi64(e0,e1,e2,e3,e4,e5,e6,e7) \
+ _mm512_set_epi64(e7,e6,e5,e4,e3,e2,e1,e0)
+
+#define _mm512_setr_epi32(e0,e1,e2,e3,e4,e5,e6,e7, \
+ e8,e9,e10,e11,e12,e13,e14,e15) \
+ _mm512_set_epi32(e15,e14,e13,e12,e11,e10,e9,e8,e7,e6,e5,e4,e3,e2,e1,e0)
+
+#define _mm512_setr_pd(e0,e1,e2,e3,e4,e5,e6,e7) \
+ _mm512_set_pd(e7,e6,e5,e4,e3,e2,e1,e0)
+
+#define _mm512_setr_ps(e0,e1,e2,e3,e4,e5,e6,e7,e8,e9,e10,e11,e12,e13,e14,e15) \
+ _mm512_set_ps(e15,e14,e13,e12,e11,e10,e9,e8,e7,e6,e5,e4,e3,e2,e1,e0)
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_setzero_ps (void)
+{
+ return __extension__ (__m512){ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
+ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 };
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_setzero_pd (void)
+{
+ return __extension__ (__m512d) { 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 };
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_setzero_si512 (void)
+{
+ return __extension__ (__m512i)(__v8di){ 0, 0, 0, 0, 0, 0, 0, 0 };
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mov_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_movapd512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mov_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_movapd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mov_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_movaps512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mov_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_movaps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_load_pd (void const *__P)
+{
+ return *(__m512d *) __P;
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_load_pd (__m512d __W, __mmask8 __U, void const *__P)
+{
+ return (__m512d) __builtin_ia32_loadapd512_mask ((const __v8df *) __P,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_load_pd (__mmask8 __U, void const *__P)
+{
+ return (__m512d) __builtin_ia32_loadapd512_mask ((const __v8df *) __P,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_store_pd (void *__P, __m512d __A)
+{
+ *(__m512d *) __P = __A;
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_store_pd (void *__P, __mmask8 __U, __m512d __A)
+{
+ __builtin_ia32_storeapd512_mask ((__v8df *) __P, (__v8df) __A,
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_load_ps (void const *__P)
+{
+ return *(__m512 *) __P;
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_load_ps (__m512 __W, __mmask16 __U, void const *__P)
+{
+ return (__m512) __builtin_ia32_loadaps512_mask ((const __v16sf *) __P,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_load_ps (__mmask16 __U, void const *__P)
+{
+ return (__m512) __builtin_ia32_loadaps512_mask ((const __v16sf *) __P,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_store_ps (void *__P, __m512 __A)
+{
+ *(__m512 *) __P = __A;
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_store_ps (void *__P, __mmask16 __U, __m512 __A)
+{
+ __builtin_ia32_storeaps512_mask ((__v16sf *) __P, (__v16sf) __A,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mov_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_movdqa64_512_mask ((__v8di) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mov_epi64 (__mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_movdqa64_512_mask ((__v8di) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_load_epi64 (void const *__P)
+{
+ return *(__m512i *) __P;
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_load_epi64 (__m512i __W, __mmask8 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_movdqa64load512_mask ((const __v8di *) __P,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_load_epi64 (__mmask8 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_movdqa64load512_mask ((const __v8di *) __P,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_store_epi64 (void *__P, __m512i __A)
+{
+ *(__m512i *) __P = __A;
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_store_epi64 (void *__P, __mmask8 __U, __m512i __A)
+{
+ __builtin_ia32_movdqa64store512_mask ((__v8di *) __P, (__v8di) __A,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mov_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_movdqa32_512_mask ((__v16si) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mov_epi32 (__mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_movdqa32_512_mask ((__v16si) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_load_si512 (void const *__P)
+{
+ return *(__m512i *) __P;
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_load_epi32 (void const *__P)
+{
+ return *(__m512i *) __P;
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_load_epi32 (__m512i __W, __mmask16 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_movdqa32load512_mask ((const __v16si *) __P,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_load_epi32 (__mmask16 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_movdqa32load512_mask ((const __v16si *) __P,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_store_si512 (void *__P, __m512i __A)
+{
+ *(__m512i *) __P = __A;
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_store_epi32 (void *__P, __m512i __A)
+{
+ *(__m512i *) __P = __A;
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_store_epi32 (void *__P, __mmask16 __U, __m512i __A)
+{
+ __builtin_ia32_movdqa32store512_mask ((__v16si *) __P, (__v16si) __A,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mullo_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmulld512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mullo_epi32 (__mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmulld512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mullo_epi32 (__m512i __W, __mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmulld512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sllv_epi32 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psllv16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sllv_epi32 (__m512i __W, __mmask16 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psllv16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sllv_epi32 (__mmask16 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psllv16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srav_epi32 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrav16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srav_epi32 (__m512i __W, __mmask16 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrav16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srav_epi32 (__mmask16 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrav16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srlv_epi32 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrlv16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srlv_epi32 (__m512i __W, __mmask16 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrlv16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srlv_epi32 (__mmask16 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrlv16si_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_add_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_paddq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_add_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_paddq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_add_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_paddq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sub_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_psubq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sub_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_psubq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sub_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_psubq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sllv_epi64 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psllv8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sllv_epi64 (__m512i __W, __mmask8 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psllv8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sllv_epi64 (__mmask8 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psllv8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srav_epi64 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrav8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srav_epi64 (__m512i __W, __mmask8 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrav8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srav_epi64 (__mmask8 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrav8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srlv_epi64 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrlv8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srlv_epi64 (__m512i __W, __mmask8 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrlv8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srlv_epi64 (__mmask8 __U, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_psrlv8di_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_add_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_paddd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_add_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_paddd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_add_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_paddd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mul_epi32 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_pmuldq512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mul_epi32 (__m512i __W, __mmask8 __M, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_pmuldq512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v8di) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mul_epi32 (__mmask8 __M, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_pmuldq512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sub_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_psubd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sub_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_psubd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sub_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_psubd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mul_epu32 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_pmuludq512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mul_epu32 (__m512i __W, __mmask8 __M, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_pmuludq512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v8di) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mul_epu32 (__mmask8 __M, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_pmuludq512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_slli_epi64 (__m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psllqi512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_slli_epi64 (__m512i __W, __mmask8 __U, __m512i __A,
+ unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psllqi512_mask ((__v8di) __A, __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_slli_epi64 (__mmask8 __U, __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psllqi512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+#else
+#define _mm512_slli_epi64(X, C) \
+ ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)-1))
+
+#define _mm512_mask_slli_epi64(W, U, X, C) \
+ ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_slli_epi64(U, X, C) \
+ ((__m512i) __builtin_ia32_psllqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sll_epi64 (__m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psllq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sll_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psllq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sll_epi64 (__mmask8 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psllq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srli_epi64 (__m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psrlqi512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srli_epi64 (__m512i __W, __mmask8 __U,
+ __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psrlqi512_mask ((__v8di) __A, __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srli_epi64 (__mmask8 __U, __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psrlqi512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+#else
+#define _mm512_srli_epi64(X, C) \
+ ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)-1))
+
+#define _mm512_mask_srli_epi64(W, U, X, C) \
+ ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_srli_epi64(U, X, C) \
+ ((__m512i) __builtin_ia32_psrlqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srl_epi64 (__m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrlq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srl_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrlq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srl_epi64 (__mmask8 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrlq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srai_epi64 (__m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psraqi512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srai_epi64 (__m512i __W, __mmask8 __U, __m512i __A,
+ unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psraqi512_mask ((__v8di) __A, __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srai_epi64 (__mmask8 __U, __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psraqi512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+#else
+#define _mm512_srai_epi64(X, C) \
+ ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)-1))
+
+#define _mm512_mask_srai_epi64(W, U, X, C) \
+ ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_srai_epi64(U, X, C) \
+ ((__m512i) __builtin_ia32_psraqi512_mask ((__v8di)(__m512i)(X), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sra_epi64 (__m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psraq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sra_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psraq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sra_epi64 (__mmask8 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psraq512_mask ((__v8di) __A,
+ (__v2di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_slli_epi32 (__m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_pslldi512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_slli_epi32 (__m512i __W, __mmask16 __U, __m512i __A,
+ unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_pslldi512_mask ((__v16si) __A, __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_slli_epi32 (__mmask16 __U, __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_pslldi512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+#else
+#define _mm512_slli_epi32(X, C) \
+ ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)-1))
+
+#define _mm512_mask_slli_epi32(W, U, X, C) \
+ ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)(W),\
+ (__mmask16)(U)))
+
+#define _mm512_maskz_slli_epi32(U, X, C) \
+ ((__m512i) __builtin_ia32_pslldi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sll_epi32 (__m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_pslld512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sll_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_pslld512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sll_epi32 (__mmask16 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_pslld512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srli_epi32 (__m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psrldi512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srli_epi32 (__m512i __W, __mmask16 __U,
+ __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psrldi512_mask ((__v16si) __A, __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srli_epi32 (__mmask16 __U, __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psrldi512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+#else
+#define _mm512_srli_epi32(X, C) \
+ ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)-1))
+
+#define _mm512_mask_srli_epi32(W, U, X, C) \
+ ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)(W),\
+ (__mmask16)(U)))
+
+#define _mm512_maskz_srli_epi32(U, X, C) \
+ ((__m512i) __builtin_ia32_psrldi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srl_epi32 (__m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrld512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srl_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrld512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srl_epi32 (__mmask16 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrld512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_srai_epi32 (__m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psradi512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_srai_epi32 (__m512i __W, __mmask16 __U, __m512i __A,
+ unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psradi512_mask ((__v16si) __A, __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_srai_epi32 (__mmask16 __U, __m512i __A, unsigned int __B)
+{
+ return (__m512i) __builtin_ia32_psradi512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+#else
+#define _mm512_srai_epi32(X, C) \
+ ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)-1))
+
+#define _mm512_mask_srai_epi32(W, U, X, C) \
+ ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)(W),\
+ (__mmask16)(U)))
+
+#define _mm512_maskz_srai_epi32(U, X, C) \
+ ((__m512i) __builtin_ia32_psradi512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sra_epi32 (__m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrad512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sra_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrad512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sra_epi32 (__mmask16 __U, __m512i __A, __m128i __B)
+{
+ return (__m512i) __builtin_ia32_psrad512_mask ((__v16si) __A,
+ (__v4si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ternarylogic_epi64 (__m512i __A, __m512i __B, __m512i __C, const int imm)
+{
+ return (__m512i) __builtin_ia32_pternlogq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __C, imm,
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ternarylogic_epi64 (__m512i __A, __mmask8 __U, __m512i __B,
+ __m512i __C, const int imm)
+{
+ return (__m512i) __builtin_ia32_pternlogq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __C, imm,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ternarylogic_epi64 (__mmask8 __U, __m512i __A, __m512i __B,
+ __m512i __C, const int imm)
+{
+ return (__m512i) __builtin_ia32_pternlogq512_maskz ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __C,
+ imm, (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ternarylogic_epi32 (__m512i __A, __m512i __B, __m512i __C, const int imm)
+{
+ return (__m512i) __builtin_ia32_pternlogd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __C,
+ imm, (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ternarylogic_epi32 (__m512i __A, __mmask16 __U, __m512i __B,
+ __m512i __C, const int imm)
+{
+ return (__m512i) __builtin_ia32_pternlogd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __C,
+ imm, (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ternarylogic_epi32 (__mmask16 __U, __m512i __A, __m512i __B,
+ __m512i __C, const int imm)
+{
+ return (__m512i) __builtin_ia32_pternlogd512_maskz ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __C,
+ imm, (__mmask16) __U);
+}
+#else
+#define _mm512_ternarylogic_epi64(A, B, C, I) \
+ ((__m512i) __builtin_ia32_pternlogq512_mask ((__v8di)(__m512i)(A), \
+ (__v8di)(__m512i)(B), (__v8di)(__m512i)(C), (int)(I), (__mmask8)-1))
+#define _mm512_mask_ternarylogic_epi64(A, U, B, C, I) \
+ ((__m512i) __builtin_ia32_pternlogq512_mask ((__v8di)(__m512i)(A), \
+ (__v8di)(__m512i)(B), (__v8di)(__m512i)(C), (int)(I), (__mmask8)(U)))
+#define _mm512_maskz_ternarylogic_epi64(U, A, B, C, I) \
+ ((__m512i) __builtin_ia32_pternlogq512_maskz ((__v8di)(__m512i)(A), \
+ (__v8di)(__m512i)(B), (__v8di)(__m512i)(C), (int)(I), (__mmask8)(U)))
+#define _mm512_ternarylogic_epi32(A, B, C, I) \
+ ((__m512i) __builtin_ia32_pternlogd512_mask ((__v16si)(__m512i)(A), \
+ (__v16si)(__m512i)(B), (__v16si)(__m512i)(C), (int)(I), \
+ (__mmask16)-1))
+#define _mm512_mask_ternarylogic_epi32(A, U, B, C, I) \
+ ((__m512i) __builtin_ia32_pternlogd512_mask ((__v16si)(__m512i)(A), \
+ (__v16si)(__m512i)(B), (__v16si)(__m512i)(C), (int)(I), \
+ (__mmask16)(U)))
+#define _mm512_maskz_ternarylogic_epi32(U, A, B, C, I) \
+ ((__m512i) __builtin_ia32_pternlogd512_maskz ((__v16si)(__m512i)(A), \
+ (__v16si)(__m512i)(B), (__v16si)(__m512i)(C), (int)(I), \
+ (__mmask16)(U)))
+#endif
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rcp14_pd (__m512d __A)
+{
+ return (__m512d) __builtin_ia32_rcp14pd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rcp14_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rcp14pd512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rcp14_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rcp14pd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rcp14_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_rcp14ps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rcp14_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rcp14ps512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rcp14_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rcp14ps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rsqrt14_pd (__m512d __A)
+{
+ return (__m512d) __builtin_ia32_rsqrt14pd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rsqrt14_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rsqrt14pd512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rsqrt14_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rsqrt14pd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rsqrt14_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_rsqrt14ps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rsqrt14_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rsqrt14ps512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rsqrt14_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rsqrt14ps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sqrt_round_pd (__m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_sqrtpd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sqrt_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_sqrtpd512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sqrt_round_pd (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_sqrtpd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sqrt_round_ps (__m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_sqrtps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sqrt_round_ps (__m512 __W, __mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_sqrtps512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sqrt_round_ps (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_sqrtps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+#else
+#define _mm512_sqrt_round_pd(A, C) \
+ (__m512d)__builtin_ia32_sqrtpd512_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_sqrt_round_pd(W, U, A, C) \
+ (__m512d)__builtin_ia32_sqrtpd512_mask(A, W, U, C)
+
+#define _mm512_maskz_sqrt_round_pd(U, A, C) \
+ (__m512d)__builtin_ia32_sqrtpd512_mask(A, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_sqrt_round_ps(A, C) \
+ (__m512)__builtin_ia32_sqrtps512_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_sqrt_round_ps(W, U, A, C) \
+ (__m512)__builtin_ia32_sqrtps512_mask(A, W, U, C)
+
+#define _mm512_maskz_sqrt_round_ps(U, A, C) \
+ (__m512)__builtin_ia32_sqrtps512_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi8_epi32 (__m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxbd512_mask ((__v16qi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi8_epi32 (__m512i __W, __mmask16 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxbd512_mask ((__v16qi) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi8_epi32 (__mmask16 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxbd512_mask ((__v16qi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi8_epi64 (__m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxbq512_mask ((__v16qi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi8_epi64 (__m512i __W, __mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxbq512_mask ((__v16qi) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi8_epi64 (__mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxbq512_mask ((__v16qi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi16_epi32 (__m256i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxwd512_mask ((__v16hi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi16_epi32 (__m512i __W, __mmask16 __U, __m256i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxwd512_mask ((__v16hi) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi16_epi32 (__mmask16 __U, __m256i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxwd512_mask ((__v16hi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi16_epi64 (__m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxwq512_mask ((__v8hi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi16_epi64 (__m512i __W, __mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxwq512_mask ((__v8hi) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi16_epi64 (__mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovsxwq512_mask ((__v8hi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi32_epi64 (__m256i __X)
+{
+ return (__m512i) __builtin_ia32_pmovsxdq512_mask ((__v8si) __X,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi32_epi64 (__m512i __W, __mmask8 __U, __m256i __X)
+{
+ return (__m512i) __builtin_ia32_pmovsxdq512_mask ((__v8si) __X,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi32_epi64 (__mmask8 __U, __m256i __X)
+{
+ return (__m512i) __builtin_ia32_pmovsxdq512_mask ((__v8si) __X,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepu8_epi32 (__m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxbd512_mask ((__v16qi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepu8_epi32 (__m512i __W, __mmask16 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxbd512_mask ((__v16qi) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepu8_epi32 (__mmask16 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxbd512_mask ((__v16qi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepu8_epi64 (__m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxbq512_mask ((__v16qi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepu8_epi64 (__m512i __W, __mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxbq512_mask ((__v16qi) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepu8_epi64 (__mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxbq512_mask ((__v16qi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepu16_epi32 (__m256i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxwd512_mask ((__v16hi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepu16_epi32 (__m512i __W, __mmask16 __U, __m256i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxwd512_mask ((__v16hi) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepu16_epi32 (__mmask16 __U, __m256i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxwd512_mask ((__v16hi) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepu16_epi64 (__m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxwq512_mask ((__v8hi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepu16_epi64 (__m512i __W, __mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxwq512_mask ((__v8hi) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepu16_epi64 (__mmask8 __U, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pmovzxwq512_mask ((__v8hi) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepu32_epi64 (__m256i __X)
+{
+ return (__m512i) __builtin_ia32_pmovzxdq512_mask ((__v8si) __X,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepu32_epi64 (__m512i __W, __mmask8 __U, __m256i __X)
+{
+ return (__m512i) __builtin_ia32_pmovzxdq512_mask ((__v8si) __X,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepu32_epi64 (__mmask8 __U, __m256i __X)
+{
+ return (__m512i) __builtin_ia32_pmovzxdq512_mask ((__v8si) __X,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_add_round_pd (__m512d __A, __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_addpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_add_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_addpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_add_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_addpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_add_round_ps (__m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_addps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_add_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_addps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_add_round_ps (__mmask16 __U, __m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_addps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sub_round_pd (__m512d __A, __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_subpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sub_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_subpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sub_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_subpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sub_round_ps (__m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_subps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sub_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_subps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sub_round_ps (__mmask16 __U, __m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_subps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+#else
+#define _mm512_add_round_pd(A, B, C) \
+ (__m512d)__builtin_ia32_addpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_add_round_pd(W, U, A, B, C) \
+ (__m512d)__builtin_ia32_addpd512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_add_round_pd(U, A, B, C) \
+ (__m512d)__builtin_ia32_addpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_add_round_ps(A, B, C) \
+ (__m512)__builtin_ia32_addps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_add_round_ps(W, U, A, B, C) \
+ (__m512)__builtin_ia32_addps512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_add_round_ps(U, A, B, C) \
+ (__m512)__builtin_ia32_addps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, C)
+
+#define _mm512_sub_round_pd(A, B, C) \
+ (__m512d)__builtin_ia32_subpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_sub_round_pd(W, U, A, B, C) \
+ (__m512d)__builtin_ia32_subpd512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_sub_round_pd(U, A, B, C) \
+ (__m512d)__builtin_ia32_subpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_sub_round_ps(A, B, C) \
+ (__m512)__builtin_ia32_subps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_sub_round_ps(W, U, A, B, C) \
+ (__m512)__builtin_ia32_subps512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_sub_round_ps(U, A, B, C) \
+ (__m512)__builtin_ia32_subps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, C)
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mul_round_pd (__m512d __A, __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_mulpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mul_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_mulpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mul_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_mulpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mul_round_ps (__m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_mulps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mul_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_mulps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mul_round_ps (__mmask16 __U, __m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_mulps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_div_round_pd (__m512d __M, __m512d __V, const int __R)
+{
+ return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __M,
+ (__v8df) __V,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_div_round_pd (__m512d __W, __mmask8 __U, __m512d __M,
+ __m512d __V, const int __R)
+{
+ return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __M,
+ (__v8df) __V,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_div_round_pd (__mmask8 __U, __m512d __M, __m512d __V,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __M,
+ (__v8df) __V,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_div_round_ps (__m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_div_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_div_round_ps (__mmask16 __U, __m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+#else
+#define _mm512_mul_round_pd(A, B, C) \
+ (__m512d)__builtin_ia32_mulpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_mul_round_pd(W, U, A, B, C) \
+ (__m512d)__builtin_ia32_mulpd512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_mul_round_pd(U, A, B, C) \
+ (__m512d)__builtin_ia32_mulpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_mul_round_ps(A, B, C) \
+ (__m512)__builtin_ia32_mulps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_mul_round_ps(W, U, A, B, C) \
+ (__m512)__builtin_ia32_mulps512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_mul_round_ps(U, A, B, C) \
+ (__m512)__builtin_ia32_mulps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, C)
+
+#define _mm512_div_round_pd(A, B, C) \
+ (__m512d)__builtin_ia32_divpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_div_round_pd(W, U, A, B, C) \
+ (__m512d)__builtin_ia32_divpd512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_div_round_pd(U, A, B, C) \
+ (__m512d)__builtin_ia32_divpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_div_round_ps(A, B, C) \
+ (__m512)__builtin_ia32_divps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_div_round_ps(W, U, A, B, C) \
+ (__m512)__builtin_ia32_divps512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_div_round_ps(U, A, B, C) \
+ (__m512)__builtin_ia32_divps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, C)
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_round_pd (__m512d __A, __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_maxpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_maxpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_maxpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_round_ps (__m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_maxps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_maxps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_round_ps (__mmask16 __U, __m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_maxps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_round_pd (__m512d __A, __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_minpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_minpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_minpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_round_ps (__m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_minps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_minps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_round_ps (__mmask16 __U, __m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_minps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+#else
+#define _mm512_max_round_pd(A, B, R) \
+ (__m512d)__builtin_ia32_maxpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), -1, R)
+
+#define _mm512_mask_max_round_pd(W, U, A, B, R) \
+ (__m512d)__builtin_ia32_maxpd512_mask(A, B, W, U, R)
+
+#define _mm512_maskz_max_round_pd(U, A, B, R) \
+ (__m512d)__builtin_ia32_maxpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), U, R)
+
+#define _mm512_max_round_ps(A, B, R) \
+ (__m512)__builtin_ia32_maxps512_mask(A, B, (__v16sf)_mm512_setzero_pd(), -1, R)
+
+#define _mm512_mask_max_round_ps(W, U, A, B, R) \
+ (__m512)__builtin_ia32_maxps512_mask(A, B, W, U, R)
+
+#define _mm512_maskz_max_round_ps(U, A, B, R) \
+ (__m512)__builtin_ia32_maxps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, R)
+
+#define _mm512_min_round_pd(A, B, R) \
+ (__m512d)__builtin_ia32_minpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), -1, R)
+
+#define _mm512_mask_min_round_pd(W, U, A, B, R) \
+ (__m512d)__builtin_ia32_minpd512_mask(A, B, W, U, R)
+
+#define _mm512_maskz_min_round_pd(U, A, B, R) \
+ (__m512d)__builtin_ia32_minpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), U, R)
+
+#define _mm512_min_round_ps(A, B, R) \
+ (__m512)__builtin_ia32_minps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), -1, R)
+
+#define _mm512_mask_min_round_ps(W, U, A, B, R) \
+ (__m512)__builtin_ia32_minps512_mask(A, B, W, U, R)
+
+#define _mm512_maskz_min_round_ps(U, A, B, R) \
+ (__m512)__builtin_ia32_minps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, R)
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_scalef_round_pd (__m512d __A, __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_scalefpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_scalef_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ __m512d __B, const int __R)
+{
+ return (__m512d) __builtin_ia32_scalefpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_scalef_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_scalefpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_scalef_round_ps (__m512 __A, __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_scalefps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_scalef_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __R)
+{
+ return (__m512) __builtin_ia32_scalefps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_scalef_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ const int __R)
+{
+ return (__m512) __builtin_ia32_scalefps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+#else
+#define _mm512_scalef_round_pd(A, B, C) \
+ (__m512d)__builtin_ia32_scalefpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), -1, C)
+
+#define _mm512_mask_scalef_round_pd(W, U, A, B, C) \
+ (__m512d)__builtin_ia32_scalefpd512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_scalef_round_pd(U, A, B, C) \
+ (__m512d)__builtin_ia32_scalefpd512_mask(A, B, (__v8df)_mm512_setzero_pd(), U, C)
+
+#define _mm512_scalef_round_ps(A, B, C) \
+ (__m512)__builtin_ia32_scalefps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), -1, C)
+
+#define _mm512_mask_scalef_round_ps(W, U, A, B, C) \
+ (__m512)__builtin_ia32_scalefps512_mask(A, B, W, U, C)
+
+#define _mm512_maskz_scalef_round_ps(U, A, B, C) \
+ (__m512)__builtin_ia32_scalefps512_mask(A, B, (__v16sf)_mm512_setzero_ps(), U, C)
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmadd_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmadd_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmadd_round_pd (__m512d __A, __m512d __B, __m512d __C,
+ __mmask8 __U, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmadd_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmadd_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmadd_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmadd_round_ps (__m512 __A, __m512 __B, __m512 __C,
+ __mmask16 __U, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmadd_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsub_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsub_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsub_round_pd (__m512d __A, __m512d __B, __m512d __C,
+ __mmask8 __U, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmsubpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsub_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsub_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsub_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsub_round_ps (__m512 __A, __m512 __B, __m512 __C,
+ __mmask16 __U, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmsubps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmaddsub_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmaddsub_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmaddsub_round_pd (__m512d __A, __m512d __B, __m512d __C,
+ __mmask8 __U, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmaddsub_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmaddsub_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmaddsub_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmaddsub_round_ps (__m512 __A, __m512 __B, __m512 __C,
+ __mmask16 __U, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmaddsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsubadd_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsubadd_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsubadd_round_pd (__m512d __A, __m512d __B, __m512d __C,
+ __mmask8 __U, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmsubaddpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsubadd_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsubadd_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsubadd_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsubadd_round_ps (__m512 __A, __m512 __B, __m512 __C,
+ __mmask16 __U, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmsubaddps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsubadd_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmadd_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmadd_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfnmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmadd_round_pd (__m512d __A, __m512d __B, __m512d __C,
+ __mmask8 __U, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask3 (-(__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmadd_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmadd_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmadd_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfnmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmadd_round_ps (__m512 __A, __m512 __B, __m512 __C,
+ __mmask16 __U, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask3 (-(__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmadd_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmsub_round_pd (__m512d __A, __m512d __B, __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmsub_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfnmsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmsub_round_pd (__m512d __A, __m512d __B, __m512d __C,
+ __mmask8 __U, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfnmsubpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmsub_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512d __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmsub_round_ps (__m512 __A, __m512 __B, __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmsub_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfnmsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmsub_round_ps (__m512 __A, __m512 __B, __m512 __C,
+ __mmask16 __U, const int __R)
+{
+ return (__m512) __builtin_ia32_vfnmsubps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmsub_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512 __C, const int __R)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U, __R);
+}
+#else
+#define _mm512_fmadd_round_pd(A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, C, -1, R)
+
+#define _mm512_mask_fmadd_round_pd(A, U, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, C, U, R)
+
+#define _mm512_mask3_fmadd_round_pd(A, B, C, U, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmadd_round_pd(U, A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_maskz(A, B, C, U, R)
+
+#define _mm512_fmadd_round_ps(A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask(A, B, C, -1, R)
+
+#define _mm512_mask_fmadd_round_ps(A, U, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask(A, B, C, U, R)
+
+#define _mm512_mask3_fmadd_round_ps(A, B, C, U, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmadd_round_ps(U, A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_maskz(A, B, C, U, R)
+
+#define _mm512_fmsub_round_pd(A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, -(C), -1, R)
+
+#define _mm512_mask_fmsub_round_pd(A, U, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, -(C), U, R)
+
+#define _mm512_mask3_fmsub_round_pd(A, B, C, U, R) \
+ (__m512d)__builtin_ia32_vfmsubpd512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmsub_round_pd(U, A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_maskz(A, B, -(C), U, R)
+
+#define _mm512_fmsub_round_ps(A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask(A, B, -(C), -1, R)
+
+#define _mm512_mask_fmsub_round_ps(A, U, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask(A, B, -(C), U, R)
+
+#define _mm512_mask3_fmsub_round_ps(A, B, C, U, R) \
+ (__m512)__builtin_ia32_vfmsubps512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmsub_round_ps(U, A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_maskz(A, B, -(C), U, R)
+
+#define _mm512_fmaddsub_round_pd(A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddsubpd512_mask(A, B, C, -1, R)
+
+#define _mm512_mask_fmaddsub_round_pd(A, U, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask(A, B, C, U, R)
+
+#define _mm512_mask3_fmaddsub_round_pd(A, B, C, U, R) \
+ (__m512d)__builtin_ia32_vfmaddsubpd512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmaddsub_round_pd(U, A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddsubpd512_maskz(A, B, C, U, R)
+
+#define _mm512_fmaddsub_round_ps(A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddsubps512_mask(A, B, C, -1, R)
+
+#define _mm512_mask_fmaddsub_round_ps(A, U, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddsubps512_mask(A, B, C, U, R)
+
+#define _mm512_mask3_fmaddsub_round_ps(A, B, C, U, R) \
+ (__m512)__builtin_ia32_vfmaddsubps512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmaddsub_round_ps(U, A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddsubps512_maskz(A, B, C, U, R)
+
+#define _mm512_fmsubadd_round_pd(A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddsubpd512_mask(A, B, -(C), -1, R)
+
+#define _mm512_mask_fmsubadd_round_pd(A, U, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddsubpd512_mask(A, B, -(C), U, R)
+
+#define _mm512_mask3_fmsubadd_round_pd(A, B, C, U, R) \
+ (__m512d)__builtin_ia32_vfmsubaddpd512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmsubadd_round_pd(U, A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddsubpd512_maskz(A, B, -(C), U, R)
+
+#define _mm512_fmsubadd_round_ps(A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddsubps512_mask(A, B, -(C), -1, R)
+
+#define _mm512_mask_fmsubadd_round_ps(A, U, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddsubps512_mask(A, B, -(C), U, R)
+
+#define _mm512_mask3_fmsubadd_round_ps(A, B, C, U, R) \
+ (__m512)__builtin_ia32_vfmsubaddps512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fmsubadd_round_ps(U, A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddsubps512_maskz(A, B, -(C), U, R)
+
+#define _mm512_fnmadd_round_pd(A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask(-(A), B, C, -1, R)
+
+#define _mm512_mask_fnmadd_round_pd(A, U, B, C, R) \
+ (__m512d)__builtin_ia32_vfnmaddpd512_mask(-(A), B, C, U, R)
+
+#define _mm512_mask3_fnmadd_round_pd(A, B, C, U, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask3(-(A), B, C, U, R)
+
+#define _mm512_maskz_fnmadd_round_pd(U, A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_maskz(-(A), B, C, U, R)
+
+#define _mm512_fnmadd_round_ps(A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask(-(A), B, C, -1, R)
+
+#define _mm512_mask_fnmadd_round_ps(A, U, B, C, R) \
+ (__m512)__builtin_ia32_vfnmaddps512_mask(-(A), B, C, U, R)
+
+#define _mm512_mask3_fnmadd_round_ps(A, B, C, U, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask3(-(A), B, C, U, R)
+
+#define _mm512_maskz_fnmadd_round_ps(U, A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_maskz(-(A), B, C, U, R)
+
+#define _mm512_fnmsub_round_pd(A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_mask(-(A), B, -(C), -1, R)
+
+#define _mm512_mask_fnmsub_round_pd(A, U, B, C, R) \
+ (__m512d)__builtin_ia32_vfnmsubpd512_mask(A, B, C, U, R)
+
+#define _mm512_mask3_fnmsub_round_pd(A, B, C, U, R) \
+ (__m512d)__builtin_ia32_vfnmsubpd512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fnmsub_round_pd(U, A, B, C, R) \
+ (__m512d)__builtin_ia32_vfmaddpd512_maskz(-(A), B, -(C), U, R)
+
+#define _mm512_fnmsub_round_ps(A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_mask(-(A), B, -(C), -1, R)
+
+#define _mm512_mask_fnmsub_round_ps(A, U, B, C, R) \
+ (__m512)__builtin_ia32_vfnmsubps512_mask(A, B, C, U, R)
+
+#define _mm512_mask3_fnmsub_round_ps(A, B, C, U, R) \
+ (__m512)__builtin_ia32_vfnmsubps512_mask3(A, B, C, U, R)
+
+#define _mm512_maskz_fnmsub_round_ps(U, A, B, C, R) \
+ (__m512)__builtin_ia32_vfmaddps512_maskz(-(A), B, -(C), U, R)
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_abs_epi64 (__m512i __A)
+{
+ return (__m512i) __builtin_ia32_pabsq512_mask ((__v8di) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_abs_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_pabsq512_mask ((__v8di) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_abs_epi64 (__mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_pabsq512_mask ((__v8di) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_abs_epi32 (__m512i __A)
+{
+ return (__m512i) __builtin_ia32_pabsd512_mask ((__v16si) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_abs_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_pabsd512_mask ((__v16si) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_abs_epi32 (__mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_pabsd512_mask ((__v16si) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcastss_ps (__m128 __A)
+{
+ __v16sf __O;
+ return (__m512) __builtin_ia32_broadcastss512 ((__v4sf) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcastss_ps (__m512 __O, __mmask16 __M, __m128 __A)
+{
+ return (__m512) __builtin_ia32_broadcastss512 ((__v4sf) __A,
+ (__v16sf) __O, __M);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcastss_ps (__mmask16 __M, __m128 __A)
+{
+ return (__m512) __builtin_ia32_broadcastss512 ((__v4sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __M);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcastsd_pd (__m128d __A)
+{
+ __v8df __O;
+ return (__m512d) __builtin_ia32_broadcastsd512 ((__v2df) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcastsd_pd (__m512d __O, __mmask8 __M, __m128d __A)
+{
+ return (__m512d) __builtin_ia32_broadcastsd512 ((__v2df) __A,
+ (__v8df) __O, __M);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcastsd_pd (__mmask8 __M, __m128d __A)
+{
+ return (__m512d) __builtin_ia32_broadcastsd512 ((__v2df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcastd_epi32 (__m128i __A)
+{
+ __v16si __O;
+ return (__m512i) __builtin_ia32_pbroadcastd512 ((__v4si) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcastd_epi32 (__m512i __O, __mmask16 __M, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pbroadcastd512 ((__v4si) __A,
+ (__v16si) __O, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcastd_epi32 (__mmask16 __M, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pbroadcastd512 ((__v4si) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set1_epi32 (int __A)
+{
+ __v16si __O;
+ return (__m512i) __builtin_ia32_pbroadcastd512_gpr_mask (__A, __O,
+ (__mmask16)(-1));
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_set1_epi32 (__m512i __O, __mmask16 __M, int __A)
+{
+ return (__m512i) __builtin_ia32_pbroadcastd512_gpr_mask (__A, (__v16si) __O,
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_set1_epi32 (__mmask16 __M, int __A)
+{
+ return (__m512i)
+ __builtin_ia32_pbroadcastd512_gpr_mask (__A,
+ (__v16si) _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcastq_epi64 (__m128i __A)
+{
+ __v8di __O;
+ return (__m512i) __builtin_ia32_pbroadcastq512 ((__v2di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcastq_epi64 (__m512i __O, __mmask8 __M, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pbroadcastq512 ((__v2di) __A,
+ (__v8di) __O, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcastq_epi64 (__mmask8 __M, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_pbroadcastq512 ((__v2di) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set1_epi64 (long long __A)
+{
+ __v8di __O;
+#ifdef TARGET_64BIT
+ return (__m512i) __builtin_ia32_pbroadcastq512_gpr_mask (__A, __O,
+ (__mmask8)(-1));
+#else
+ return (__m512i) __builtin_ia32_pbroadcastq512_mem_mask (__A, __O,
+ (__mmask8)(-1));
+#endif
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_set1_epi64 (__m512i __O, __mmask8 __M, long long __A)
+{
+#ifdef TARGET_64BIT
+ return (__m512i) __builtin_ia32_pbroadcastq512_gpr_mask (__A, (__v8di) __O,
+ __M);
+#else
+ return (__m512i) __builtin_ia32_pbroadcastq512_mem_mask (__A, (__v8di) __O,
+ __M);
+#endif
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_set1_epi64 (__mmask8 __M, long long __A)
+{
+#ifdef TARGET_64BIT
+ return (__m512i)
+ __builtin_ia32_pbroadcastq512_gpr_mask (__A,
+ (__v8di) _mm512_setzero_si512 (),
+ __M);
+#else
+ return (__m512i)
+ __builtin_ia32_pbroadcastq512_mem_mask (__A,
+ (__v8di) _mm512_setzero_si512 (),
+ __M);
+#endif
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcast_f32x4 (__m128 __A)
+{
+ __v16sf __O;
+ return (__m512) __builtin_ia32_broadcastf32x4_512 ((__v4sf) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcast_f32x4 (__m512 __O, __mmask16 __M, __m128 __A)
+{
+ return (__m512) __builtin_ia32_broadcastf32x4_512 ((__v4sf) __A,
+ (__v16sf) __O,
+ __M);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcast_f32x4 (__mmask16 __M, __m128 __A)
+{
+ return (__m512) __builtin_ia32_broadcastf32x4_512 ((__v4sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcast_i32x4 (__m128i __A)
+{
+ __v16si __O;
+ return (__m512i) __builtin_ia32_broadcasti32x4_512 ((__v4si) __A,
+ __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcast_i32x4 (__m512i __O, __mmask16 __M, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_broadcasti32x4_512 ((__v4si) __A,
+ (__v16si) __O,
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcast_i32x4 (__mmask16 __M, __m128i __A)
+{
+ return (__m512i) __builtin_ia32_broadcasti32x4_512 ((__v4si) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcast_f64x4 (__m256d __A)
+{
+ __v8df __O;
+ return (__m512d) __builtin_ia32_broadcastf64x4_512 ((__v4df) __A,
+ __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcast_f64x4 (__m512d __O, __mmask8 __M, __m256d __A)
+{
+ return (__m512d) __builtin_ia32_broadcastf64x4_512 ((__v4df) __A,
+ (__v8df) __O,
+ __M);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcast_f64x4 (__mmask8 __M, __m256d __A)
+{
+ return (__m512d) __builtin_ia32_broadcastf64x4_512 ((__v4df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_broadcast_i64x4 (__m256i __A)
+{
+ __v8di __O;
+ return (__m512i) __builtin_ia32_broadcasti64x4_512 ((__v4di) __A,
+ __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_broadcast_i64x4 (__m512i __O, __mmask8 __M, __m256i __A)
+{
+ return (__m512i) __builtin_ia32_broadcasti64x4_512 ((__v4di) __A,
+ (__v8di) __O,
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_broadcast_i64x4 (__mmask8 __M, __m256i __A)
+{
+ return (__m512i) __builtin_ia32_broadcasti64x4_512 ((__v4di) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+typedef enum
+{
+ _MM_PERM_AAAA = 0x00, _MM_PERM_AAAB = 0x01, _MM_PERM_AAAC = 0x02,
+ _MM_PERM_AAAD = 0x03, _MM_PERM_AABA = 0x04, _MM_PERM_AABB = 0x05,
+ _MM_PERM_AABC = 0x06, _MM_PERM_AABD = 0x07, _MM_PERM_AACA = 0x08,
+ _MM_PERM_AACB = 0x09, _MM_PERM_AACC = 0x0A, _MM_PERM_AACD = 0x0B,
+ _MM_PERM_AADA = 0x0C, _MM_PERM_AADB = 0x0D, _MM_PERM_AADC = 0x0E,
+ _MM_PERM_AADD = 0x0F, _MM_PERM_ABAA = 0x10, _MM_PERM_ABAB = 0x11,
+ _MM_PERM_ABAC = 0x12, _MM_PERM_ABAD = 0x13, _MM_PERM_ABBA = 0x14,
+ _MM_PERM_ABBB = 0x15, _MM_PERM_ABBC = 0x16, _MM_PERM_ABBD = 0x17,
+ _MM_PERM_ABCA = 0x18, _MM_PERM_ABCB = 0x19, _MM_PERM_ABCC = 0x1A,
+ _MM_PERM_ABCD = 0x1B, _MM_PERM_ABDA = 0x1C, _MM_PERM_ABDB = 0x1D,
+ _MM_PERM_ABDC = 0x1E, _MM_PERM_ABDD = 0x1F, _MM_PERM_ACAA = 0x20,
+ _MM_PERM_ACAB = 0x21, _MM_PERM_ACAC = 0x22, _MM_PERM_ACAD = 0x23,
+ _MM_PERM_ACBA = 0x24, _MM_PERM_ACBB = 0x25, _MM_PERM_ACBC = 0x26,
+ _MM_PERM_ACBD = 0x27, _MM_PERM_ACCA = 0x28, _MM_PERM_ACCB = 0x29,
+ _MM_PERM_ACCC = 0x2A, _MM_PERM_ACCD = 0x2B, _MM_PERM_ACDA = 0x2C,
+ _MM_PERM_ACDB = 0x2D, _MM_PERM_ACDC = 0x2E, _MM_PERM_ACDD = 0x2F,
+ _MM_PERM_ADAA = 0x30, _MM_PERM_ADAB = 0x31, _MM_PERM_ADAC = 0x32,
+ _MM_PERM_ADAD = 0x33, _MM_PERM_ADBA = 0x34, _MM_PERM_ADBB = 0x35,
+ _MM_PERM_ADBC = 0x36, _MM_PERM_ADBD = 0x37, _MM_PERM_ADCA = 0x38,
+ _MM_PERM_ADCB = 0x39, _MM_PERM_ADCC = 0x3A, _MM_PERM_ADCD = 0x3B,
+ _MM_PERM_ADDA = 0x3C, _MM_PERM_ADDB = 0x3D, _MM_PERM_ADDC = 0x3E,
+ _MM_PERM_ADDD = 0x3F, _MM_PERM_BAAA = 0x40, _MM_PERM_BAAB = 0x41,
+ _MM_PERM_BAAC = 0x42, _MM_PERM_BAAD = 0x43, _MM_PERM_BABA = 0x44,
+ _MM_PERM_BABB = 0x45, _MM_PERM_BABC = 0x46, _MM_PERM_BABD = 0x47,
+ _MM_PERM_BACA = 0x48, _MM_PERM_BACB = 0x49, _MM_PERM_BACC = 0x4A,
+ _MM_PERM_BACD = 0x4B, _MM_PERM_BADA = 0x4C, _MM_PERM_BADB = 0x4D,
+ _MM_PERM_BADC = 0x4E, _MM_PERM_BADD = 0x4F, _MM_PERM_BBAA = 0x50,
+ _MM_PERM_BBAB = 0x51, _MM_PERM_BBAC = 0x52, _MM_PERM_BBAD = 0x53,
+ _MM_PERM_BBBA = 0x54, _MM_PERM_BBBB = 0x55, _MM_PERM_BBBC = 0x56,
+ _MM_PERM_BBBD = 0x57, _MM_PERM_BBCA = 0x58, _MM_PERM_BBCB = 0x59,
+ _MM_PERM_BBCC = 0x5A, _MM_PERM_BBCD = 0x5B, _MM_PERM_BBDA = 0x5C,
+ _MM_PERM_BBDB = 0x5D, _MM_PERM_BBDC = 0x5E, _MM_PERM_BBDD = 0x5F,
+ _MM_PERM_BCAA = 0x60, _MM_PERM_BCAB = 0x61, _MM_PERM_BCAC = 0x62,
+ _MM_PERM_BCAD = 0x63, _MM_PERM_BCBA = 0x64, _MM_PERM_BCBB = 0x65,
+ _MM_PERM_BCBC = 0x66, _MM_PERM_BCBD = 0x67, _MM_PERM_BCCA = 0x68,
+ _MM_PERM_BCCB = 0x69, _MM_PERM_BCCC = 0x6A, _MM_PERM_BCCD = 0x6B,
+ _MM_PERM_BCDA = 0x6C, _MM_PERM_BCDB = 0x6D, _MM_PERM_BCDC = 0x6E,
+ _MM_PERM_BCDD = 0x6F, _MM_PERM_BDAA = 0x70, _MM_PERM_BDAB = 0x71,
+ _MM_PERM_BDAC = 0x72, _MM_PERM_BDAD = 0x73, _MM_PERM_BDBA = 0x74,
+ _MM_PERM_BDBB = 0x75, _MM_PERM_BDBC = 0x76, _MM_PERM_BDBD = 0x77,
+ _MM_PERM_BDCA = 0x78, _MM_PERM_BDCB = 0x79, _MM_PERM_BDCC = 0x7A,
+ _MM_PERM_BDCD = 0x7B, _MM_PERM_BDDA = 0x7C, _MM_PERM_BDDB = 0x7D,
+ _MM_PERM_BDDC = 0x7E, _MM_PERM_BDDD = 0x7F, _MM_PERM_CAAA = 0x80,
+ _MM_PERM_CAAB = 0x81, _MM_PERM_CAAC = 0x82, _MM_PERM_CAAD = 0x83,
+ _MM_PERM_CABA = 0x84, _MM_PERM_CABB = 0x85, _MM_PERM_CABC = 0x86,
+ _MM_PERM_CABD = 0x87, _MM_PERM_CACA = 0x88, _MM_PERM_CACB = 0x89,
+ _MM_PERM_CACC = 0x8A, _MM_PERM_CACD = 0x8B, _MM_PERM_CADA = 0x8C,
+ _MM_PERM_CADB = 0x8D, _MM_PERM_CADC = 0x8E, _MM_PERM_CADD = 0x8F,
+ _MM_PERM_CBAA = 0x90, _MM_PERM_CBAB = 0x91, _MM_PERM_CBAC = 0x92,
+ _MM_PERM_CBAD = 0x93, _MM_PERM_CBBA = 0x94, _MM_PERM_CBBB = 0x95,
+ _MM_PERM_CBBC = 0x96, _MM_PERM_CBBD = 0x97, _MM_PERM_CBCA = 0x98,
+ _MM_PERM_CBCB = 0x99, _MM_PERM_CBCC = 0x9A, _MM_PERM_CBCD = 0x9B,
+ _MM_PERM_CBDA = 0x9C, _MM_PERM_CBDB = 0x9D, _MM_PERM_CBDC = 0x9E,
+ _MM_PERM_CBDD = 0x9F, _MM_PERM_CCAA = 0xA0, _MM_PERM_CCAB = 0xA1,
+ _MM_PERM_CCAC = 0xA2, _MM_PERM_CCAD = 0xA3, _MM_PERM_CCBA = 0xA4,
+ _MM_PERM_CCBB = 0xA5, _MM_PERM_CCBC = 0xA6, _MM_PERM_CCBD = 0xA7,
+ _MM_PERM_CCCA = 0xA8, _MM_PERM_CCCB = 0xA9, _MM_PERM_CCCC = 0xAA,
+ _MM_PERM_CCCD = 0xAB, _MM_PERM_CCDA = 0xAC, _MM_PERM_CCDB = 0xAD,
+ _MM_PERM_CCDC = 0xAE, _MM_PERM_CCDD = 0xAF, _MM_PERM_CDAA = 0xB0,
+ _MM_PERM_CDAB = 0xB1, _MM_PERM_CDAC = 0xB2, _MM_PERM_CDAD = 0xB3,
+ _MM_PERM_CDBA = 0xB4, _MM_PERM_CDBB = 0xB5, _MM_PERM_CDBC = 0xB6,
+ _MM_PERM_CDBD = 0xB7, _MM_PERM_CDCA = 0xB8, _MM_PERM_CDCB = 0xB9,
+ _MM_PERM_CDCC = 0xBA, _MM_PERM_CDCD = 0xBB, _MM_PERM_CDDA = 0xBC,
+ _MM_PERM_CDDB = 0xBD, _MM_PERM_CDDC = 0xBE, _MM_PERM_CDDD = 0xBF,
+ _MM_PERM_DAAA = 0xC0, _MM_PERM_DAAB = 0xC1, _MM_PERM_DAAC = 0xC2,
+ _MM_PERM_DAAD = 0xC3, _MM_PERM_DABA = 0xC4, _MM_PERM_DABB = 0xC5,
+ _MM_PERM_DABC = 0xC6, _MM_PERM_DABD = 0xC7, _MM_PERM_DACA = 0xC8,
+ _MM_PERM_DACB = 0xC9, _MM_PERM_DACC = 0xCA, _MM_PERM_DACD = 0xCB,
+ _MM_PERM_DADA = 0xCC, _MM_PERM_DADB = 0xCD, _MM_PERM_DADC = 0xCE,
+ _MM_PERM_DADD = 0xCF, _MM_PERM_DBAA = 0xD0, _MM_PERM_DBAB = 0xD1,
+ _MM_PERM_DBAC = 0xD2, _MM_PERM_DBAD = 0xD3, _MM_PERM_DBBA = 0xD4,
+ _MM_PERM_DBBB = 0xD5, _MM_PERM_DBBC = 0xD6, _MM_PERM_DBBD = 0xD7,
+ _MM_PERM_DBCA = 0xD8, _MM_PERM_DBCB = 0xD9, _MM_PERM_DBCC = 0xDA,
+ _MM_PERM_DBCD = 0xDB, _MM_PERM_DBDA = 0xDC, _MM_PERM_DBDB = 0xDD,
+ _MM_PERM_DBDC = 0xDE, _MM_PERM_DBDD = 0xDF, _MM_PERM_DCAA = 0xE0,
+ _MM_PERM_DCAB = 0xE1, _MM_PERM_DCAC = 0xE2, _MM_PERM_DCAD = 0xE3,
+ _MM_PERM_DCBA = 0xE4, _MM_PERM_DCBB = 0xE5, _MM_PERM_DCBC = 0xE6,
+ _MM_PERM_DCBD = 0xE7, _MM_PERM_DCCA = 0xE8, _MM_PERM_DCCB = 0xE9,
+ _MM_PERM_DCCC = 0xEA, _MM_PERM_DCCD = 0xEB, _MM_PERM_DCDA = 0xEC,
+ _MM_PERM_DCDB = 0xED, _MM_PERM_DCDC = 0xEE, _MM_PERM_DCDD = 0xEF,
+ _MM_PERM_DDAA = 0xF0, _MM_PERM_DDAB = 0xF1, _MM_PERM_DDAC = 0xF2,
+ _MM_PERM_DDAD = 0xF3, _MM_PERM_DDBA = 0xF4, _MM_PERM_DDBB = 0xF5,
+ _MM_PERM_DDBC = 0xF6, _MM_PERM_DDBD = 0xF7, _MM_PERM_DDCA = 0xF8,
+ _MM_PERM_DDCB = 0xF9, _MM_PERM_DDCC = 0xFA, _MM_PERM_DDCD = 0xFB,
+ _MM_PERM_DDDA = 0xFC, _MM_PERM_DDDB = 0xFD, _MM_PERM_DDDC = 0xFE,
+ _MM_PERM_DDDD = 0xFF
+} _MM_PERM_ENUM;
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_shuffle_epi32 (__m512i __A, _MM_PERM_ENUM __mask)
+{
+ return (__m512i) __builtin_ia32_pshufd512_mask ((__v16si) __A,
+ __mask,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_shuffle_epi32 (__m512i __W, __mmask16 __U, __m512i __A,
+ _MM_PERM_ENUM __mask)
+{
+ return (__m512i) __builtin_ia32_pshufd512_mask ((__v16si) __A,
+ __mask,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_shuffle_epi32 (__mmask16 __U, __m512i __A, _MM_PERM_ENUM __mask)
+{
+ return (__m512i) __builtin_ia32_pshufd512_mask ((__v16si) __A,
+ __mask,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_shuffle_i64x2 (__m512i __A, __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_shuf_i64x2_mask ((__v8di) __A,
+ (__v8di) __B, __imm,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_shuffle_i64x2 (__m512i __W, __mmask8 __U, __m512i __A,
+ __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_shuf_i64x2_mask ((__v8di) __A,
+ (__v8di) __B, __imm,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_shuffle_i64x2 (__mmask8 __U, __m512i __A, __m512i __B,
+ const int __imm)
+{
+ return (__m512i) __builtin_ia32_shuf_i64x2_mask ((__v8di) __A,
+ (__v8di) __B, __imm,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_shuffle_i32x4 (__m512i __A, __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_shuf_i32x4_mask ((__v16si) __A,
+ (__v16si) __B,
+ __imm,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_shuffle_i32x4 (__m512i __W, __mmask16 __U, __m512i __A,
+ __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_shuf_i32x4_mask ((__v16si) __A,
+ (__v16si) __B,
+ __imm,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_shuffle_i32x4 (__mmask16 __U, __m512i __A, __m512i __B,
+ const int __imm)
+{
+ return (__m512i) __builtin_ia32_shuf_i32x4_mask ((__v16si) __A,
+ (__v16si) __B,
+ __imm,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_shuffle_f64x2 (__m512d __A, __m512d __B, const int __imm)
+{
+ return (__m512d) __builtin_ia32_shuf_f64x2_mask ((__v8df) __A,
+ (__v8df) __B, __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_shuffle_f64x2 (__m512d __W, __mmask8 __U, __m512d __A,
+ __m512d __B, const int __imm)
+{
+ return (__m512d) __builtin_ia32_shuf_f64x2_mask ((__v8df) __A,
+ (__v8df) __B, __imm,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_shuffle_f64x2 (__mmask8 __U, __m512d __A, __m512d __B,
+ const int __imm)
+{
+ return (__m512d) __builtin_ia32_shuf_f64x2_mask ((__v8df) __A,
+ (__v8df) __B, __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_shuffle_f32x4 (__m512 __A, __m512 __B, const int __imm)
+{
+ return (__m512) __builtin_ia32_shuf_f32x4_mask ((__v16sf) __A,
+ (__v16sf) __B, __imm,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_shuffle_f32x4 (__m512 __W, __mmask16 __U, __m512 __A,
+ __m512 __B, const int __imm)
+{
+ return (__m512) __builtin_ia32_shuf_f32x4_mask ((__v16sf) __A,
+ (__v16sf) __B, __imm,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_shuffle_f32x4 (__mmask16 __U, __m512 __A, __m512 __B,
+ const int __imm)
+{
+ return (__m512) __builtin_ia32_shuf_f32x4_mask ((__v16sf) __A,
+ (__v16sf) __B, __imm,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+#else
+#define _mm512_shuffle_epi32(X, C) \
+ ((__m512i) __builtin_ia32_pshufd512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)-1))
+
+#define _mm512_mask_shuffle_epi32(W, U, X, C) \
+ ((__m512i) __builtin_ia32_pshufd512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)(W),\
+ (__mmask16)(U)))
+
+#define _mm512_maskz_shuffle_epi32(U, X, C) \
+ ((__m512i) __builtin_ia32_pshufd512_mask ((__v16si)(__m512i)(X), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)(U)))
+
+#define _mm512_shuffle_i64x2(X, Y, C) \
+ ((__m512i) __builtin_ia32_shuf_i64x2_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)-1))
+
+#define _mm512_mask_shuffle_i64x2(W, U, X, Y, C) \
+ ((__m512i) __builtin_ia32_shuf_i64x2_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(C),\
+ (__v8di)(__m512i)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_shuffle_i64x2(U, X, Y, C) \
+ ((__m512i) __builtin_ia32_shuf_i64x2_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(C),\
+ (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)(U)))
+
+#define _mm512_shuffle_i32x4(X, Y, C) \
+ ((__m512i) __builtin_ia32_shuf_i32x4_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)-1))
+
+#define _mm512_mask_shuffle_i32x4(W, U, X, Y, C) \
+ ((__m512i) __builtin_ia32_shuf_i32x4_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(C),\
+ (__v16si)(__m512i)(W),\
+ (__mmask16)(U)))
+
+#define _mm512_maskz_shuffle_i32x4(U, X, Y, C) \
+ ((__m512i) __builtin_ia32_shuf_i32x4_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(C),\
+ (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)(U)))
+
+#define _mm512_shuffle_f64x2(X, Y, C) \
+ ((__m512d) __builtin_ia32_shuf_f64x2_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(C),\
+ (__v8df)(__m512d)_mm512_setzero_pd(),\
+ (__mmask8)-1))
+
+#define _mm512_mask_shuffle_f64x2(W, U, X, Y, C) \
+ ((__m512d) __builtin_ia32_shuf_f64x2_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(C),\
+ (__v8df)(__m512d)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_shuffle_f64x2(U, X, Y, C) \
+ ((__m512d) __builtin_ia32_shuf_f64x2_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(C),\
+ (__v8df)(__m512d)_mm512_setzero_pd(),\
+ (__mmask8)(U)))
+
+#define _mm512_shuffle_f32x4(X, Y, C) \
+ ((__m512) __builtin_ia32_shuf_f32x4_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(C),\
+ (__v16sf)(__m512)_mm512_setzero_ps(),\
+ (__mmask16)-1))
+
+#define _mm512_mask_shuffle_f32x4(W, U, X, Y, C) \
+ ((__m512) __builtin_ia32_shuf_f32x4_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(C),\
+ (__v16sf)(__m512)(W),\
+ (__mmask16)(U)))
+
+#define _mm512_maskz_shuffle_f32x4(U, X, Y, C) \
+ ((__m512) __builtin_ia32_shuf_f32x4_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(C),\
+ (__v16sf)(__m512)_mm512_setzero_ps(),\
+ (__mmask16)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rolv_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prolvd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rolv_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prolvd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rolv_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prolvd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rorv_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prorvd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rorv_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prorvd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rorv_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prorvd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rolv_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prolvq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rolv_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prolvq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rolv_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prolvq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rorv_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prorvq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rorv_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prorvq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rorv_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_prorvq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtt_roundpd_epi32 (__m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtt_roundpd_epi32 (__m256i __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttpd2dq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtt_roundpd_epi32 (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtt_roundpd_epu32 (__m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtt_roundpd_epu32 (__m256i __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttpd2udq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtt_roundpd_epu32 (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvttpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U, __R);
+}
+#else
+#define _mm512_cvtt_roundpd_epi32(A, B) \
+ ((__m256i)__builtin_ia32_cvttpd2dq512_mask(A, (__v8si)_mm256_setzero_si256(), -1, B))
+
+#define _mm512_mask_cvtt_roundpd_epi32(W, U, A, B) \
+ ((__m256i)__builtin_ia32_cvttpd2dq512_mask(A, (__v8si)(W), U, B))
+
+#define _mm512_maskz_cvtt_roundpd_epi32(U, A, B) \
+ ((__m256i)__builtin_ia32_cvttpd2dq512_mask(A, (__v8si)_mm256_setzero_si256(), U, B))
+
+#define _mm512_cvtt_roundpd_epu32(A, B) \
+ ((__m256i)__builtin_ia32_cvttpd2udq512_mask(A, (__v8si)_mm256_setzero_si256(), -1, B))
+
+#define _mm512_mask_cvtt_roundpd_epu32(W, U, A, B) \
+ ((__m256i)__builtin_ia32_cvttpd2udq512_mask(A, (__v8si)(W), U, B))
+
+#define _mm512_maskz_cvtt_roundpd_epu32(U, A, B) \
+ ((__m256i)__builtin_ia32_cvttpd2udq512_mask(A, (__v8si)_mm256_setzero_si256(), U, B))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundpd_epi32 (__m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundpd_epi32 (__m256i __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtpd2dq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundpd_epi32 (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundpd_epu32 (__m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundpd_epu32 (__m256i __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtpd2udq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundpd_epu32 (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m256i) __builtin_ia32_cvtpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U, __R);
+}
+#else
+#define _mm512_cvt_roundpd_epi32(A, B) \
+ ((__m256i)__builtin_ia32_cvtpd2dq512_mask(A, (__v8si)_mm256_setzero_si256(), -1, B))
+
+#define _mm512_mask_cvt_roundpd_epi32(W, U, A, B) \
+ ((__m256i)__builtin_ia32_cvtpd2dq512_mask(A, (__v8si)(W), U, B))
+
+#define _mm512_maskz_cvt_roundpd_epi32(U, A, B) \
+ ((__m256i)__builtin_ia32_cvtpd2dq512_mask(A, (__v8si)_mm256_setzero_si256(), U, B))
+
+#define _mm512_cvt_roundpd_epu32(A, B) \
+ ((__m256i)__builtin_ia32_cvtpd2udq512_mask(A, (__v8si)_mm256_setzero_si256(), -1, B))
+
+#define _mm512_mask_cvt_roundpd_epu32(W, U, A, B) \
+ ((__m256i)__builtin_ia32_cvtpd2udq512_mask(A, (__v8si)(W), U, B))
+
+#define _mm512_maskz_cvt_roundpd_epu32(U, A, B) \
+ ((__m256i)__builtin_ia32_cvtpd2udq512_mask(A, (__v8si)_mm256_setzero_si256(), U, B))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtt_roundps_epi32 (__m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtt_roundps_epi32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2dq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtt_roundps_epi32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtt_roundps_epu32 (__m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtt_roundps_epu32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2udq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtt_roundps_epu32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvttps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U, __R);
+}
+#else
+#define _mm512_cvtt_roundps_epi32(A, B) \
+ ((__m512i)__builtin_ia32_cvttps2dq512_mask(A, (__v16si)_mm512_setzero_si512 (), -1, B))
+
+#define _mm512_mask_cvtt_roundps_epi32(W, U, A, B) \
+ ((__m512i)__builtin_ia32_cvttps2dq512_mask(A, (__v16si)(W), U, B))
+
+#define _mm512_maskz_cvtt_roundps_epi32(U, A, B) \
+ ((__m512i)__builtin_ia32_cvttps2dq512_mask(A, (__v16si)_mm512_setzero_si512 (), U, B))
+
+#define _mm512_cvtt_roundps_epu32(A, B) \
+ ((__m512i)__builtin_ia32_cvttps2udq512_mask(A, (__v16si)_mm512_setzero_si512 (), -1, B))
+
+#define _mm512_mask_cvtt_roundps_epu32(W, U, A, B) \
+ ((__m512i)__builtin_ia32_cvttps2udq512_mask(A, (__v16si)(W), U, B))
+
+#define _mm512_maskz_cvtt_roundps_epu32(U, A, B) \
+ ((__m512i)__builtin_ia32_cvttps2udq512_mask(A, (__v16si)_mm512_setzero_si512 (), U, B))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundps_epi32 (__m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundps_epi32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2dq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundps_epi32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundps_epu32 (__m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundps_epu32 (__m512i __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2udq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundps_epu32 (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512i) __builtin_ia32_cvtps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U, __R);
+}
+#else
+#define _mm512_cvt_roundps_epi32(A, B) \
+ ((__m512i)__builtin_ia32_cvtps2dq512_mask(A, (__v16si)_mm512_setzero_si512 (), -1, B))
+
+#define _mm512_mask_cvt_roundps_epi32(W, U, A, B) \
+ ((__m512i)__builtin_ia32_cvtps2dq512_mask(A, (__v16si)(W), U, B))
+
+#define _mm512_maskz_cvt_roundps_epi32(U, A, B) \
+ ((__m512i)__builtin_ia32_cvtps2dq512_mask(A, (__v16si)_mm512_setzero_si512 (), U, B))
+
+#define _mm512_cvt_roundps_epu32(A, B) \
+ ((__m512i)__builtin_ia32_cvtps2udq512_mask(A, (__v16si)_mm512_setzero_si512 (), -1, B))
+
+#define _mm512_mask_cvt_roundps_epu32(W, U, A, B) \
+ ((__m512i)__builtin_ia32_cvtps2udq512_mask(A, (__v16si)(W), U, B))
+
+#define _mm512_maskz_cvt_roundps_epu32(U, A, B) \
+ ((__m512i)__builtin_ia32_cvtps2udq512_mask(A, (__v16si)_mm512_setzero_si512 (), U, B))
+#endif
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtu32_sd (__m128d __A, unsigned __B)
+{
+ return (__m128d) __builtin_ia32_cvtusi2sd32 ((__v2df) __A, __B);
+}
+
+#ifdef __x86_64__
+#ifdef __OPTIMIZE__
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundu64_sd (__m128d __A, unsigned long long __B, const int __R)
+{
+ return (__m128d) __builtin_ia32_cvtusi2sd64 ((__v2df) __A, __B, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundi64_sd (__m128d __A, long long __B, const int __R)
+{
+ return (__m128d) __builtin_ia32_cvtsi2sd64 ((__v2df) __A, __B, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsi64_sd (__m128d __A, long long __B, const int __R)
+{
+ return (__m128d) __builtin_ia32_cvtsi2sd64 ((__v2df) __A, __B, __R);
+}
+#else
+#define _mm_cvt_roundu64_sd(A, B, C) \
+ (__m128d)__builtin_ia32_cvtusi2sd64(A, B, C)
+
+#define _mm_cvt_roundi64_sd(A, B, C) \
+ (__m128d)__builtin_ia32_cvtsi2sd64(A, B, C)
+
+#define _mm_cvt_roundsi64_sd(A, B, C) \
+ (__m128d)__builtin_ia32_cvtsi2sd64(A, B, C)
+#endif
+
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundu32_ss (__m128 __A, unsigned __B, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtusi2ss32 ((__v4sf) __A, __B, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsi32_ss (__m128 __A, int __B, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtsi2ss32 ((__v4sf) __A, __B, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundi32_ss (__m128 __A, int __B, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtsi2ss32 ((__v4sf) __A, __B, __R);
+}
+#else
+#define _mm_cvt_roundu32_ss(A, B, C) \
+ (__m128)__builtin_ia32_cvtusi2ss32(A, B, C)
+
+#define _mm_cvt_roundi32_ss(A, B, C) \
+ (__m128)__builtin_ia32_cvtsi2ss32(A, B, C)
+
+#define _mm_cvt_roundsi32_ss(A, B, C) \
+ (__m128)__builtin_ia32_cvtsi2ss32(A, B, C)
+#endif
+
+#ifdef __x86_64__
+#ifdef __OPTIMIZE__
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundu64_ss (__m128 __A, unsigned long long __B, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtusi2ss64 ((__v4sf) __A, __B, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsi64_ss (__m128 __A, long long __B, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtsi2ss64 ((__v4sf) __A, __B, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundi64_ss (__m128 __A, long long __B, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtsi2ss64 ((__v4sf) __A, __B, __R);
+}
+#else
+#define _mm_cvt_roundu64_ss(A, B, C) \
+ (__m128)__builtin_ia32_cvtusi2ss64(A, B, C)
+
+#define _mm_cvt_roundi64_ss(A, B, C) \
+ (__m128)__builtin_ia32_cvtsi2ss64(A, B, C)
+
+#define _mm_cvt_roundsi64_ss(A, B, C) \
+ (__m128)__builtin_ia32_cvtsi2ss64(A, B, C)
+#endif
+
+#endif
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi32_epi8 (__m512i __A)
+{
+ __v16qi __O;
+ return (__m128i) __builtin_ia32_pmovdb512_mask ((__v16si) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi32_epi8 (__m128i __O, __mmask16 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovdb512_mask ((__v16si) __A,
+ (__v16qi) __O, __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi32_epi8 (__mmask16 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovdb512_mask ((__v16si) __A,
+ (__v16qi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtsepi32_epi8 (__m512i __A)
+{
+ __v16qi __O;
+ return (__m128i) __builtin_ia32_pmovsdb512_mask ((__v16si) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtsepi32_epi8 (__m128i __O, __mmask16 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovsdb512_mask ((__v16si) __A,
+ (__v16qi) __O, __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtsepi32_epi8 (__mmask16 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovsdb512_mask ((__v16si) __A,
+ (__v16qi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtusepi32_epi8 (__m512i __A)
+{
+ __v16qi __O;
+ return (__m128i) __builtin_ia32_pmovusdb512_mask ((__v16si) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtusepi32_epi8 (__m128i __O, __mmask16 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovusdb512_mask ((__v16si) __A,
+ (__v16qi) __O,
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtusepi32_epi8 (__mmask16 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovusdb512_mask ((__v16si) __A,
+ (__v16qi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi32_epi16 (__m512i __A)
+{
+ __v16hi __O;
+ return (__m256i) __builtin_ia32_pmovdw512_mask ((__v16si) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi32_epi16 (__m256i __O, __mmask16 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovdw512_mask ((__v16si) __A,
+ (__v16hi) __O, __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi32_epi16 (__mmask16 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovdw512_mask ((__v16si) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtsepi32_epi16 (__m512i __A)
+{
+ __v16hi __O;
+ return (__m256i) __builtin_ia32_pmovsdw512_mask ((__v16si) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtsepi32_epi16 (__m256i __O, __mmask16 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovsdw512_mask ((__v16si) __A,
+ (__v16hi) __O, __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtsepi32_epi16 (__mmask16 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovsdw512_mask ((__v16si) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtusepi32_epi16 (__m512i __A)
+{
+ __v16hi __O;
+ return (__m256i) __builtin_ia32_pmovusdw512_mask ((__v16si) __A, __O,
+ (__mmask16) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtusepi32_epi16 (__m256i __O, __mmask16 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovusdw512_mask ((__v16si) __A,
+ (__v16hi) __O,
+ __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtusepi32_epi16 (__mmask16 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovusdw512_mask ((__v16si) __A,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi64_epi32 (__m512i __A)
+{
+ __v8si __O;
+ return (__m256i) __builtin_ia32_pmovqd512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi64_epi32 (__m256i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovqd512_mask ((__v8di) __A,
+ (__v8si) __O, __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi64_epi32 (__mmask8 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovqd512_mask ((__v8di) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtsepi64_epi32 (__m512i __A)
+{
+ __v8si __O;
+ return (__m256i) __builtin_ia32_pmovsqd512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtsepi64_epi32 (__m256i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovsqd512_mask ((__v8di) __A,
+ (__v8si) __O, __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtsepi64_epi32 (__mmask8 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovsqd512_mask ((__v8di) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtusepi64_epi32 (__m512i __A)
+{
+ __v8si __O;
+ return (__m256i) __builtin_ia32_pmovusqd512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtusepi64_epi32 (__m256i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovusqd512_mask ((__v8di) __A,
+ (__v8si) __O, __M);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtusepi64_epi32 (__mmask8 __M, __m512i __A)
+{
+ return (__m256i) __builtin_ia32_pmovusqd512_mask ((__v8di) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi64_epi16 (__m512i __A)
+{
+ __v8hi __O;
+ return (__m128i) __builtin_ia32_pmovqw512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi64_epi16 (__m128i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovqw512_mask ((__v8di) __A,
+ (__v8hi) __O, __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi64_epi16 (__mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovqw512_mask ((__v8di) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtsepi64_epi16 (__m512i __A)
+{
+ __v8hi __O;
+ return (__m128i) __builtin_ia32_pmovsqw512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtsepi64_epi16 (__m128i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovsqw512_mask ((__v8di) __A,
+ (__v8hi) __O, __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtsepi64_epi16 (__mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovsqw512_mask ((__v8di) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtusepi64_epi16 (__m512i __A)
+{
+ __v8hi __O;
+ return (__m128i) __builtin_ia32_pmovusqw512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtusepi64_epi16 (__m128i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovusqw512_mask ((__v8di) __A,
+ (__v8hi) __O, __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtusepi64_epi16 (__mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovusqw512_mask ((__v8di) __A,
+ (__v8hi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi64_epi8 (__m512i __A)
+{
+ __v16qi __O;
+ return (__m128i) __builtin_ia32_pmovqb512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi64_epi8 (__m128i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovqb512_mask ((__v8di) __A,
+ (__v16qi) __O, __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi64_epi8 (__mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovqb512_mask ((__v8di) __A,
+ (__v16qi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtsepi64_epi8 (__m512i __A)
+{
+ __v16qi __O;
+ return (__m128i) __builtin_ia32_pmovsqb512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtsepi64_epi8 (__m128i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovsqb512_mask ((__v8di) __A,
+ (__v16qi) __O, __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtsepi64_epi8 (__mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovsqb512_mask ((__v8di) __A,
+ (__v16qi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtusepi64_epi8 (__m512i __A)
+{
+ __v16qi __O;
+ return (__m128i) __builtin_ia32_pmovusqb512_mask ((__v8di) __A, __O,
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtusepi64_epi8 (__m128i __O, __mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovusqb512_mask ((__v8di) __A,
+ (__v16qi) __O,
+ __M);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtusepi64_epi8 (__mmask8 __M, __m512i __A)
+{
+ return (__m128i) __builtin_ia32_pmovusqb512_mask ((__v8di) __A,
+ (__v16qi)
+ _mm_setzero_si128 (),
+ __M);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi32_pd (__m256i __A)
+{
+ return (__m512d) __builtin_ia32_cvtdq2pd512_mask ((__v8si) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi32_pd (__m512d __W, __mmask8 __U, __m256i __A)
+{
+ return (__m512d) __builtin_ia32_cvtdq2pd512_mask ((__v8si) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi32_pd (__mmask8 __U, __m256i __A)
+{
+ return (__m512d) __builtin_ia32_cvtdq2pd512_mask ((__v8si) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepu32_pd (__m256i __A)
+{
+ return (__m512d) __builtin_ia32_cvtudq2pd512_mask ((__v8si) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepu32_pd (__m512d __W, __mmask8 __U, __m256i __A)
+{
+ return (__m512d) __builtin_ia32_cvtudq2pd512_mask ((__v8si) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepu32_pd (__mmask8 __U, __m256i __A)
+{
+ return (__m512d) __builtin_ia32_cvtudq2pd512_mask ((__v8si) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundepi32_ps (__m512i __A, const int __R)
+{
+ return (__m512) __builtin_ia32_cvtdq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundepi32_ps (__m512 __W, __mmask16 __U, __m512i __A,
+ const int __R)
+{
+ return (__m512) __builtin_ia32_cvtdq2ps512_mask ((__v16si) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundepi32_ps (__mmask16 __U, __m512i __A, const int __R)
+{
+ return (__m512) __builtin_ia32_cvtdq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundepu32_ps (__m512i __A, const int __R)
+{
+ return (__m512) __builtin_ia32_cvtudq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundepu32_ps (__m512 __W, __mmask16 __U, __m512i __A,
+ const int __R)
+{
+ return (__m512) __builtin_ia32_cvtudq2ps512_mask ((__v16si) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundepu32_ps (__mmask16 __U, __m512i __A, const int __R)
+{
+ return (__m512) __builtin_ia32_cvtudq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+#else
+#define _mm512_cvt_roundepi32_ps(A, B) \
+ (__m512)__builtin_ia32_cvtdq2ps512_mask((__v16si)(A), (__v16sf)_mm512_setzero_ps(), -1, B)
+
+#define _mm512_mask_cvt_roundepi32_ps(W, U, A, B) \
+ (__m512)__builtin_ia32_cvtdq2ps512_mask((__v16si)(A), W, U, B)
+
+#define _mm512_maskz_cvt_roundepi32_ps(U, A, B) \
+ (__m512)__builtin_ia32_cvtdq2ps512_mask((__v16si)(A), (__v16sf)_mm512_setzero_ps(), U, B)
+
+#define _mm512_cvt_roundepu32_ps(A, B) \
+ (__m512)__builtin_ia32_cvtudq2ps512_mask((__v16si)(A), (__v16sf)_mm512_setzero_ps(), -1, B)
+
+#define _mm512_mask_cvt_roundepu32_ps(W, U, A, B) \
+ (__m512)__builtin_ia32_cvtudq2ps512_mask((__v16si)(A), W, U, B)
+
+#define _mm512_maskz_cvt_roundepu32_ps(U, A, B) \
+ (__m512)__builtin_ia32_cvtudq2ps512_mask((__v16si)(A), (__v16sf)_mm512_setzero_ps(), U, B)
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_extractf64x4_pd (__m512d __A, const int __imm)
+{
+ return (__m256d) __builtin_ia32_extractf64x4_mask ((__v8df) __A,
+ __imm,
+ (__v4df)
+ _mm256_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_extractf64x4_pd (__m256d __W, __mmask8 __U, __m512d __A,
+ const int __imm)
+{
+ return (__m256d) __builtin_ia32_extractf64x4_mask ((__v8df) __A,
+ __imm,
+ (__v4df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_extractf64x4_pd (__mmask8 __U, __m512d __A, const int __imm)
+{
+ return (__m256d) __builtin_ia32_extractf64x4_mask ((__v8df) __A,
+ __imm,
+ (__v4df)
+ _mm256_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_extractf32x4_ps (__m512 __A, const int __imm)
+{
+ return (__m128) __builtin_ia32_extractf32x4_mask ((__v16sf) __A,
+ __imm,
+ (__v4sf)
+ _mm_setzero_ps (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_extractf32x4_ps (__m128 __W, __mmask8 __U, __m512 __A,
+ const int __imm)
+{
+ return (__m128) __builtin_ia32_extractf32x4_mask ((__v16sf) __A,
+ __imm,
+ (__v4sf) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_extractf32x4_ps (__mmask8 __U, __m512 __A, const int __imm)
+{
+ return (__m128) __builtin_ia32_extractf32x4_mask ((__v16sf) __A,
+ __imm,
+ (__v4sf)
+ _mm_setzero_ps (),
+ (__mmask8) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_extracti64x4_epi64 (__m512i __A, const int __imm)
+{
+ return (__m256i) __builtin_ia32_extracti64x4_mask ((__v8di) __A,
+ __imm,
+ (__v4di)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_extracti64x4_epi64 (__m256i __W, __mmask8 __U, __m512i __A,
+ const int __imm)
+{
+ return (__m256i) __builtin_ia32_extracti64x4_mask ((__v8di) __A,
+ __imm,
+ (__v4di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_extracti64x4_epi64 (__mmask8 __U, __m512i __A, const int __imm)
+{
+ return (__m256i) __builtin_ia32_extracti64x4_mask ((__v8di) __A,
+ __imm,
+ (__v4di)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_extracti32x4_epi32 (__m512i __A, const int __imm)
+{
+ return (__m128i) __builtin_ia32_extracti32x4_mask ((__v16si) __A,
+ __imm,
+ (__v4si)
+ _mm_setzero_si128 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_extracti32x4_epi32 (__m128i __W, __mmask8 __U, __m512i __A,
+ const int __imm)
+{
+ return (__m128i) __builtin_ia32_extracti32x4_mask ((__v16si) __A,
+ __imm,
+ (__v4si) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m128i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_extracti32x4_epi32 (__mmask8 __U, __m512i __A, const int __imm)
+{
+ return (__m128i) __builtin_ia32_extracti32x4_mask ((__v16si) __A,
+ __imm,
+ (__v4si)
+ _mm_setzero_si128 (),
+ (__mmask8) __U);
+}
+#else
+
+#define _mm512_extractf64x4_pd(X, C) \
+ ((__m256d) __builtin_ia32_extractf64x4_mask ((__v8df)(__m512d) (X), \
+ (int) (C),\
+ (__v4df)(__m256d)_mm256_setzero_pd(),\
+ (__mmask8)-1))
+
+#define _mm512_mask_extractf64x4_pd(W, U, X, C) \
+ ((__m256d) __builtin_ia32_extractf64x4_mask ((__v8df)(__m512d) (X), \
+ (int) (C),\
+ (__v4df)(__m256d)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_extractf64x4_pd(U, X, C) \
+ ((__m256d) __builtin_ia32_extractf64x4_mask ((__v8df)(__m512d) (X), \
+ (int) (C),\
+ (__v4df)(__m256d)_mm256_setzero_pd(),\
+ (__mmask8)(U)))
+
+#define _mm512_extractf32x4_ps(X, C) \
+ ((__m128) __builtin_ia32_extractf32x4_mask ((__v16sf)(__m512) (X), \
+ (int) (C),\
+ (__v4sf)(__m128)_mm_setzero_ps(),\
+ (__mmask8)-1))
+
+#define _mm512_mask_extractf32x4_ps(W, U, X, C) \
+ ((__m128) __builtin_ia32_extractf32x4_mask ((__v16sf)(__m512) (X), \
+ (int) (C),\
+ (__v4sf)(__m128)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_extractf32x4_ps(U, X, C) \
+ ((__m128) __builtin_ia32_extractf32x4_mask ((__v16sf)(__m512) (X), \
+ (int) (C),\
+ (__v4sf)(__m128)_mm_setzero_ps(),\
+ (__mmask8)(U)))
+
+#define _mm512_extracti64x4_epi64(X, C) \
+ ((__m256i) __builtin_ia32_extracti64x4_mask ((__v8di)(__m512i) (X), \
+ (int) (C),\
+ (__v4di)(__m256i)_mm256_setzero_si256 (),\
+ (__mmask8)-1))
+
+#define _mm512_mask_extracti64x4_epi64(W, U, X, C) \
+ ((__m256i) __builtin_ia32_extracti64x4_mask ((__v8di)(__m512i) (X), \
+ (int) (C),\
+ (__v4di)(__m256i)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_extracti64x4_epi64(U, X, C) \
+ ((__m256i) __builtin_ia32_extracti64x4_mask ((__v8di)(__m512i) (X), \
+ (int) (C),\
+ (__v4di)(__m256i)_mm256_setzero_si256 (),\
+ (__mmask8)(U)))
+
+#define _mm512_extracti32x4_epi32(X, C) \
+ ((__m128i) __builtin_ia32_extracti32x4_mask ((__v16si)(__m512i) (X), \
+ (int) (C),\
+ (__v4si)(__m128i)_mm_setzero_si128 (),\
+ (__mmask8)-1))
+
+#define _mm512_mask_extracti32x4_epi32(W, U, X, C) \
+ ((__m128i) __builtin_ia32_extracti32x4_mask ((__v16si)(__m512i) (X), \
+ (int) (C),\
+ (__v4si)(__m128i)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_extracti32x4_epi32(U, X, C) \
+ ((__m128i) __builtin_ia32_extracti32x4_mask ((__v16si)(__m512i) (X), \
+ (int) (C),\
+ (__v4si)(__m128i)_mm_setzero_si128 (),\
+ (__mmask8)(U)))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_inserti32x4 (__m512i __A, __m128i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_inserti32x4_mask ((__v16si) __A,
+ (__v4si) __B,
+ __imm,
+ (__v16si) __A, -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_insertf32x4 (__m512 __A, __m128 __B, const int __imm)
+{
+ return (__m512) __builtin_ia32_insertf32x4_mask ((__v16sf) __A,
+ (__v4sf) __B,
+ __imm,
+ (__v16sf) __A, -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_inserti64x4 (__m512i __A, __m256i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_inserti64x4_mask ((__v8di) __A,
+ (__v4di) __B,
+ __imm,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_inserti64x4 (__m512i __W, __mmask8 __U, __m512i __A,
+ __m256i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_inserti64x4_mask ((__v8di) __A,
+ (__v4di) __B,
+ __imm,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_inserti64x4 (__mmask8 __U, __m512i __A, __m256i __B,
+ const int __imm)
+{
+ return (__m512i) __builtin_ia32_inserti64x4_mask ((__v8di) __A,
+ (__v4di) __B,
+ __imm,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_insertf64x4 (__m512d __A, __m256d __B, const int __imm)
+{
+ return (__m512d) __builtin_ia32_insertf64x4_mask ((__v8df) __A,
+ (__v4df) __B,
+ __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_insertf64x4 (__m512d __W, __mmask8 __U, __m512d __A,
+ __m256d __B, const int __imm)
+{
+ return (__m512d) __builtin_ia32_insertf64x4_mask ((__v8df) __A,
+ (__v4df) __B,
+ __imm,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_insertf64x4 (__mmask8 __U, __m512d __A, __m256d __B,
+ const int __imm)
+{
+ return (__m512d) __builtin_ia32_insertf64x4_mask ((__v8df) __A,
+ (__v4df) __B,
+ __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+#else
+#define _mm512_insertf32x4(X, Y, C) \
+ ((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X), \
+ (__v4sf)(__m128) (Y), (int) (C), (__v16sf)(__m512) (X), (__mmask16)(-1)))
+
+#define _mm512_inserti32x4(X, Y, C) \
+ ((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X), \
+ (__v4si)(__m128i) (Y), (int) (C), (__v16si)(__m512i) (X), (__mmask16)(-1)))
+
+#define _mm512_insertf64x4(X, Y, C) \
+ ((__m512d) __builtin_ia32_insertf64x4_mask ((__v8df)(__m512d) (X), \
+ (__v4df)(__m256d) (Y), (int) (C), \
+ (__v8df)(__m512d)_mm512_setzero_pd(), \
+ (__mmask8)-1))
+
+#define _mm512_mask_insertf64x4(W, U, X, Y, C) \
+ ((__m512d) __builtin_ia32_insertf64x4_mask ((__v8df)(__m512d) (X), \
+ (__v4df)(__m256d) (Y), (int) (C), \
+ (__v8df)(__m512d)(W), \
+ (__mmask8)(U)))
+
+#define _mm512_maskz_insertf64x4(U, X, Y, C) \
+ ((__m512d) __builtin_ia32_insertf64x4_mask ((__v8df)(__m512d) (X), \
+ (__v4df)(__m256d) (Y), (int) (C), \
+ (__v8df)(__m512d)_mm512_setzero_pd(), \
+ (__mmask8)(U)))
+
+#define _mm512_inserti64x4(X, Y, C) \
+ ((__m512i) __builtin_ia32_inserti64x4_mask ((__v8di)(__m512i) (X), \
+ (__v4di)(__m256i) (Y), (int) (C), \
+ (__v8di)(__m512i)_mm512_setzero_si512 (), \
+ (__mmask8)-1))
+
+#define _mm512_mask_inserti64x4(W, U, X, Y, C) \
+ ((__m512i) __builtin_ia32_inserti64x4_mask ((__v8di)(__m512i) (X), \
+ (__v4di)(__m256i) (Y), (int) (C),\
+ (__v8di)(__m512i)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_inserti64x4(U, X, Y, C) \
+ ((__m512i) __builtin_ia32_inserti64x4_mask ((__v8di)(__m512i) (X), \
+ (__v4di)(__m256i) (Y), (int) (C), \
+ (__v8di)(__m512i)_mm512_setzero_si512 (), \
+ (__mmask8)(U)))
+#endif
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_loadu_pd (void const *__P)
+{
+ return (__m512d) __builtin_ia32_loadupd512_mask ((const __v8df *) __P,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_loadu_pd (__m512d __W, __mmask8 __U, void const *__P)
+{
+ return (__m512d) __builtin_ia32_loadupd512_mask ((const __v8df *) __P,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_loadu_pd (__mmask8 __U, void const *__P)
+{
+ return (__m512d) __builtin_ia32_loadupd512_mask ((const __v8df *) __P,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_storeu_pd (void *__P, __m512d __A)
+{
+ __builtin_ia32_storeupd512_mask ((__v8df *) __P, (__v8df) __A,
+ (__mmask8) -1);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_storeu_pd (void *__P, __mmask8 __U, __m512d __A)
+{
+ __builtin_ia32_storeupd512_mask ((__v8df *) __P, (__v8df) __A,
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_loadu_ps (void const *__P)
+{
+ return (__m512) __builtin_ia32_loadups512_mask ((const __v16sf *) __P,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_loadu_ps (__m512 __W, __mmask16 __U, void const *__P)
+{
+ return (__m512) __builtin_ia32_loadups512_mask ((const __v16sf *) __P,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_loadu_ps (__mmask16 __U, void const *__P)
+{
+ return (__m512) __builtin_ia32_loadups512_mask ((const __v16sf *) __P,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_storeu_ps (void *__P, __m512 __A)
+{
+ __builtin_ia32_storeups512_mask ((__v16sf *) __P, (__v16sf) __A,
+ (__mmask16) -1);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_storeu_ps (void *__P, __mmask16 __U, __m512 __A)
+{
+ __builtin_ia32_storeups512_mask ((__v16sf *) __P, (__v16sf) __A,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_loadu_epi64 (__m512i __W, __mmask8 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_loaddqudi512_mask ((const __v8di *) __P,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_loadu_epi64 (__mmask8 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_loaddqudi512_mask ((const __v8di *) __P,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_storeu_epi64 (void *__P, __mmask8 __U, __m512i __A)
+{
+ __builtin_ia32_storedqudi512_mask ((__v8di *) __P, (__v8di) __A,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_loadu_si512 (void const *__P)
+{
+ return (__m512i) __builtin_ia32_loaddqusi512_mask ((const __v16si *) __P,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_loadu_epi32 (__m512i __W, __mmask16 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_loaddqusi512_mask ((const __v16si *) __P,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_loadu_epi32 (__mmask16 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_loaddqusi512_mask ((const __v16si *) __P,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_storeu_si512 (void *__P, __m512i __A)
+{
+ __builtin_ia32_storedqusi512_mask ((__v16si *) __P, (__v16si) __A,
+ (__mmask16) -1);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_storeu_epi32 (void *__P, __mmask16 __U, __m512i __A)
+{
+ __builtin_ia32_storedqusi512_mask ((__v16si *) __P, (__v16si) __A,
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutevar_pd (__m512d __A, __m512i __C)
+{
+ return (__m512d) __builtin_ia32_vpermilvarpd512_mask ((__v8df) __A,
+ (__v8di) __C,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutevar_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512i __C)
+{
+ return (__m512d) __builtin_ia32_vpermilvarpd512_mask ((__v8df) __A,
+ (__v8di) __C,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutevar_pd (__mmask8 __U, __m512d __A, __m512i __C)
+{
+ return (__m512d) __builtin_ia32_vpermilvarpd512_mask ((__v8df) __A,
+ (__v8di) __C,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutevar_ps (__m512 __A, __m512i __C)
+{
+ return (__m512) __builtin_ia32_vpermilvarps512_mask ((__v16sf) __A,
+ (__v16si) __C,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutevar_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512i __C)
+{
+ return (__m512) __builtin_ia32_vpermilvarps512_mask ((__v16sf) __A,
+ (__v16si) __C,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutevar_ps (__mmask16 __U, __m512 __A, __m512i __C)
+{
+ return (__m512) __builtin_ia32_vpermilvarps512_mask ((__v16sf) __A,
+ (__v16si) __C,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutex2var_epi64 (__m512i __A, __m512i __I, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermt2varq512_mask ((__v8di) __I
+ /* idx */ ,
+ (__v8di) __A,
+ (__v8di) __B,
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutex2var_epi64 (__m512i __A, __mmask8 __U, __m512i __I,
+ __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermt2varq512_mask ((__v8di) __I
+ /* idx */ ,
+ (__v8di) __A,
+ (__v8di) __B,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask2_permutex2var_epi64 (__m512i __A, __m512i __I,
+ __mmask8 __U, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermi2varq512_mask ((__v8di) __A,
+ (__v8di) __I
+ /* idx */ ,
+ (__v8di) __B,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutex2var_epi64 (__mmask8 __U, __m512i __A,
+ __m512i __I, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermt2varq512_maskz ((__v8di) __I
+ /* idx */ ,
+ (__v8di) __A,
+ (__v8di) __B,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutex2var_epi32 (__m512i __A, __m512i __I, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermt2vard512_mask ((__v16si) __I
+ /* idx */ ,
+ (__v16si) __A,
+ (__v16si) __B,
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutex2var_epi32 (__m512i __A, __mmask16 __U,
+ __m512i __I, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermt2vard512_mask ((__v16si) __I
+ /* idx */ ,
+ (__v16si) __A,
+ (__v16si) __B,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask2_permutex2var_epi32 (__m512i __A, __m512i __I,
+ __mmask16 __U, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermi2vard512_mask ((__v16si) __A,
+ (__v16si) __I
+ /* idx */ ,
+ (__v16si) __B,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutex2var_epi32 (__mmask16 __U, __m512i __A,
+ __m512i __I, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_vpermt2vard512_maskz ((__v16si) __I
+ /* idx */ ,
+ (__v16si) __A,
+ (__v16si) __B,
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutex2var_pd (__m512d __A, __m512i __I, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_vpermt2varpd512_mask ((__v8di) __I
+ /* idx */ ,
+ (__v8df) __A,
+ (__v8df) __B,
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutex2var_pd (__m512d __A, __mmask8 __U, __m512i __I,
+ __m512d __B)
+{
+ return (__m512d) __builtin_ia32_vpermt2varpd512_mask ((__v8di) __I
+ /* idx */ ,
+ (__v8df) __A,
+ (__v8df) __B,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask2_permutex2var_pd (__m512d __A, __m512i __I, __mmask8 __U,
+ __m512d __B)
+{
+ return (__m512d) __builtin_ia32_vpermi2varpd512_mask ((__v8df) __A,
+ (__v8di) __I
+ /* idx */ ,
+ (__v8df) __B,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutex2var_pd (__mmask8 __U, __m512d __A, __m512i __I,
+ __m512d __B)
+{
+ return (__m512d) __builtin_ia32_vpermt2varpd512_maskz ((__v8di) __I
+ /* idx */ ,
+ (__v8df) __A,
+ (__v8df) __B,
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutex2var_ps (__m512 __A, __m512i __I, __m512 __B)
+{
+ return (__m512) __builtin_ia32_vpermt2varps512_mask ((__v16si) __I
+ /* idx */ ,
+ (__v16sf) __A,
+ (__v16sf) __B,
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutex2var_ps (__m512 __A, __mmask16 __U, __m512i __I, __m512 __B)
+{
+ return (__m512) __builtin_ia32_vpermt2varps512_mask ((__v16si) __I
+ /* idx */ ,
+ (__v16sf) __A,
+ (__v16sf) __B,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask2_permutex2var_ps (__m512 __A, __m512i __I, __mmask16 __U,
+ __m512 __B)
+{
+ return (__m512) __builtin_ia32_vpermi2varps512_mask ((__v16sf) __A,
+ (__v16si) __I
+ /* idx */ ,
+ (__v16sf) __B,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutex2var_ps (__mmask16 __U, __m512 __A, __m512i __I,
+ __m512 __B)
+{
+ return (__m512) __builtin_ia32_vpermt2varps512_maskz ((__v16si) __I
+ /* idx */ ,
+ (__v16sf) __A,
+ (__v16sf) __B,
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permute_pd (__m512d __X, const int __C)
+{
+ return (__m512d) __builtin_ia32_vpermilpd512_mask ((__v8df) __X, __C,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permute_pd (__m512d __W, __mmask8 __U, __m512d __X, const int __C)
+{
+ return (__m512d) __builtin_ia32_vpermilpd512_mask ((__v8df) __X, __C,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permute_pd (__mmask8 __U, __m512d __X, const int __C)
+{
+ return (__m512d) __builtin_ia32_vpermilpd512_mask ((__v8df) __X, __C,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permute_ps (__m512 __X, const int __C)
+{
+ return (__m512) __builtin_ia32_vpermilps512_mask ((__v16sf) __X, __C,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permute_ps (__m512 __W, __mmask16 __U, __m512 __X, const int __C)
+{
+ return (__m512) __builtin_ia32_vpermilps512_mask ((__v16sf) __X, __C,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permute_ps (__mmask16 __U, __m512 __X, const int __C)
+{
+ return (__m512) __builtin_ia32_vpermilps512_mask ((__v16sf) __X, __C,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+#else
+#define _mm512_permute_pd(X, C) \
+ ((__m512d) __builtin_ia32_vpermilpd512_mask ((__v8df)(__m512d)(X), (int)(C), \
+ (__v8df)(__m512d)(X), \
+ (__mmask8)(-1)))
+
+#define _mm512_mask_permute_pd(W, U, X, C) \
+ ((__m512d) __builtin_ia32_vpermilpd512_mask ((__v8df)(__m512d)(X), (int)(C), \
+ (__v8df)(__m512d)(W), \
+ (__mmask8)(U)))
+
+#define _mm512_maskz_permute_pd(U, X, C) \
+ ((__m512d) __builtin_ia32_vpermilpd512_mask ((__v8df)(__m512d)(X), (int)(C), \
+ (__v8df)(__m512d)_mm512_setzero_pd(), \
+ (__mmask8)(U)))
+
+#define _mm512_permute_ps(X, C) \
+ ((__m512) __builtin_ia32_vpermilps512_mask ((__v16sf)(__m512)(X), (int)(C), \
+ (__v16sf)(__m512)(X), \
+ (__mmask16)(-1)))
+
+#define _mm512_mask_permute_ps(W, U, X, C) \
+ ((__m512) __builtin_ia32_vpermilps512_mask ((__v16sf)(__m512)(X), (int)(C), \
+ (__v16sf)(__m512)(W), \
+ (__mmask16)(U)))
+
+#define _mm512_maskz_permute_ps(U, X, C) \
+ ((__m512) __builtin_ia32_vpermilps512_mask ((__v16sf)(__m512)(X), (int)(C), \
+ (__v16sf)(__m512)_mm512_setzero_ps(), \
+ (__mmask16)(U)))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutex_epi64 (__m512i __X, const int __I)
+{
+ return (__m512i) __builtin_ia32_permdi512_mask ((__v8di) __X, __I,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) (-1));
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutex_epi64 (__m512i __W, __mmask8 __M,
+ __m512i __X, const int __I)
+{
+ return (__m512i) __builtin_ia32_permdi512_mask ((__v8di) __X, __I,
+ (__v8di) __W,
+ (__mmask8) __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutex_epi64 (__mmask8 __M, __m512i __X, const int __I)
+{
+ return (__m512i) __builtin_ia32_permdi512_mask ((__v8di) __X, __I,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __M);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutex_pd (__m512d __X, const int __M)
+{
+ return (__m512d) __builtin_ia32_permdf512_mask ((__v8df) __X, __M,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutex_pd (__m512d __W, __mmask8 __U, __m512d __X, const int __M)
+{
+ return (__m512d) __builtin_ia32_permdf512_mask ((__v8df) __X, __M,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutex_pd (__mmask8 __U, __m512d __X, const int __M)
+{
+ return (__m512d) __builtin_ia32_permdf512_mask ((__v8df) __X, __M,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+#else
+#define _mm512_permutex_pd(X, M) \
+ ((__m512d) __builtin_ia32_permdf512_mask ((__v8df)(__m512d)(X), (int)(M), \
+ (__v8df)(__m512d)(X), (__mmask8)-1))
+
+#define _mm512_mask_permutex_pd(W, U, X, M) \
+ ((__m512d) __builtin_ia32_permdf512_mask ((__v8df)(__m512d)(X), (int)(M), \
+ (__v8df)(__m512d)(W), (__mmask8)(U)))
+
+#define _mm512_maskz_permutex_pd(U, X, M) \
+ ((__m512d) __builtin_ia32_permdf512_mask ((__v8df)(__m512d)(X), (int)(M), \
+ (__v8df)(__m512d)_mm512_setzero_pd(),\
+ (__mmask8)(U)))
+
+#define _mm512_permutex_epi64(X, I) \
+ ((__m512i) __builtin_ia32_permdi512_mask ((__v8di)(__m512i)(X), \
+ (int)(I), \
+ (__v8di)(__m512i)(X), \
+ (__mmask8)(-1)))
+
+#define _mm512_maskz_permutex_epi64(M, X, I) \
+ ((__m512i) __builtin_ia32_permdi512_mask ((__v8di)(__m512i)(X), \
+ (int)(I), \
+ (__v8di)(__m512i) \
+ (_mm512_setzero_si512 ()),\
+ (__mmask8)(M)))
+
+#define _mm512_mask_permutex_epi64(W, M, X, I) \
+ ((__m512i) __builtin_ia32_permdi512_mask ((__v8di)(__m512i)(X), \
+ (int)(I), \
+ (__v8di)(__m512i)(W), \
+ (__mmask8)(M)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutexvar_epi64 (__mmask8 __M, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_permvardi512_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutexvar_epi64 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_permvardi512_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutexvar_epi64 (__m512i __W, __mmask8 __M, __m512i __X,
+ __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_permvardi512_mask ((__v8di) __X,
+ (__v8di) __Y,
+ (__v8di) __W,
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutexvar_epi32 (__mmask16 __M, __m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_permvarsi512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutexvar_epi32 (__m512i __X, __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_permvarsi512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutexvar_epi32 (__m512i __W, __mmask16 __M, __m512i __X,
+ __m512i __Y)
+{
+ return (__m512i) __builtin_ia32_permvarsi512_mask ((__v16si) __X,
+ (__v16si) __Y,
+ (__v16si) __W,
+ __M);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutexvar_pd (__m512i __X, __m512d __Y)
+{
+ return (__m512d) __builtin_ia32_permvardf512_mask ((__v8df) __Y,
+ (__v8di) __X,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutexvar_pd (__m512d __W, __mmask8 __U, __m512i __X, __m512d __Y)
+{
+ return (__m512d) __builtin_ia32_permvardf512_mask ((__v8df) __Y,
+ (__v8di) __X,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutexvar_pd (__mmask8 __U, __m512i __X, __m512d __Y)
+{
+ return (__m512d) __builtin_ia32_permvardf512_mask ((__v8df) __Y,
+ (__v8di) __X,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_permutexvar_ps (__m512i __X, __m512 __Y)
+{
+ return (__m512) __builtin_ia32_permvarsf512_mask ((__v16sf) __Y,
+ (__v16si) __X,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_permutexvar_ps (__m512 __W, __mmask16 __U, __m512i __X, __m512 __Y)
+{
+ return (__m512) __builtin_ia32_permvarsf512_mask ((__v16sf) __Y,
+ (__v16si) __X,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_permutexvar_ps (__mmask16 __U, __m512i __X, __m512 __Y)
+{
+ return (__m512) __builtin_ia32_permvarsf512_mask ((__v16sf) __Y,
+ (__v16si) __X,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_shuffle_ps (__m512 __M, __m512 __V, const int __imm)
+{
+ return (__m512) __builtin_ia32_shufps512_mask ((__v16sf) __M,
+ (__v16sf) __V, __imm,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_shuffle_ps (__m512 __W, __mmask16 __U, __m512 __M,
+ __m512 __V, const int __imm)
+{
+ return (__m512) __builtin_ia32_shufps512_mask ((__v16sf) __M,
+ (__v16sf) __V, __imm,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_shuffle_ps (__mmask16 __U, __m512 __M, __m512 __V, const int __imm)
+{
+ return (__m512) __builtin_ia32_shufps512_mask ((__v16sf) __M,
+ (__v16sf) __V, __imm,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_shuffle_pd (__m512d __M, __m512d __V, const int __imm)
+{
+ return (__m512d) __builtin_ia32_shufpd512_mask ((__v8df) __M,
+ (__v8df) __V, __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_shuffle_pd (__m512d __W, __mmask8 __U, __m512d __M,
+ __m512d __V, const int __imm)
+{
+ return (__m512d) __builtin_ia32_shufpd512_mask ((__v8df) __M,
+ (__v8df) __V, __imm,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_shuffle_pd (__mmask8 __U, __m512d __M, __m512d __V,
+ const int __imm)
+{
+ return (__m512d) __builtin_ia32_shufpd512_mask ((__v8df) __M,
+ (__v8df) __V, __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fixupimm_round_pd (__m512d __A, __m512d __B, __m512i __C,
+ const int __imm, const int __R)
+{
+ return (__m512d) __builtin_ia32_fixupimmpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8di) __C,
+ __imm,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fixupimm_round_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512i __C, const int __imm, const int __R)
+{
+ return (__m512d) __builtin_ia32_fixupimmpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8di) __C,
+ __imm,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fixupimm_round_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512i __C, const int __imm, const int __R)
+{
+ return (__m512d) __builtin_ia32_fixupimmpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ (__v8di) __C,
+ __imm,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fixupimm_round_ps (__m512 __A, __m512 __B, __m512i __C,
+ const int __imm, const int __R)
+{
+ return (__m512) __builtin_ia32_fixupimmps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16si) __C,
+ __imm,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fixupimm_round_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512i __C, const int __imm, const int __R)
+{
+ return (__m512) __builtin_ia32_fixupimmps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16si) __C,
+ __imm,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fixupimm_round_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512i __C, const int __imm, const int __R)
+{
+ return (__m512) __builtin_ia32_fixupimmps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16si) __C,
+ __imm,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fixupimm_round_sd (__m128d __A, __m128d __B, __m128i __C,
+ const int __imm, const int __R)
+{
+ return (__m128d) __builtin_ia32_fixupimmsd_mask ((__v2df) __A,
+ (__v2df) __B,
+ (__v2di) __C, __imm,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fixupimm_round_sd (__m128d __A, __mmask8 __U, __m128d __B,
+ __m128i __C, const int __imm, const int __R)
+{
+ return (__m128d) __builtin_ia32_fixupimmsd_mask ((__v2df) __A,
+ (__v2df) __B,
+ (__v2di) __C, __imm,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fixupimm_round_sd (__mmask8 __U, __m128d __A, __m128d __B,
+ __m128i __C, const int __imm, const int __R)
+{
+ return (__m128d) __builtin_ia32_fixupimmsd_maskz ((__v2df) __A,
+ (__v2df) __B,
+ (__v2di) __C,
+ __imm,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fixupimm_round_ss (__m128 __A, __m128 __B, __m128i __C,
+ const int __imm, const int __R)
+{
+ return (__m128) __builtin_ia32_fixupimmss_mask ((__v4sf) __A,
+ (__v4sf) __B,
+ (__v4si) __C, __imm,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fixupimm_round_ss (__m128 __A, __mmask8 __U, __m128 __B,
+ __m128i __C, const int __imm, const int __R)
+{
+ return (__m128) __builtin_ia32_fixupimmss_mask ((__v4sf) __A,
+ (__v4sf) __B,
+ (__v4si) __C, __imm,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fixupimm_round_ss (__mmask8 __U, __m128 __A, __m128 __B,
+ __m128i __C, const int __imm, const int __R)
+{
+ return (__m128) __builtin_ia32_fixupimmss_maskz ((__v4sf) __A,
+ (__v4sf) __B,
+ (__v4si) __C, __imm,
+ (__mmask8) __U, __R);
+}
+
+#else
+#define _mm512_shuffle_pd(X, Y, C) \
+ ((__m512d)__builtin_ia32_shufpd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(C),\
+ (__v8df)(__m512d)_mm512_setzero_pd(),\
+ (__mmask8)-1))
+
+#define _mm512_mask_shuffle_pd(W, U, X, Y, C) \
+ ((__m512d)__builtin_ia32_shufpd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(C),\
+ (__v8df)(__m512d)(W),\
+ (__mmask8)(U)))
+
+#define _mm512_maskz_shuffle_pd(U, X, Y, C) \
+ ((__m512d)__builtin_ia32_shufpd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(C),\
+ (__v8df)(__m512d)_mm512_setzero_pd(),\
+ (__mmask8)(U)))
+
+#define _mm512_shuffle_ps(X, Y, C) \
+ ((__m512)__builtin_ia32_shufps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(C),\
+ (__v16sf)(__m512)_mm512_setzero_ps(),\
+ (__mmask16)-1))
+
+#define _mm512_mask_shuffle_ps(W, U, X, Y, C) \
+ ((__m512)__builtin_ia32_shufps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(C),\
+ (__v16sf)(__m512)(W),\
+ (__mmask16)(U)))
+
+#define _mm512_maskz_shuffle_ps(U, X, Y, C) \
+ ((__m512)__builtin_ia32_shufps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(C),\
+ (__v16sf)(__m512)_mm512_setzero_ps(),\
+ (__mmask16)(U)))
+
+#define _mm512_fixupimm_round_pd(X, Y, Z, C, R) \
+ ((__m512d)__builtin_ia32_fixupimmpd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (__v8di)(__m512i)(Z), (int)(C), \
+ (__mmask8)(-1), (R)))
+
+#define _mm512_mask_fixupimm_round_pd(X, U, Y, Z, C, R) \
+ ((__m512d)__builtin_ia32_fixupimmpd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (__v8di)(__m512i)(Z), (int)(C), \
+ (__mmask8)(U), (R)))
+
+#define _mm512_maskz_fixupimm_round_pd(U, X, Y, Z, C, R) \
+ ((__m512d)__builtin_ia32_fixupimmpd512_maskz ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (__v8di)(__m512i)(Z), (int)(C), \
+ (__mmask8)(U), (R)))
+
+#define _mm512_fixupimm_round_ps(X, Y, Z, C, R) \
+ ((__m512)__builtin_ia32_fixupimmps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (__v16si)(__m512i)(Z), (int)(C), \
+ (__mmask16)(-1), (R)))
+
+#define _mm512_mask_fixupimm_round_ps(X, U, Y, Z, C, R) \
+ ((__m512)__builtin_ia32_fixupimmps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (__v16si)(__m512i)(Z), (int)(C), \
+ (__mmask16)(U), (R)))
+
+#define _mm512_maskz_fixupimm_round_ps(U, X, Y, Z, C, R) \
+ ((__m512)__builtin_ia32_fixupimmps512_maskz ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (__v16si)(__m512i)(Z), (int)(C), \
+ (__mmask16)(U), (R)))
+
+#define _mm_fixupimm_round_sd(X, Y, Z, C, R) \
+ ((__m128d)__builtin_ia32_fixupimmsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (__v2di)(__m128i)(Z), (int)(C), \
+ (__mmask8)(-1), (R)))
+
+#define _mm_mask_fixupimm_round_sd(X, U, Y, Z, C, R) \
+ ((__m128d)__builtin_ia32_fixupimmsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (__v2di)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), (R)))
+
+#define _mm_maskz_fixupimm_round_sd(U, X, Y, Z, C, R) \
+ ((__m128d)__builtin_ia32_fixupimmsd_maskz ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (__v2di)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), (R)))
+
+#define _mm_fixupimm_round_ss(X, Y, Z, C, R) \
+ ((__m128)__builtin_ia32_fixupimmss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (__v4si)(__m128i)(Z), (int)(C), \
+ (__mmask8)(-1), (R)))
+
+#define _mm_mask_fixupimm_round_ss(X, U, Y, Z, C, R) \
+ ((__m128)__builtin_ia32_fixupimmss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (__v4si)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), (R)))
+
+#define _mm_maskz_fixupimm_round_ss(U, X, Y, Z, C, R) \
+ ((__m128)__builtin_ia32_fixupimmss_maskz ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (__v4si)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), (R)))
+#endif
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_movehdup_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_movshdup512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_movehdup_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_movshdup512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_movehdup_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_movshdup512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_moveldup_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_movsldup512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_moveldup_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_movsldup512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_moveldup_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_movsldup512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_or_si512 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_or_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_or_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_or_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_or_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_porq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_or_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_porq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_or_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_porq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_xor_si512 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pxord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_xor_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pxord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_xor_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pxord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_xor_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pxord512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_xor_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_xor_epi64 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_xor_epi64 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pxorq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rol_epi32 (__m512i __A, const int __B)
+{
+ return (__m512i) __builtin_ia32_prold512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rol_epi32 (__m512i __W, __mmask16 __U, __m512i __A, const int __B)
+{
+ return (__m512i) __builtin_ia32_prold512_mask ((__v16si) __A, __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rol_epi32 (__mmask16 __U, __m512i __A, const int __B)
+{
+ return (__m512i) __builtin_ia32_prold512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ror_epi32 (__m512i __A, int __B)
+{
+ return (__m512i) __builtin_ia32_prord512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ror_epi32 (__m512i __W, __mmask16 __U, __m512i __A, int __B)
+{
+ return (__m512i) __builtin_ia32_prord512_mask ((__v16si) __A, __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ror_epi32 (__mmask16 __U, __m512i __A, int __B)
+{
+ return (__m512i) __builtin_ia32_prord512_mask ((__v16si) __A, __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_rol_epi64 (__m512i __A, const int __B)
+{
+ return (__m512i) __builtin_ia32_prolq512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_rol_epi64 (__m512i __W, __mmask8 __U, __m512i __A, const int __B)
+{
+ return (__m512i) __builtin_ia32_prolq512_mask ((__v8di) __A, __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_rol_epi64 (__mmask8 __U, __m512i __A, const int __B)
+{
+ return (__m512i) __builtin_ia32_prolq512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ror_epi64 (__m512i __A, int __B)
+{
+ return (__m512i) __builtin_ia32_prorq512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ror_epi64 (__m512i __W, __mmask8 __U, __m512i __A, int __B)
+{
+ return (__m512i) __builtin_ia32_prorq512_mask ((__v8di) __A, __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ror_epi64 (__mmask8 __U, __m512i __A, int __B)
+{
+ return (__m512i) __builtin_ia32_prorq512_mask ((__v8di) __A, __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#else
+#define _mm512_rol_epi32(A, B) \
+ ((__m512i)__builtin_ia32_prold512_mask ((__v16si)(__m512i)(A), \
+ (int)(B), \
+ (__v16si)_mm512_setzero_si512 (), \
+ (__mmask16)(-1)))
+#define _mm512_mask_rol_epi32(W, U, A, B) \
+ ((__m512i)__builtin_ia32_prold512_mask ((__v16si)(__m512i)(A), \
+ (int)(B), \
+ (__v16si)(__m512i)(W), \
+ (__mmask16)(U)))
+#define _mm512_maskz_rol_epi32(U, A, B) \
+ ((__m512i)__builtin_ia32_prold512_mask ((__v16si)(__m512i)(A), \
+ (int)(B), \
+ (__v16si)_mm512_setzero_si512 (), \
+ (__mmask16)(U)))
+#define _mm512_ror_epi32(A, B) \
+ ((__m512i)__builtin_ia32_prord512_mask ((__v16si)(__m512i)(A), \
+ (int)(B), \
+ (__v16si)_mm512_setzero_si512 (), \
+ (__mmask16)(-1)))
+#define _mm512_mask_ror_epi32(W, U, A, B) \
+ ((__m512i)__builtin_ia32_prord512_mask ((__v16si)(__m512i)(A), \
+ (int)(B), \
+ (__v16si)(__m512i)(W), \
+ (__mmask16)(U)))
+#define _mm512_maskz_ror_epi32(U, A, B) \
+ ((__m512i)__builtin_ia32_prord512_mask ((__v16si)(__m512i)(A), \
+ (int)(B), \
+ (__v16si)_mm512_setzero_si512 (), \
+ (__mmask16)(U)))
+#define _mm512_rol_epi64(A, B) \
+ ((__m512i)__builtin_ia32_prolq512_mask ((__v8di)(__m512i)(A), \
+ (int)(B), \
+ (__v8di)_mm512_setzero_si512 (), \
+ (__mmask8)(-1)))
+#define _mm512_mask_rol_epi64(W, U, A, B) \
+ ((__m512i)__builtin_ia32_prolq512_mask ((__v8di)(__m512i)(A), \
+ (int)(B), \
+ (__v8di)(__m512i)(W), \
+ (__mmask8)(U)))
+#define _mm512_maskz_rol_epi64(U, A, B) \
+ ((__m512i)__builtin_ia32_prolq512_mask ((__v8di)(__m512i)(A), \
+ (int)(B), \
+ (__v8di)_mm512_setzero_si512 (), \
+ (__mmask8)(U)))
+
+#define _mm512_ror_epi64(A, B) \
+ ((__m512i)__builtin_ia32_prorq512_mask ((__v8di)(__m512i)(A), \
+ (int)(B), \
+ (__v8di)_mm512_setzero_si512 (), \
+ (__mmask8)(-1)))
+#define _mm512_mask_ror_epi64(W, U, A, B) \
+ ((__m512i)__builtin_ia32_prorq512_mask ((__v8di)(__m512i)(A), \
+ (int)(B), \
+ (__v8di)(__m512i)(W), \
+ (__mmask8)(U)))
+#define _mm512_maskz_ror_epi64(U, A, B) \
+ ((__m512i)__builtin_ia32_prorq512_mask ((__v8di)(__m512i)(A), \
+ (int)(B), \
+ (__v8di)_mm512_setzero_si512 (), \
+ (__mmask8)(U)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_and_si512 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_and_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_and_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_and_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_and_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_and_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W, __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_and_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_pd (),
+ __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_andnot_si512 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandnd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_andnot_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandnd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_andnot_epi32 (__m512i __W, __mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandnd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_andnot_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandnd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_andnot_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandnq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_andnot_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandnq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W, __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_andnot_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pandnq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_pd (),
+ __U);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_test_epi32_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_ptestmd512 ((__v16si) __A,
+ (__v16si) __B,
+ (__mmask16) -1);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_test_epi32_mask (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_ptestmd512 ((__v16si) __A,
+ (__v16si) __B, __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_test_epi64_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_ptestmq512 ((__v8di) __A,
+ (__v8di) __B,
+ (__mmask8) -1);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_test_epi64_mask (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_ptestmq512 ((__v8di) __A, (__v8di) __B, __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpackhi_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckhdq512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpackhi_epi32 (__m512i __W, __mmask16 __U, __m512i __A,
+ __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckhdq512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpackhi_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckhdq512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpackhi_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckhqdq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpackhi_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckhqdq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpackhi_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckhqdq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpacklo_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckldq512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpacklo_epi32 (__m512i __W, __mmask16 __U, __m512i __A,
+ __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckldq512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpacklo_epi32 (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpckldq512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpacklo_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpcklqdq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpacklo_epi64 (__m512i __W, __mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpcklqdq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpacklo_epi64 (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_punpcklqdq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+#ifdef __x86_64__
+#ifdef __OPTIMIZE__
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundss_u64 (__m128 __A, const int __R)
+{
+ return (unsigned long long) __builtin_ia32_vcvtss2usi64 ((__v4sf) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundss_si64 (__m128 __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvtss2si64 ((__v4sf) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundss_i64 (__m128 __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvtss2si64 ((__v4sf) __A, __R);
+}
+
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundss_u64 (__m128 __A, const int __R)
+{
+ return (unsigned long long) __builtin_ia32_vcvttss2usi64 ((__v4sf) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundss_i64 (__m128 __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvttss2si64 ((__v4sf) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundss_si64 (__m128 __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvttss2si64 ((__v4sf) __A, __R);
+}
+#else
+#define _mm_cvt_roundss_u64(A, B) \
+ ((unsigned long long)__builtin_ia32_vcvtss2usi64(A, B))
+
+#define _mm_cvt_roundss_si64(A, B) \
+ ((long long)__builtin_ia32_vcvtss2si64(A, B))
+
+#define _mm_cvt_roundss_i64(A, B) \
+ ((long long)__builtin_ia32_vcvtss2si64(A, B))
+
+#define _mm_cvtt_roundss_u64(A, B) \
+ ((unsigned long long)__builtin_ia32_vcvttss2usi64(A, B))
+
+#define _mm_cvtt_roundss_i64(A, B) \
+ ((long long)__builtin_ia32_vcvttss2si64(A, B))
+
+#define _mm_cvtt_roundss_si64(A, B) \
+ ((long long)__builtin_ia32_vcvttss2si64(A, B))
+#endif
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundss_u32 (__m128 __A, const int __R)
+{
+ return (unsigned) __builtin_ia32_vcvtss2usi32 ((__v4sf) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundss_si32 (__m128 __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvtss2si32 ((__v4sf) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundss_i32 (__m128 __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvtss2si32 ((__v4sf) __A, __R);
+}
+
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundss_u32 (__m128 __A, const int __R)
+{
+ return (unsigned) __builtin_ia32_vcvttss2usi32 ((__v4sf) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundss_i32 (__m128 __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvttss2si32 ((__v4sf) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundss_si32 (__m128 __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvttss2si32 ((__v4sf) __A, __R);
+}
+#else
+#define _mm_cvt_roundss_u32(A, B) \
+ ((unsigned)__builtin_ia32_vcvtss2usi32(A, B))
+
+#define _mm_cvt_roundss_si32(A, B) \
+ ((int)__builtin_ia32_vcvtss2si32(A, B))
+
+#define _mm_cvt_roundss_i32(A, B) \
+ ((int)__builtin_ia32_vcvtss2si32(A, B))
+
+#define _mm_cvtt_roundss_u32(A, B) \
+ ((unsigned)__builtin_ia32_vcvttss2usi32(A, B))
+
+#define _mm_cvtt_roundss_si32(A, B) \
+ ((int)__builtin_ia32_vcvttss2si32(A, B))
+
+#define _mm_cvtt_roundss_i32(A, B) \
+ ((int)__builtin_ia32_vcvttss2si32(A, B))
+#endif
+
+#ifdef __x86_64__
+#ifdef __OPTIMIZE__
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsd_u64 (__m128d __A, const int __R)
+{
+ return (unsigned long long) __builtin_ia32_vcvtsd2usi64 ((__v2df) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsd_si64 (__m128d __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvtsd2si64 ((__v2df) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsd_i64 (__m128d __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvtsd2si64 ((__v2df) __A, __R);
+}
+
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundsd_u64 (__m128d __A, const int __R)
+{
+ return (unsigned long long) __builtin_ia32_vcvttsd2usi64 ((__v2df) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundsd_si64 (__m128d __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvttsd2si64 ((__v2df) __A, __R);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundsd_i64 (__m128d __A, const int __R)
+{
+ return (long long) __builtin_ia32_vcvttsd2si64 ((__v2df) __A, __R);
+}
+#else
+#define _mm_cvt_roundsd_u64(A, B) \
+ ((unsigned long long)__builtin_ia32_vcvtsd2usi64(A, B))
+
+#define _mm_cvt_roundsd_si64(A, B) \
+ ((long long)__builtin_ia32_vcvtsd2si64(A, B))
+
+#define _mm_cvt_roundsd_i64(A, B) \
+ ((long long)__builtin_ia32_vcvtsd2si64(A, B))
+
+#define _mm_cvtt_roundsd_u64(A, B) \
+ ((unsigned long long)__builtin_ia32_vcvttsd2usi64(A, B))
+
+#define _mm_cvtt_roundsd_si64(A, B) \
+ ((long long)__builtin_ia32_vcvttsd2si64(A, B))
+
+#define _mm_cvtt_roundsd_i64(A, B) \
+ ((long long)__builtin_ia32_vcvttsd2si64(A, B))
+#endif
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsd_u32 (__m128d __A, const int __R)
+{
+ return (unsigned) __builtin_ia32_vcvtsd2usi32 ((__v2df) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsd_si32 (__m128d __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvtsd2si32 ((__v2df) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvt_roundsd_i32 (__m128d __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvtsd2si32 ((__v2df) __A, __R);
+}
+
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundsd_u32 (__m128d __A, const int __R)
+{
+ return (unsigned) __builtin_ia32_vcvttsd2usi32 ((__v2df) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundsd_i32 (__m128d __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvttsd2si32 ((__v2df) __A, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtt_roundsd_si32 (__m128d __A, const int __R)
+{
+ return (int) __builtin_ia32_vcvttsd2si32 ((__v2df) __A, __R);
+}
+#else
+#define _mm_cvt_roundsd_u32(A, B) \
+ ((unsigned)__builtin_ia32_vcvtsd2usi32(A, B))
+
+#define _mm_cvt_roundsd_si32(A, B) \
+ ((int)__builtin_ia32_vcvtsd2si32(A, B))
+
+#define _mm_cvt_roundsd_i32(A, B) \
+ ((int)__builtin_ia32_vcvtsd2si32(A, B))
+
+#define _mm_cvtt_roundsd_u32(A, B) \
+ ((unsigned)__builtin_ia32_vcvttsd2usi32(A, B))
+
+#define _mm_cvtt_roundsd_si32(A, B) \
+ ((int)__builtin_ia32_vcvttsd2si32(A, B))
+
+#define _mm_cvtt_roundsd_i32(A, B) \
+ ((int)__builtin_ia32_vcvttsd2si32(A, B))
+#endif
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_movedup_pd (__m512d __A)
+{
+ return (__m512d) __builtin_ia32_movddup512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_movedup_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_movddup512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_movedup_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_movddup512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpacklo_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_unpcklpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpacklo_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_unpcklpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpacklo_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_unpcklpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpackhi_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_unpckhpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpackhi_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_unpckhpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpackhi_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_unpckhpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpackhi_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_unpckhps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpackhi_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_unpckhps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpackhi_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_unpckhps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundps_pd (__m256 __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_cvtps2pd512_mask ((__v8sf) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundps_pd (__m512d __W, __mmask8 __U, __m256 __A,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_cvtps2pd512_mask ((__v8sf) __A,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundps_pd (__mmask8 __U, __m256 __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_cvtps2pd512_mask ((__v8sf) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundph_ps (__m256i __A, const int __R)
+{
+ return (__m512) __builtin_ia32_vcvtph2ps512_mask ((__v16hi) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundph_ps (__m512 __W, __mmask16 __U, __m256i __A,
+ const int __R)
+{
+ return (__m512) __builtin_ia32_vcvtph2ps512_mask ((__v16hi) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundph_ps (__mmask16 __U, __m256i __A, const int __R)
+{
+ return (__m512) __builtin_ia32_vcvtph2ps512_mask ((__v16hi) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundps_ph (__m512 __A, const int __I)
+{
+ return (__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf) __A,
+ __I,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtps_ph (__m512 __A, const int __I)
+{
+ return (__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf) __A,
+ __I,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ -1);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundps_ph (__m256i __U, __mmask16 __W, __m512 __A,
+ const int __I)
+{
+ return (__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf) __A,
+ __I,
+ (__v16hi) __U,
+ (__mmask16) __W);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtps_ph (__m256i __U, __mmask16 __W, __m512 __A, const int __I)
+{
+ return (__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf) __A,
+ __I,
+ (__v16hi) __U,
+ (__mmask16) __W);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundps_ph (__mmask16 __W, __m512 __A, const int __I)
+{
+ return (__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf) __A,
+ __I,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __W);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtps_ph (__mmask16 __W, __m512 __A, const int __I)
+{
+ return (__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf) __A,
+ __I,
+ (__v16hi)
+ _mm256_setzero_si256 (),
+ (__mmask16) __W);
+}
+#else
+#define _mm512_cvt_roundps_pd(A, B) \
+ (__m512d)__builtin_ia32_cvtps2pd512_mask(A, (__v8df)_mm512_setzero_pd(), -1, B)
+
+#define _mm512_mask_cvt_roundps_pd(W, U, A, B) \
+ (__m512d)__builtin_ia32_cvtps2pd512_mask(A, (__v8df)(W), U, B)
+
+#define _mm512_maskz_cvt_roundps_pd(U, A, B) \
+ (__m512d)__builtin_ia32_cvtps2pd512_mask(A, (__v8df)_mm512_setzero_pd(), U, B)
+
+#define _mm512_cvt_roundph_ps(A, B) \
+ (__m512)__builtin_ia32_vcvtph2ps512_mask((__v16hi)(A), (__v16sf)_mm512_setzero_ps(), -1, B)
+
+#define _mm512_mask_cvt_roundph_ps(W, U, A, B) \
+ (__m512)__builtin_ia32_vcvtph2ps512_mask((__v16hi)(A), (__v16sf)(W), U, B)
+
+#define _mm512_maskz_cvt_roundph_ps(U, A, B) \
+ (__m512)__builtin_ia32_vcvtph2ps512_mask((__v16hi)(A), (__v16sf)_mm512_setzero_ps(), U, B)
+
+#define _mm512_cvt_roundps_ph(A, I) \
+ ((__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf)(__m512) A, (int) (I),\
+ (__v16hi)_mm256_setzero_si256 (), -1))
+#define _mm512_cvtps_ph(A, I) \
+ ((__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf)(__m512) A, (int) (I),\
+ (__v16hi)_mm256_setzero_si256 (), -1))
+#define _mm512_mask_cvt_roundps_ph(U, W, A, I) \
+ ((__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf)(__m512) A, (int) (I),\
+ (__v16hi)(__m256i)(U), (__mmask16) (W)))
+#define _mm512_mask_cvtps_ph(U, W, A, I) \
+ ((__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf)(__m512) A, (int) (I),\
+ (__v16hi)(__m256i)(U), (__mmask16) (W)))
+#define _mm512_maskz_cvt_roundps_ph(W, A, I) \
+ ((__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf)(__m512) A, (int) (I),\
+ (__v16hi)_mm256_setzero_si256 (), (__mmask16) (W)))
+#define _mm512_maskz_cvtps_ph(W, A, I) \
+ ((__m256i) __builtin_ia32_vcvtps2ph512_mask ((__v16sf)(__m512) A, (int) (I),\
+ (__v16hi)_mm256_setzero_si256 (), (__mmask16) (W)))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvt_roundpd_ps (__m512d __A, const int __R)
+{
+ return (__m256) __builtin_ia32_cvtpd2ps512_mask ((__v8df) __A,
+ (__v8sf)
+ _mm256_setzero_ps (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvt_roundpd_ps (__m256 __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m256) __builtin_ia32_cvtpd2ps512_mask ((__v8df) __A,
+ (__v8sf) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvt_roundpd_ps (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m256) __builtin_ia32_cvtpd2ps512_mask ((__v8df) __A,
+ (__v8sf)
+ _mm256_setzero_ps (),
+ (__mmask8) __U, __R);
+}
+
+#else
+#define _mm512_cvt_roundpd_ps(A, B) \
+ (__m256)__builtin_ia32_cvtpd2ps512_mask(A, (__v8sf)_mm256_setzero_ps(), -1, B)
+
+#define _mm512_mask_cvt_roundpd_ps(W, U, A, B) \
+ (__m256)__builtin_ia32_cvtpd2ps512_mask(A, (__v8sf)(W), U, B)
+
+#define _mm512_maskz_cvt_roundpd_ps(U, A, B) \
+ (__m256)__builtin_ia32_cvtpd2ps512_mask(A, (__v8sf)_mm256_setzero_ps(), U, B)
+#endif
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_stream_si512 (__m512i * __P, __m512i __A)
+{
+ __builtin_ia32_movntdq512 ((__v8di *) __P, (__v8di) __A);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_stream_ps (float *__P, __m512 __A)
+{
+ __builtin_ia32_movntps512 (__P, (__v16sf) __A);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_stream_pd (double *__P, __m512d __A)
+{
+ __builtin_ia32_movntpd512 (__P, (__v8df) __A);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getexp_round_ps (__m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_getexpps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getexp_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512) __builtin_ia32_getexpps512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getexp_round_ps (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_getexpps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getexp_round_pd (__m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_getexppd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getexp_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_getexppd512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getexp_round_pd (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_getexppd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U, __R);
+}
+
+/* Constants for mantissa extraction */
+typedef enum
+{
+ _MM_MANT_NORM_1_2, /* interval [1, 2) */
+ _MM_MANT_NORM_p5_2, /* interval [0.5, 2) */
+ _MM_MANT_NORM_p5_1, /* interval [0.5, 1) */
+ _MM_MANT_NORM_p75_1p5 /* interval [0.75, 1.5) */
+} _MM_MANTISSA_NORM_ENUM;
+
+typedef enum
+{
+ _MM_MANT_SIGN_src, /* sign = sign(SRC) */
+ _MM_MANT_SIGN_zero, /* sign = 0 */
+ _MM_MANT_SIGN_nan /* DEST = NaN if sign(SRC) = 1 */
+} _MM_MANTISSA_SIGN_ENUM;
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getmant_round_pd (__m512d __A, _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_getmantpd512_mask ((__v8df) __A,
+ (__C << 2) | __B,
+ _mm512_setzero_pd (),
+ (__mmask8) -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getmant_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_getmantpd512_mask ((__v8df) __A,
+ (__C << 2) | __B,
+ (__v8df) __W, __U,
+ __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getmant_round_pd (__mmask8 __U, __m512d __A,
+ _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C, const int __R)
+{
+ return (__m512d) __builtin_ia32_getmantpd512_mask ((__v8df) __A,
+ (__C << 2) | __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getmant_round_ps (__m512 __A, _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C, const int __R)
+{
+ return (__m512) __builtin_ia32_getmantps512_mask ((__v16sf) __A,
+ (__C << 2) | __B,
+ _mm512_setzero_ps (),
+ (__mmask16) -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getmant_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C, const int __R)
+{
+ return (__m512) __builtin_ia32_getmantps512_mask ((__v16sf) __A,
+ (__C << 2) | __B,
+ (__v16sf) __W, __U,
+ __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getmant_round_ps (__mmask16 __U, __m512 __A,
+ _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C, const int __R)
+{
+ return (__m512) __builtin_ia32_getmantps512_mask ((__v16sf) __A,
+ (__C << 2) | __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __U, __R);
+}
+
+#else
+#define _mm512_getmant_round_pd(X, B, C, R) \
+ ((__m512d)__builtin_ia32_getmantpd512_mask ((__v8df)(__m512d)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8df)(__m512d)_mm512_setzero_pd(), \
+ (__mmask8)-1,\
+ (R)))
+
+#define _mm512_mask_getmant_round_pd(W, U, X, B, C, R) \
+ ((__m512d)__builtin_ia32_getmantpd512_mask ((__v8df)(__m512d)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8df)(__m512d)(W), \
+ (__mmask8)(U),\
+ (R)))
+
+#define _mm512_maskz_getmant_round_pd(U, X, B, C, R) \
+ ((__m512d)__builtin_ia32_getmantpd512_mask ((__v8df)(__m512d)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8df)(__m512d)_mm512_setzero_pd(), \
+ (__mmask8)(U),\
+ (R)))
+#define _mm512_getmant_round_ps(X, B, C, R) \
+ ((__m512)__builtin_ia32_getmantps512_mask ((__v16sf)(__m512)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16sf)(__m512)_mm512_setzero_ps(), \
+ (__mmask16)-1,\
+ (R)))
+
+#define _mm512_mask_getmant_round_ps(W, U, X, B, C, R) \
+ ((__m512)__builtin_ia32_getmantps512_mask ((__v16sf)(__m512)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16sf)(__m512)(W), \
+ (__mmask16)(U),\
+ (R)))
+
+#define _mm512_maskz_getmant_round_ps(U, X, B, C, R) \
+ ((__m512)__builtin_ia32_getmantps512_mask ((__v16sf)(__m512)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16sf)(__m512)_mm512_setzero_ps(), \
+ (__mmask16)(U),\
+ (R)))
+#define _mm512_getexp_round_ps(A, R) \
+ ((__m512)__builtin_ia32_getexpps512_mask((__v16sf)(__m512)(A), \
+ (__v16sf)_mm512_setzero_ps(), (__mmask16)-1, R))
+
+#define _mm512_mask_getexp_round_ps(W, U, A, R) \
+ ((__m512)__builtin_ia32_getexpps512_mask((__v16sf)(__m512)(A), \
+ (__v16sf)(__m512)(W), (__mmask16)(U), R))
+
+#define _mm512_maskz_getexp_round_ps(U, A, R) \
+ ((__m512)__builtin_ia32_getexpps512_mask((__v16sf)(__m512)(A), \
+ (__v16sf)_mm512_setzero_ps(), (__mmask16)(U), R))
+
+#define _mm512_getexp_round_pd(A, R) \
+ ((__m512d)__builtin_ia32_getexppd512_mask((__v8df)(__m512d)(A), \
+ (__v8df)_mm512_setzero_pd(), (__mmask8)-1, R))
+
+#define _mm512_mask_getexp_round_pd(W, U, A, R) \
+ ((__m512d)__builtin_ia32_getexppd512_mask((__v8df)(__m512d)(A), \
+ (__v8df)(__m512d)(W), (__mmask8)(U), R))
+
+#define _mm512_maskz_getexp_round_pd(U, A, R) \
+ ((__m512d)__builtin_ia32_getexppd512_mask((__v8df)(__m512d)(A), \
+ (__v8df)_mm512_setzero_pd(), (__mmask8)(U), R))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_roundscale_round_ps (__m512 __A, const int __imm, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A, __imm,
+ (__v16sf) __A, -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_roundscale_round_ps (__m512 __A, __mmask16 __B, __m512 __C,
+ const int __imm, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __C, __imm,
+ (__v16sf) __A,
+ (__mmask16) __B, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_roundscale_round_ps (__mmask16 __A, __m512 __B,
+ const int __imm, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __B,
+ __imm,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __A, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_roundscale_round_pd (__m512d __A, const int __imm, const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A, __imm,
+ (__v8df) __A, -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_roundscale_round_pd (__m512d __A, __mmask8 __B,
+ __m512d __C, const int __imm, const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __C, __imm,
+ (__v8df) __A,
+ (__mmask8) __B, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_roundscale_round_pd (__mmask8 __A, __m512d __B,
+ const int __imm, const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __B,
+ __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __A, __R);
+}
+#else
+#define _mm512_roundscale_round_ps(A, B, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(A), (int)(B),\
+ (__v16sf)(__m512)(A), (__mmask16)(-1), R))
+#define _mm512_mask_roundscale_round_ps(A, B, C, D, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(C), \
+ (int)(D), \
+ (__v16sf)(__m512)(A), \
+ (__mmask16)(B), R))
+#define _mm512_maskz_roundscale_round_ps(A, B, C, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(B), \
+ (int)(C), \
+ (__v16sf)_mm512_setzero_ps(),\
+ (__mmask16)(A), R))
+#define _mm512_roundscale_round_pd(A, B, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(A), (int)(B),\
+ (__v8df)(__m512d)(A), (__mmask8)(-1), R))
+#define _mm512_mask_roundscale_round_pd(A, B, C, D, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(C), \
+ (int)(D), \
+ (__v8df)(__m512d)(A), \
+ (__mmask8)(B), R))
+#define _mm512_maskz_roundscale_round_pd(A, B, C, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(B), \
+ (int)(C), \
+ (__v8df)_mm512_setzero_pd(),\
+ (__mmask8)(A), R))
+#endif
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_floor_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_FLOOR,
+ (__v16sf) __A, -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_floor_pd (__m512d __A)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_FLOOR,
+ (__v8df) __A, -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ceil_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_CEIL,
+ (__v16sf) __A, -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ceil_pd (__m512d __A)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_CEIL,
+ (__v8df) __A, -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_floor_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_FLOOR,
+ (__v16sf) __W, __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_floor_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_FLOOR,
+ (__v8df) __W, __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ceil_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_CEIL,
+ (__v16sf) __W, __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ceil_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_CEIL,
+ (__v8df) __W, __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_floor_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_FLOOR,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_floor_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_FLOOR,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ceil_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_CEIL,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ceil_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_CEIL,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_floor_round_ps (__m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_FLOOR,
+ (__v16sf) __A, -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_floor_round_pd (__m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_FLOOR,
+ (__v8df) __A, -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ceil_round_ps (__m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_CEIL,
+ (__v16sf) __A, -1, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_ceil_round_pd (__m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_CEIL,
+ (__v8df) __A, -1, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_floor_round_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_FLOOR,
+ (__v16sf) __W, __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_floor_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_FLOOR,
+ (__v8df) __W, __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ceil_round_ps (__m512 __W, __mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_CEIL,
+ (__v16sf) __W, __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_ceil_round_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_CEIL,
+ (__v8df) __W, __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_floor_round_ps (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_FLOOR,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_floor_round_pd (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_FLOOR,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __U, __R);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ceil_round_ps (__mmask16 __U, __m512 __A, const int __R)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A,
+ _MM_FROUND_CEIL,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __U, __R);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_ceil_round_pd (__mmask8 __U, __m512d __A, const int __R)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A,
+ _MM_FROUND_CEIL,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __U, __R);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_alignr_epi32 (__m512i __A, __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_alignd512_mask ((__v16si) __A,
+ (__v16si) __B, __imm,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_alignr_epi32 (__m512i __W, __mmask16 __U, __m512i __A,
+ __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_alignd512_mask ((__v16si) __A,
+ (__v16si) __B, __imm,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_alignr_epi32 (__mmask16 __U, __m512i __A, __m512i __B,
+ const int __imm)
+{
+ return (__m512i) __builtin_ia32_alignd512_mask ((__v16si) __A,
+ (__v16si) __B, __imm,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_alignr_epi64 (__m512i __A, __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_alignq512_mask ((__v8di) __A,
+ (__v8di) __B, __imm,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_alignr_epi64 (__m512i __W, __mmask8 __U, __m512i __A,
+ __m512i __B, const int __imm)
+{
+ return (__m512i) __builtin_ia32_alignq512_mask ((__v8di) __A,
+ (__v8di) __B, __imm,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_alignr_epi64 (__mmask8 __U, __m512i __A, __m512i __B,
+ const int __imm)
+{
+ return (__m512i) __builtin_ia32_alignq512_mask ((__v8di) __A,
+ (__v8di) __B, __imm,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+#else
+#define _mm512_floor_round_ps(A, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(A), \
+ _MM_FROUND_FLOOR, \
+ (__v16sf)(__m512)(A), \
+ (__mmask16)(-1), R))
+#define _mm512_mask_floor_round_ps(A, B, C, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(C), \
+ _MM_FROUND_FLOOR, \
+ (__v16sf)(__m512)(A), \
+ (__mmask16)(B), R))
+#define _mm512_maskz_floor_round_ps(A, B, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(B), \
+ _MM_FROUND_FLOOR, \
+ (__v16sf)_mm512_setzero_ps(),\
+ (__mmask16)(A), R))
+#define _mm512_floor_round_pd(A, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(A), \
+ _MM_FROUND_FLOOR, \
+ (__v8df)(__m512d)(A), \
+ (__mmask8)(-1), R))
+#define _mm512_mask_floor_round_pd(A, B, C, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(C), \
+ _MM_FROUND_FLOOR, \
+ (__v8df)(__m512d)(A), \
+ (__mmask8)(B), R))
+#define _mm512_maskz_floor_round_pd(A, B, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(B), \
+ _MM_FROUND_FLOOR, \
+ (__v8df)_mm512_setzero_pd(),\
+ (__mmask8)(A), R))
+#define _mm512_ceil_round_ps(A, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(A), \
+ _MM_FROUND_CEIL, \
+ (__v16sf)(__m512)(A), \
+ (__mmask16)(-1), R))
+#define _mm512_mask_ceil_round_ps(A, B, C, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(C), \
+ _MM_FROUND_CEIL, \
+ (__v16sf)(__m512)(A), \
+ (__mmask16)(B), R))
+#define _mm512_maskz_ceil_round_ps(A, B, R) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(B), \
+ _MM_FROUND_CEIL, \
+ (__v16sf)_mm512_setzero_ps(),\
+ (__mmask16)(A), R))
+#define _mm512_ceil_round_pd(A, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(A), \
+ _MM_FROUND_CEIL, \
+ (__v8df)(__m512d)(A), \
+ (__mmask8)(-1), R))
+#define _mm512_mask_ceil_round_pd(A, B, C, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(C), \
+ _MM_FROUND_CEIL, \
+ (__v8df)(__m512d)(A), \
+ (__mmask8)(B), R))
+#define _mm512_maskz_ceil_round_pd(A, B, R) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(B), \
+ _MM_FROUND_CEIL, \
+ (__v8df)_mm512_setzero_pd(),\
+ (__mmask8)(A), R))
+
+#define _mm512_alignr_epi32(X, Y, C) \
+ ((__m512i)__builtin_ia32_alignd512_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(C), (__v16si)(__m512i)(X), \
+ (__mmask16)-1))
+
+#define _mm512_mask_alignr_epi32(W, U, X, Y, C) \
+ ((__m512i)__builtin_ia32_alignd512_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(C), (__v16si)(__m512i)(W), \
+ (__mmask16)(U)))
+
+#define _mm512_maskz_alignr_epi32(U, X, Y, C) \
+ ((__m512i)__builtin_ia32_alignd512_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(C), (__v16si)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask16)(U)))
+
+#define _mm512_alignr_epi64(X, Y, C) \
+ ((__m512i)__builtin_ia32_alignq512_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(C), (__v8di)(__m512i)(X), (__mmask8)-1))
+
+#define _mm512_mask_alignr_epi64(W, U, X, Y, C) \
+ ((__m512i)__builtin_ia32_alignq512_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(C), (__v8di)(__m512i)(W), (__mmask8)(U)))
+
+#define _mm512_maskz_alignr_epi64(U, X, Y, C) \
+ ((__m512i)__builtin_ia32_alignq512_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(C), (__v8di)(__m512i)_mm512_setzero_si512 (),\
+ (__mmask8)(U)))
+#endif
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmpeq_epi32_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_pcmpeqd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__mmask16) -1);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmpeq_epi32_mask (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_pcmpeqd512_mask ((__v16si) __A,
+ (__v16si) __B, __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmpeq_epi64_mask (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_pcmpeqq512_mask ((__v8di) __A,
+ (__v8di) __B, __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmpeq_epi64_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_pcmpeqq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__mmask8) -1);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmpgt_epi32_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_pcmpgtd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__mmask16) -1);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmpgt_epi32_mask (__mmask16 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask16) __builtin_ia32_pcmpgtd512_mask ((__v16si) __A,
+ (__v16si) __B, __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmpgt_epi64_mask (__mmask8 __U, __m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_pcmpgtq512_mask ((__v8di) __A,
+ (__v8di) __B, __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmpgt_epi64_mask (__m512i __A, __m512i __B)
+{
+ return (__mmask8) __builtin_ia32_pcmpgtq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__mmask8) -1);
+}
+
+#define _MM_CMPINT_EQ 0x0
+#define _MM_CMPINT_LT 0x1
+#define _MM_CMPINT_LE 0x2
+#define _MM_CMPINT_UNUSED 0x3
+#define _MM_CMPINT_NE 0x4
+#define _MM_CMPINT_NLT 0x5
+#define _MM_CMPINT_GE 0x5
+#define _MM_CMPINT_NLE 0x6
+#define _MM_CMPINT_GT 0x6
+
+#ifdef __OPTIMIZE__
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_epi64_mask (__m512i __X, __m512i __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpq512_mask ((__v8di) __X,
+ (__v8di) __Y, __P,
+ (__mmask8) -1);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_epi32_mask (__m512i __X, __m512i __Y, const int __P)
+{
+ return (__mmask16) __builtin_ia32_cmpd512_mask ((__v16si) __X,
+ (__v16si) __Y, __P,
+ (__mmask16) -1);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_epu64_mask (__m512i __X, __m512i __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_ucmpq512_mask ((__v8di) __X,
+ (__v8di) __Y, __P,
+ (__mmask8) -1);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_epu32_mask (__m512i __X, __m512i __Y, const int __P)
+{
+ return (__mmask16) __builtin_ia32_ucmpd512_mask ((__v16si) __X,
+ (__v16si) __Y, __P,
+ (__mmask16) -1);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_round_pd_mask (__m512d __X, __m512d __Y, const int __P,
+ const int __R)
+{
+ return (__mmask8) __builtin_ia32_cmppd512_mask ((__v8df) __X,
+ (__v8df) __Y, __P,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_round_ps_mask (__m512 __X, __m512 __Y, const int __P, const int __R)
+{
+ return (__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf) __X,
+ (__v16sf) __Y, __P,
+ (__mmask16) -1, __R);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_epi64_mask (__mmask8 __U, __m512i __X, __m512i __Y,
+ const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpq512_mask ((__v8di) __X,
+ (__v8di) __Y, __P,
+ (__mmask8) __U);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_epi32_mask (__mmask16 __U, __m512i __X, __m512i __Y,
+ const int __P)
+{
+ return (__mmask16) __builtin_ia32_cmpd512_mask ((__v16si) __X,
+ (__v16si) __Y, __P,
+ (__mmask16) __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_epu64_mask (__mmask8 __U, __m512i __X, __m512i __Y,
+ const int __P)
+{
+ return (__mmask8) __builtin_ia32_ucmpq512_mask ((__v8di) __X,
+ (__v8di) __Y, __P,
+ (__mmask8) __U);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_epu32_mask (__mmask16 __U, __m512i __X, __m512i __Y,
+ const int __P)
+{
+ return (__mmask16) __builtin_ia32_ucmpd512_mask ((__v16si) __X,
+ (__v16si) __Y, __P,
+ (__mmask16) __U);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_round_pd_mask (__mmask8 __U, __m512d __X, __m512d __Y,
+ const int __P, const int __R)
+{
+ return (__mmask8) __builtin_ia32_cmppd512_mask ((__v8df) __X,
+ (__v8df) __Y, __P,
+ (__mmask8) __U, __R);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_round_ps_mask (__mmask16 __U, __m512 __X, __m512 __Y,
+ const int __P, const int __R)
+{
+ return (__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf) __X,
+ (__v16sf) __Y, __P,
+ (__mmask16) __U, __R);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmp_round_sd_mask (__m128d __X, __m128d __Y, const int __P, const int __R)
+{
+ return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
+ (__v2df) __Y, __P,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_cmp_round_sd_mask (__mmask8 __M, __m128d __X, __m128d __Y,
+ const int __P, const int __R)
+{
+ return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
+ (__v2df) __Y, __P,
+ (__mmask8) __M, __R);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmp_round_ss_mask (__m128 __X, __m128 __Y, const int __P, const int __R)
+{
+ return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
+ (__v4sf) __Y, __P,
+ (__mmask8) -1, __R);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_cmp_round_ss_mask (__mmask8 __M, __m128 __X, __m128 __Y,
+ const int __P, const int __R)
+{
+ return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
+ (__v4sf) __Y, __P,
+ (__mmask8) __M, __R);
+}
+
+#else
+#define _mm512_cmp_epi64_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpq512_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(P),\
+ (__mmask8)-1))
+
+#define _mm512_cmp_epi32_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpd512_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(P),\
+ (__mmask16)-1))
+
+#define _mm512_cmp_epu64_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_ucmpq512_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(P),\
+ (__mmask8)-1))
+
+#define _mm512_cmp_epu32_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_ucmpd512_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(P),\
+ (__mmask16)-1))
+
+#define _mm512_cmp_round_pd_mask(X, Y, P, R) \
+ ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(P),\
+ (__mmask8)-1, R))
+
+#define _mm512_cmp_round_ps_mask(X, Y, P, R) \
+ ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(P),\
+ (__mmask16)-1, R))
+
+#define _mm512_mask_cmp_epi64_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpq512_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(P),\
+ (__mmask8)M))
+
+#define _mm512_mask_cmp_epi32_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpd512_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(P),\
+ (__mmask16)M))
+
+#define _mm512_mask_cmp_epu64_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_ucmpq512_mask ((__v8di)(__m512i)(X), \
+ (__v8di)(__m512i)(Y), (int)(P),\
+ (__mmask8)M))
+
+#define _mm512_mask_cmp_epu32_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_ucmpd512_mask ((__v16si)(__m512i)(X), \
+ (__v16si)(__m512i)(Y), (int)(P),\
+ (__mmask16)M))
+
+#define _mm512_mask_cmp_round_pd_mask(M, X, Y, P, R) \
+ ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(P),\
+ (__mmask8)M, R))
+
+#define _mm512_mask_cmp_round_ps_mask(M, X, Y, P, R) \
+ ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(P),\
+ (__mmask16)M, R))
+
+#define _mm_cmp_round_sd_mask(X, Y, P, R) \
+ ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (int)(P),\
+ (__mmask8)-1, R))
+
+#define _mm_mask_cmp_round_sd_mask(M, X, Y, P, R) \
+ ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (int)(P),\
+ (M), R))
+
+#define _mm_cmp_round_ss_mask(X, Y, P, R) \
+ ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (int)(P), \
+ (__mmask8)-1, R))
+
+#define _mm_mask_cmp_round_ss_mask(M, X, Y, P, R) \
+ ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (int)(P), \
+ (M), R))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32gather_ps (__m512i __index, float const *__addr, int __scale)
+{
+ __m512 v1_old = _mm512_setzero_ps ();
+ __mmask16 mask = 0xFFFF;
+
+ return (__m512) __builtin_ia32_gathersiv16sf ((__v16sf) v1_old,
+ __addr,
+ (__v16si) __index,
+ mask, __scale);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32gather_ps (__m512 v1_old, __mmask16 __mask,
+ __m512i __index, float const *__addr, int __scale)
+{
+ return (__m512) __builtin_ia32_gathersiv16sf ((__v16sf) v1_old,
+ __addr,
+ (__v16si) __index,
+ __mask, __scale);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32gather_pd (__m256i __index, double const *__addr, int __scale)
+{
+ __m512d v1_old = _mm512_setzero_pd ();
+ __mmask8 mask = 0xFF;
+
+ return (__m512d) __builtin_ia32_gathersiv8df ((__v8df) v1_old,
+ __addr,
+ (__v8si) __index, mask,
+ __scale);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32gather_pd (__m512d __v1_old, __mmask8 __mask,
+ __m256i __index, double const *__addr, int __scale)
+{
+ return (__m512d) __builtin_ia32_gathersiv8df ((__v8df) __v1_old,
+ __addr,
+ (__v8si) __index,
+ __mask, __scale);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64gather_ps (__m512i __index, float const *__addr, int __scale)
+{
+ __m256 v1_old = _mm256_setzero_ps ();
+ __mmask8 mask = 0xFF;
+
+ return (__m256) __builtin_ia32_gatherdiv16sf ((__v8sf) v1_old,
+ __addr,
+ (__v8di) __index, mask,
+ __scale);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64gather_ps (__m256 __v1_old, __mmask8 __mask,
+ __m512i __index, float const *__addr, int __scale)
+{
+ return (__m256) __builtin_ia32_gatherdiv16sf ((__v8sf) __v1_old,
+ __addr,
+ (__v8di) __index,
+ __mask, __scale);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64gather_pd (__m512i __index, double const *__addr, int __scale)
+{
+ __m512d v1_old = _mm512_setzero_pd ();
+ __mmask8 mask = 0xFF;
+
+ return (__m512d) __builtin_ia32_gatherdiv8df ((__v8df) v1_old,
+ __addr,
+ (__v8di) __index, mask,
+ __scale);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64gather_pd (__m512d __v1_old, __mmask8 __mask,
+ __m512i __index, double const *__addr, int __scale)
+{
+ return (__m512d) __builtin_ia32_gatherdiv8df ((__v8df) __v1_old,
+ __addr,
+ (__v8di) __index,
+ __mask, __scale);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32gather_epi32 (__m512i __index, int const *__addr, int __scale)
+{
+ __m512i v1_old = _mm512_setzero_si512 ();
+ __mmask16 mask = 0xFFFF;
+
+ return (__m512i) __builtin_ia32_gathersiv16si ((__v16si) v1_old,
+ __addr,
+ (__v16si) __index,
+ mask, __scale);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32gather_epi32 (__m512i __v1_old, __mmask16 __mask,
+ __m512i __index, int const *__addr, int __scale)
+{
+ return (__m512i) __builtin_ia32_gathersiv16si ((__v16si) __v1_old,
+ __addr,
+ (__v16si) __index,
+ __mask, __scale);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32gather_epi64 (__m256i __index, long long const *__addr, int __scale)
+{
+ __m512i v1_old = _mm512_setzero_si512 ();
+ __mmask8 mask = 0xFF;
+
+ return (__m512i) __builtin_ia32_gathersiv8di ((__v8di) v1_old,
+ __addr,
+ (__v8si) __index, mask,
+ __scale);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32gather_epi64 (__m512i __v1_old, __mmask8 __mask,
+ __m256i __index, long long const *__addr,
+ int __scale)
+{
+ return (__m512i) __builtin_ia32_gathersiv8di ((__v8di) __v1_old,
+ __addr,
+ (__v8si) __index,
+ __mask, __scale);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64gather_epi32 (__m512i __index, int const *__addr, int __scale)
+{
+ __m256i v1_old = _mm256_setzero_si256 ();
+ __mmask8 mask = 0xFF;
+
+ return (__m256i) __builtin_ia32_gatherdiv16si ((__v8si) v1_old,
+ __addr,
+ (__v8di) __index,
+ mask, __scale);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64gather_epi32 (__m256i __v1_old, __mmask8 __mask,
+ __m512i __index, int const *__addr, int __scale)
+{
+ return (__m256i) __builtin_ia32_gatherdiv16si ((__v8si) __v1_old,
+ __addr,
+ (__v8di) __index,
+ __mask, __scale);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64gather_epi64 (__m512i __index, long long const *__addr, int __scale)
+{
+ __m512i v1_old = _mm512_setzero_si512 ();
+ __mmask8 mask = 0xFF;
+
+ return (__m512i) __builtin_ia32_gatherdiv8di ((__v8di) v1_old,
+ __addr,
+ (__v8di) __index, mask,
+ __scale);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64gather_epi64 (__m512i __v1_old, __mmask8 __mask,
+ __m512i __index, long long const *__addr,
+ int __scale)
+{
+ return (__m512i) __builtin_ia32_gatherdiv8di ((__v8di) __v1_old,
+ __addr,
+ (__v8di) __index,
+ __mask, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32scatter_ps (float *__addr, __m512i __index, __m512 __v1, int __scale)
+{
+ __builtin_ia32_scattersiv16sf (__addr, (__mmask16) 0xFFFF,
+ (__v16si) __index, (__v16sf) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32scatter_ps (float *__addr, __mmask16 __mask,
+ __m512i __index, __m512 __v1, int __scale)
+{
+ __builtin_ia32_scattersiv16sf (__addr, __mask, (__v16si) __index,
+ (__v16sf) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32scatter_pd (double *__addr, __m256i __index, __m512d __v1,
+ int __scale)
+{
+ __builtin_ia32_scattersiv8df (__addr, (__mmask8) 0xFF,
+ (__v8si) __index, (__v8df) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32scatter_pd (double *__addr, __mmask8 __mask,
+ __m256i __index, __m512d __v1, int __scale)
+{
+ __builtin_ia32_scattersiv8df (__addr, __mask, (__v8si) __index,
+ (__v8df) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64scatter_ps (float *__addr, __m512i __index, __m256 __v1, int __scale)
+{
+ __builtin_ia32_scatterdiv16sf (__addr, (__mmask8) 0xFF,
+ (__v8di) __index, (__v8sf) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64scatter_ps (float *__addr, __mmask8 __mask,
+ __m512i __index, __m256 __v1, int __scale)
+{
+ __builtin_ia32_scatterdiv16sf (__addr, __mask, (__v8di) __index,
+ (__v8sf) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64scatter_pd (double *__addr, __m512i __index, __m512d __v1,
+ int __scale)
+{
+ __builtin_ia32_scatterdiv8df (__addr, (__mmask8) 0xFF,
+ (__v8di) __index, (__v8df) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64scatter_pd (double *__addr, __mmask8 __mask,
+ __m512i __index, __m512d __v1, int __scale)
+{
+ __builtin_ia32_scatterdiv8df (__addr, __mask, (__v8di) __index,
+ (__v8df) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32scatter_epi32 (int *__addr, __m512i __index,
+ __m512i __v1, int __scale)
+{
+ __builtin_ia32_scattersiv16si (__addr, (__mmask16) 0xFFFF,
+ (__v16si) __index, (__v16si) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32scatter_epi32 (int *__addr, __mmask16 __mask,
+ __m512i __index, __m512i __v1, int __scale)
+{
+ __builtin_ia32_scattersiv16si (__addr, __mask, (__v16si) __index,
+ (__v16si) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i32scatter_epi64 (long long *__addr, __m256i __index,
+ __m512i __v1, int __scale)
+{
+ __builtin_ia32_scattersiv8di (__addr, (__mmask8) 0xFF,
+ (__v8si) __index, (__v8di) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i32scatter_epi64 (long long *__addr, __mmask8 __mask,
+ __m256i __index, __m512i __v1, int __scale)
+{
+ __builtin_ia32_scattersiv8di (__addr, __mask, (__v8si) __index,
+ (__v8di) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64scatter_epi32 (int *__addr, __m512i __index,
+ __m256i __v1, int __scale)
+{
+ __builtin_ia32_scatterdiv16si (__addr, (__mmask8) 0xFF,
+ (__v8di) __index, (__v8si) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64scatter_epi32 (int *__addr, __mmask8 __mask,
+ __m512i __index, __m256i __v1, int __scale)
+{
+ __builtin_ia32_scatterdiv16si (__addr, __mask, (__v8di) __index,
+ (__v8si) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_i64scatter_epi64 (long long *__addr, __m512i __index,
+ __m512i __v1, int __scale)
+{
+ __builtin_ia32_scatterdiv8di (__addr, (__mmask8) 0xFF,
+ (__v8di) __index, (__v8di) __v1, __scale);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_i64scatter_epi64 (long long *__addr, __mmask8 __mask,
+ __m512i __index, __m512i __v1, int __scale)
+{
+ __builtin_ia32_scatterdiv8di (__addr, __mask, (__v8di) __index,
+ (__v8di) __v1, __scale);
+}
+#else
+#define _mm512_i32gather_ps(INDEX, ADDR, SCALE) \
+ (__m512) __builtin_ia32_gathersiv16sf ((__v16sf)_mm512_setzero_ps(), \
+ (float const *)ADDR, \
+ (__v16si)(__m512i)INDEX, \
+ (__mmask16)0xFFFF, (int)SCALE)
+
+#define _mm512_mask_i32gather_ps(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m512) __builtin_ia32_gathersiv16sf ((__v16sf)(__m512)V1OLD, \
+ (float const *)ADDR, \
+ (__v16si)(__m512i)INDEX, \
+ (__mmask16)MASK, (int)SCALE)
+
+#define _mm512_i32gather_pd(INDEX, ADDR, SCALE) \
+ (__m512d) __builtin_ia32_gathersiv8df ((__v8df)_mm512_setzero_pd(), \
+ (double const *)ADDR, \
+ (__v8si)(__m256i)INDEX, \
+ (__mmask8)0xFF, (int)SCALE)
+
+#define _mm512_mask_i32gather_pd(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m512d) __builtin_ia32_gathersiv8df ((__v8df)(__m512d)V1OLD, \
+ (double const *)ADDR, \
+ (__v8si)(__m256i)INDEX, \
+ (__mmask8)MASK, (int)SCALE)
+
+#define _mm512_i64gather_ps(INDEX, ADDR, SCALE) \
+ (__m256) __builtin_ia32_gatherdiv16sf ((__v8sf)_mm256_setzero_ps(), \
+ (float const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)0xFF, (int)SCALE)
+
+#define _mm512_mask_i64gather_ps(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m256) __builtin_ia32_gatherdiv16sf ((__v8sf)(__m256)V1OLD, \
+ (float const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)MASK, (int)SCALE)
+
+#define _mm512_i64gather_pd(INDEX, ADDR, SCALE) \
+ (__m512d) __builtin_ia32_gatherdiv8df ((__v8df)_mm512_setzero_pd(), \
+ (double const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)0xFF, (int)SCALE)
+
+#define _mm512_mask_i64gather_pd(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m512d) __builtin_ia32_gatherdiv8df ((__v8df)(__m512d)V1OLD, \
+ (double const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)MASK, (int)SCALE)
+
+#define _mm512_i32gather_epi32(INDEX, ADDR, SCALE) \
+ (__m512i) __builtin_ia32_gathersiv16si ((__v16si)_mm512_setzero_si512 (), \
+ (int const *)ADDR, \
+ (__v16si)(__m512i)INDEX, \
+ (__mmask16)0xFFFF, (int)SCALE)
+
+#define _mm512_mask_i32gather_epi32(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m512i) __builtin_ia32_gathersiv16si ((__v16si)(__m512i)V1OLD, \
+ (int const *)ADDR, \
+ (__v16si)(__m512i)INDEX, \
+ (__mmask16)MASK, (int)SCALE)
+
+#define _mm512_i32gather_epi64(INDEX, ADDR, SCALE) \
+ (__m512i) __builtin_ia32_gathersiv8di ((__v8di)_mm512_setzero_si512 (), \
+ (long long const *)ADDR, \
+ (__v8si)(__m256i)INDEX, \
+ (__mmask8)0xFF, (int)SCALE)
+
+#define _mm512_mask_i32gather_epi64(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m512i) __builtin_ia32_gathersiv8di ((__v8di)(__m512i)V1OLD, \
+ (long long const *)ADDR, \
+ (__v8si)(__m256i)INDEX, \
+ (__mmask8)MASK, (int)SCALE)
+
+#define _mm512_i64gather_epi32(INDEX, ADDR, SCALE) \
+ (__m256i) __builtin_ia32_gatherdiv16si ((__v8si)_mm256_setzero_si256(), \
+ (int const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)0xFF, (int)SCALE)
+
+#define _mm512_mask_i64gather_epi32(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m256i) __builtin_ia32_gatherdiv16si ((__v8si)(__m256i)V1OLD, \
+ (int const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)MASK, (int)SCALE)
+
+#define _mm512_i64gather_epi64(INDEX, ADDR, SCALE) \
+ (__m512i) __builtin_ia32_gatherdiv8di ((__v8di)_mm512_setzero_si512 (), \
+ (long long const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)0xFF, (int)SCALE)
+
+#define _mm512_mask_i64gather_epi64(V1OLD, MASK, INDEX, ADDR, SCALE) \
+ (__m512i) __builtin_ia32_gatherdiv8di ((__v8di)(__m512i)V1OLD, \
+ (long long const *)ADDR, \
+ (__v8di)(__m512i)INDEX, \
+ (__mmask8)MASK, (int)SCALE)
+
+#define _mm512_i32scatter_ps(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv16sf ((float *)ADDR, (__mmask16)0xFFFF, \
+ (__v16si)(__m512i)INDEX, \
+ (__v16sf)(__m512)V1, (int)SCALE)
+
+#define _mm512_mask_i32scatter_ps(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv16sf ((float *)ADDR, (__mmask16)MASK, \
+ (__v16si)(__m512i)INDEX, \
+ (__v16sf)(__m512)V1, (int)SCALE)
+
+#define _mm512_i32scatter_pd(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv8df ((double *)ADDR, (__mmask8)0xFF, \
+ (__v8si)(__m256i)INDEX, \
+ (__v8df)(__m512d)V1, (int)SCALE)
+
+#define _mm512_mask_i32scatter_pd(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv8df ((double *)ADDR, (__mmask8)MASK, \
+ (__v8si)(__m256i)INDEX, \
+ (__v8df)(__m512d)V1, (int)SCALE)
+
+#define _mm512_i64scatter_ps(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv16sf ((float *)ADDR, (__mmask8)0xFF, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8sf)(__m256)V1, (int)SCALE)
+
+#define _mm512_mask_i64scatter_ps(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv16sf ((float *)ADDR, (__mmask16)MASK, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8sf)(__m256)V1, (int)SCALE)
+
+#define _mm512_i64scatter_pd(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv8df ((double *)ADDR, (__mmask8)0xFF, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8df)(__m512d)V1, (int)SCALE)
+
+#define _mm512_mask_i64scatter_pd(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv8df ((double *)ADDR, (__mmask8)MASK, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8df)(__m512d)V1, (int)SCALE)
+
+#define _mm512_i32scatter_epi32(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv16si ((int *)ADDR, (__mmask16)0xFFFF, \
+ (__v16si)(__m512i)INDEX, \
+ (__v16si)(__m512i)V1, (int)SCALE)
+
+#define _mm512_mask_i32scatter_epi32(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv16si ((int *)ADDR, (__mmask16)MASK, \
+ (__v16si)(__m512i)INDEX, \
+ (__v16si)(__m512i)V1, (int)SCALE)
+
+#define _mm512_i32scatter_epi64(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv8di ((long long *)ADDR, (__mmask8)0xFF, \
+ (__v8si)(__m256i)INDEX, \
+ (__v8di)(__m512i)V1, (int)SCALE)
+
+#define _mm512_mask_i32scatter_epi64(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scattersiv8di ((long long *)ADDR, (__mmask8)MASK, \
+ (__v8si)(__m256i)INDEX, \
+ (__v8di)(__m512i)V1, (int)SCALE)
+
+#define _mm512_i64scatter_epi32(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv16si ((int *)ADDR, (__mmask8)0xFF, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8si)(__m256i)V1, (int)SCALE)
+
+#define _mm512_mask_i64scatter_epi32(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv16si ((int *)ADDR, (__mmask8)MASK, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8si)(__m256i)V1, (int)SCALE)
+
+#define _mm512_i64scatter_epi64(ADDR, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv8di ((long long *)ADDR, (__mmask8)0xFF, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8di)(__m512i)V1, (int)SCALE)
+
+#define _mm512_mask_i64scatter_epi64(ADDR, MASK, INDEX, V1, SCALE) \
+ __builtin_ia32_scatterdiv8di ((long long *)ADDR, (__mmask8)MASK, \
+ (__v8di)(__m512i)INDEX, \
+ (__v8di)(__m512i)V1, (int)SCALE)
+#endif
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compress_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_compressdf512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_compress_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_compressdf512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compressstoreu_pd (void *__P, __mmask8 __U, __m512d __A)
+{
+ __builtin_ia32_compressstoredf512_mask ((__v8df *) __P, (__v8df) __A,
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compress_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_compresssf512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_compress_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_compresssf512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compressstoreu_ps (void *__P, __mmask16 __U, __m512 __A)
+{
+ __builtin_ia32_compressstoresf512_mask ((__v16sf *) __P, (__v16sf) __A,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compress_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_compressdi512_mask ((__v8di) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_compress_epi64 (__mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_compressdi512_mask ((__v8di) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compressstoreu_epi64 (void *__P, __mmask8 __U, __m512i __A)
+{
+ __builtin_ia32_compressstoredi512_mask ((__v8di *) __P, (__v8di) __A,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compress_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_compresssi512_mask ((__v16si) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_compress_epi32 (__mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_compresssi512_mask ((__v16si) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_compressstoreu_epi32 (void *__P, __mmask16 __U, __m512i __A)
+{
+ __builtin_ia32_compressstoresi512_mask ((__v16si *) __P, (__v16si) __A,
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expand_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_expanddf512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expand_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_expanddf512_maskz ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expandloadu_pd (__m512d __W, __mmask8 __U, void const *__P)
+{
+ return (__m512d) __builtin_ia32_expandloaddf512_mask ((const __v8df *) __P,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expandloadu_pd (__mmask8 __U, void const *__P)
+{
+ return (__m512d) __builtin_ia32_expandloaddf512_maskz ((const __v8df *) __P,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expand_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_expandsf512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expand_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_expandsf512_maskz ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expandloadu_ps (__m512 __W, __mmask16 __U, void const *__P)
+{
+ return (__m512) __builtin_ia32_expandloadsf512_mask ((const __v16sf *) __P,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expandloadu_ps (__mmask16 __U, void const *__P)
+{
+ return (__m512) __builtin_ia32_expandloadsf512_maskz ((const __v16sf *) __P,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expand_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_expanddi512_mask ((__v8di) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expand_epi64 (__mmask8 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_expanddi512_maskz ((__v8di) __A,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expandloadu_epi64 (__m512i __W, __mmask8 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_expandloaddi512_mask ((const __v8di *) __P,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P)
+{
+ return (__m512i)
+ __builtin_ia32_expandloaddi512_maskz ((const __v8di *) __P,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expand_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_expandsi512_mask ((__v16si) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expand_epi32 (__mmask16 __U, __m512i __A)
+{
+ return (__m512i) __builtin_ia32_expandsi512_maskz ((__v16si) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_expandloadu_epi32 (__m512i __W, __mmask16 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_expandloadsi512_mask ((const __v16si *) __P,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_expandloadu_epi32 (__mmask16 __U, void const *__P)
+{
+ return (__m512i) __builtin_ia32_expandloadsi512_maskz ((const __v16si *) __P,
+ (__v16si)
+ _mm512_setzero_si512
+ (), (__mmask16) __U);
+}
+
+/* Mask arithmetic operations */
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kand (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_kandhi ((__mmask16) __A, (__mmask16) __B);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kandn (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_kandnhi ((__mmask16) __A, (__mmask16) __B);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kor (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_korhi ((__mmask16) __A, (__mmask16) __B);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kortestz (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_kortestzhi ((__mmask16) __A,
+ (__mmask16) __B);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kortestc (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_kortestchi ((__mmask16) __A,
+ (__mmask16) __B);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kxnor (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_kxnorhi ((__mmask16) __A, (__mmask16) __B);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kxor (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_kxorhi ((__mmask16) __A, (__mmask16) __B);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_knot (__mmask16 __A)
+{
+ return (__mmask16) __builtin_ia32_knothi ((__mmask16) __A);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_kunpackb (__mmask16 __A, __mmask16 __B)
+{
+ return (__mmask16) __builtin_ia32_kunpckhi ((__mmask16) __A, (__mmask16) __B);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_inserti32x4 (__mmask16 __B, __m512i __C, __m128i __D,
+ const int __imm)
+{
+ return (__m512i) __builtin_ia32_inserti32x4_mask ((__v16si) __C,
+ (__v4si) __D,
+ __imm,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __B);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_insertf32x4 (__mmask16 __B, __m512 __C, __m128 __D,
+ const int __imm)
+{
+ return (__m512) __builtin_ia32_insertf32x4_mask ((__v16sf) __C,
+ (__v4sf) __D,
+ __imm,
+ (__v16sf)
+ _mm512_setzero_ps (), __B);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_inserti32x4 (__m512i __A, __mmask16 __B, __m512i __C,
+ __m128i __D, const int __imm)
+{
+ return (__m512i) __builtin_ia32_inserti32x4_mask ((__v16si) __C,
+ (__v4si) __D,
+ __imm,
+ (__v16si) __A,
+ __B);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_insertf32x4 (__m512 __A, __mmask16 __B, __m512 __C,
+ __m128 __D, const int __imm)
+{
+ return (__m512) __builtin_ia32_insertf32x4_mask ((__v16sf) __C,
+ (__v4sf) __D,
+ __imm,
+ (__v16sf) __A, __B);
+}
+#else
+#define _mm512_maskz_insertf32x4(A, X, Y, C) \
+ ((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X), \
+ (__v4sf)(__m128) (Y), (int) (C), (__v16sf)_mm512_setzero_ps(), \
+ (__mmask8)(A)))
+
+#define _mm512_maskz_inserti32x4(A, X, Y, C) \
+ ((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X), \
+ (__v4si)(__m128i) (Y), (int) (C), (__v16si)_mm512_setzero_si512 (), \
+ (__mmask8)(A)))
+
+#define _mm512_mask_insertf32x4(A, B, X, Y, C) \
+ ((__m512) __builtin_ia32_insertf32x4_mask ((__v16sf)(__m512) (X), \
+ (__v4sf)(__m128) (Y), (int) (C), (__v16sf)(__m512) (A), \
+ (__mmask8)(B)))
+
+#define _mm512_mask_inserti32x4(A, B, X, Y, C) \
+ ((__m512i) __builtin_ia32_inserti32x4_mask ((__v16si)(__m512i) (X), \
+ (__v4si)(__m128i) (Y), (int) (C), (__v16si)(__m512i) (A), \
+ (__mmask8)(B)))
+#endif
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxsq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_epi64 (__mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxsq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_epi64 (__m512i __W, __mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxsq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_epi64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminsq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_epi64 (__m512i __W, __mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminsq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_epi64 (__mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminsq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_epu64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxuq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_epu64 (__mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxuq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_epu64 (__m512i __W, __mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxuq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_epu64 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminuq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ (__mmask8) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_epu64 (__m512i __W, __mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminuq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_epu64 (__mmask8 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminuq512_mask ((__v8di) __A,
+ (__v8di) __B,
+ (__v8di)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxsd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_epi32 (__mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxsd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_epi32 (__m512i __W, __mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxsd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_epi32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminsd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_epi32 (__mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminsd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_epi32 (__m512i __W, __mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminsd512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_epu32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxud512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_epu32 (__mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxud512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_epu32 (__m512i __W, __mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pmaxud512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W, __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_epu32 (__m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminud512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_epu32 (__mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminud512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ __M);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_epu32 (__m512i __W, __mmask16 __M, __m512i __A, __m512i __B)
+{
+ return (__m512i) __builtin_ia32_pminud512_mask ((__v16si) __A,
+ (__v16si) __B,
+ (__v16si) __W, __M);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_unpacklo_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_unpcklps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_unpacklo_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_unpcklps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_unpacklo_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_unpcklps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_blend_pd (__mmask8 __U, __m512d __A, __m512d __W)
+{
+ return (__m512d) __builtin_ia32_blendmpd_512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_blend_ps (__mmask16 __U, __m512 __A, __m512 __W)
+{
+ return (__m512) __builtin_ia32_blendmps_512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_blend_epi64 (__mmask8 __U, __m512i __A, __m512i __W)
+{
+ return (__m512i) __builtin_ia32_blendmq_512_mask ((__v8di) __A,
+ (__v8di) __W,
+ (__mmask8) __U);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_blend_epi32 (__mmask16 __U, __m512i __A, __m512i __W)
+{
+ return (__m512i) __builtin_ia32_blendmd_512_mask ((__v16si) __A,
+ (__v16si) __W,
+ (__mmask16) __U);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comi_round_ss (__m128 __A, __m128 __B, const int __P, const int __R)
+{
+ return __builtin_ia32_vcomiss ((__v4sf) __A, (__v4sf) __B, __P, __R);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_comi_round_sd (__m128d __A, __m128d __B, const int __P, const int __R)
+{
+ return __builtin_ia32_vcomisd ((__v2df) __A, (__v2df) __B, __P, __R);
+}
+#else
+#define _mm_comi_round_ss(A, B, C, D)\
+__builtin_ia32_vcomiss(A, B, C, D)
+#define _mm_comi_round_sd(A, B, C, D)\
+__builtin_ia32_vcomisd(A, B, C, D)
+#endif
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sqrt_pd (__m512d __A)
+{
+ return (__m512d) __builtin_ia32_sqrtpd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sqrt_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_sqrtpd512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sqrt_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_sqrtpd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sqrt_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_sqrtps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sqrt_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_sqrtps512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sqrt_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_sqrtps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_add_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_addpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_add_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_addpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_add_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_addpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_add_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_addps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_add_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_addps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_add_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_addps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sub_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_subpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sub_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_subpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sub_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_subpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_sub_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_subps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_sub_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_subps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_sub_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_subps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mul_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_mulpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mul_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_mulpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mul_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_mulpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mul_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_mulps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_mul_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_mulps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_mul_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_mulps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_div_pd (__m512d __M, __m512d __V)
+{
+ return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __M,
+ (__v8df) __V,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_div_pd (__m512d __W, __mmask8 __U, __m512d __M, __m512d __V)
+{
+ return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __M,
+ (__v8df) __V,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_div_pd (__mmask8 __U, __m512d __M, __m512d __V)
+{
+ return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __M,
+ (__v8df) __V,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_div_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_div_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_div_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_maxpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_maxpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_maxpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_max_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_maxps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_max_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_maxps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_max_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_maxps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_minpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_minpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_minpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_min_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_minps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_min_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_minps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_min_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_minps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_scalef_pd (__m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_scalefpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_scalef_pd (__m512d __W, __mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_scalefpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_scalef_pd (__mmask8 __U, __m512d __A, __m512d __B)
+{
+ return (__m512d) __builtin_ia32_scalefpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_scalef_ps (__m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_scalefps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_scalef_ps (__m512 __W, __mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_scalefps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_scalef_ps (__mmask16 __U, __m512 __A, __m512 __B)
+{
+ return (__m512) __builtin_ia32_scalefps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmadd_pd (__m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmadd_pd (__m512d __A, __mmask8 __U, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmadd_pd (__m512d __A, __m512d __B, __m512d __C, __mmask8 __U)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmadd_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmadd_ps (__m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmadd_ps (__m512 __A, __mmask16 __U, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmadd_ps (__m512 __A, __m512 __B, __m512 __C, __mmask16 __U)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmadd_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsub_pd (__m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsub_pd (__m512d __A, __mmask8 __U, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsub_pd (__m512d __A, __m512d __B, __m512d __C, __mmask8 __U)
+{
+ return (__m512d) __builtin_ia32_vfmsubpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsub_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsub_ps (__m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsub_ps (__m512 __A, __mmask16 __U, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsub_ps (__m512 __A, __m512 __B, __m512 __C, __mmask16 __U)
+{
+ return (__m512) __builtin_ia32_vfmsubps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsub_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmaddsub_pd (__m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmaddsub_pd (__m512d __A, __mmask8 __U, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmaddsub_pd (__m512d __A, __m512d __B, __m512d __C, __mmask8 __U)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmaddsub_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmaddsub_ps (__m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmaddsub_ps (__m512 __A, __mmask16 __U, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmaddsub_ps (__m512 __A, __m512 __B, __m512 __C, __mmask16 __U)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmaddsub_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsubadd_pd (__m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsubadd_pd (__m512d __A, __mmask8 __U, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsubadd_pd (__m512d __A, __m512d __B, __m512d __C, __mmask8 __U)
+{
+ return (__m512d) __builtin_ia32_vfmsubaddpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsubadd_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddsubpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fmsubadd_ps (__m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fmsubadd_ps (__m512 __A, __mmask16 __U, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fmsubadd_ps (__m512 __A, __m512 __B, __m512 __C, __mmask16 __U)
+{
+ return (__m512) __builtin_ia32_vfmsubaddps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fmsubadd_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddsubps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmadd_pd (__m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmadd_pd (__m512d __A, __mmask8 __U, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfnmaddpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmadd_pd (__m512d __A, __m512d __B, __m512d __C, __mmask8 __U)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask3 (-(__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmadd_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmadd_ps (__m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmadd_ps (__m512 __A, __mmask16 __U, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfnmaddps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmadd_ps (__m512 __A, __m512 __B, __m512 __C, __mmask16 __U)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask3 (-(__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmadd_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmsub_pd (__m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_mask (-(__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmsub_pd (__m512d __A, __mmask8 __U, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfnmsubpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmsub_pd (__m512d __A, __m512d __B, __m512d __C, __mmask8 __U)
+{
+ return (__m512d) __builtin_ia32_vfnmsubpd512_mask3 ((__v8df) __A,
+ (__v8df) __B,
+ (__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmsub_pd (__mmask8 __U, __m512d __A, __m512d __B, __m512d __C)
+{
+ return (__m512d) __builtin_ia32_vfmaddpd512_maskz (-(__v8df) __A,
+ (__v8df) __B,
+ -(__v8df) __C,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fnmsub_ps (__m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_mask (-(__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fnmsub_ps (__m512 __A, __mmask16 __U, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfnmsubps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask3_fnmsub_ps (__m512 __A, __m512 __B, __m512 __C, __mmask16 __U)
+{
+ return (__m512) __builtin_ia32_vfnmsubps512_mask3 ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fnmsub_ps (__mmask16 __U, __m512 __A, __m512 __B, __m512 __C)
+{
+ return (__m512) __builtin_ia32_vfmaddps512_maskz (-(__v16sf) __A,
+ (__v16sf) __B,
+ -(__v16sf) __C,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvttpd_epi32 (__m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvttpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvttpd_epi32 (__m256i __W, __mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvttpd2dq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvttpd_epi32 (__mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvttpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvttpd_epu32 (__m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvttpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvttpd_epu32 (__m256i __W, __mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvttpd2udq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvttpd_epu32 (__mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvttpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtpd_epi32 (__m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvtpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtpd_epi32 (__m256i __W, __mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvtpd2dq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtpd_epi32 (__mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvtpd2dq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtpd_epu32 (__m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvtpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtpd_epu32 (__m256i __W, __mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvtpd2udq512_mask ((__v8df) __A,
+ (__v8si) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtpd_epu32 (__mmask8 __U, __m512d __A)
+{
+ return (__m256i) __builtin_ia32_cvtpd2udq512_mask ((__v8df) __A,
+ (__v8si)
+ _mm256_setzero_si256 (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvttps_epi32 (__m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvttps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvttps_epi32 (__m512i __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvttps2dq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvttps_epi32 (__mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvttps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvttps_epu32 (__m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvttps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvttps_epu32 (__m512i __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvttps2udq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvttps_epu32 (__mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvttps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtps_epi32 (__m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvtps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtps_epi32 (__m512i __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvtps2dq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtps_epi32 (__mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvtps2dq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtps_epu32 (__m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvtps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtps_epu32 (__m512i __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvtps2udq512_mask ((__v16sf) __A,
+ (__v16si) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512i
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtps_epu32 (__mmask16 __U, __m512 __A)
+{
+ return (__m512i) __builtin_ia32_cvtps2udq512_mask ((__v16sf) __A,
+ (__v16si)
+ _mm512_setzero_si512 (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#ifdef __x86_64__
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtu64_ss (__m128 __A, unsigned long long __B)
+{
+ return (__m128) __builtin_ia32_cvtusi2ss64 ((__v4sf) __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtu64_sd (__m128d __A, unsigned long long __B)
+{
+ return (__m128d) __builtin_ia32_cvtusi2sd64 ((__v2df) __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
+}
+#endif
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtu32_ss (__m128 __A, unsigned __B)
+{
+ return (__m128) __builtin_ia32_cvtusi2ss32 ((__v4sf) __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepi32_ps (__m512i __A)
+{
+ return (__m512) __builtin_ia32_cvtdq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepi32_ps (__m512 __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512) __builtin_ia32_cvtdq2ps512_mask ((__v16si) __A,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepi32_ps (__mmask16 __U, __m512i __A)
+{
+ return (__m512) __builtin_ia32_cvtdq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtepu32_ps (__m512i __A)
+{
+ return (__m512) __builtin_ia32_cvtudq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtepu32_ps (__m512 __W, __mmask16 __U, __m512i __A)
+{
+ return (__m512) __builtin_ia32_cvtudq2ps512_mask ((__v16si) __A,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtepu32_ps (__mmask16 __U, __m512i __A)
+{
+ return (__m512) __builtin_ia32_cvtudq2ps512_mask ((__v16si) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fixupimm_pd (__m512d __A, __m512d __B, __m512i __C, const int __imm)
+{
+ return (__m512d) __builtin_ia32_fixupimmpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8di) __C,
+ __imm,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fixupimm_pd (__m512d __A, __mmask8 __U, __m512d __B,
+ __m512i __C, const int __imm)
+{
+ return (__m512d) __builtin_ia32_fixupimmpd512_mask ((__v8df) __A,
+ (__v8df) __B,
+ (__v8di) __C,
+ __imm,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fixupimm_pd (__mmask8 __U, __m512d __A, __m512d __B,
+ __m512i __C, const int __imm)
+{
+ return (__m512d) __builtin_ia32_fixupimmpd512_maskz ((__v8df) __A,
+ (__v8df) __B,
+ (__v8di) __C,
+ __imm,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_fixupimm_ps (__m512 __A, __m512 __B, __m512i __C, const int __imm)
+{
+ return (__m512) __builtin_ia32_fixupimmps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16si) __C,
+ __imm,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_fixupimm_ps (__m512 __A, __mmask16 __U, __m512 __B,
+ __m512i __C, const int __imm)
+{
+ return (__m512) __builtin_ia32_fixupimmps512_mask ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16si) __C,
+ __imm,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_fixupimm_ps (__mmask16 __U, __m512 __A, __m512 __B,
+ __m512i __C, const int __imm)
+{
+ return (__m512) __builtin_ia32_fixupimmps512_maskz ((__v16sf) __A,
+ (__v16sf) __B,
+ (__v16si) __C,
+ __imm,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fixupimm_sd (__m128d __A, __m128d __B, __m128i __C, const int __imm)
+{
+ return (__m128d) __builtin_ia32_fixupimmsd_mask ((__v2df) __A,
+ (__v2df) __B,
+ (__v2di) __C, __imm,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fixupimm_sd (__m128d __A, __mmask8 __U, __m128d __B,
+ __m128i __C, const int __imm)
+{
+ return (__m128d) __builtin_ia32_fixupimmsd_mask ((__v2df) __A,
+ (__v2df) __B,
+ (__v2di) __C, __imm,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fixupimm_sd (__mmask8 __U, __m128d __A, __m128d __B,
+ __m128i __C, const int __imm)
+{
+ return (__m128d) __builtin_ia32_fixupimmsd_maskz ((__v2df) __A,
+ (__v2df) __B,
+ (__v2di) __C,
+ __imm,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_fixupimm_ss (__m128 __A, __m128 __B, __m128i __C, const int __imm)
+{
+ return (__m128) __builtin_ia32_fixupimmss_mask ((__v4sf) __A,
+ (__v4sf) __B,
+ (__v4si) __C, __imm,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_fixupimm_ss (__m128 __A, __mmask8 __U, __m128 __B,
+ __m128i __C, const int __imm)
+{
+ return (__m128) __builtin_ia32_fixupimmss_mask ((__v4sf) __A,
+ (__v4sf) __B,
+ (__v4si) __C, __imm,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_fixupimm_ss (__mmask8 __U, __m128 __A, __m128 __B,
+ __m128i __C, const int __imm)
+{
+ return (__m128) __builtin_ia32_fixupimmss_maskz ((__v4sf) __A,
+ (__v4sf) __B,
+ (__v4si) __C, __imm,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+#else
+#define _mm512_fixupimm_pd(X, Y, Z, C) \
+ ((__m512d)__builtin_ia32_fixupimmpd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (__v8di)(__m512i)(Z), (int)(C), \
+ (__mmask8)(-1), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_fixupimm_pd(X, U, Y, Z, C) \
+ ((__m512d)__builtin_ia32_fixupimmpd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (__v8di)(__m512i)(Z), (int)(C), \
+ (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_maskz_fixupimm_pd(U, X, Y, Z, C) \
+ ((__m512d)__builtin_ia32_fixupimmpd512_maskz ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (__v8di)(__m512i)(Z), (int)(C), \
+ (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_fixupimm_ps(X, Y, Z, C) \
+ ((__m512)__builtin_ia32_fixupimmps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (__v16si)(__m512i)(Z), (int)(C), \
+ (__mmask16)(-1), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_fixupimm_ps(X, U, Y, Z, C) \
+ ((__m512)__builtin_ia32_fixupimmps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (__v16si)(__m512i)(Z), (int)(C), \
+ (__mmask16)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_maskz_fixupimm_ps(U, X, Y, Z, C) \
+ ((__m512)__builtin_ia32_fixupimmps512_maskz ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (__v16si)(__m512i)(Z), (int)(C), \
+ (__mmask16)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm_fixupimm_sd(X, Y, Z, C) \
+ ((__m128d)__builtin_ia32_fixupimmsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (__v2di)(__m128i)(Z), (int)(C), \
+ (__mmask8)(-1), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm_mask_fixupimm_sd(X, U, Y, Z, C) \
+ ((__m128d)__builtin_ia32_fixupimmsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (__v2di)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm_maskz_fixupimm_sd(U, X, Y, Z, C) \
+ ((__m128d)__builtin_ia32_fixupimmsd_maskz ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (__v2di)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm_fixupimm_ss(X, Y, Z, C) \
+ ((__m128)__builtin_ia32_fixupimmss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (__v4si)(__m128i)(Z), (int)(C), \
+ (__mmask8)(-1), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm_mask_fixupimm_ss(X, U, Y, Z, C) \
+ ((__m128)__builtin_ia32_fixupimmss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (__v4si)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm_maskz_fixupimm_ss(U, X, Y, Z, C) \
+ ((__m128)__builtin_ia32_fixupimmss_maskz ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (__v4si)(__m128i)(Z), (int)(C), \
+ (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+#endif
+
+#ifdef __x86_64__
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtss_u64 (__m128 __A)
+{
+ return (unsigned long long) __builtin_ia32_vcvtss2usi64 ((__v4sf)
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttss_u64 (__m128 __A)
+{
+ return (unsigned long long) __builtin_ia32_vcvttss2usi64 ((__v4sf)
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttss_i64 (__m128 __A)
+{
+ return (long long) __builtin_ia32_vcvttss2si64 ((__v4sf) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+#endif /* __x86_64__ */
+
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtss_u32 (__m128 __A)
+{
+ return (unsigned) __builtin_ia32_vcvtss2usi32 ((__v4sf) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttss_u32 (__m128 __A)
+{
+ return (unsigned) __builtin_ia32_vcvttss2usi32 ((__v4sf) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttss_i32 (__m128 __A)
+{
+ return (int) __builtin_ia32_vcvttss2si32 ((__v4sf) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#ifdef __x86_64__
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsd_u64 (__m128d __A)
+{
+ return (unsigned long long) __builtin_ia32_vcvtsd2usi64 ((__v2df)
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline unsigned long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttsd_u64 (__m128d __A)
+{
+ return (unsigned long long) __builtin_ia32_vcvttsd2usi64 ((__v2df)
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline long long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttsd_i64 (__m128d __A)
+{
+ return (long long) __builtin_ia32_vcvttsd2si64 ((__v2df) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+#endif /* __x86_64__ */
+
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtsd_u32 (__m128d __A)
+{
+ return (unsigned) __builtin_ia32_vcvtsd2usi32 ((__v2df) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline unsigned
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttsd_u32 (__m128d __A)
+{
+ return (unsigned) __builtin_ia32_vcvttsd2usi32 ((__v2df) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline int
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvttsd_i32 (__m128d __A)
+{
+ return (int) __builtin_ia32_vcvttsd2si32 ((__v2df) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtps_pd (__m256 __A)
+{
+ return (__m512d) __builtin_ia32_cvtps2pd512_mask ((__v8sf) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtps_pd (__m512d __W, __mmask8 __U, __m256 __A)
+{
+ return (__m512d) __builtin_ia32_cvtps2pd512_mask ((__v8sf) __A,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtps_pd (__mmask8 __U, __m256 __A)
+{
+ return (__m512d) __builtin_ia32_cvtps2pd512_mask ((__v8sf) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtph_ps (__m256i __A)
+{
+ return (__m512) __builtin_ia32_vcvtph2ps512_mask ((__v16hi) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtph_ps (__m512 __W, __mmask16 __U, __m256i __A)
+{
+ return (__m512) __builtin_ia32_vcvtph2ps512_mask ((__v16hi) __A,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtph_ps (__mmask16 __U, __m256i __A)
+{
+ return (__m512) __builtin_ia32_vcvtph2ps512_mask ((__v16hi) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtpd_ps (__m512d __A)
+{
+ return (__m256) __builtin_ia32_cvtpd2ps512_mask ((__v8df) __A,
+ (__v8sf)
+ _mm256_setzero_ps (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtpd_ps (__m256 __W, __mmask8 __U, __m512d __A)
+{
+ return (__m256) __builtin_ia32_cvtpd2ps512_mask ((__v8df) __A,
+ (__v8sf) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtpd_ps (__mmask8 __U, __m512d __A)
+{
+ return (__m256) __builtin_ia32_cvtpd2ps512_mask ((__v8df) __A,
+ (__v8sf)
+ _mm256_setzero_ps (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getexp_ps (__m512 __A)
+{
+ return (__m512) __builtin_ia32_getexpps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getexp_ps (__m512 __W, __mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_getexpps512_mask ((__v16sf) __A,
+ (__v16sf) __W,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getexp_ps (__mmask16 __U, __m512 __A)
+{
+ return (__m512) __builtin_ia32_getexpps512_mask ((__v16sf) __A,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getexp_pd (__m512d __A)
+{
+ return (__m512d) __builtin_ia32_getexppd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getexp_pd (__m512d __W, __mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_getexppd512_mask ((__v8df) __A,
+ (__v8df) __W,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getexp_pd (__mmask8 __U, __m512d __A)
+{
+ return (__m512d) __builtin_ia32_getexppd512_mask ((__v8df) __A,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getmant_pd (__m512d __A, _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C)
+{
+ return (__m512d) __builtin_ia32_getmantpd512_mask ((__v8df) __A,
+ (__C << 2) | __B,
+ _mm512_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getmant_pd (__m512d __W, __mmask8 __U, __m512d __A,
+ _MM_MANTISSA_NORM_ENUM __B, _MM_MANTISSA_SIGN_ENUM __C)
+{
+ return (__m512d) __builtin_ia32_getmantpd512_mask ((__v8df) __A,
+ (__C << 2) | __B,
+ (__v8df) __W, __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getmant_pd (__mmask8 __U, __m512d __A,
+ _MM_MANTISSA_NORM_ENUM __B, _MM_MANTISSA_SIGN_ENUM __C)
+{
+ return (__m512d) __builtin_ia32_getmantpd512_mask ((__v8df) __A,
+ (__C << 2) | __B,
+ (__v8df)
+ _mm512_setzero_pd (),
+ __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_getmant_ps (__m512 __A, _MM_MANTISSA_NORM_ENUM __B,
+ _MM_MANTISSA_SIGN_ENUM __C)
+{
+ return (__m512) __builtin_ia32_getmantps512_mask ((__v16sf) __A,
+ (__C << 2) | __B,
+ _mm512_setzero_ps (),
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_getmant_ps (__m512 __W, __mmask16 __U, __m512 __A,
+ _MM_MANTISSA_NORM_ENUM __B, _MM_MANTISSA_SIGN_ENUM __C)
+{
+ return (__m512) __builtin_ia32_getmantps512_mask ((__v16sf) __A,
+ (__C << 2) | __B,
+ (__v16sf) __W, __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_getmant_ps (__mmask16 __U, __m512 __A,
+ _MM_MANTISSA_NORM_ENUM __B, _MM_MANTISSA_SIGN_ENUM __C)
+{
+ return (__m512) __builtin_ia32_getmantps512_mask ((__v16sf) __A,
+ (__C << 2) | __B,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#else
+#define _mm512_getmant_pd(X, B, C) \
+ ((__m512d)__builtin_ia32_getmantpd512_mask ((__v8df)(__m512d)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8df)(__m512d)_mm512_setzero_pd(), \
+ (__mmask8)-1,\
+ _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_getmant_pd(W, U, X, B, C) \
+ ((__m512d)__builtin_ia32_getmantpd512_mask ((__v8df)(__m512d)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8df)(__m512d)(W), \
+ (__mmask8)(U),\
+ _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_maskz_getmant_pd(U, X, B, C) \
+ ((__m512d)__builtin_ia32_getmantpd512_mask ((__v8df)(__m512d)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8df)(__m512d)_mm512_setzero_pd(), \
+ (__mmask8)(U),\
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm512_getmant_ps(X, B, C) \
+ ((__m512)__builtin_ia32_getmantps512_mask ((__v16sf)(__m512)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16sf)(__m512)_mm512_setzero_ps(), \
+ (__mmask16)-1,\
+ _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_getmant_ps(W, U, X, B, C) \
+ ((__m512)__builtin_ia32_getmantps512_mask ((__v16sf)(__m512)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16sf)(__m512)(W), \
+ (__mmask16)(U),\
+ _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_maskz_getmant_ps(U, X, B, C) \
+ ((__m512)__builtin_ia32_getmantps512_mask ((__v16sf)(__m512)(X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16sf)(__m512)_mm512_setzero_ps(), \
+ (__mmask16)(U),\
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm512_getexp_ps(A) \
+ ((__m512)__builtin_ia32_getexpps512_mask((__v16sf)(__m512)(A), \
+ (__v16sf)_mm512_setzero_ps(), (__mmask16)-1, _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_getexp_ps(W, U, A) \
+ ((__m512)__builtin_ia32_getexpps512_mask((__v16sf)(__m512)(A), \
+ (__v16sf)(__m512)(W), (__mmask16)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_maskz_getexp_ps(U, A) \
+ ((__m512)__builtin_ia32_getexpps512_mask((__v16sf)(__m512)(A), \
+ (__v16sf)_mm512_setzero_ps(), (__mmask16)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_getexp_pd(A) \
+ ((__m512d)__builtin_ia32_getexppd512_mask((__v8df)(__m512d)(A), \
+ (__v8df)_mm512_setzero_pd(), (__mmask8)-1, _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_getexp_pd(W, U, A) \
+ ((__m512d)__builtin_ia32_getexppd512_mask((__v8df)(__m512d)(A), \
+ (__v8df)(__m512d)(W), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_maskz_getexp_pd(U, A) \
+ ((__m512d)__builtin_ia32_getexppd512_mask((__v8df)(__m512d)(A), \
+ (__v8df)_mm512_setzero_pd(), (__mmask8)(U), _MM_FROUND_CUR_DIRECTION))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_roundscale_ps (__m512 __A, const int __imm)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __A, __imm,
+ (__v16sf) __A, -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_roundscale_ps (__m512 __A, __mmask16 __B, __m512 __C,
+ const int __imm)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __C, __imm,
+ (__v16sf) __A,
+ (__mmask16) __B,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_roundscale_ps (__mmask16 __A, __m512 __B, const int __imm)
+{
+ return (__m512) __builtin_ia32_rndscaleps_mask ((__v16sf) __B,
+ __imm,
+ (__v16sf)
+ _mm512_setzero_ps (),
+ (__mmask16) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_roundscale_pd (__m512d __A, const int __imm)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __A, __imm,
+ (__v8df) __A, -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_roundscale_pd (__m512d __A, __mmask8 __B, __m512d __C,
+ const int __imm)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __C, __imm,
+ (__v8df) __A,
+ (__mmask8) __B,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m512d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_roundscale_pd (__mmask8 __A, __m512d __B, const int __imm)
+{
+ return (__m512d) __builtin_ia32_rndscalepd_mask ((__v8df) __B,
+ __imm,
+ (__v8df)
+ _mm512_setzero_pd (),
+ (__mmask8) __A,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#else
+#define _mm512_roundscale_ps(A, B) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(A), (int)(B),\
+ (__v16sf)(__m512)(A), (__mmask16)(-1), _MM_FROUND_CUR_DIRECTION))
+#define _mm512_mask_roundscale_ps(A, B, C, D) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(C), \
+ (int)(D), \
+ (__v16sf)(__m512)(A), \
+ (__mmask16)(B), _MM_FROUND_CUR_DIRECTION))
+#define _mm512_maskz_roundscale_ps(A, B, C) \
+ ((__m512) __builtin_ia32_rndscaleps_mask ((__v16sf)(__m512)(B), \
+ (int)(C), \
+ (__v16sf)_mm512_setzero_ps(),\
+ (__mmask16)(A), _MM_FROUND_CUR_DIRECTION))
+#define _mm512_roundscale_pd(A, B) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(A), (int)(B),\
+ (__v8df)(__m512d)(A), (__mmask8)(-1), _MM_FROUND_CUR_DIRECTION))
+#define _mm512_mask_roundscale_pd(A, B, C, D) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(C), \
+ (int)(D), \
+ (__v8df)(__m512d)(A), \
+ (__mmask8)(B), _MM_FROUND_CUR_DIRECTION))
+#define _mm512_maskz_roundscale_pd(A, B, C) \
+ ((__m512d) __builtin_ia32_rndscalepd_mask ((__v8df)(__m512d)(B), \
+ (int)(C), \
+ (__v8df)_mm512_setzero_pd(),\
+ (__mmask8)(A), _MM_FROUND_CUR_DIRECTION))
+#endif
+
+#ifdef __OPTIMIZE__
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_pd_mask (__m512d __X, __m512d __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmppd512_mask ((__v8df) __X,
+ (__v8df) __Y, __P,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cmp_ps_mask (__m512 __X, __m512 __Y, const int __P)
+{
+ return (__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf) __X,
+ (__v16sf) __Y, __P,
+ (__mmask16) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask16
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_ps_mask (__mmask16 __U, __m512 __X, __m512 __Y, const int __P)
+{
+ return (__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf) __X,
+ (__v16sf) __Y, __P,
+ (__mmask16) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cmp_pd_mask (__mmask8 __U, __m512d __X, __m512d __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmppd512_mask ((__v8df) __X,
+ (__v8df) __Y, __P,
+ (__mmask8) __U,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmp_sd_mask (__m128d __X, __m128d __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
+ (__v2df) __Y, __P,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_cmp_sd_mask (__mmask8 __M, __m128d __X, __m128d __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
+ (__v2df) __Y, __P,
+ (__mmask8) __M,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmp_ss_mask (__m128 __X, __m128 __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
+ (__v4sf) __Y, __P,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_cmp_ss_mask (__mmask8 __M, __m128 __X, __m128 __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
+ (__v4sf) __Y, __P,
+ (__mmask8) __M,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#else
+#define _mm512_cmp_pd_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(P),\
+ (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_cmp_ps_mask(X, Y, P) \
+ ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(P),\
+ (__mmask16)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_cmp_pd_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(P),\
+ (__mmask8)M, _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_cmp_ps_mask(M, X, Y, P) \
+ ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(P),\
+ (__mmask16)M,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_cmp_sd_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (int)(P),\
+ (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_mask_cmp_sd_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (int)(P),\
+ M,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_cmp_ss_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (int)(P), \
+ (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_mask_cmp_ss_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (int)(P), \
+ M,_MM_FROUND_CUR_DIRECTION))
+#endif
+
+#ifdef __DISABLE_AVX512F__
+#undef __DISABLE_AVX512F__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX512F__ */
+
+#endif /* _AVX512FINTRIN_H_INCLUDED */
diff --git a/gcc/config/i386/avx512pfintrin.h b/gcc/config/i386/avx512pfintrin.h
new file mode 100644
index 00000000000..4dba640458d
--- /dev/null
+++ b/gcc/config/i386/avx512pfintrin.h
@@ -0,0 +1,130 @@
+/* Copyright (C) 2013
+ Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#ifndef _IMMINTRIN_H_INCLUDED
+#error "Never use <avx512pfintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX512PFINTRIN_H_INCLUDED
+#define _AVX512PFINTRIN_H_INCLUDED
+
+#ifndef __AVX512PF__
+#pragma GCC push_options
+#pragma GCC target("avx512pf")
+#define __DISABLE_AVX512PF__
+#endif /* __AVX512PF__ */
+
+/* Internal data types for implementing the intrinsics. */
+typedef long long __v8di __attribute__ ((__vector_size__ (64)));
+typedef int __v16si __attribute__ ((__vector_size__ (64)));
+
+/* The Intel API is flexible enough that we must allow aliasing with other
+ vector types, and their scalar components. */
+typedef long long __m512i __attribute__ ((__vector_size__ (64), __may_alias__));
+
+typedef unsigned char __mmask8;
+typedef unsigned short __mmask16;
+
+#ifdef __OPTIMIZE__
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_prefetch_i32gather_ps (__m512i index, __mmask16 mask,
+ int const *addr, int scale, int hint)
+{
+ __builtin_ia32_gatherpfdps (mask, (__v16si) index, addr, scale, hint);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_prefetch_i64gather_ps (__m512i index, __mmask8 mask,
+ int const *addr, int scale, int hint)
+{
+ __builtin_ia32_gatherpfqps (mask, (__v8di) index, addr, scale, hint);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_prefetch_i32scatter_ps (int const *addr, __m512i index, int scale,
+ int hint)
+{
+ __builtin_ia32_scatterpfdps ((__mmask16) 0xFFFF, (__v16si) index, addr, scale,
+ hint);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_prefetch_i32scatter_ps (int const *addr, __mmask16 mask,
+ __m512i index, int scale, int hint)
+{
+ __builtin_ia32_scatterpfdps (mask, (__v16si) index, addr, scale, hint);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_prefetch_i64scatter_ps (int const *addr, __m512i index, int scale,
+ int hint)
+{
+ __builtin_ia32_scatterpfqps ((__mmask8) 0xFF, (__v8di) index, addr, scale,
+ hint);
+}
+
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_prefetch_i64scatter_ps (int const *addr, __mmask16 mask,
+ __m512i index, int scale, int hint)
+{
+ __builtin_ia32_scatterpfqps (mask, (__v8di) index, addr, scale, hint);
+}
+#else
+#define _mm512_mask_prefetch_i32gather_ps(INDEX, MASK, ADDR, SCALE, HINT) \
+ __builtin_ia32_gatherpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \
+ (int const *)ADDR, (int)SCALE, (int)HINT)
+
+#define _mm512_mask_prefetch_i64gather_ps(INDEX, MASK, ADDR, SCALE, HINT) \
+ __builtin_ia32_gatherpfqps ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
+ (int const *)ADDR, (int)SCALE, (int)HINT)
+
+#define _mm512_prefetch_i32scatter_ps(ADDR, INDEX, SCALE, HINT) \
+ __builtin_ia32_scatterpfdps ((__mmask16)0xFFFF, (__v16si)(__m512i)INDEX, \
+ (int const *)ADDR, (int)SCALE, (int)HINT)
+
+#define _mm512_mask_prefetch_i32scatter_ps(ADDR, MASK, INDEX, SCALE, HINT) \
+ __builtin_ia32_scatterpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \
+ (int const *)ADDR, (int)SCALE, (int)HINT)
+
+#define _mm512_prefetch_i64scatter_ps(ADDR, INDEX, SCALE, HINT) \
+ __builtin_ia32_scatterpfqps ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \
+ (int const *)ADDR, (int)SCALE, (int)HINT)
+
+#define _mm512_mask_prefetch_i64scatter_ps(ADDR, MASK, INDEX, SCALE, HINT) \
+ __builtin_ia32_scatterpfqps ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \
+ (int const *)ADDR, (int)SCALE, (int)HINT)
+#endif
+
+#ifdef __DISABLE_AVX512PF__
+#undef __DISABLE_AVX512PF__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX512PF__ */
+
+#endif /* _AVX512PFINTRIN_H_INCLUDED */
diff --git a/gcc/config/i386/i386-builtin-types.def b/gcc/config/i386/i386-builtin-types.def
index c866170bde8..86ad31ea478 100644
--- a/gcc/config/i386/i386-builtin-types.def
+++ b/gcc/config/i386/i386-builtin-types.def
@@ -99,6 +99,15 @@ DEF_VECTOR_TYPE (V16HI, HI)
DEF_VECTOR_TYPE (V32QI, QI)
DEF_VECTOR_TYPE (V4UDI, UDI, V4DI)
DEF_VECTOR_TYPE (V8USI, USI, V8SI)
+DEF_VECTOR_TYPE (V16UHI, UHI, V16HI)
+
+# AVX512F vectors
+DEF_VECTOR_TYPE (V32SF, FLOAT)
+DEF_VECTOR_TYPE (V16SF, FLOAT)
+DEF_VECTOR_TYPE (V8DF, DOUBLE)
+DEF_VECTOR_TYPE (V8DI, DI)
+DEF_VECTOR_TYPE (V16SI, SI)
+DEF_VECTOR_TYPE (V64QI, QI)
DEF_POINTER_TYPE (PCCHAR, CHAR, CONST)
DEF_POINTER_TYPE (PCDOUBLE, DOUBLE, CONST)
@@ -123,21 +132,29 @@ DEF_POINTER_TYPE (PV2SF, V2SF)
DEF_POINTER_TYPE (PV4DF, V4DF)
DEF_POINTER_TYPE (PV4DI, V4DI)
DEF_POINTER_TYPE (PV4SF, V4SF)
+DEF_POINTER_TYPE (PV8DF, V8DF)
DEF_POINTER_TYPE (PV8SF, V8SF)
DEF_POINTER_TYPE (PV4SI, V4SI)
DEF_POINTER_TYPE (PV8SI, V8SI)
+DEF_POINTER_TYPE (PV8DI, V8DI)
+DEF_POINTER_TYPE (PV16SI, V16SI)
+DEF_POINTER_TYPE (PV16SF, V16SF)
DEF_POINTER_TYPE (PCV2SI, V2SI, CONST)
DEF_POINTER_TYPE (PCV2DF, V2DF, CONST)
DEF_POINTER_TYPE (PCV2SF, V2SF, CONST)
DEF_POINTER_TYPE (PCV4DF, V4DF, CONST)
DEF_POINTER_TYPE (PCV4SF, V4SF, CONST)
+DEF_POINTER_TYPE (PCV8DF, V8DF, CONST)
DEF_POINTER_TYPE (PCV8SF, V8SF, CONST)
+DEF_POINTER_TYPE (PCV16SF, V16SF, CONST)
DEF_POINTER_TYPE (PCV2DI, V2DI, CONST)
DEF_POINTER_TYPE (PCV4SI, V4SI, CONST)
DEF_POINTER_TYPE (PCV4DI, V4DI, CONST)
DEF_POINTER_TYPE (PCV8SI, V8SI, CONST)
+DEF_POINTER_TYPE (PCV8DI, V8DI, CONST)
+DEF_POINTER_TYPE (PCV16SI, V16SI, CONST)
DEF_FUNCTION_TYPE (FLOAT128)
DEF_FUNCTION_TYPE (UINT64)
@@ -165,6 +182,7 @@ DEF_FUNCTION_TYPE (UINT16, UINT16)
DEF_FUNCTION_TYPE (UINT64, PUNSIGNED)
DEF_FUNCTION_TYPE (V16QI, PCCHAR)
DEF_FUNCTION_TYPE (V16QI, V16QI)
+DEF_FUNCTION_TYPE (V16QI, V16SI)
DEF_FUNCTION_TYPE (V2DF, PCDOUBLE)
DEF_FUNCTION_TYPE (V2DF, V2DF)
DEF_FUNCTION_TYPE (V2DF, V2SI)
@@ -190,6 +208,8 @@ DEF_FUNCTION_TYPE (V4DF, V2DF)
DEF_FUNCTION_TYPE (V4DF, V4DF)
DEF_FUNCTION_TYPE (V4DF, V4SF)
DEF_FUNCTION_TYPE (V4DF, V4SI)
+DEF_FUNCTION_TYPE (V8DF, V8SI)
+DEF_FUNCTION_TYPE (V8DF, V8DF)
DEF_FUNCTION_TYPE (V4HI, V4HI)
DEF_FUNCTION_TYPE (V4SF, PCFLOAT)
DEF_FUNCTION_TYPE (V4SF, V2DF)
@@ -207,6 +227,7 @@ DEF_FUNCTION_TYPE (V4SI, V4SI)
DEF_FUNCTION_TYPE (V4SI, V8HI)
DEF_FUNCTION_TYPE (V4SI, V8SI)
DEF_FUNCTION_TYPE (V8HI, V16QI)
+DEF_FUNCTION_TYPE (V8HI, V8DI)
DEF_FUNCTION_TYPE (V8HI, V8HI)
DEF_FUNCTION_TYPE (V8QI, V8QI)
DEF_FUNCTION_TYPE (V8SF, PCFLOAT)
@@ -216,10 +237,15 @@ DEF_FUNCTION_TYPE (V8SF, V4SF)
DEF_FUNCTION_TYPE (V8SF, V8SF)
DEF_FUNCTION_TYPE (V8SF, V8SI)
DEF_FUNCTION_TYPE (V8SF, V8HI)
+DEF_FUNCTION_TYPE (V16SF, V16SF)
+DEF_FUNCTION_TYPE (V8SI, V8DI)
DEF_FUNCTION_TYPE (V8SI, V4SI)
+DEF_FUNCTION_TYPE (V8SF, V8DF)
+DEF_FUNCTION_TYPE (V8SF, V8DF, V8SF, QI)
DEF_FUNCTION_TYPE (V8SI, V8SF)
DEF_FUNCTION_TYPE (V32QI, V32QI)
DEF_FUNCTION_TYPE (V32QI, V16QI)
+DEF_FUNCTION_TYPE (V16HI, V16SI)
DEF_FUNCTION_TYPE (V16HI, V16HI)
DEF_FUNCTION_TYPE (V16HI, V8HI)
DEF_FUNCTION_TYPE (V8SI, V8SI)
@@ -239,6 +265,28 @@ DEF_FUNCTION_TYPE (V4DI, V8HI)
DEF_FUNCTION_TYPE (V4DI, V4SI)
DEF_FUNCTION_TYPE (V4DI, PV4DI)
DEF_FUNCTION_TYPE (V4DI, V2DI)
+DEF_FUNCTION_TYPE (V16SF, FLOAT)
+DEF_FUNCTION_TYPE (V16SI, INT)
+DEF_FUNCTION_TYPE (V8DF, DOUBLE)
+DEF_FUNCTION_TYPE (V8DI, INT64)
+DEF_FUNCTION_TYPE (V16SF, V4SF)
+DEF_FUNCTION_TYPE (V8DF, V4DF)
+DEF_FUNCTION_TYPE (V8DI, V4DI)
+DEF_FUNCTION_TYPE (V16QI, V8DI)
+DEF_FUNCTION_TYPE (UINT, V4SF)
+DEF_FUNCTION_TYPE (UINT64, V4SF)
+DEF_FUNCTION_TYPE (UINT, V2DF)
+DEF_FUNCTION_TYPE (UINT64, V2DF)
+DEF_FUNCTION_TYPE (V16SI, V16SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V16SI, HI)
+DEF_FUNCTION_TYPE (V8DI, V8DI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI, QI)
+DEF_FUNCTION_TYPE (V16SI, PV4SI)
+DEF_FUNCTION_TYPE (V16SF, PV4SF)
+DEF_FUNCTION_TYPE (V8DI, PV4DI)
+DEF_FUNCTION_TYPE (V8DF, PV4DF)
+DEF_FUNCTION_TYPE (V8UHI, V8UHI)
+DEF_FUNCTION_TYPE (V8USI, V8USI)
DEF_FUNCTION_TYPE (DI, V2DI, INT)
DEF_FUNCTION_TYPE (DOUBLE, V2DF, INT)
@@ -270,6 +318,8 @@ DEF_FUNCTION_TYPE (V1DI, V1DI, V1DI)
DEF_FUNCTION_TYPE (V1DI, V2SI, V2SI)
DEF_FUNCTION_TYPE (V1DI, V8QI, V8QI)
DEF_FUNCTION_TYPE (V2DF, PCV2DF, V2DI)
+DEF_FUNCTION_TYPE (V2DF, V2DF, UINT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, UINT64)
DEF_FUNCTION_TYPE (V2DF, V2DF, DI)
DEF_FUNCTION_TYPE (V2DF, V2DF, INT)
DEF_FUNCTION_TYPE (V2DF, V2DF, PCDOUBLE)
@@ -295,16 +345,23 @@ DEF_FUNCTION_TYPE (V2SI, V2SI, V2SI)
DEF_FUNCTION_TYPE (V2SI, V4HI, V4HI)
DEF_FUNCTION_TYPE (V4DF, PCV4DF, V4DI)
DEF_FUNCTION_TYPE (V4DF, V4DF, INT)
+DEF_FUNCTION_TYPE (V4DF, V8DF, INT)
+DEF_FUNCTION_TYPE (V4DF, V8DF, INT, V4DF, QI)
DEF_FUNCTION_TYPE (V4DF, V4DF, V4DF)
DEF_FUNCTION_TYPE (V4DF, V4DF, V4DI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DI)
DEF_FUNCTION_TYPE (V4HI, V2SI, V2SI)
DEF_FUNCTION_TYPE (V4HI, V4HI, INT)
DEF_FUNCTION_TYPE (V4HI, V4HI, SI)
DEF_FUNCTION_TYPE (V4HI, V4HI, V4HI)
DEF_FUNCTION_TYPE (V4HI, V8QI, V8QI)
DEF_FUNCTION_TYPE (V4SF, PCV4SF, V4SI)
+DEF_FUNCTION_TYPE (V4SF, V4SF, UINT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, UINT64)
DEF_FUNCTION_TYPE (V4SF, V4SF, DI)
DEF_FUNCTION_TYPE (V4SF, V4SF, INT)
+DEF_FUNCTION_TYPE (INT, V4SF, V4SF, INT, INT)
+DEF_FUNCTION_TYPE (INT, V2DF, V2DF, INT, INT)
DEF_FUNCTION_TYPE (V4SF, V4SF, PCV2SF)
DEF_FUNCTION_TYPE (V4SF, V4SF, SI)
DEF_FUNCTION_TYPE (V4SF, V4SF, V2DF)
@@ -331,30 +388,75 @@ DEF_FUNCTION_TYPE (V8QI, V4HI, V4HI)
DEF_FUNCTION_TYPE (V8QI, V8QI, V8QI)
DEF_FUNCTION_TYPE (V8SF, PCV8SF, V8SI)
DEF_FUNCTION_TYPE (V8SF, V8SF, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, INT)
+DEF_FUNCTION_TYPE (V4SF, V16SF, INT)
+DEF_FUNCTION_TYPE (V4SF, V16SF, INT, V4SF, QI)
DEF_FUNCTION_TYPE (V8SF, V8SF, V8SF)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF)
DEF_FUNCTION_TYPE (V8SF, V8SF, V8SI)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SI)
DEF_FUNCTION_TYPE (V32QI, V16HI, V16HI)
DEF_FUNCTION_TYPE (V16HI, V8SI, V8SI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V4DF, INT, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF, INT, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, INT, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF, V8DI, INT, QI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, INT, V16SF, HI)
+DEF_FUNCTION_TYPE (V16SF, V16SF, INT, V16SF, HI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V4SI, INT, V16SI, HI)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, V16SI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, V16SI, INT, HI)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, V16SI, INT, HI, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V4SF, V4SI, INT, QI)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V4SF, V4SI, INT, QI, INT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V2DF, V2DI, INT, QI)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V2DF, V2DI, INT, QI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V4SF, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V4SF, INT, V16SF, HI)
DEF_FUNCTION_TYPE (V32QI, V32QI, V32QI)
DEF_FUNCTION_TYPE (V16HI, V32QI, V32QI)
DEF_FUNCTION_TYPE (V16HI, V16HI, V8HI)
DEF_FUNCTION_TYPE (V16HI, V16HI, V16HI)
DEF_FUNCTION_TYPE (V16HI, V16HI, INT)
+DEF_FUNCTION_TYPE (V16HI, V16SF, INT)
+DEF_FUNCTION_TYPE (V16HI, V16SF, INT, V16HI, HI)
+DEF_FUNCTION_TYPE (V16HI, V16HI, V16HI, INT, V16HI, HI)
DEF_FUNCTION_TYPE (V16HI, V16HI, SI)
DEF_FUNCTION_TYPE (V16HI, V16HI, V16HI, INT)
DEF_FUNCTION_TYPE (V32QI, V32QI, V32QI, INT)
DEF_FUNCTION_TYPE (V8SI, V4DF, V4DF)
DEF_FUNCTION_TYPE (V8SI, V8SI, V4SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V4SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V4SI, INT)
+DEF_FUNCTION_TYPE (V4SI, V16SI, INT)
+DEF_FUNCTION_TYPE (V4SI, V16SI, INT, V4SI, QI)
DEF_FUNCTION_TYPE (V8SI, V8SI, V8SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V16SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V16SI, INT, V16SI, HI)
DEF_FUNCTION_TYPE (V8SI, V16HI, V16HI)
DEF_FUNCTION_TYPE (V8SI, V8SI, INT)
DEF_FUNCTION_TYPE (V8SI, V8SI, SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, SI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, INT)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V4SI, V16SI, HI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, INT, V16SI, HI)
DEF_FUNCTION_TYPE (V8SI, PCV8SI, V8SI)
DEF_FUNCTION_TYPE (V4DI, V4DI, V4DI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI)
+DEF_FUNCTION_TYPE (V16SI, V8DF, V8DF)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI, INT, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V4DI, INT, V8DI, QI)
DEF_FUNCTION_TYPE (V4DI, V8SI, V8SI)
DEF_FUNCTION_TYPE (V4UDI, V8USI, V8USI)
DEF_FUNCTION_TYPE (V4DI, V4DI, V2DI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V2DI)
DEF_FUNCTION_TYPE (V4DI, PCV4DI, V4DI)
+DEF_FUNCTION_TYPE (V4DI, V8DI, INT)
+DEF_FUNCTION_TYPE (V4DI, V8DI, INT, V4DI, QI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V2DI, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, INT, V8DI, QI)
DEF_FUNCTION_TYPE (V4DI, V4DI, INT)
DEF_FUNCTION_TYPE (V2DI, V4DI, INT)
DEF_FUNCTION_TYPE (VOID, PVOID, INT64)
@@ -362,8 +464,10 @@ DEF_FUNCTION_TYPE (VOID, PCHAR, V16QI)
DEF_FUNCTION_TYPE (VOID, PCHAR, V32QI)
DEF_FUNCTION_TYPE (VOID, PDOUBLE, V2DF)
DEF_FUNCTION_TYPE (VOID, PDOUBLE, V4DF)
+DEF_FUNCTION_TYPE (VOID, PDOUBLE, V8DF)
DEF_FUNCTION_TYPE (VOID, PFLOAT, V4SF)
DEF_FUNCTION_TYPE (VOID, PFLOAT, V8SF)
+DEF_FUNCTION_TYPE (VOID, PFLOAT, V16SF)
DEF_FUNCTION_TYPE (VOID, PINT, INT)
DEF_FUNCTION_TYPE (VOID, PLONGLONG, LONGLONG)
DEF_FUNCTION_TYPE (VOID, PULONGLONG, ULONGLONG)
@@ -374,6 +478,34 @@ DEF_FUNCTION_TYPE (VOID, PV4DI, V4DI)
DEF_FUNCTION_TYPE (VOID, PV4SF, V4SF)
DEF_FUNCTION_TYPE (VOID, PV8SF, V8SF)
DEF_FUNCTION_TYPE (VOID, UNSIGNED, UNSIGNED)
+DEF_FUNCTION_TYPE (VOID, PV8DI, V8DI)
+
+# Instructions returning mask
+DEF_FUNCTION_TYPE (HI, HI)
+DEF_FUNCTION_TYPE (HI, HI, HI)
+DEF_FUNCTION_TYPE (HI, HI, INT)
+DEF_FUNCTION_TYPE (QI, V8DI, V8DI)
+DEF_FUNCTION_TYPE (QI, V8DI, V8DI, QI)
+DEF_FUNCTION_TYPE (HI, V16SI, V16SI)
+DEF_FUNCTION_TYPE (HI, V16SI, V16SI, HI)
+DEF_FUNCTION_TYPE (QI, V8DI, V8DI, INT)
+DEF_FUNCTION_TYPE (QI, V8DI, V8DI, INT, QI)
+DEF_FUNCTION_TYPE (HI, V16SI, V16SI, INT)
+DEF_FUNCTION_TYPE (HI, V16SI, V16SI, INT ,HI)
+DEF_FUNCTION_TYPE (QI, V8DF, V8DF, INT)
+DEF_FUNCTION_TYPE (QI, V8DF, V8DF, INT, QI)
+DEF_FUNCTION_TYPE (QI, V8DF, V8DF, INT, QI, INT)
+DEF_FUNCTION_TYPE (HI, V16SF, V16SF, INT)
+DEF_FUNCTION_TYPE (HI, V16SF, V16SF, INT, HI)
+DEF_FUNCTION_TYPE (HI, V16SF, V16SF, INT, HI, INT)
+DEF_FUNCTION_TYPE (QI, V2DF, V2DF, INT)
+DEF_FUNCTION_TYPE (QI, V2DF, V2DF, INT, QI)
+DEF_FUNCTION_TYPE (QI, V2DF, V2DF, INT, QI, INT)
+DEF_FUNCTION_TYPE (QI, V4SF, V4SF, INT)
+DEF_FUNCTION_TYPE (QI, V4SF, V4SF, INT, QI)
+DEF_FUNCTION_TYPE (QI, V4SF, V4SF, INT, QI, INT)
+DEF_FUNCTION_TYPE (V16SI, HI)
+DEF_FUNCTION_TYPE (V8DI, QI)
DEF_FUNCTION_TYPE (INT, V16QI, V16QI, INT)
DEF_FUNCTION_TYPE (UCHAR, UINT, UINT, UINT)
@@ -413,11 +545,69 @@ DEF_FUNCTION_TYPE (V8SF, V8SF, V4SF, INT)
DEF_FUNCTION_TYPE (V8SF, V8SF, V8SF, INT)
DEF_FUNCTION_TYPE (V8SF, V8SF, V8SF, V8SF)
DEF_FUNCTION_TYPE (V8SF, V8SF, V8SF, V8SI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF, V8DF)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, V16SF)
DEF_FUNCTION_TYPE (V8SI, V8SI, V4SI, INT)
DEF_FUNCTION_TYPE (V8SI, V8SI, V8SI, INT)
DEF_FUNCTION_TYPE (V8SI, V8SI, V8SI, V8SI)
DEF_FUNCTION_TYPE (V4DI, V4DI, V4DI, INT)
DEF_FUNCTION_TYPE (V4DI, V4DI, V2DI, INT)
+
+# Instructions with masking
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V8SF, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V8SI, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DI, V8SI, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DI, V8HI, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DI, V16QI, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DF, V8DI, V8DF, V8DF)
+DEF_FUNCTION_TYPE (V8DF, V8DI, V8DF, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DI, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF, V8DF, QI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V16SI, V16SI, HI)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V2DF, V2DF, QI)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V4SF, V2DF, QI)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, HI)
+DEF_FUNCTION_TYPE (V16SF, V16SI, V16SF, HI)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, V16SF, HI)
+DEF_FUNCTION_TYPE (V16SF, V16SI, V16SF, V16SF)
+DEF_FUNCTION_TYPE (V16SF, V16SI, V16SF, V16SF, HI)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SI, V16SF, HI)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V2DF, V4SF, QI)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V4SF, V4SF, QI)
+DEF_FUNCTION_TYPE (V16SF, V4SF, V16SF, HI)
+DEF_FUNCTION_TYPE (V8DF, V4DF, V8DF, QI)
+DEF_FUNCTION_TYPE (V8DF, V2DF, V8DF, QI)
+DEF_FUNCTION_TYPE (V16SI, V4SI, V16SI, HI)
+DEF_FUNCTION_TYPE (V16SI, SI, V16SI, HI)
+DEF_FUNCTION_TYPE (V16SI, V16HI, V16SI, HI)
+DEF_FUNCTION_TYPE (V16SI, V16QI, V16SI, HI)
+DEF_FUNCTION_TYPE (V8SI, V8DF, V8SI, QI)
+DEF_FUNCTION_TYPE (V8DI, V4DI, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DI, V2DI, V8DI, QI)
+DEF_FUNCTION_TYPE (V8DI, DI, V8DI, QI)
+DEF_FUNCTION_TYPE (V16SF, PCV16SF, V16SF, HI)
+DEF_FUNCTION_TYPE (V8DF, PCV8DF, V8DF, QI)
+DEF_FUNCTION_TYPE (V16SI, PCV16SI, V16SI, HI)
+DEF_FUNCTION_TYPE (V8DI, PCV8DI, V8DI, QI)
+DEF_FUNCTION_TYPE (V2DF, PCDOUBLE, V2DF, QI)
+DEF_FUNCTION_TYPE (V4SF, PCFLOAT, V4SF, QI)
+DEF_FUNCTION_TYPE (V16QI, V16SI, V16QI, HI)
+DEF_FUNCTION_TYPE (V16HI, V16SI, V16HI, HI)
+DEF_FUNCTION_TYPE (V8SI, V8DI, V8SI, QI)
+DEF_FUNCTION_TYPE (V8HI, V8DI, V8HI, QI)
+DEF_FUNCTION_TYPE (V16QI, V8DI, V16QI, QI)
+DEF_FUNCTION_TYPE (VOID, PV8DF, V8DF, QI)
+DEF_FUNCTION_TYPE (VOID, PV16SF, V16SF, HI)
+DEF_FUNCTION_TYPE (VOID, PV8DI, V8DI, QI)
+DEF_FUNCTION_TYPE (VOID, PV16SI, V16SI, HI)
+DEF_FUNCTION_TYPE (VOID, PDOUBLE, V2DF, QI)
+DEF_FUNCTION_TYPE (VOID, PFLOAT, V4SF, QI)
+DEF_FUNCTION_TYPE (V16SI, V16SF, V16SI, HI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI, V8DI, INT, QI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V16SI, V16SI, INT, HI)
+
DEF_FUNCTION_TYPE (VOID, PCVOID, UNSIGNED, UNSIGNED)
DEF_FUNCTION_TYPE (VOID, PV2DF, V2DI, V2DF)
DEF_FUNCTION_TYPE (VOID, PV4DF, V4DI, V4DF)
@@ -439,6 +629,13 @@ DEF_FUNCTION_TYPE (V8UHI, V8UHI, V8UHI, V8UHI)
DEF_FUNCTION_TYPE (V16UQI, V16UQI, V16UQI, V16UQI)
DEF_FUNCTION_TYPE (V4DF, V4DF, V4DF, V4DI)
DEF_FUNCTION_TYPE (V8SF, V8SF, V8SF, V8SI)
+DEF_FUNCTION_TYPE (V8DI, V8DI, V8DI, V8DI)
+DEF_FUNCTION_TYPE (V16SI, V16SI, V16SI, V16SI)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DI, V8DF)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SI, V16SF)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V4SF, INT, V4SF, QI)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V2DF, INT, V2DF, QI)
+DEF_FUNCTION_TYPE (V8DI, V16SI, V16SI, V8DI, QI)
DEF_FUNCTION_TYPE (V2DI, V2DI, V2DI, UINT, UINT)
DEF_FUNCTION_TYPE (V4HI, HI, HI, HI, HI)
@@ -451,6 +648,43 @@ DEF_FUNCTION_TYPE (V8QI, QI, QI, QI, QI, QI, QI, QI, QI)
DEF_FUNCTION_TYPE (UCHAR, UCHAR, UINT, UINT, PUNSIGNED)
DEF_FUNCTION_TYPE (UCHAR, UCHAR, ULONGLONG, ULONGLONG, PULONGLONG)
+# Instructions with rounding
+DEF_FUNCTION_TYPE (UINT64, V2DF, INT)
+DEF_FUNCTION_TYPE (UINT64, V4SF, INT)
+DEF_FUNCTION_TYPE (UINT, V2DF, INT)
+DEF_FUNCTION_TYPE (UINT, V4SF, INT)
+DEF_FUNCTION_TYPE (INT64, V2DF, INT)
+DEF_FUNCTION_TYPE (INT64, V4SF, INT)
+DEF_FUNCTION_TYPE (INT, V2DF, INT)
+DEF_FUNCTION_TYPE (INT, V4SF, INT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, UINT64, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, UINT64, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, UINT, INT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, INT64, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, INT64, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, INT, INT)
+DEF_FUNCTION_TYPE (V16SI, V16SF, V16SI, HI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SI, V16SF, HI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, HI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16HI, V16SF, HI, INT)
+DEF_FUNCTION_TYPE (V8SI, V8DF, V8SI, QI, INT)
+DEF_FUNCTION_TYPE (V8SF, V8DF, V8SF, QI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF, QI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8SF, V8DF, QI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, V16SF, V16SF, HI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, V8DF, V8DF, QI, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V4SF, V4SF, QI, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V2DF, V4SF, QI, INT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V2DF, V2DF, QI, INT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V4SF, V2DF, QI, INT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V2DF, V2DF, INT)
+
+DEF_FUNCTION_TYPE (V16SF, V16SF, INT, V16SF, HI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, INT, V8DF, QI, INT)
+DEF_FUNCTION_TYPE (V4SF, V4SF, V4SF, INT, V4SF, QI, INT)
+DEF_FUNCTION_TYPE (V2DF, V2DF, V2DF, INT, V2DF, QI, INT)
+DEF_FUNCTION_TYPE (V8DI, V8DI, SI, V8DI, V8DI)
+
DEF_FUNCTION_TYPE (V2DF, V2DF, PCDOUBLE, V4SI, V2DF, INT)
DEF_FUNCTION_TYPE (V4DF, V4DF, PCDOUBLE, V4SI, V4DF, INT)
DEF_FUNCTION_TYPE (V4DF, V4DF, PCDOUBLE, V8SI, V4DF, INT)
@@ -472,6 +706,30 @@ DEF_FUNCTION_TYPE (V4SI, V4SI, PCINT, V2DI, V4SI, INT)
DEF_FUNCTION_TYPE (V4SI, V4SI, PCINT, V4DI, V4SI, INT)
DEF_FUNCTION_TYPE (V8SI, V8SI, PCINT, V4DI, V8SI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, PCFLOAT, V16SI, HI, INT)
+DEF_FUNCTION_TYPE (V16SF, V16SF, PCFLOAT, V8DI, HI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, PCDOUBLE, V8SI, QI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, PCDOUBLE, V16SI, QI, INT)
+DEF_FUNCTION_TYPE (V8SF, V8SF, PCFLOAT, V8DI, QI, INT)
+DEF_FUNCTION_TYPE (V8DF, V8DF, PCDOUBLE, V8DI, QI, INT)
+DEF_FUNCTION_TYPE (V16SI, V16SI, PCINT, V16SI, HI, INT)
+DEF_FUNCTION_TYPE (V16SI, V16SI, PCINT, V8DI, HI, INT)
+DEF_FUNCTION_TYPE (V8DI, V8DI, PCINT64, V8SI, QI, INT)
+DEF_FUNCTION_TYPE (V8DI, V8DI, PCINT64, V16SI, QI, INT)
+DEF_FUNCTION_TYPE (V8SI, V8SI, PCINT, V8DI, QI, INT)
+DEF_FUNCTION_TYPE (V8DI, V8DI, PCINT64, V8DI, QI, INT)
+DEF_FUNCTION_TYPE (VOID, PFLOAT, HI, V16SI, V16SF, INT)
+DEF_FUNCTION_TYPE (VOID, PDOUBLE, QI, V8SI, V8DF, INT)
+DEF_FUNCTION_TYPE (VOID, PFLOAT, QI, V8DI, V8SF, INT)
+DEF_FUNCTION_TYPE (VOID, PDOUBLE, QI, V8DI, V8DF, INT)
+DEF_FUNCTION_TYPE (VOID, PINT, HI, V16SI, V16SI, INT)
+DEF_FUNCTION_TYPE (VOID, PLONGLONG, QI, V8SI, V8DI, INT)
+DEF_FUNCTION_TYPE (VOID, PINT, QI, V8DI, V8SI, INT)
+DEF_FUNCTION_TYPE (VOID, PLONGLONG, QI, V8DI, V8DI, INT)
+
+DEF_FUNCTION_TYPE (VOID, HI, V16SI, PCINT, INT, INT)
+DEF_FUNCTION_TYPE (VOID, QI, V8DI, PCINT, INT, INT)
+
DEF_FUNCTION_TYPE_ALIAS (V2DF_FTYPE_V2DF, ROUND)
DEF_FUNCTION_TYPE_ALIAS (V4DF_FTYPE_V4DF, ROUND)
DEF_FUNCTION_TYPE_ALIAS (V4SF_FTYPE_V4SF, ROUND)
@@ -479,6 +737,7 @@ DEF_FUNCTION_TYPE_ALIAS (V8SF_FTYPE_V8SF, ROUND)
DEF_FUNCTION_TYPE_ALIAS (V4SI_FTYPE_V2DF_V2DF, ROUND)
DEF_FUNCTION_TYPE_ALIAS (V8SI_FTYPE_V4DF_V4DF, ROUND)
+DEF_FUNCTION_TYPE_ALIAS (V16SI_FTYPE_V8DF_V8DF, ROUND)
DEF_FUNCTION_TYPE_ALIAS (V4SI_FTYPE_V4SF, ROUND)
DEF_FUNCTION_TYPE_ALIAS (V8SI_FTYPE_V8SF, ROUND)
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index dd48cc51656..95ebf52d2b5 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -27922,12 +27922,334 @@ enum ix86_builtins
IX86_BUILTIN_GATHERDIV4SI,
IX86_BUILTIN_GATHERDIV8SI,
+ /* AVX512F */
+ IX86_BUILTIN_ADDPD512,
+ IX86_BUILTIN_ADDPS512,
+ IX86_BUILTIN_ALIGND512,
+ IX86_BUILTIN_ALIGNQ512,
+ IX86_BUILTIN_BLENDMD512,
+ IX86_BUILTIN_BLENDMPD512,
+ IX86_BUILTIN_BLENDMPS512,
+ IX86_BUILTIN_BLENDMQ512,
+ IX86_BUILTIN_BROADCASTF32X4_512,
+ IX86_BUILTIN_BROADCASTF64X4_512,
+ IX86_BUILTIN_BROADCASTI32X4_512,
+ IX86_BUILTIN_BROADCASTI64X4_512,
+ IX86_BUILTIN_BROADCASTSD512,
+ IX86_BUILTIN_BROADCASTSS512,
+ IX86_BUILTIN_CMPD512,
+ IX86_BUILTIN_CMPPD512,
+ IX86_BUILTIN_CMPPS512,
+ IX86_BUILTIN_CMPQ512,
+ IX86_BUILTIN_CMPSD_MASK,
+ IX86_BUILTIN_CMPSS_MASK,
+ IX86_BUILTIN_COMIDF,
+ IX86_BUILTIN_COMISF,
+ IX86_BUILTIN_COMPRESSPD512,
+ IX86_BUILTIN_COMPRESSPDSTORE512,
+ IX86_BUILTIN_COMPRESSPS512,
+ IX86_BUILTIN_COMPRESSPSSTORE512,
+ IX86_BUILTIN_CVTDQ2PD512,
+ IX86_BUILTIN_CVTDQ2PS512,
+ IX86_BUILTIN_CVTPD2DQ512,
+ IX86_BUILTIN_CVTPD2PS512,
+ IX86_BUILTIN_CVTPD2UDQ512,
+ IX86_BUILTIN_CVTPH2PS512,
+ IX86_BUILTIN_CVTPS2DQ512,
+ IX86_BUILTIN_CVTPS2PD512,
+ IX86_BUILTIN_CVTPS2PH512,
+ IX86_BUILTIN_CVTPS2UDQ512,
+ IX86_BUILTIN_CVTSI2SD64,
+ IX86_BUILTIN_CVTSI2SS32,
+ IX86_BUILTIN_CVTSI2SS64,
+ IX86_BUILTIN_CVTTPD2DQ512,
+ IX86_BUILTIN_CVTTPD2UDQ512,
+ IX86_BUILTIN_CVTTPS2DQ512,
+ IX86_BUILTIN_CVTTPS2UDQ512,
+ IX86_BUILTIN_CVTUDQ2PD512,
+ IX86_BUILTIN_CVTUDQ2PS512,
+ IX86_BUILTIN_CVTUSI2SD32,
+ IX86_BUILTIN_CVTUSI2SD64,
+ IX86_BUILTIN_CVTUSI2SS32,
+ IX86_BUILTIN_CVTUSI2SS64,
+ IX86_BUILTIN_DIVPD512,
+ IX86_BUILTIN_DIVPS512,
+ IX86_BUILTIN_EXPANDPD512,
+ IX86_BUILTIN_EXPANDPD512Z,
+ IX86_BUILTIN_EXPANDPDLOAD512,
+ IX86_BUILTIN_EXPANDPDLOAD512Z,
+ IX86_BUILTIN_EXPANDPS512,
+ IX86_BUILTIN_EXPANDPS512Z,
+ IX86_BUILTIN_EXPANDPSLOAD512,
+ IX86_BUILTIN_EXPANDPSLOAD512Z,
+ IX86_BUILTIN_EXTRACTF32X4,
+ IX86_BUILTIN_EXTRACTF64X4,
+ IX86_BUILTIN_EXTRACTI32X4,
+ IX86_BUILTIN_EXTRACTI64X4,
+ IX86_BUILTIN_FIXUPIMMPD512_MASK,
+ IX86_BUILTIN_FIXUPIMMPD512_MASKZ,
+ IX86_BUILTIN_FIXUPIMMPS512_MASK,
+ IX86_BUILTIN_FIXUPIMMPS512_MASKZ,
+ IX86_BUILTIN_FIXUPIMMSD128_MASK,
+ IX86_BUILTIN_FIXUPIMMSD128_MASKZ,
+ IX86_BUILTIN_FIXUPIMMSS128_MASK,
+ IX86_BUILTIN_FIXUPIMMSS128_MASKZ,
+ IX86_BUILTIN_GETEXPPD512,
+ IX86_BUILTIN_GETEXPPS512,
+ IX86_BUILTIN_GETMANTPD512,
+ IX86_BUILTIN_GETMANTPS512,
+ IX86_BUILTIN_INSERTF32X4,
+ IX86_BUILTIN_INSERTF64X4,
+ IX86_BUILTIN_INSERTI32X4,
+ IX86_BUILTIN_INSERTI64X4,
+ IX86_BUILTIN_LOADAPD512,
+ IX86_BUILTIN_LOADAPS512,
+ IX86_BUILTIN_LOADDQUDI512,
+ IX86_BUILTIN_LOADDQUSI512,
+ IX86_BUILTIN_LOADUPD512,
+ IX86_BUILTIN_LOADUPS512,
+ IX86_BUILTIN_MAXPD512,
+ IX86_BUILTIN_MAXPS512,
+ IX86_BUILTIN_MINPD512,
+ IX86_BUILTIN_MINPS512,
+ IX86_BUILTIN_MOVAPD512,
+ IX86_BUILTIN_MOVAPS512,
+ IX86_BUILTIN_MOVDDUP512,
+ IX86_BUILTIN_MOVDQA32LOAD512,
+ IX86_BUILTIN_MOVDQA32STORE512,
+ IX86_BUILTIN_MOVDQA32_512,
+ IX86_BUILTIN_MOVDQA64LOAD512,
+ IX86_BUILTIN_MOVDQA64STORE512,
+ IX86_BUILTIN_MOVDQA64_512,
+ IX86_BUILTIN_MOVNTDQ512,
+ IX86_BUILTIN_MOVNTPD512,
+ IX86_BUILTIN_MOVNTPS512,
+ IX86_BUILTIN_MOVSHDUP512,
+ IX86_BUILTIN_MOVSLDUP512,
+ IX86_BUILTIN_MULPD512,
+ IX86_BUILTIN_MULPS512,
+ IX86_BUILTIN_PABSD512,
+ IX86_BUILTIN_PABSQ512,
+ IX86_BUILTIN_PADDD512,
+ IX86_BUILTIN_PADDQ512,
+ IX86_BUILTIN_PANDD512,
+ IX86_BUILTIN_PANDND512,
+ IX86_BUILTIN_PANDNQ512,
+ IX86_BUILTIN_PANDQ512,
+ IX86_BUILTIN_PBROADCASTD512,
+ IX86_BUILTIN_PBROADCASTD512_GPR,
+ IX86_BUILTIN_PBROADCASTMB512,
+ IX86_BUILTIN_PBROADCASTMW512,
+ IX86_BUILTIN_PBROADCASTQ512,
+ IX86_BUILTIN_PBROADCASTQ512_GPR,
+ IX86_BUILTIN_PBROADCASTQ512_MEM,
+ IX86_BUILTIN_PCMPEQD512_MASK,
+ IX86_BUILTIN_PCMPEQQ512_MASK,
+ IX86_BUILTIN_PCMPGTD512_MASK,
+ IX86_BUILTIN_PCMPGTQ512_MASK,
+ IX86_BUILTIN_PCOMPRESSD512,
+ IX86_BUILTIN_PCOMPRESSDSTORE512,
+ IX86_BUILTIN_PCOMPRESSQ512,
+ IX86_BUILTIN_PCOMPRESSQSTORE512,
+ IX86_BUILTIN_PEXPANDD512,
+ IX86_BUILTIN_PEXPANDD512Z,
+ IX86_BUILTIN_PEXPANDDLOAD512,
+ IX86_BUILTIN_PEXPANDDLOAD512Z,
+ IX86_BUILTIN_PEXPANDQ512,
+ IX86_BUILTIN_PEXPANDQ512Z,
+ IX86_BUILTIN_PEXPANDQLOAD512,
+ IX86_BUILTIN_PEXPANDQLOAD512Z,
+ IX86_BUILTIN_PMAXSD512,
+ IX86_BUILTIN_PMAXSQ512,
+ IX86_BUILTIN_PMAXUD512,
+ IX86_BUILTIN_PMAXUQ512,
+ IX86_BUILTIN_PMINSD512,
+ IX86_BUILTIN_PMINSQ512,
+ IX86_BUILTIN_PMINUD512,
+ IX86_BUILTIN_PMINUQ512,
+ IX86_BUILTIN_PMOVDB512,
+ IX86_BUILTIN_PMOVDW512,
+ IX86_BUILTIN_PMOVQB512,
+ IX86_BUILTIN_PMOVQD512,
+ IX86_BUILTIN_PMOVQW512,
+ IX86_BUILTIN_PMOVSDB512,
+ IX86_BUILTIN_PMOVSDW512,
+ IX86_BUILTIN_PMOVSQB512,
+ IX86_BUILTIN_PMOVSQD512,
+ IX86_BUILTIN_PMOVSQW512,
+ IX86_BUILTIN_PMOVSXBD512,
+ IX86_BUILTIN_PMOVSXBQ512,
+ IX86_BUILTIN_PMOVSXDQ512,
+ IX86_BUILTIN_PMOVSXWD512,
+ IX86_BUILTIN_PMOVSXWQ512,
+ IX86_BUILTIN_PMOVUSDB512,
+ IX86_BUILTIN_PMOVUSDW512,
+ IX86_BUILTIN_PMOVUSQB512,
+ IX86_BUILTIN_PMOVUSQD512,
+ IX86_BUILTIN_PMOVUSQW512,
+ IX86_BUILTIN_PMOVZXBD512,
+ IX86_BUILTIN_PMOVZXBQ512,
+ IX86_BUILTIN_PMOVZXDQ512,
+ IX86_BUILTIN_PMOVZXWD512,
+ IX86_BUILTIN_PMOVZXWQ512,
+ IX86_BUILTIN_PMULDQ512,
+ IX86_BUILTIN_PMULLD512,
+ IX86_BUILTIN_PMULUDQ512,
+ IX86_BUILTIN_PORD512,
+ IX86_BUILTIN_PORQ512,
+ IX86_BUILTIN_PROLD512,
+ IX86_BUILTIN_PROLQ512,
+ IX86_BUILTIN_PROLVD512,
+ IX86_BUILTIN_PROLVQ512,
+ IX86_BUILTIN_PRORD512,
+ IX86_BUILTIN_PRORQ512,
+ IX86_BUILTIN_PRORVD512,
+ IX86_BUILTIN_PRORVQ512,
+ IX86_BUILTIN_PSHUFD512,
+ IX86_BUILTIN_PSLLD512,
+ IX86_BUILTIN_PSLLDI512,
+ IX86_BUILTIN_PSLLQ512,
+ IX86_BUILTIN_PSLLQI512,
+ IX86_BUILTIN_PSLLVV16SI,
+ IX86_BUILTIN_PSLLVV8DI,
+ IX86_BUILTIN_PSRAD512,
+ IX86_BUILTIN_PSRADI512,
+ IX86_BUILTIN_PSRAQ512,
+ IX86_BUILTIN_PSRAQI512,
+ IX86_BUILTIN_PSRAVV16SI,
+ IX86_BUILTIN_PSRAVV8DI,
+ IX86_BUILTIN_PSRLD512,
+ IX86_BUILTIN_PSRLDI512,
+ IX86_BUILTIN_PSRLQ512,
+ IX86_BUILTIN_PSRLQI512,
+ IX86_BUILTIN_PSRLVV16SI,
+ IX86_BUILTIN_PSRLVV8DI,
+ IX86_BUILTIN_PSUBD512,
+ IX86_BUILTIN_PSUBQ512,
+ IX86_BUILTIN_PTESTMD512,
+ IX86_BUILTIN_PTESTMQ512,
+ IX86_BUILTIN_PTESTNMD512,
+ IX86_BUILTIN_PTESTNMQ512,
+ IX86_BUILTIN_PUNPCKHDQ512,
+ IX86_BUILTIN_PUNPCKHQDQ512,
+ IX86_BUILTIN_PUNPCKLDQ512,
+ IX86_BUILTIN_PUNPCKLQDQ512,
+ IX86_BUILTIN_PXORD512,
+ IX86_BUILTIN_PXORQ512,
+ IX86_BUILTIN_RCP14PD512,
+ IX86_BUILTIN_RCP14PS512,
+ IX86_BUILTIN_RNDSCALEPD,
+ IX86_BUILTIN_RNDSCALEPS,
+ IX86_BUILTIN_RSQRT14PD512,
+ IX86_BUILTIN_RSQRT14PS512,
+ IX86_BUILTIN_SCALEFPD512,
+ IX86_BUILTIN_SCALEFPS512,
+ IX86_BUILTIN_SHUFPD512,
+ IX86_BUILTIN_SHUFPS512,
+ IX86_BUILTIN_SHUF_F32x4,
+ IX86_BUILTIN_SHUF_F64x2,
+ IX86_BUILTIN_SHUF_I32x4,
+ IX86_BUILTIN_SHUF_I64x2,
IX86_BUILTIN_SQRTPD512,
- IX86_BUILTIN_EXP2PS,
+ IX86_BUILTIN_SQRTPD512_MASK,
+ IX86_BUILTIN_SQRTPS512_MASK,
IX86_BUILTIN_SQRTPS_NR512,
-
- /* Alternate 4 element gather for the vectorizer where
- all operands are 32-byte wide. */
+ IX86_BUILTIN_STOREAPD512,
+ IX86_BUILTIN_STOREAPS512,
+ IX86_BUILTIN_STOREDQUDI512,
+ IX86_BUILTIN_STOREDQUSI512,
+ IX86_BUILTIN_STOREUPD512,
+ IX86_BUILTIN_STOREUPS512,
+ IX86_BUILTIN_SUBPD512,
+ IX86_BUILTIN_SUBPS512,
+ IX86_BUILTIN_UCMPD512,
+ IX86_BUILTIN_UCMPQ512,
+ IX86_BUILTIN_UNPCKHPD512,
+ IX86_BUILTIN_UNPCKHPS512,
+ IX86_BUILTIN_UNPCKLPD512,
+ IX86_BUILTIN_UNPCKLPS512,
+ IX86_BUILTIN_VCVTSD2SI32,
+ IX86_BUILTIN_VCVTSD2SI64,
+ IX86_BUILTIN_VCVTSD2USI32,
+ IX86_BUILTIN_VCVTSD2USI64,
+ IX86_BUILTIN_VCVTSS2SI32,
+ IX86_BUILTIN_VCVTSS2SI64,
+ IX86_BUILTIN_VCVTSS2USI32,
+ IX86_BUILTIN_VCVTSS2USI64,
+ IX86_BUILTIN_VCVTTSD2SI32,
+ IX86_BUILTIN_VCVTTSD2SI64,
+ IX86_BUILTIN_VCVTTSD2USI32,
+ IX86_BUILTIN_VCVTTSD2USI64,
+ IX86_BUILTIN_VCVTTSS2SI32,
+ IX86_BUILTIN_VCVTTSS2SI64,
+ IX86_BUILTIN_VCVTTSS2USI32,
+ IX86_BUILTIN_VCVTTSS2USI64,
+ IX86_BUILTIN_VFMADDPD512_MASK,
+ IX86_BUILTIN_VFMADDPD512_MASK3,
+ IX86_BUILTIN_VFMADDPD512_MASKZ,
+ IX86_BUILTIN_VFMADDPS512_MASK,
+ IX86_BUILTIN_VFMADDPS512_MASK3,
+ IX86_BUILTIN_VFMADDPS512_MASKZ,
+ IX86_BUILTIN_VFMADDSUBPD512_MASK,
+ IX86_BUILTIN_VFMADDSUBPD512_MASK3,
+ IX86_BUILTIN_VFMADDSUBPD512_MASKZ,
+ IX86_BUILTIN_VFMADDSUBPS512_MASK,
+ IX86_BUILTIN_VFMADDSUBPS512_MASK3,
+ IX86_BUILTIN_VFMADDSUBPS512_MASKZ,
+ IX86_BUILTIN_VFMSUBADDPD512_MASK3,
+ IX86_BUILTIN_VFMSUBADDPS512_MASK3,
+ IX86_BUILTIN_VFMSUBPD512_MASK3,
+ IX86_BUILTIN_VFMSUBPS512_MASK3,
+ IX86_BUILTIN_VFNMADDPD512_MASK,
+ IX86_BUILTIN_VFNMADDPS512_MASK,
+ IX86_BUILTIN_VFNMSUBPD512_MASK,
+ IX86_BUILTIN_VFNMSUBPD512_MASK3,
+ IX86_BUILTIN_VFNMSUBPS512_MASK,
+ IX86_BUILTIN_VFNMSUBPS512_MASK3,
+ IX86_BUILTIN_VPCLZCNTD512,
+ IX86_BUILTIN_VPCLZCNTQ512,
+ IX86_BUILTIN_VPCONFLICTD512,
+ IX86_BUILTIN_VPCONFLICTQ512,
+ IX86_BUILTIN_VPERMDF512,
+ IX86_BUILTIN_VPERMDI512,
+ IX86_BUILTIN_VPERMI2VARD512,
+ IX86_BUILTIN_VPERMI2VARPD512,
+ IX86_BUILTIN_VPERMI2VARPS512,
+ IX86_BUILTIN_VPERMI2VARQ512,
+ IX86_BUILTIN_VPERMILPD512,
+ IX86_BUILTIN_VPERMILPS512,
+ IX86_BUILTIN_VPERMILVARPD512,
+ IX86_BUILTIN_VPERMILVARPS512,
+ IX86_BUILTIN_VPERMT2VARD512,
+ IX86_BUILTIN_VPERMT2VARD512_MASKZ,
+ IX86_BUILTIN_VPERMT2VARPD512,
+ IX86_BUILTIN_VPERMT2VARPD512_MASKZ,
+ IX86_BUILTIN_VPERMT2VARPS512,
+ IX86_BUILTIN_VPERMT2VARPS512_MASKZ,
+ IX86_BUILTIN_VPERMT2VARQ512,
+ IX86_BUILTIN_VPERMT2VARQ512_MASKZ,
+ IX86_BUILTIN_VPERMVARDF512,
+ IX86_BUILTIN_VPERMVARDI512,
+ IX86_BUILTIN_VPERMVARSF512,
+ IX86_BUILTIN_VPERMVARSI512,
+ IX86_BUILTIN_VTERNLOGD512_MASK,
+ IX86_BUILTIN_VTERNLOGD512_MASKZ,
+ IX86_BUILTIN_VTERNLOGQ512_MASK,
+ IX86_BUILTIN_VTERNLOGQ512_MASKZ,
+
+ /* Mask arithmetic operations */
+ IX86_BUILTIN_KAND16,
+ IX86_BUILTIN_KANDN16,
+ IX86_BUILTIN_KNOT16,
+ IX86_BUILTIN_KOR16,
+ IX86_BUILTIN_KORTESTC16,
+ IX86_BUILTIN_KORTESTZ16,
+ IX86_BUILTIN_KUNPCKBW,
+ IX86_BUILTIN_KXNOR16,
+ IX86_BUILTIN_KXOR16,
+
+ /* Alternate 4 and 8 element gather/scatter for the vectorizer
+ where all operands are 32-byte or 64-byte wide respectively. */
IX86_BUILTIN_GATHERALTSIV4DF,
IX86_BUILTIN_GATHERALTDIV8SF,
IX86_BUILTIN_GATHERALTSIV4DI,
@@ -27943,6 +28265,28 @@ enum ix86_builtins
IX86_BUILTIN_GATHER3SIV16SF,
IX86_BUILTIN_GATHER3SIV16SI,
IX86_BUILTIN_GATHER3SIV8DF,
+ IX86_BUILTIN_GATHER3SIV8DI,
+ IX86_BUILTIN_SCATTERDIV16SF,
+ IX86_BUILTIN_SCATTERDIV16SI,
+ IX86_BUILTIN_SCATTERDIV8DF,
+ IX86_BUILTIN_SCATTERDIV8DI,
+ IX86_BUILTIN_SCATTERSIV16SF,
+ IX86_BUILTIN_SCATTERSIV16SI,
+ IX86_BUILTIN_SCATTERSIV8DF,
+ IX86_BUILTIN_SCATTERSIV8DI,
+
+ /* AVX512PF */
+ IX86_BUILTIN_GATHERPFDPS,
+ IX86_BUILTIN_GATHERPFQPS,
+ IX86_BUILTIN_SCATTERPFDPS,
+ IX86_BUILTIN_SCATTERPFQPS,
+ IX86_BUILTIN_EXP2PD_MASK,
+ IX86_BUILTIN_EXP2PS_MASK,
+ IX86_BUILTIN_EXP2PS,
+ IX86_BUILTIN_RCP28PD,
+ IX86_BUILTIN_RCP28PS,
+ IX86_BUILTIN_RSQRT28PD,
+ IX86_BUILTIN_RSQRT28PS,
/* TFmode support builtins. */
IX86_BUILTIN_INFQ,
@@ -28497,6 +28841,39 @@ static const struct builtin_description bdesc_special_args[] =
{ OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_maskstored256, "__builtin_ia32_maskstored256", IX86_BUILTIN_MASKSTORED256, UNKNOWN, (int) VOID_FTYPE_PV8SI_V8SI_V8SI },
{ OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_maskstoreq256, "__builtin_ia32_maskstoreq256", IX86_BUILTIN_MASKSTOREQ256, UNKNOWN, (int) VOID_FTYPE_PV4DI_V4DI_V4DI },
+ /* AVX512F */
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressstorev16sf_mask, "__builtin_ia32_compressstoresf512_mask", IX86_BUILTIN_COMPRESSPSSTORE512, UNKNOWN, (int) VOID_FTYPE_PV16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressstorev16si_mask, "__builtin_ia32_compressstoresi512_mask", IX86_BUILTIN_PCOMPRESSDSTORE512, UNKNOWN, (int) VOID_FTYPE_PV16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressstorev8df_mask, "__builtin_ia32_compressstoredf512_mask", IX86_BUILTIN_COMPRESSPDSTORE512, UNKNOWN, (int) VOID_FTYPE_PV8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressstorev8di_mask, "__builtin_ia32_compressstoredi512_mask", IX86_BUILTIN_PCOMPRESSQSTORE512, UNKNOWN, (int) VOID_FTYPE_PV8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16sf_mask, "__builtin_ia32_expandloadsf512_mask", IX86_BUILTIN_EXPANDPSLOAD512, UNKNOWN, (int) V16SF_FTYPE_PCV16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16sf_maskz, "__builtin_ia32_expandloadsf512_maskz", IX86_BUILTIN_EXPANDPSLOAD512Z, UNKNOWN, (int) V16SF_FTYPE_PCV16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16si_mask, "__builtin_ia32_expandloadsi512_mask", IX86_BUILTIN_PEXPANDDLOAD512, UNKNOWN, (int) V16SI_FTYPE_PCV16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16si_maskz, "__builtin_ia32_expandloadsi512_maskz", IX86_BUILTIN_PEXPANDDLOAD512Z, UNKNOWN, (int) V16SI_FTYPE_PCV16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8df_mask, "__builtin_ia32_expandloaddf512_mask", IX86_BUILTIN_EXPANDPDLOAD512, UNKNOWN, (int) V8DF_FTYPE_PCV8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8df_maskz, "__builtin_ia32_expandloaddf512_maskz", IX86_BUILTIN_EXPANDPDLOAD512Z, UNKNOWN, (int) V8DF_FTYPE_PCV8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8di_mask, "__builtin_ia32_expandloaddi512_mask", IX86_BUILTIN_PEXPANDQLOAD512, UNKNOWN, (int) V8DI_FTYPE_PCV8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8di_maskz, "__builtin_ia32_expandloaddi512_maskz", IX86_BUILTIN_PEXPANDQLOAD512Z, UNKNOWN, (int) V8DI_FTYPE_PCV8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loaddquv16si_mask, "__builtin_ia32_loaddqusi512_mask", IX86_BUILTIN_LOADDQUSI512, UNKNOWN, (int) V16SI_FTYPE_PCV16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loaddquv8di_mask, "__builtin_ia32_loaddqudi512_mask", IX86_BUILTIN_LOADDQUDI512, UNKNOWN, (int) V8DI_FTYPE_PCV8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadupd512_mask, "__builtin_ia32_loadupd512_mask", IX86_BUILTIN_LOADUPD512, UNKNOWN, (int) V8DF_FTYPE_PCV8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadups512_mask, "__builtin_ia32_loadups512_mask", IX86_BUILTIN_LOADUPS512, UNKNOWN, (int) V16SF_FTYPE_PCV16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv16sf_mask, "__builtin_ia32_loadaps512_mask", IX86_BUILTIN_LOADAPS512, UNKNOWN, (int) V16SF_FTYPE_PCV16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv16si_mask, "__builtin_ia32_movdqa32load512_mask", IX86_BUILTIN_MOVDQA32LOAD512, UNKNOWN, (int) V16SI_FTYPE_PCV16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv8df_mask, "__builtin_ia32_loadapd512_mask", IX86_BUILTIN_LOADAPD512, UNKNOWN, (int) V8DF_FTYPE_PCV8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv8di_mask, "__builtin_ia32_movdqa64load512_mask", IX86_BUILTIN_MOVDQA64LOAD512, UNKNOWN, (int) V8DI_FTYPE_PCV8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_movntv16sf, "__builtin_ia32_movntps512", IX86_BUILTIN_MOVNTPS512, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V16SF },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_movntv8df, "__builtin_ia32_movntpd512", IX86_BUILTIN_MOVNTPD512, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V8DF },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_movntv8di, "__builtin_ia32_movntdq512", IX86_BUILTIN_MOVNTDQ512, UNKNOWN, (int) VOID_FTYPE_PV8DI_V8DI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storedquv16si_mask, "__builtin_ia32_storedqusi512_mask", IX86_BUILTIN_STOREDQUSI512, UNKNOWN, (int) VOID_FTYPE_PV16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storedquv8di_mask, "__builtin_ia32_storedqudi512_mask", IX86_BUILTIN_STOREDQUDI512, UNKNOWN, (int) VOID_FTYPE_PV8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storeupd512_mask, "__builtin_ia32_storeupd512_mask", IX86_BUILTIN_STOREUPD512, UNKNOWN, (int) VOID_FTYPE_PV8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storeups512_mask, "__builtin_ia32_storeups512_mask", IX86_BUILTIN_STOREUPS512, UNKNOWN, (int) VOID_FTYPE_PV16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storev16sf_mask, "__builtin_ia32_storeaps512_mask", IX86_BUILTIN_STOREAPS512, UNKNOWN, (int) VOID_FTYPE_PV16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storev16si_mask, "__builtin_ia32_movdqa32store512_mask", IX86_BUILTIN_MOVDQA32STORE512, UNKNOWN, (int) VOID_FTYPE_PV16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storev8df_mask, "__builtin_ia32_storeapd512_mask", IX86_BUILTIN_STOREAPD512, UNKNOWN, (int) VOID_FTYPE_PV8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_storev8di_mask, "__builtin_ia32_movdqa64store512_mask", IX86_BUILTIN_MOVDQA64STORE512, UNKNOWN, (int) VOID_FTYPE_PV8DI_V8DI_QI },
+
{ OPTION_MASK_ISA_LWP, CODE_FOR_lwp_llwpcb, "__builtin_ia32_llwpcb", IX86_BUILTIN_LLWPCB, UNKNOWN, (int) VOID_FTYPE_PVOID },
{ OPTION_MASK_ISA_LWP, CODE_FOR_lwp_slwpcb, "__builtin_ia32_slwpcb", IX86_BUILTIN_SLWPCB, UNKNOWN, (int) PVOID_FTYPE_VOID },
{ OPTION_MASK_ISA_LWP, CODE_FOR_lwp_lwpvalsi3, "__builtin_ia32_lwpval32", IX86_BUILTIN_LWPVAL32, UNKNOWN, (int) VOID_FTYPE_UINT_UINT_UINT },
@@ -29348,6 +29725,322 @@ static const struct builtin_description bdesc_args[] =
{ OPTION_MASK_ISA_BMI2, CODE_FOR_bmi2_pdep_di3, "__builtin_ia32_pdep_di", IX86_BUILTIN_PDEP64, UNKNOWN, (int) UINT64_FTYPE_UINT64_UINT64 },
{ OPTION_MASK_ISA_BMI2, CODE_FOR_bmi2_pext_si3, "__builtin_ia32_pext_si", IX86_BUILTIN_PEXT32, UNKNOWN, (int) UINT_FTYPE_UINT_UINT },
{ OPTION_MASK_ISA_BMI2, CODE_FOR_bmi2_pext_di3, "__builtin_ia32_pext_di", IX86_BUILTIN_PEXT64, UNKNOWN, (int) UINT64_FTYPE_UINT64_UINT64 },
+
+ /* AVX512F */
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_alignv16si_mask, "__builtin_ia32_alignd512_mask", IX86_BUILTIN_ALIGND512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_alignv8di_mask, "__builtin_ia32_alignq512_mask", IX86_BUILTIN_ALIGNQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_blendmv16si, "__builtin_ia32_blendmd_512_mask", IX86_BUILTIN_BLENDMD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_blendmv8df, "__builtin_ia32_blendmpd_512_mask", IX86_BUILTIN_BLENDMPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_blendmv16sf, "__builtin_ia32_blendmps_512_mask", IX86_BUILTIN_BLENDMPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_blendmv8di, "__builtin_ia32_blendmq_512_mask", IX86_BUILTIN_BLENDMQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_broadcastv16sf_mask, "__builtin_ia32_broadcastf32x4_512", IX86_BUILTIN_BROADCASTF32X4_512, UNKNOWN, (int) V16SF_FTYPE_V4SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_broadcastv8df_mask, "__builtin_ia32_broadcastf64x4_512", IX86_BUILTIN_BROADCASTF64X4_512, UNKNOWN, (int) V8DF_FTYPE_V4DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_broadcastv16si_mask, "__builtin_ia32_broadcasti32x4_512", IX86_BUILTIN_BROADCASTI32X4_512, UNKNOWN, (int) V16SI_FTYPE_V4SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_broadcastv8di_mask, "__builtin_ia32_broadcasti64x4_512", IX86_BUILTIN_BROADCASTI64X4_512, UNKNOWN, (int) V8DI_FTYPE_V4DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vec_dupv8df_mask, "__builtin_ia32_broadcastsd512", IX86_BUILTIN_BROADCASTSD512, UNKNOWN, (int) V8DF_FTYPE_V2DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vec_dupv16sf_mask, "__builtin_ia32_broadcastss512", IX86_BUILTIN_BROADCASTSS512, UNKNOWN, (int) V16SF_FTYPE_V4SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_cmpv16si3_mask, "__builtin_ia32_cmpd512_mask", IX86_BUILTIN_CMPD512, UNKNOWN, (int) HI_FTYPE_V16SI_V16SI_INT_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_cmpv8di3_mask, "__builtin_ia32_cmpq512_mask", IX86_BUILTIN_CMPQ512, UNKNOWN, (int) QI_FTYPE_V8DI_V8DI_INT_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressv8df_mask, "__builtin_ia32_compressdf512_mask", IX86_BUILTIN_COMPRESSPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressv16sf_mask, "__builtin_ia32_compresssf512_mask", IX86_BUILTIN_COMPRESSPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_floatv8siv8df2_mask, "__builtin_ia32_cvtdq2pd512_mask", IX86_BUILTIN_CVTDQ2PD512, UNKNOWN, (int) V8DF_FTYPE_V8SI_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vcvtps2ph512_mask, "__builtin_ia32_vcvtps2ph512_mask", IX86_BUILTIN_CVTPS2PH512, UNKNOWN, (int) V16HI_FTYPE_V16SF_INT_V16HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ufloatv8siv8df_mask, "__builtin_ia32_cvtudq2pd512_mask", IX86_BUILTIN_CVTUDQ2PD512, UNKNOWN, (int) V8DF_FTYPE_V8SI_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_cvtusi2sd32, "__builtin_ia32_cvtusi2sd32", IX86_BUILTIN_CVTUSI2SD32, UNKNOWN, (int) V2DF_FTYPE_V2DF_UINT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8df_mask, "__builtin_ia32_expanddf512_mask", IX86_BUILTIN_EXPANDPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8df_maskz, "__builtin_ia32_expanddf512_maskz", IX86_BUILTIN_EXPANDPD512Z, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16sf_mask, "__builtin_ia32_expandsf512_mask", IX86_BUILTIN_EXPANDPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16sf_maskz, "__builtin_ia32_expandsf512_maskz", IX86_BUILTIN_EXPANDPS512Z, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vextractf32x4_mask, "__builtin_ia32_extractf32x4_mask", IX86_BUILTIN_EXTRACTF32X4, UNKNOWN, (int) V4SF_FTYPE_V16SF_INT_V4SF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vextractf64x4_mask, "__builtin_ia32_extractf64x4_mask", IX86_BUILTIN_EXTRACTF64X4, UNKNOWN, (int) V4DF_FTYPE_V8DF_INT_V4DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vextracti32x4_mask, "__builtin_ia32_extracti32x4_mask", IX86_BUILTIN_EXTRACTI32X4, UNKNOWN, (int) V4SI_FTYPE_V16SI_INT_V4SI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vextracti64x4_mask, "__builtin_ia32_extracti64x4_mask", IX86_BUILTIN_EXTRACTI64X4, UNKNOWN, (int) V4DI_FTYPE_V8DI_INT_V4DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vinsertf32x4_mask, "__builtin_ia32_insertf32x4_mask", IX86_BUILTIN_INSERTF32X4, UNKNOWN, (int) V16SF_FTYPE_V16SF_V4SF_INT_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vinsertf64x4_mask, "__builtin_ia32_insertf64x4_mask", IX86_BUILTIN_INSERTF64X4, UNKNOWN, (int) V8DF_FTYPE_V8DF_V4DF_INT_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vinserti32x4_mask, "__builtin_ia32_inserti32x4_mask", IX86_BUILTIN_INSERTI32X4, UNKNOWN, (int) V16SI_FTYPE_V16SI_V4SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vinserti64x4_mask, "__builtin_ia32_inserti64x4_mask", IX86_BUILTIN_INSERTI64X4, UNKNOWN, (int) V8DI_FTYPE_V8DI_V4DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv8df_mask, "__builtin_ia32_movapd512_mask", IX86_BUILTIN_MOVAPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv16sf_mask, "__builtin_ia32_movaps512_mask", IX86_BUILTIN_MOVAPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_movddup512_mask, "__builtin_ia32_movddup512_mask", IX86_BUILTIN_MOVDDUP512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv16si_mask, "__builtin_ia32_movdqa32_512_mask", IX86_BUILTIN_MOVDQA32_512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_loadv8di_mask, "__builtin_ia32_movdqa64_512_mask", IX86_BUILTIN_MOVDQA64_512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_movshdup512_mask, "__builtin_ia32_movshdup512_mask", IX86_BUILTIN_MOVSHDUP512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_movsldup512_mask, "__builtin_ia32_movsldup512_mask", IX86_BUILTIN_MOVSLDUP512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_absv16si2_mask, "__builtin_ia32_pabsd512_mask", IX86_BUILTIN_PABSD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_absv8di2_mask, "__builtin_ia32_pabsq512_mask", IX86_BUILTIN_PABSQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_addv16si3_mask, "__builtin_ia32_paddd512_mask", IX86_BUILTIN_PADDD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_addv8di3_mask, "__builtin_ia32_paddq512_mask", IX86_BUILTIN_PADDQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_andv16si3_mask, "__builtin_ia32_pandd512_mask", IX86_BUILTIN_PANDD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_andnotv16si3_mask, "__builtin_ia32_pandnd512_mask", IX86_BUILTIN_PANDND512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_andnotv8di3_mask, "__builtin_ia32_pandnq512_mask", IX86_BUILTIN_PANDNQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_andv8di3_mask, "__builtin_ia32_pandq512_mask", IX86_BUILTIN_PANDQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vec_dupv16si_mask, "__builtin_ia32_pbroadcastd512", IX86_BUILTIN_PBROADCASTD512, UNKNOWN, (int) V16SI_FTYPE_V4SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vec_dup_gprv16si_mask, "__builtin_ia32_pbroadcastd512_gpr_mask", IX86_BUILTIN_PBROADCASTD512_GPR, UNKNOWN, (int) V16SI_FTYPE_SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_avx512cd_maskb_vec_dupv8di, "__builtin_ia32_broadcastmb512", IX86_BUILTIN_PBROADCASTMB512, UNKNOWN, (int) V8DI_FTYPE_QI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_avx512cd_maskw_vec_dupv16si, "__builtin_ia32_broadcastmw512", IX86_BUILTIN_PBROADCASTMW512, UNKNOWN, (int) V16SI_FTYPE_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vec_dupv8di_mask, "__builtin_ia32_pbroadcastq512", IX86_BUILTIN_PBROADCASTQ512, UNKNOWN, (int) V8DI_FTYPE_V2DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_avx512f_vec_dup_gprv8di_mask, "__builtin_ia32_pbroadcastq512_gpr_mask", IX86_BUILTIN_PBROADCASTQ512_GPR, UNKNOWN, (int) V8DI_FTYPE_DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F & ~OPTION_MASK_ISA_64BIT, CODE_FOR_avx512f_vec_dup_memv8di_mask, "__builtin_ia32_pbroadcastq512_mem_mask", IX86_BUILTIN_PBROADCASTQ512_MEM, UNKNOWN, (int) V8DI_FTYPE_DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_eqv16si3_mask, "__builtin_ia32_pcmpeqd512_mask", IX86_BUILTIN_PCMPEQD512_MASK, UNKNOWN, (int) HI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_eqv8di3_mask, "__builtin_ia32_pcmpeqq512_mask", IX86_BUILTIN_PCMPEQQ512_MASK, UNKNOWN, (int) QI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_gtv16si3_mask, "__builtin_ia32_pcmpgtd512_mask", IX86_BUILTIN_PCMPGTD512_MASK, UNKNOWN, (int) HI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_gtv8di3_mask, "__builtin_ia32_pcmpgtq512_mask", IX86_BUILTIN_PCMPGTQ512_MASK, UNKNOWN, (int) QI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressv16si_mask, "__builtin_ia32_compresssi512_mask", IX86_BUILTIN_PCOMPRESSD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_compressv8di_mask, "__builtin_ia32_compressdi512_mask", IX86_BUILTIN_PCOMPRESSQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16si_mask, "__builtin_ia32_expandsi512_mask", IX86_BUILTIN_PEXPANDD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv16si_maskz, "__builtin_ia32_expandsi512_maskz", IX86_BUILTIN_PEXPANDD512Z, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8di_mask, "__builtin_ia32_expanddi512_mask", IX86_BUILTIN_PEXPANDQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_expandv8di_maskz, "__builtin_ia32_expanddi512_maskz", IX86_BUILTIN_PEXPANDQ512Z, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_smaxv16si3_mask, "__builtin_ia32_pmaxsd512_mask", IX86_BUILTIN_PMAXSD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_smaxv8di3_mask, "__builtin_ia32_pmaxsq512_mask", IX86_BUILTIN_PMAXSQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_umaxv16si3_mask, "__builtin_ia32_pmaxud512_mask", IX86_BUILTIN_PMAXUD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_umaxv8di3_mask, "__builtin_ia32_pmaxuq512_mask", IX86_BUILTIN_PMAXUQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sminv16si3_mask, "__builtin_ia32_pminsd512_mask", IX86_BUILTIN_PMINSD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sminv8di3_mask, "__builtin_ia32_pminsq512_mask", IX86_BUILTIN_PMINSQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_uminv16si3_mask, "__builtin_ia32_pminud512_mask", IX86_BUILTIN_PMINUD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_uminv8di3_mask, "__builtin_ia32_pminuq512_mask", IX86_BUILTIN_PMINUQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_truncatev16siv16qi2_mask, "__builtin_ia32_pmovdb512_mask", IX86_BUILTIN_PMOVDB512, UNKNOWN, (int) V16QI_FTYPE_V16SI_V16QI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_truncatev16siv16hi2_mask, "__builtin_ia32_pmovdw512_mask", IX86_BUILTIN_PMOVDW512, UNKNOWN, (int) V16HI_FTYPE_V16SI_V16HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_truncatev8div16qi2_mask, "__builtin_ia32_pmovqb512_mask", IX86_BUILTIN_PMOVQB512, UNKNOWN, (int) V16QI_FTYPE_V8DI_V16QI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_truncatev8div8si2_mask, "__builtin_ia32_pmovqd512_mask", IX86_BUILTIN_PMOVQD512, UNKNOWN, (int) V8SI_FTYPE_V8DI_V8SI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_truncatev8div8hi2_mask, "__builtin_ia32_pmovqw512_mask", IX86_BUILTIN_PMOVQW512, UNKNOWN, (int) V8HI_FTYPE_V8DI_V8HI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ss_truncatev16siv16qi2_mask, "__builtin_ia32_pmovsdb512_mask", IX86_BUILTIN_PMOVSDB512, UNKNOWN, (int) V16QI_FTYPE_V16SI_V16QI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ss_truncatev16siv16hi2_mask, "__builtin_ia32_pmovsdw512_mask", IX86_BUILTIN_PMOVSDW512, UNKNOWN, (int) V16HI_FTYPE_V16SI_V16HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ss_truncatev8div16qi2_mask, "__builtin_ia32_pmovsqb512_mask", IX86_BUILTIN_PMOVSQB512, UNKNOWN, (int) V16QI_FTYPE_V8DI_V16QI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ss_truncatev8div8si2_mask, "__builtin_ia32_pmovsqd512_mask", IX86_BUILTIN_PMOVSQD512, UNKNOWN, (int) V8SI_FTYPE_V8DI_V8SI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ss_truncatev8div8hi2_mask, "__builtin_ia32_pmovsqw512_mask", IX86_BUILTIN_PMOVSQW512, UNKNOWN, (int) V8HI_FTYPE_V8DI_V8HI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sign_extendv16qiv16si2_mask, "__builtin_ia32_pmovsxbd512_mask", IX86_BUILTIN_PMOVSXBD512, UNKNOWN, (int) V16SI_FTYPE_V16QI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sign_extendv8qiv8di2_mask, "__builtin_ia32_pmovsxbq512_mask", IX86_BUILTIN_PMOVSXBQ512, UNKNOWN, (int) V8DI_FTYPE_V16QI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sign_extendv8siv8di2_mask, "__builtin_ia32_pmovsxdq512_mask", IX86_BUILTIN_PMOVSXDQ512, UNKNOWN, (int) V8DI_FTYPE_V8SI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sign_extendv16hiv16si2_mask, "__builtin_ia32_pmovsxwd512_mask", IX86_BUILTIN_PMOVSXWD512, UNKNOWN, (int) V16SI_FTYPE_V16HI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sign_extendv8hiv8di2_mask, "__builtin_ia32_pmovsxwq512_mask", IX86_BUILTIN_PMOVSXWQ512, UNKNOWN, (int) V8DI_FTYPE_V8HI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_us_truncatev16siv16qi2_mask, "__builtin_ia32_pmovusdb512_mask", IX86_BUILTIN_PMOVUSDB512, UNKNOWN, (int) V16QI_FTYPE_V16SI_V16QI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_us_truncatev16siv16hi2_mask, "__builtin_ia32_pmovusdw512_mask", IX86_BUILTIN_PMOVUSDW512, UNKNOWN, (int) V16HI_FTYPE_V16SI_V16HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_us_truncatev8div16qi2_mask, "__builtin_ia32_pmovusqb512_mask", IX86_BUILTIN_PMOVUSQB512, UNKNOWN, (int) V16QI_FTYPE_V8DI_V16QI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_us_truncatev8div8si2_mask, "__builtin_ia32_pmovusqd512_mask", IX86_BUILTIN_PMOVUSQD512, UNKNOWN, (int) V8SI_FTYPE_V8DI_V8SI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_us_truncatev8div8hi2_mask, "__builtin_ia32_pmovusqw512_mask", IX86_BUILTIN_PMOVUSQW512, UNKNOWN, (int) V8HI_FTYPE_V8DI_V8HI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_zero_extendv16qiv16si2_mask, "__builtin_ia32_pmovzxbd512_mask", IX86_BUILTIN_PMOVZXBD512, UNKNOWN, (int) V16SI_FTYPE_V16QI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_zero_extendv8qiv8di2_mask, "__builtin_ia32_pmovzxbq512_mask", IX86_BUILTIN_PMOVZXBQ512, UNKNOWN, (int) V8DI_FTYPE_V16QI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_zero_extendv8siv8di2_mask, "__builtin_ia32_pmovzxdq512_mask", IX86_BUILTIN_PMOVZXDQ512, UNKNOWN, (int) V8DI_FTYPE_V8SI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_zero_extendv16hiv16si2_mask, "__builtin_ia32_pmovzxwd512_mask", IX86_BUILTIN_PMOVZXWD512, UNKNOWN, (int) V16SI_FTYPE_V16HI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_zero_extendv8hiv8di2_mask, "__builtin_ia32_pmovzxwq512_mask", IX86_BUILTIN_PMOVZXWQ512, UNKNOWN, (int) V8DI_FTYPE_V8HI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_vec_widen_smult_even_v16si_mask, "__builtin_ia32_pmuldq512_mask", IX86_BUILTIN_PMULDQ512, UNKNOWN, (int) V8DI_FTYPE_V16SI_V16SI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_mulv16si3_mask, "__builtin_ia32_pmulld512_mask" , IX86_BUILTIN_PMULLD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_vec_widen_umult_even_v16si_mask, "__builtin_ia32_pmuludq512_mask", IX86_BUILTIN_PMULUDQ512, UNKNOWN, (int) V8DI_FTYPE_V16SI_V16SI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_iorv16si3_mask, "__builtin_ia32_pord512_mask", IX86_BUILTIN_PORD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_iorv8di3_mask, "__builtin_ia32_porq512_mask", IX86_BUILTIN_PORQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rolv16si_mask, "__builtin_ia32_prold512_mask", IX86_BUILTIN_PROLD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rolv8di_mask, "__builtin_ia32_prolq512_mask", IX86_BUILTIN_PROLQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rolvv16si_mask, "__builtin_ia32_prolvd512_mask", IX86_BUILTIN_PROLVD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rolvv8di_mask, "__builtin_ia32_prolvq512_mask", IX86_BUILTIN_PROLVQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rorv16si_mask, "__builtin_ia32_prord512_mask", IX86_BUILTIN_PRORD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rorv8di_mask, "__builtin_ia32_prorq512_mask", IX86_BUILTIN_PRORQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rorvv16si_mask, "__builtin_ia32_prorvd512_mask", IX86_BUILTIN_PRORVD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rorvv8di_mask, "__builtin_ia32_prorvq512_mask", IX86_BUILTIN_PRORVQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_pshufdv3_mask, "__builtin_ia32_pshufd512_mask", IX86_BUILTIN_PSHUFD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashlv16si3_mask, "__builtin_ia32_pslld512_mask", IX86_BUILTIN_PSLLD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V4SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashlv16si3_mask, "__builtin_ia32_pslldi512_mask", IX86_BUILTIN_PSLLDI512, UNKNOWN, (int) V16SI_FTYPE_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashlv8di3_mask, "__builtin_ia32_psllq512_mask", IX86_BUILTIN_PSLLQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V2DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashlv8di3_mask, "__builtin_ia32_psllqi512_mask", IX86_BUILTIN_PSLLQI512, UNKNOWN, (int) V8DI_FTYPE_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ashlvv16si_mask, "__builtin_ia32_psllv16si_mask", IX86_BUILTIN_PSLLVV16SI, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ashlvv8di_mask, "__builtin_ia32_psllv8di_mask", IX86_BUILTIN_PSLLVV8DI, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashrv16si3_mask, "__builtin_ia32_psrad512_mask", IX86_BUILTIN_PSRAD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V4SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashrv16si3_mask, "__builtin_ia32_psradi512_mask", IX86_BUILTIN_PSRADI512, UNKNOWN, (int) V16SI_FTYPE_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashrv8di3_mask, "__builtin_ia32_psraq512_mask", IX86_BUILTIN_PSRAQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V2DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ashrv8di3_mask, "__builtin_ia32_psraqi512_mask", IX86_BUILTIN_PSRAQI512, UNKNOWN, (int) V8DI_FTYPE_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ashrvv16si_mask, "__builtin_ia32_psrav16si_mask", IX86_BUILTIN_PSRAVV16SI, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ashrvv8di_mask, "__builtin_ia32_psrav8di_mask", IX86_BUILTIN_PSRAVV8DI, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_lshrv16si3_mask, "__builtin_ia32_psrld512_mask", IX86_BUILTIN_PSRLD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V4SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_lshrv16si3_mask, "__builtin_ia32_psrldi512_mask", IX86_BUILTIN_PSRLDI512, UNKNOWN, (int) V16SI_FTYPE_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_lshrv8di3_mask, "__builtin_ia32_psrlq512_mask", IX86_BUILTIN_PSRLQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V2DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_lshrv8di3_mask, "__builtin_ia32_psrlqi512_mask", IX86_BUILTIN_PSRLQI512, UNKNOWN, (int) V8DI_FTYPE_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_lshrvv16si_mask, "__builtin_ia32_psrlv16si_mask", IX86_BUILTIN_PSRLVV16SI, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_lshrvv8di_mask, "__builtin_ia32_psrlv8di_mask", IX86_BUILTIN_PSRLVV8DI, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_subv16si3_mask, "__builtin_ia32_psubd512_mask", IX86_BUILTIN_PSUBD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_subv8di3_mask, "__builtin_ia32_psubq512_mask", IX86_BUILTIN_PSUBQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_testmv16si3_mask, "__builtin_ia32_ptestmd512", IX86_BUILTIN_PTESTMD512, UNKNOWN, (int) HI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_testmv8di3_mask, "__builtin_ia32_ptestmq512", IX86_BUILTIN_PTESTMQ512, UNKNOWN, (int) QI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_avx512f_testnmv16si3_mask, "__builtin_ia32_ptestnmd512", IX86_BUILTIN_PTESTNMD512, UNKNOWN, (int) HI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_avx512f_testnmv8di3_mask, "__builtin_ia32_ptestnmq512", IX86_BUILTIN_PTESTNMQ512, UNKNOWN, (int) QI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_interleave_highv16si_mask, "__builtin_ia32_punpckhdq512_mask", IX86_BUILTIN_PUNPCKHDQ512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_interleave_highv8di_mask, "__builtin_ia32_punpckhqdq512_mask", IX86_BUILTIN_PUNPCKHQDQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_interleave_lowv16si_mask, "__builtin_ia32_punpckldq512_mask", IX86_BUILTIN_PUNPCKLDQ512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_interleave_lowv8di_mask, "__builtin_ia32_punpcklqdq512_mask", IX86_BUILTIN_PUNPCKLQDQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_xorv16si3_mask, "__builtin_ia32_pxord512_mask", IX86_BUILTIN_PXORD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_xorv8di3_mask, "__builtin_ia32_pxorq512_mask", IX86_BUILTIN_PXORQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_rcp14v8df_mask, "__builtin_ia32_rcp14pd512_mask", IX86_BUILTIN_RCP14PD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_rcp14v16sf_mask, "__builtin_ia32_rcp14ps512_mask", IX86_BUILTIN_RCP14PS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_rsqrt14v8df_mask, "__builtin_ia32_rsqrt14pd512_mask", IX86_BUILTIN_RSQRT14PD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_rsqrt14v16sf_mask, "__builtin_ia32_rsqrt14ps512_mask", IX86_BUILTIN_RSQRT14PS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_shufpd512_mask, "__builtin_ia32_shufpd512_mask", IX86_BUILTIN_SHUFPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_INT_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_shufps512_mask, "__builtin_ia32_shufps512_mask", IX86_BUILTIN_SHUFPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_INT_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_shuf_f32x4_mask, "__builtin_ia32_shuf_f32x4_mask", IX86_BUILTIN_SHUF_F32x4, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_INT_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_shuf_f64x2_mask, "__builtin_ia32_shuf_f64x2_mask", IX86_BUILTIN_SHUF_F64x2, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_INT_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_shuf_i32x4_mask, "__builtin_ia32_shuf_i32x4_mask", IX86_BUILTIN_SHUF_I32x4, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_INT_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_shuf_i64x2_mask, "__builtin_ia32_shuf_i64x2_mask", IX86_BUILTIN_SHUF_I64x2, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ucmpv16si3_mask, "__builtin_ia32_ucmpd512_mask", IX86_BUILTIN_UCMPD512, UNKNOWN, (int) HI_FTYPE_V16SI_V16SI_INT_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ucmpv8di3_mask, "__builtin_ia32_ucmpq512_mask", IX86_BUILTIN_UCMPQ512, UNKNOWN, (int) QI_FTYPE_V8DI_V8DI_INT_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_unpckhpd512_mask, "__builtin_ia32_unpckhpd512_mask", IX86_BUILTIN_UNPCKHPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_unpckhps512_mask, "__builtin_ia32_unpckhps512_mask", IX86_BUILTIN_UNPCKHPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_unpcklpd512_mask, "__builtin_ia32_unpcklpd512_mask", IX86_BUILTIN_UNPCKLPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_unpcklps512_mask, "__builtin_ia32_unpcklps512_mask", IX86_BUILTIN_UNPCKLPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_clzv16si2_mask, "__builtin_ia32_vplzcntd_512_mask", IX86_BUILTIN_VPCLZCNTD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_clzv8di2_mask, "__builtin_ia32_vplzcntq_512_mask", IX86_BUILTIN_VPCLZCNTQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_conflictv16si_mask, "__builtin_ia32_vpconflictsi_512_mask", IX86_BUILTIN_VPCONFLICTD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512CD, CODE_FOR_conflictv8di_mask, "__builtin_ia32_vpconflictdi_512_mask", IX86_BUILTIN_VPCONFLICTQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_permv8df_mask, "__builtin_ia32_permdf512_mask", IX86_BUILTIN_VPERMDF512, UNKNOWN, (int) V8DF_FTYPE_V8DF_INT_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_permv8di_mask, "__builtin_ia32_permdi512_mask", IX86_BUILTIN_VPERMDI512, UNKNOWN, (int) V8DI_FTYPE_V8DI_INT_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermi2varv16si3_mask, "__builtin_ia32_vpermi2vard512_mask", IX86_BUILTIN_VPERMI2VARD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermi2varv8df3_mask, "__builtin_ia32_vpermi2varpd512_mask", IX86_BUILTIN_VPERMI2VARPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DI_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermi2varv16sf3_mask, "__builtin_ia32_vpermi2varps512_mask", IX86_BUILTIN_VPERMI2VARPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SI_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermi2varv8di3_mask, "__builtin_ia32_vpermi2varq512_mask", IX86_BUILTIN_VPERMI2VARQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermilv8df_mask, "__builtin_ia32_vpermilpd512_mask", IX86_BUILTIN_VPERMILPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_INT_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermilv16sf_mask, "__builtin_ia32_vpermilps512_mask", IX86_BUILTIN_VPERMILPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_INT_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermilvarv8df3_mask, "__builtin_ia32_vpermilvarpd512_mask", IX86_BUILTIN_VPERMILVARPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DI_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermilvarv16sf3_mask, "__builtin_ia32_vpermilvarps512_mask", IX86_BUILTIN_VPERMILVARPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SI_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv16si3_mask, "__builtin_ia32_vpermt2vard512_mask", IX86_BUILTIN_VPERMT2VARD512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv16si3_maskz, "__builtin_ia32_vpermt2vard512_maskz", IX86_BUILTIN_VPERMT2VARD512_MASKZ, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv8df3_mask, "__builtin_ia32_vpermt2varpd512_mask", IX86_BUILTIN_VPERMT2VARPD512, UNKNOWN, (int) V8DF_FTYPE_V8DI_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv8df3_maskz, "__builtin_ia32_vpermt2varpd512_maskz", IX86_BUILTIN_VPERMT2VARPD512_MASKZ, UNKNOWN, (int) V8DF_FTYPE_V8DI_V8DF_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv16sf3_mask, "__builtin_ia32_vpermt2varps512_mask", IX86_BUILTIN_VPERMT2VARPS512, UNKNOWN, (int) V16SF_FTYPE_V16SI_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv16sf3_maskz, "__builtin_ia32_vpermt2varps512_maskz", IX86_BUILTIN_VPERMT2VARPS512_MASKZ, UNKNOWN, (int) V16SF_FTYPE_V16SI_V16SF_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv8di3_mask, "__builtin_ia32_vpermt2varq512_mask", IX86_BUILTIN_VPERMT2VARQ512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vpermt2varv8di3_maskz, "__builtin_ia32_vpermt2varq512_maskz", IX86_BUILTIN_VPERMT2VARQ512_MASKZ, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_permvarv8df_mask, "__builtin_ia32_permvardf512_mask", IX86_BUILTIN_VPERMVARDF512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DI_V8DF_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_permvarv8di_mask, "__builtin_ia32_permvardi512_mask", IX86_BUILTIN_VPERMVARDI512, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_permvarv16sf_mask, "__builtin_ia32_permvarsf512_mask", IX86_BUILTIN_VPERMVARSF512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SI_V16SF_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_permvarv16si_mask, "__builtin_ia32_permvarsi512_mask", IX86_BUILTIN_VPERMVARSI512, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vternlogv16si_mask, "__builtin_ia32_pternlogd512_mask", IX86_BUILTIN_VTERNLOGD512_MASK, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_INT_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vternlogv16si_maskz, "__builtin_ia32_pternlogd512_maskz", IX86_BUILTIN_VTERNLOGD512_MASKZ, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_INT_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vternlogv8di_mask, "__builtin_ia32_pternlogq512_mask", IX86_BUILTIN_VTERNLOGQ512_MASK, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_INT_QI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vternlogv8di_maskz, "__builtin_ia32_pternlogq512_maskz", IX86_BUILTIN_VTERNLOGQ512_MASKZ, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_INT_QI },
+
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_copysignv16sf3, "__builtin_ia32_copysignps512", IX86_BUILTIN_CPYSGNPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_copysignv8df3, "__builtin_ia32_copysignpd512", IX86_BUILTIN_CPYSGNPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sqrtv8df2, "__builtin_ia32_sqrtpd512", IX86_BUILTIN_SQRTPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sqrtv16sf2, "__builtin_ia32_sqrtps512", IX86_BUILTIN_SQRTPS_NR512, UNKNOWN, (int) V16SF_FTYPE_V16SF },
+ { OPTION_MASK_ISA_AVX512ER, CODE_FOR_avx512er_exp2v16sf, "__builtin_ia32_exp2ps", IX86_BUILTIN_EXP2PS, UNKNOWN, (int) V16SF_FTYPE_V16SF },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_roundv8df2_vec_pack_sfix, "__builtin_ia32_roundpd_az_vec_pack_sfix512", IX86_BUILTIN_ROUNDPD_AZ_VEC_PACK_SFIX512, UNKNOWN, (int) V16SI_FTYPE_V8DF_V8DF },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_roundpd_vec_pack_sfix512, "__builtin_ia32_floorpd_vec_pack_sfix512", IX86_BUILTIN_FLOORPD_VEC_PACK_SFIX512, (enum rtx_code) ROUND_FLOOR, (int) V16SI_FTYPE_V8DF_V8DF_ROUND },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_roundpd_vec_pack_sfix512, "__builtin_ia32_ceilpd_vec_pack_sfix512", IX86_BUILTIN_CEILPD_VEC_PACK_SFIX512, (enum rtx_code) ROUND_CEIL, (int) V16SI_FTYPE_V8DF_V8DF_ROUND },
+
+ /* Mask arithmetic operations */
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_andhi3, "__builtin_ia32_kandhi", IX86_BUILTIN_KAND16, UNKNOWN, (int) HI_FTYPE_HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_kandnhi, "__builtin_ia32_kandnhi", IX86_BUILTIN_KANDN16, UNKNOWN, (int) HI_FTYPE_HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_one_cmplhi2, "__builtin_ia32_knothi", IX86_BUILTIN_KNOT16, UNKNOWN, (int) HI_FTYPE_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_iorhi3, "__builtin_ia32_korhi", IX86_BUILTIN_KOR16, UNKNOWN, (int) HI_FTYPE_HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_kortestchi, "__builtin_ia32_kortestchi", IX86_BUILTIN_KORTESTC16, UNKNOWN, (int) HI_FTYPE_HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_kortestzhi, "__builtin_ia32_kortestzhi", IX86_BUILTIN_KORTESTZ16, UNKNOWN, (int) HI_FTYPE_HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_kunpckhi, "__builtin_ia32_kunpckhi", IX86_BUILTIN_KUNPCKBW, UNKNOWN, (int) HI_FTYPE_HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_kxnorhi, "__builtin_ia32_kxnorhi", IX86_BUILTIN_KXNOR16, UNKNOWN, (int) HI_FTYPE_HI_HI },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_xorhi3, "__builtin_ia32_kxorhi", IX86_BUILTIN_KXOR16, UNKNOWN, (int) HI_FTYPE_HI_HI },
+};
+
+/* Builtins with rounding support. */
+static const struct builtin_description bdesc_round_args[] =
+{
+ /* AVX512F */
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_addv8df3_mask_round, "__builtin_ia32_addpd512_mask", IX86_BUILTIN_ADDPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_addv16sf3_mask_round, "__builtin_ia32_addps512_mask", IX86_BUILTIN_ADDPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_cmpv8df3_mask_round, "__builtin_ia32_cmppd512_mask", IX86_BUILTIN_CMPPD512, UNKNOWN, (int) QI_FTYPE_V8DF_V8DF_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_cmpv16sf3_mask_round, "__builtin_ia32_cmpps512_mask", IX86_BUILTIN_CMPPS512, UNKNOWN, (int) HI_FTYPE_V16SF_V16SF_INT_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vmcmpv2df3_mask_round, "__builtin_ia32_cmpsd_mask", IX86_BUILTIN_CMPSD_MASK, UNKNOWN, (int) QI_FTYPE_V2DF_V2DF_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vmcmpv4sf3_mask_round, "__builtin_ia32_cmpss_mask", IX86_BUILTIN_CMPSS_MASK, UNKNOWN, (int) QI_FTYPE_V4SF_V4SF_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sse2_comi_round, "__builtin_ia32_vcomisd", IX86_BUILTIN_COMIDF, UNKNOWN, (int) INT_FTYPE_V2DF_V2DF_INT_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sse_comi_round, "__builtin_ia32_vcomiss", IX86_BUILTIN_COMISF, UNKNOWN, (int) INT_FTYPE_V4SF_V4SF_INT_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_floatv16siv16sf2_mask_round, "__builtin_ia32_cvtdq2ps512_mask", IX86_BUILTIN_CVTDQ2PS512, UNKNOWN, (int) V16SF_FTYPE_V16SI_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_cvtpd2dq512_mask_round, "__builtin_ia32_cvtpd2dq512_mask", IX86_BUILTIN_CVTPD2DQ512, UNKNOWN, (int) V8SI_FTYPE_V8DF_V8SI_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_cvtpd2ps512_mask_round, "__builtin_ia32_cvtpd2ps512_mask", IX86_BUILTIN_CVTPD2PS512, UNKNOWN, (int) V8SF_FTYPE_V8DF_V8SF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ufix_notruncv8dfv8si_mask_round, "__builtin_ia32_cvtpd2udq512_mask", IX86_BUILTIN_CVTPD2UDQ512, UNKNOWN, (int) V8SI_FTYPE_V8DF_V8SI_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vcvtph2ps512_mask_round, "__builtin_ia32_vcvtph2ps512_mask", IX86_BUILTIN_CVTPH2PS512, UNKNOWN, (int) V16SF_FTYPE_V16HI_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fix_notruncv16sfv16si_mask_round, "__builtin_ia32_cvtps2dq512_mask", IX86_BUILTIN_CVTPS2DQ512, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_cvtps2pd512_mask_round, "__builtin_ia32_cvtps2pd512_mask", IX86_BUILTIN_CVTPS2PD512, UNKNOWN, (int) V8DF_FTYPE_V8SF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_ufix_notruncv16sfv16si_mask_round, "__builtin_ia32_cvtps2udq512_mask", IX86_BUILTIN_CVTPS2UDQ512, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_HI_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_sse2_cvtsi2sdq_round, "__builtin_ia32_cvtsi2sd64", IX86_BUILTIN_CVTSI2SD64, UNKNOWN, (int) V2DF_FTYPE_V2DF_INT64_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sse_cvtsi2ss_round, "__builtin_ia32_cvtsi2ss32", IX86_BUILTIN_CVTSI2SS32, UNKNOWN, (int) V4SF_FTYPE_V4SF_INT_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_sse_cvtsi2ssq_round, "__builtin_ia32_cvtsi2ss64", IX86_BUILTIN_CVTSI2SS64, UNKNOWN, (int) V4SF_FTYPE_V4SF_INT64_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_fix_truncv8dfv8si2_mask_round, "__builtin_ia32_cvttpd2dq512_mask", IX86_BUILTIN_CVTTPD2DQ512, UNKNOWN, (int) V8SI_FTYPE_V8DF_V8SI_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ufix_truncv8dfv8si2_mask_round, "__builtin_ia32_cvttpd2udq512_mask", IX86_BUILTIN_CVTTPD2UDQ512, UNKNOWN, (int) V8SI_FTYPE_V8DF_V8SI_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_fix_truncv16sfv16si2_mask_round, "__builtin_ia32_cvttps2dq512_mask", IX86_BUILTIN_CVTTPS2DQ512, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ufix_truncv16sfv16si2_mask_round, "__builtin_ia32_cvttps2udq512_mask", IX86_BUILTIN_CVTTPS2UDQ512, UNKNOWN, (int) V16SI_FTYPE_V16SF_V16SI_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_ufloatv16siv16sf2_mask_round, "__builtin_ia32_cvtudq2ps512_mask", IX86_BUILTIN_CVTUDQ2PS512, UNKNOWN, (int) V16SF_FTYPE_V16SI_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_cvtusi2sd64_round, "__builtin_ia32_cvtusi2sd64", IX86_BUILTIN_CVTUSI2SD64, UNKNOWN, (int) V2DF_FTYPE_V2DF_UINT64_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_cvtusi2ss32_round, "__builtin_ia32_cvtusi2ss32", IX86_BUILTIN_CVTUSI2SS32, UNKNOWN, (int) V4SF_FTYPE_V4SF_UINT_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_cvtusi2ss64_round, "__builtin_ia32_cvtusi2ss64", IX86_BUILTIN_CVTUSI2SS64, UNKNOWN, (int) V4SF_FTYPE_V4SF_UINT64_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_divv8df3_mask_round, "__builtin_ia32_divpd512_mask", IX86_BUILTIN_DIVPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_divv16sf3_mask_round, "__builtin_ia32_divps512_mask", IX86_BUILTIN_DIVPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fixupimmv8df_mask_round, "__builtin_ia32_fixupimmpd512_mask", IX86_BUILTIN_FIXUPIMMPD512_MASK, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DI_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fixupimmv8df_maskz_round, "__builtin_ia32_fixupimmpd512_maskz", IX86_BUILTIN_FIXUPIMMPD512_MASKZ, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DI_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fixupimmv16sf_mask_round, "__builtin_ia32_fixupimmps512_mask", IX86_BUILTIN_FIXUPIMMPS512_MASK, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SI_INT_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fixupimmv16sf_maskz_round, "__builtin_ia32_fixupimmps512_maskz", IX86_BUILTIN_FIXUPIMMPS512_MASKZ, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SI_INT_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sfixupimmv2df_mask_round, "__builtin_ia32_fixupimmsd_mask", IX86_BUILTIN_FIXUPIMMSD128_MASK, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_V2DI_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sfixupimmv2df_maskz_round, "__builtin_ia32_fixupimmsd_maskz", IX86_BUILTIN_FIXUPIMMSD128_MASKZ, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_V2DI_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sfixupimmv4sf_mask_round, "__builtin_ia32_fixupimmss_mask", IX86_BUILTIN_FIXUPIMMSS128_MASK, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_V4SI_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sfixupimmv4sf_maskz_round, "__builtin_ia32_fixupimmss_maskz", IX86_BUILTIN_FIXUPIMMSS128_MASKZ, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_V4SI_INT_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_getexpv8df_mask_round, "__builtin_ia32_getexppd512_mask", IX86_BUILTIN_GETEXPPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_getexpv16sf_mask_round, "__builtin_ia32_getexpps512_mask", IX86_BUILTIN_GETEXPPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_getmantv8df_mask_round, "__builtin_ia32_getmantpd512_mask", IX86_BUILTIN_GETMANTPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_INT_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_getmantv16sf_mask_round, "__builtin_ia32_getmantps512_mask", IX86_BUILTIN_GETMANTPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_INT_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_smaxv8df3_mask_round, "__builtin_ia32_maxpd512_mask", IX86_BUILTIN_MAXPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_smaxv16sf3_mask_round, "__builtin_ia32_maxps512_mask", IX86_BUILTIN_MAXPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sminv8df3_mask_round, "__builtin_ia32_minpd512_mask", IX86_BUILTIN_MINPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sminv16sf3_mask_round, "__builtin_ia32_minps512_mask", IX86_BUILTIN_MINPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_mulv8df3_mask_round, "__builtin_ia32_mulpd512_mask", IX86_BUILTIN_MULPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_mulv16sf3_mask_round, "__builtin_ia32_mulps512_mask", IX86_BUILTIN_MULPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rndscalev8df_mask_round, "__builtin_ia32_rndscalepd_mask", IX86_BUILTIN_RNDSCALEPD, UNKNOWN, (int) V8DF_FTYPE_V8DF_INT_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_rndscalev16sf_mask_round, "__builtin_ia32_rndscaleps_mask", IX86_BUILTIN_RNDSCALEPS, UNKNOWN, (int) V16SF_FTYPE_V16SF_INT_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_scalefv8df_mask_round, "__builtin_ia32_scalefpd512_mask", IX86_BUILTIN_SCALEFPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_scalefv16sf_mask_round, "__builtin_ia32_scalefps512_mask", IX86_BUILTIN_SCALEFPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sqrtv8df2_mask_round, "__builtin_ia32_sqrtpd512_mask", IX86_BUILTIN_SQRTPD512_MASK, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_sqrtv16sf2_mask_round, "__builtin_ia32_sqrtps512_mask", IX86_BUILTIN_SQRTPS512_MASK, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_subv8df3_mask_round, "__builtin_ia32_subpd512_mask", IX86_BUILTIN_SUBPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_subv16sf3_mask_round, "__builtin_ia32_subps512_mask", IX86_BUILTIN_SUBPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sse2_cvtsd2si_round, "__builtin_ia32_vcvtsd2si32", IX86_BUILTIN_VCVTSD2SI32, UNKNOWN, (int) INT_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_sse2_cvtsd2siq_round, "__builtin_ia32_vcvtsd2si64", IX86_BUILTIN_VCVTSD2SI64, UNKNOWN, (int) INT64_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vcvtsd2usi_round, "__builtin_ia32_vcvtsd2usi32", IX86_BUILTIN_VCVTSD2USI32, UNKNOWN, (int) UINT_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_avx512f_vcvtsd2usiq_round, "__builtin_ia32_vcvtsd2usi64", IX86_BUILTIN_VCVTSD2USI64, UNKNOWN, (int) UINT64_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sse_cvtss2si_round, "__builtin_ia32_vcvtss2si32", IX86_BUILTIN_VCVTSS2SI32, UNKNOWN, (int) INT_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_sse_cvtss2siq_round, "__builtin_ia32_vcvtss2si64", IX86_BUILTIN_VCVTSS2SI64, UNKNOWN, (int) INT64_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vcvtss2usi_round, "__builtin_ia32_vcvtss2usi32", IX86_BUILTIN_VCVTSS2USI32, UNKNOWN, (int) UINT_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_avx512f_vcvtss2usiq_round, "__builtin_ia32_vcvtss2usi64", IX86_BUILTIN_VCVTSS2USI64, UNKNOWN, (int) UINT64_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sse2_cvttsd2si_round, "__builtin_ia32_vcvttsd2si32", IX86_BUILTIN_VCVTTSD2SI32, UNKNOWN, (int) INT_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_sse2_cvttsd2siq_round, "__builtin_ia32_vcvttsd2si64", IX86_BUILTIN_VCVTTSD2SI64, UNKNOWN, (int) INT64_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vcvttsd2usi_round, "__builtin_ia32_vcvttsd2usi32", IX86_BUILTIN_VCVTTSD2USI32, UNKNOWN, (int) UINT_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_avx512f_vcvttsd2usiq_round, "__builtin_ia32_vcvttsd2usi64", IX86_BUILTIN_VCVTTSD2USI64, UNKNOWN, (int) UINT64_FTYPE_V2DF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_sse_cvttss2si_round, "__builtin_ia32_vcvttss2si32", IX86_BUILTIN_VCVTTSS2SI32, UNKNOWN, (int) INT_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_sse_cvttss2siq_round, "__builtin_ia32_vcvttss2si64", IX86_BUILTIN_VCVTTSS2SI64, UNKNOWN, (int) INT64_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_vcvttss2usi_round, "__builtin_ia32_vcvttss2usi32", IX86_BUILTIN_VCVTTSS2USI32, UNKNOWN, (int) UINT_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F | OPTION_MASK_ISA_64BIT, CODE_FOR_avx512f_vcvttss2usiq_round, "__builtin_ia32_vcvttss2usi64", IX86_BUILTIN_VCVTTSS2USI64, UNKNOWN, (int) UINT64_FTYPE_V4SF_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmadd_v8df_mask_round, "__builtin_ia32_vfmaddpd512_mask", IX86_BUILTIN_VFMADDPD512_MASK, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmadd_v8df_mask3_round, "__builtin_ia32_vfmaddpd512_mask3", IX86_BUILTIN_VFMADDPD512_MASK3, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmadd_v8df_maskz_round, "__builtin_ia32_vfmaddpd512_maskz", IX86_BUILTIN_VFMADDPD512_MASKZ, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmadd_v16sf_mask_round, "__builtin_ia32_vfmaddps512_mask", IX86_BUILTIN_VFMADDPS512_MASK, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmadd_v16sf_mask3_round, "__builtin_ia32_vfmaddps512_mask3", IX86_BUILTIN_VFMADDPS512_MASK3, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmadd_v16sf_maskz_round, "__builtin_ia32_vfmaddps512_maskz", IX86_BUILTIN_VFMADDPS512_MASKZ, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmaddsub_v8df_mask_round, "__builtin_ia32_vfmaddsubpd512_mask", IX86_BUILTIN_VFMADDSUBPD512_MASK, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmaddsub_v8df_mask3_round, "__builtin_ia32_vfmaddsubpd512_mask3", IX86_BUILTIN_VFMADDSUBPD512_MASK3, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmaddsub_v8df_maskz_round, "__builtin_ia32_vfmaddsubpd512_maskz", IX86_BUILTIN_VFMADDSUBPD512_MASKZ, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmaddsub_v16sf_mask_round, "__builtin_ia32_vfmaddsubps512_mask", IX86_BUILTIN_VFMADDSUBPS512_MASK, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmaddsub_v16sf_mask3_round, "__builtin_ia32_vfmaddsubps512_mask3", IX86_BUILTIN_VFMADDSUBPS512_MASK3, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmaddsub_v16sf_maskz_round, "__builtin_ia32_vfmaddsubps512_maskz", IX86_BUILTIN_VFMADDSUBPS512_MASKZ, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmsubadd_v8df_mask3_round, "__builtin_ia32_vfmsubaddpd512_mask3", IX86_BUILTIN_VFMSUBADDPD512_MASK3, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmsubadd_v16sf_mask3_round, "__builtin_ia32_vfmsubaddps512_mask3", IX86_BUILTIN_VFMSUBADDPS512_MASK3, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmsub_v8df_mask3_round, "__builtin_ia32_vfmsubpd512_mask3", IX86_BUILTIN_VFMSUBPD512_MASK3, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fmsub_v16sf_mask3_round, "__builtin_ia32_vfmsubps512_mask3", IX86_BUILTIN_VFMSUBPS512_MASK3, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fnmadd_v8df_mask_round, "__builtin_ia32_vfnmaddpd512_mask", IX86_BUILTIN_VFNMADDPD512_MASK, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fnmadd_v16sf_mask_round, "__builtin_ia32_vfnmaddps512_mask", IX86_BUILTIN_VFNMADDPS512_MASK, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fnmsub_v8df_mask_round, "__builtin_ia32_vfnmsubpd512_mask", IX86_BUILTIN_VFNMSUBPD512_MASK, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fnmsub_v8df_mask3_round, "__builtin_ia32_vfnmsubpd512_mask3", IX86_BUILTIN_VFNMSUBPD512_MASK3, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fnmsub_v16sf_mask_round, "__builtin_ia32_vfnmsubps512_mask", IX86_BUILTIN_VFNMSUBPS512_MASK, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512F, CODE_FOR_avx512f_fnmsub_v16sf_mask3_round, "__builtin_ia32_vfnmsubps512_mask3", IX86_BUILTIN_VFNMSUBPS512_MASK3, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT },
+
+ /* AVX512ER */
+ { OPTION_MASK_ISA_AVX512ER, CODE_FOR_avx512er_exp2v8df_mask_round, "__builtin_ia32_exp2pd_mask", IX86_BUILTIN_EXP2PD_MASK, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512ER, CODE_FOR_avx512er_exp2v16sf_mask_round, "__builtin_ia32_exp2ps_mask", IX86_BUILTIN_EXP2PS_MASK, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512ER, CODE_FOR_avx512er_rcp28v8df_mask_round, "__builtin_ia32_rcp28pd_mask", IX86_BUILTIN_RCP28PD, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512ER, CODE_FOR_avx512er_rcp28v16sf_mask_round, "__builtin_ia32_rcp28ps_mask", IX86_BUILTIN_RCP28PS, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI_INT },
+ { OPTION_MASK_ISA_AVX512ER, CODE_FOR_avx512er_rsqrt28v8df_mask_round, "__builtin_ia32_rsqrt28pd_mask", IX86_BUILTIN_RSQRT28PD, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_QI_INT },
+ { OPTION_MASK_ISA_AVX512ER, CODE_FOR_avx512er_rsqrt28v16sf_mask_round, "__builtin_ia32_rsqrt28ps_mask", IX86_BUILTIN_RSQRT28PS, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_HI_INT },
};
/* FMA4 and XOP. */
@@ -29794,6 +30487,18 @@ ix86_init_mmx_sse_builtins (void)
def_builtin_const (d->mask, d->name, ftype, d->code);
}
+ /* Add all builtins with rounding. */
+ for (i = 0, d = bdesc_round_args;
+ i < ARRAY_SIZE (bdesc_round_args);
+ i++, d++)
+ {
+ if (d->name == 0)
+ continue;
+
+ ftype = (enum ix86_builtin_func_type) d->flag;
+ def_builtin_const (d->mask, d->name, ftype, d->code);
+ }
+
/* pcmpestr[im] insns. */
for (i = 0, d = bdesc_pcmpestr;
i < ARRAY_SIZE (bdesc_pcmpestr);
@@ -29962,6 +30667,101 @@ ix86_init_mmx_sse_builtins (void)
V8SI_FTYPE_V8SI_PCINT_V4DI_V8SI_INT,
IX86_BUILTIN_GATHERALTDIV8SI);
+ /* AVX512F */
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gathersiv16sf",
+ V16SF_FTYPE_V16SF_PCFLOAT_V16SI_HI_INT,
+ IX86_BUILTIN_GATHER3SIV16SF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gathersiv8df",
+ V8DF_FTYPE_V8DF_PCDOUBLE_V8SI_QI_INT,
+ IX86_BUILTIN_GATHER3SIV8DF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatherdiv16sf",
+ V8SF_FTYPE_V8SF_PCFLOAT_V8DI_QI_INT,
+ IX86_BUILTIN_GATHER3DIV16SF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatherdiv8df",
+ V8DF_FTYPE_V8DF_PCDOUBLE_V8DI_QI_INT,
+ IX86_BUILTIN_GATHER3DIV8DF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gathersiv16si",
+ V16SI_FTYPE_V16SI_PCINT_V16SI_HI_INT,
+ IX86_BUILTIN_GATHER3SIV16SI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gathersiv8di",
+ V8DI_FTYPE_V8DI_PCINT64_V8SI_QI_INT,
+ IX86_BUILTIN_GATHER3SIV8DI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatherdiv16si",
+ V8SI_FTYPE_V8SI_PCINT_V8DI_QI_INT,
+ IX86_BUILTIN_GATHER3DIV16SI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatherdiv8di",
+ V8DI_FTYPE_V8DI_PCINT64_V8DI_QI_INT,
+ IX86_BUILTIN_GATHER3DIV8DI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatheraltsiv8df ",
+ V8DF_FTYPE_V8DF_PCDOUBLE_V16SI_QI_INT,
+ IX86_BUILTIN_GATHER3ALTSIV8DF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatheraltdiv8sf ",
+ V16SF_FTYPE_V16SF_PCFLOAT_V8DI_HI_INT,
+ IX86_BUILTIN_GATHER3ALTDIV16SF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatheraltsiv8di ",
+ V8DI_FTYPE_V8DI_PCINT64_V16SI_QI_INT,
+ IX86_BUILTIN_GATHER3ALTSIV8DI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_gatheraltdiv8si ",
+ V16SI_FTYPE_V16SI_PCINT_V8DI_HI_INT,
+ IX86_BUILTIN_GATHER3ALTDIV16SI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scattersiv16sf",
+ VOID_FTYPE_PFLOAT_HI_V16SI_V16SF_INT,
+ IX86_BUILTIN_SCATTERSIV16SF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scattersiv8df",
+ VOID_FTYPE_PDOUBLE_QI_V8SI_V8DF_INT,
+ IX86_BUILTIN_SCATTERSIV8DF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scatterdiv16sf",
+ VOID_FTYPE_PFLOAT_QI_V8DI_V8SF_INT,
+ IX86_BUILTIN_SCATTERDIV16SF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scatterdiv8df",
+ VOID_FTYPE_PDOUBLE_QI_V8DI_V8DF_INT,
+ IX86_BUILTIN_SCATTERDIV8DF);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scattersiv16si",
+ VOID_FTYPE_PINT_HI_V16SI_V16SI_INT,
+ IX86_BUILTIN_SCATTERSIV16SI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scattersiv8di",
+ VOID_FTYPE_PLONGLONG_QI_V8SI_V8DI_INT,
+ IX86_BUILTIN_SCATTERSIV8DI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scatterdiv16si",
+ VOID_FTYPE_PINT_QI_V8DI_V8SI_INT,
+ IX86_BUILTIN_SCATTERDIV16SI);
+
+ def_builtin (OPTION_MASK_ISA_AVX512F, "__builtin_ia32_scatterdiv8di",
+ VOID_FTYPE_PLONGLONG_QI_V8DI_V8DI_INT,
+ IX86_BUILTIN_SCATTERDIV8DI);
+
+ /* AVX512PF */
+ def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_gatherpfdps",
+ VOID_FTYPE_HI_V16SI_PCINT_INT_INT,
+ IX86_BUILTIN_GATHERPFDPS);
+ def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_gatherpfqps",
+ VOID_FTYPE_QI_V8DI_PCINT_INT_INT,
+ IX86_BUILTIN_GATHERPFQPS);
+ def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_scatterpfdps",
+ VOID_FTYPE_HI_V16SI_PCINT_INT_INT,
+ IX86_BUILTIN_SCATTERPFDPS);
+ def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_scatterpfqps",
+ VOID_FTYPE_QI_V8DI_PCINT_INT_INT,
+ IX86_BUILTIN_SCATTERPFQPS);
+
/* RTM. */
def_builtin (OPTION_MASK_ISA_RTM, "__builtin_ia32_xabort",
VOID_FTYPE_UNSIGNED, IX86_BUILTIN_XABORT);
@@ -32364,12 +33164,13 @@ ix86_expand_args_builtin (const struct builtin_description *d,
rtx pat, real_target;
unsigned int i, nargs;
unsigned int nargs_constant = 0;
+ unsigned int mask_pos = 0;
int num_memory = 0;
struct
{
rtx op;
enum machine_mode mode;
- } args[4];
+ } args[6];
bool last_arg_count = false;
enum insn_code icode = d->icode;
const struct insn_data_d *insn_p = &insn_data[icode];
@@ -32389,6 +33190,7 @@ ix86_expand_args_builtin (const struct builtin_description *d,
return ix86_expand_sse_round (d, exp, target);
case V4SI_FTYPE_V2DF_V2DF_ROUND:
case V8SI_FTYPE_V4DF_V4DF_ROUND:
+ case V16SI_FTYPE_V8DF_V8DF_ROUND:
return ix86_expand_sse_round_vec_pack_sfix (d, exp, target);
case INT_FTYPE_V8SF_V8SF_PTEST:
case INT_FTYPE_V4DI_V4DI_PTEST:
@@ -32467,6 +33269,32 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V4DI_FTYPE_V8HI:
case V4DI_FTYPE_V4SI:
case V4DI_FTYPE_V2DI:
+ case HI_FTYPE_HI:
+ case UINT_FTYPE_V2DF:
+ case UINT_FTYPE_V4SF:
+ case UINT64_FTYPE_V2DF:
+ case UINT64_FTYPE_V4SF:
+ case V16QI_FTYPE_V8DI:
+ case V16HI_FTYPE_V16SI:
+ case V16SI_FTYPE_HI:
+ case V16SI_FTYPE_V16SI:
+ case V16SI_FTYPE_INT:
+ case V16SF_FTYPE_FLOAT:
+ case V16SF_FTYPE_V4SF:
+ case V16SF_FTYPE_V16SF:
+ case V8HI_FTYPE_V8DI:
+ case V8UHI_FTYPE_V8UHI:
+ case V8SI_FTYPE_V8DI:
+ case V8USI_FTYPE_V8USI:
+ case V8SF_FTYPE_V8DF:
+ case V8DI_FTYPE_QI:
+ case V8DI_FTYPE_INT64:
+ case V8DI_FTYPE_V4DI:
+ case V8DI_FTYPE_V8DI:
+ case V8DF_FTYPE_DOUBLE:
+ case V8DF_FTYPE_V4DF:
+ case V8DF_FTYPE_V8DF:
+ case V8DF_FTYPE_V8SI:
nargs = 1;
break;
case V4SF_FTYPE_V4SF_VEC_MERGE:
@@ -32475,6 +33303,9 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case FLOAT128_FTYPE_FLOAT128_FLOAT128:
case V16QI_FTYPE_V16QI_V16QI:
case V16QI_FTYPE_V8HI_V8HI:
+ case V16SI_FTYPE_V16SI_V16SI:
+ case V16SF_FTYPE_V16SF_V16SF:
+ case V16SF_FTYPE_V16SF_V16SI:
case V8QI_FTYPE_V8QI_V8QI:
case V8QI_FTYPE_V4HI_V4HI:
case V8HI_FTYPE_V8HI_V8HI:
@@ -32482,6 +33313,9 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V8HI_FTYPE_V4SI_V4SI:
case V8SF_FTYPE_V8SF_V8SF:
case V8SF_FTYPE_V8SF_V8SI:
+ case V8DI_FTYPE_V8DI_V8DI:
+ case V8DF_FTYPE_V8DF_V8DF:
+ case V8DF_FTYPE_V8DF_V8DI:
case V4SI_FTYPE_V4SI_V4SI:
case V4SI_FTYPE_V8HI_V8HI:
case V4SI_FTYPE_V4SF_V4SF:
@@ -32495,6 +33329,8 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V4SF_FTYPE_V4SF_V4SI:
case V4SF_FTYPE_V4SF_V2SI:
case V4SF_FTYPE_V4SF_V2DF:
+ case V4SF_FTYPE_V4SF_UINT:
+ case V4SF_FTYPE_V4SF_UINT64:
case V4SF_FTYPE_V4SF_DI:
case V4SF_FTYPE_V4SF_SI:
case V2DI_FTYPE_V2DI_V2DI:
@@ -32511,6 +33347,8 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V2DF_FTYPE_V2DF_V2DI:
case V2DF_FTYPE_V2DF_DI:
case V2DF_FTYPE_V2DF_SI:
+ case V2DF_FTYPE_V2DF_UINT:
+ case V2DF_FTYPE_V2DF_UINT64:
case V2SF_FTYPE_V2SF_V2SF:
case V1DI_FTYPE_V1DI_V1DI:
case V1DI_FTYPE_V8QI_V8QI:
@@ -32526,6 +33364,8 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V4DI_FTYPE_V4DI_V4DI:
case V4DI_FTYPE_V8SI_V8SI:
case V4UDI_FTYPE_V8USI_V8USI:
+ case QI_FTYPE_V8DI_V8DI:
+ case HI_FTYPE_V16SI_V16SI:
if (comparison == UNKNOWN)
return ix86_expand_binop_builtin (icode, exp, target);
nargs = 2;
@@ -32563,6 +33403,8 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case UINT_FTYPE_UINT_UCHAR:
case UINT16_FTYPE_UINT16_INT:
case UINT8_FTYPE_UINT8_INT:
+ case HI_FTYPE_HI_HI:
+ case V16SI_FTYPE_V8DF_V8DF:
nargs = 2;
break;
case V2DI_FTYPE_V2DI_INT_CONVERT:
@@ -32577,12 +33419,16 @@ ix86_expand_args_builtin (const struct builtin_description *d,
break;
case V8HI_FTYPE_V8HI_INT:
case V8HI_FTYPE_V8SF_INT:
+ case V16HI_FTYPE_V16SF_INT:
case V8HI_FTYPE_V4SF_INT:
case V8SF_FTYPE_V8SF_INT:
+ case V4SF_FTYPE_V16SF_INT:
+ case V16SF_FTYPE_V16SF_INT:
case V4SI_FTYPE_V4SI_INT:
case V4SI_FTYPE_V8SI_INT:
case V4HI_FTYPE_V4HI_INT:
case V4DF_FTYPE_V4DF_INT:
+ case V4DF_FTYPE_V8DF_INT:
case V4SF_FTYPE_V4SF_INT:
case V4SF_FTYPE_V8SF_INT:
case V2DI_FTYPE_V2DI_INT:
@@ -32590,8 +33436,12 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V2DF_FTYPE_V4DF_INT:
case V16HI_FTYPE_V16HI_INT:
case V8SI_FTYPE_V8SI_INT:
+ case V16SI_FTYPE_V16SI_INT:
+ case V4SI_FTYPE_V16SI_INT:
case V4DI_FTYPE_V4DI_INT:
case V2DI_FTYPE_V4DI_INT:
+ case V4DI_FTYPE_V8DI_INT:
+ case HI_FTYPE_HI_INT:
nargs = 2;
nargs_constant = 1;
break;
@@ -32601,6 +33451,46 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V4SF_FTYPE_V4SF_V4SF_V4SF:
case V2DF_FTYPE_V2DF_V2DF_V2DF:
case V32QI_FTYPE_V32QI_V32QI_V32QI:
+ case HI_FTYPE_V16SI_V16SI_HI:
+ case QI_FTYPE_V8DI_V8DI_QI:
+ case V16HI_FTYPE_V16SI_V16HI_HI:
+ case V16QI_FTYPE_V16SI_V16QI_HI:
+ case V16QI_FTYPE_V8DI_V16QI_QI:
+ case V16SF_FTYPE_V16SF_V16SF_HI:
+ case V16SF_FTYPE_V16SF_V16SF_V16SF:
+ case V16SF_FTYPE_V16SF_V16SI_V16SF:
+ case V16SF_FTYPE_V16SI_V16SF_HI:
+ case V16SF_FTYPE_V16SI_V16SF_V16SF:
+ case V16SF_FTYPE_V4SF_V16SF_HI:
+ case V16SI_FTYPE_SI_V16SI_HI:
+ case V16SI_FTYPE_V16HI_V16SI_HI:
+ case V16SI_FTYPE_V16QI_V16SI_HI:
+ case V16SI_FTYPE_V16SF_V16SI_HI:
+ case V16SI_FTYPE_V16SI_V16SI_HI:
+ case V16SI_FTYPE_V16SI_V16SI_V16SI:
+ case V16SI_FTYPE_V4SI_V16SI_HI:
+ case V2DI_FTYPE_V2DI_V2DI_V2DI:
+ case V4DI_FTYPE_V4DI_V4DI_V4DI:
+ case V8DF_FTYPE_V2DF_V8DF_QI:
+ case V8DF_FTYPE_V4DF_V8DF_QI:
+ case V8DF_FTYPE_V8DF_V8DF_QI:
+ case V8DF_FTYPE_V8DF_V8DF_V8DF:
+ case V8DF_FTYPE_V8DF_V8DI_V8DF:
+ case V8DF_FTYPE_V8DI_V8DF_V8DF:
+ case V8DF_FTYPE_V8SF_V8DF_QI:
+ case V8DF_FTYPE_V8SI_V8DF_QI:
+ case V8DI_FTYPE_DI_V8DI_QI:
+ case V8DI_FTYPE_V16QI_V8DI_QI:
+ case V8DI_FTYPE_V2DI_V8DI_QI:
+ case V8DI_FTYPE_V4DI_V8DI_QI:
+ case V8DI_FTYPE_V8DI_V8DI_QI:
+ case V8DI_FTYPE_V8DI_V8DI_V8DI:
+ case V8DI_FTYPE_V8HI_V8DI_QI:
+ case V8DI_FTYPE_V8SI_V8DI_QI:
+ case V8HI_FTYPE_V8DI_V8HI_QI:
+ case V8SF_FTYPE_V8DF_V8SF_QI:
+ case V8SI_FTYPE_V8DF_V8SI_QI:
+ case V8SI_FTYPE_V8DI_V8SI_QI:
nargs = 3;
break;
case V32QI_FTYPE_V32QI_V32QI_INT:
@@ -32614,11 +33504,20 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case V8SF_FTYPE_V8SF_V4SF_INT:
case V4SI_FTYPE_V4SI_V4SI_INT:
case V4DF_FTYPE_V4DF_V4DF_INT:
+ case V16SF_FTYPE_V16SF_V16SF_INT:
+ case V16SF_FTYPE_V16SF_V4SF_INT:
+ case V16SI_FTYPE_V16SI_V4SI_INT:
case V4DF_FTYPE_V4DF_V2DF_INT:
case V4SF_FTYPE_V4SF_V4SF_INT:
case V2DI_FTYPE_V2DI_V2DI_INT:
case V4DI_FTYPE_V4DI_V2DI_INT:
case V2DF_FTYPE_V2DF_V2DF_INT:
+ case QI_FTYPE_V8DI_V8DI_INT:
+ case QI_FTYPE_V8DF_V8DF_INT:
+ case QI_FTYPE_V2DF_V2DF_INT:
+ case QI_FTYPE_V4SF_V4SF_INT:
+ case HI_FTYPE_V16SI_V16SI_INT:
+ case HI_FTYPE_V16SF_V16SF_INT:
nargs = 3;
nargs_constant = 1;
break;
@@ -32641,11 +33540,36 @@ ix86_expand_args_builtin (const struct builtin_description *d,
nargs = 3;
nargs_constant = 2;
break;
+ case V16SF_FTYPE_V16SF_V16SF_V16SF_HI:
+ case V16SF_FTYPE_V16SF_V16SI_V16SF_HI:
+ case V16SF_FTYPE_V16SI_V16SF_V16SF_HI:
+ case V16SI_FTYPE_V16SI_V16SI_V16SI_HI:
+ case V16SI_FTYPE_V16SI_V4SI_V16SI_HI:
+ case V2DF_FTYPE_V2DF_V2DF_V2DF_QI:
+ case V2DF_FTYPE_V2DF_V4SF_V2DF_QI:
+ case V4SF_FTYPE_V4SF_V2DF_V4SF_QI:
+ case V4SF_FTYPE_V4SF_V4SF_V4SF_QI:
+ case V8DF_FTYPE_V8DF_V8DF_V8DF_QI:
+ case V8DF_FTYPE_V8DF_V8DI_V8DF_QI:
+ case V8DF_FTYPE_V8DI_V8DF_V8DF_QI:
+ case V8DI_FTYPE_V16SI_V16SI_V8DI_QI:
+ case V8DI_FTYPE_V8DI_SI_V8DI_V8DI:
+ case V8DI_FTYPE_V8DI_V2DI_V8DI_QI:
+ case V8DI_FTYPE_V8DI_V8DI_V8DI_QI:
+ nargs = 4;
+ break;
case V2DF_FTYPE_V2DF_V2DF_V2DI_INT:
case V4DF_FTYPE_V4DF_V4DF_V4DI_INT:
case V4SF_FTYPE_V4SF_V4SF_V4SI_INT:
case V8SF_FTYPE_V8SF_V8SF_V8SI_INT:
+ case V16SF_FTYPE_V16SF_V16SF_V16SI_INT:
+ nargs = 4;
+ nargs_constant = 1;
+ break;
+ case QI_FTYPE_V2DF_V2DF_INT_QI:
+ case QI_FTYPE_V4SF_V4SF_INT_QI:
nargs = 4;
+ mask_pos = 1;
nargs_constant = 1;
break;
case V2DI_FTYPE_V2DI_V2DI_UINT_UINT:
@@ -32656,6 +33580,51 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case UCHAR_FTYPE_UCHAR_ULONGLONG_ULONGLONG_PULONGLONG:
nargs = 4;
break;
+ case QI_FTYPE_V8DI_V8DI_INT_QI:
+ case HI_FTYPE_V16SI_V16SI_INT_HI:
+ case QI_FTYPE_V8DF_V8DF_INT_QI:
+ case HI_FTYPE_V16SF_V16SF_INT_HI:
+ mask_pos = 1;
+ nargs = 4;
+ nargs_constant = 1;
+ break;
+ case V8DF_FTYPE_V8DF_INT_V8DF_QI:
+ case V16SF_FTYPE_V16SF_INT_V16SF_HI:
+ case V16HI_FTYPE_V16SF_INT_V16HI_HI:
+ case V16SI_FTYPE_V16SI_INT_V16SI_HI:
+ case V4SI_FTYPE_V16SI_INT_V4SI_QI:
+ case V4DI_FTYPE_V8DI_INT_V4DI_QI:
+ case V4DF_FTYPE_V8DF_INT_V4DF_QI:
+ case V4SF_FTYPE_V16SF_INT_V4SF_QI:
+ case V8DI_FTYPE_V8DI_INT_V8DI_QI:
+ nargs = 4;
+ mask_pos = 2;
+ nargs_constant = 1;
+ break;
+ case V16SF_FTYPE_V16SF_V4SF_INT_V16SF_HI:
+ case V16SI_FTYPE_V16SI_V4SI_INT_V16SI_HI:
+ case V8DF_FTYPE_V8DF_V8DF_INT_V8DF_QI:
+ case V8DI_FTYPE_V8DI_V8DI_INT_V8DI_QI:
+ case V16SF_FTYPE_V16SF_V16SF_INT_V16SF_HI:
+ case V16SI_FTYPE_V16SI_V16SI_INT_V16SI_HI:
+ case V4SF_FTYPE_V4SF_V4SF_INT_V4SF_QI:
+ case V2DF_FTYPE_V2DF_V2DF_INT_V2DF_QI:
+ case V8DF_FTYPE_V8DF_V4DF_INT_V8DF_QI:
+ case V8DI_FTYPE_V8DI_V4DI_INT_V8DI_QI:
+ nargs = 5;
+ mask_pos = 2;
+ nargs_constant = 1;
+ break;
+ case V8DI_FTYPE_V8DI_V8DI_V8DI_INT_QI:
+ case V16SF_FTYPE_V16SF_V16SF_V16SI_INT_HI:
+ case V16SI_FTYPE_V16SI_V16SI_V16SI_INT_HI:
+ case V2DF_FTYPE_V2DF_V2DF_V2DI_INT_QI:
+ case V4SF_FTYPE_V4SF_V4SF_V4SI_INT_QI:
+ nargs = 5;
+ mask_pos = 1;
+ nargs_constant = 1;
+ break;
+
default:
gcc_unreachable ();
}
@@ -32702,7 +33671,8 @@ ix86_expand_args_builtin (const struct builtin_description *d,
op = copy_to_reg (op);
}
}
- else if ((nargs - i) <= nargs_constant)
+ else if ((mask_pos && (nargs - i - mask_pos) == nargs_constant) ||
+ (!mask_pos && (nargs - i) <= nargs_constant))
{
if (!match)
switch (icode)
@@ -32712,6 +33682,13 @@ ix86_expand_args_builtin (const struct builtin_description *d,
error ("the last argument must be an 1-bit immediate");
return const0_rtx;
+ case CODE_FOR_avx512f_cmpv8di3_mask:
+ case CODE_FOR_avx512f_cmpv16si3_mask:
+ case CODE_FOR_avx512f_ucmpv8di3_mask:
+ case CODE_FOR_avx512f_ucmpv16si3_mask:
+ error ("the last argument must be a 3-bit immediate");
+ return const0_rtx;
+
case CODE_FOR_sse4_1_roundsd:
case CODE_FOR_sse4_1_roundss:
@@ -32728,6 +33705,8 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case CODE_FOR_sse4_1_blendps:
case CODE_FOR_avx_blendpd256:
case CODE_FOR_avx_vpermilv4df:
+ case CODE_FOR_avx512f_getmantv8df_mask:
+ case CODE_FOR_avx512f_getmantv16sf_mask:
error ("the last argument must be a 4-bit immediate");
return const0_rtx;
@@ -32737,6 +33716,10 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case CODE_FOR_xop_vpermil2v4sf3:
case CODE_FOR_xop_vpermil2v4df3:
case CODE_FOR_xop_vpermil2v8sf3:
+ case CODE_FOR_avx512f_vinsertf32x4_mask:
+ case CODE_FOR_avx512f_vinserti32x4_mask:
+ case CODE_FOR_avx512f_vextractf32x4_mask:
+ case CODE_FOR_avx512f_vextracti32x4_mask:
error ("the last argument must be a 2-bit immediate");
return const0_rtx;
@@ -32746,6 +33729,10 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case CODE_FOR_avx_vinsertf128v4df:
case CODE_FOR_avx_vinsertf128v8sf:
case CODE_FOR_avx_vinsertf128v8si:
+ case CODE_FOR_avx512f_vinsertf64x4_mask:
+ case CODE_FOR_avx512f_vinserti64x4_mask:
+ case CODE_FOR_avx512f_vextractf64x4_mask:
+ case CODE_FOR_avx512f_vextracti64x4_mask:
error ("the last argument must be a 1-bit immediate");
return const0_rtx;
@@ -32755,14 +33742,19 @@ ix86_expand_args_builtin (const struct builtin_description *d,
case CODE_FOR_avx_cmpv4sf3:
case CODE_FOR_avx_cmpv4df3:
case CODE_FOR_avx_cmpv8sf3:
+ case CODE_FOR_avx512f_cmpv8df3_mask:
+ case CODE_FOR_avx512f_cmpv16sf3_mask:
+ case CODE_FOR_avx512f_vmcmpv2df3_mask:
+ case CODE_FOR_avx512f_vmcmpv4sf3_mask:
error ("the last argument must be a 5-bit immediate");
return const0_rtx;
- default:
+ default:
switch (nargs_constant)
{
case 2:
- if ((nargs - i) == nargs_constant)
+ if ((mask_pos && (nargs - i - mask_pos) == nargs_constant) ||
+ (!mask_pos && (nargs - i) == nargs_constant))
{
error ("the next to last argument must be an 8-bit immediate");
break;
@@ -32818,6 +33810,14 @@ ix86_expand_args_builtin (const struct builtin_description *d,
pat = GEN_FCN (icode) (real_target, args[0].op, args[1].op,
args[2].op, args[3].op);
break;
+ case 5:
+ pat = GEN_FCN (icode) (real_target, args[0].op, args[1].op,
+ args[2].op, args[3].op, args[4].op);
+ case 6:
+ pat = GEN_FCN (icode) (real_target, args[0].op, args[1].op,
+ args[2].op, args[3].op, args[4].op,
+ args[5].op);
+ break;
default:
gcc_unreachable ();
}
@@ -32829,6 +33829,363 @@ ix86_expand_args_builtin (const struct builtin_description *d,
return target;
}
+/* Transform pattern of following layout:
+ (parallel [
+ set (A B)
+ (unspec [C] UNSPEC_EMBEDDED_ROUNDING)])
+ ])
+ into:
+ (set (A B))
+
+ Or:
+ (parallel [ A B
+ ...
+ (unspec [C] UNSPEC_EMBEDDED_ROUNDING)
+ ...
+ ])
+ into:
+ (parallel [ A B ... ]) */
+
+static rtx
+ix86_erase_embedded_rounding (rtx pat)
+{
+ if (GET_CODE (pat) == INSN)
+ pat = PATTERN (pat);
+
+ gcc_assert (GET_CODE (pat) == PARALLEL);
+
+ if (XVECLEN (pat, 0) == 2)
+ {
+ rtx p0 = XVECEXP (pat, 0, 0);
+ rtx p1 = XVECEXP (pat, 0, 1);
+
+ gcc_assert (GET_CODE (p0) == SET
+ && GET_CODE (p1) == UNSPEC
+ && XINT (p1, 1) == UNSPEC_EMBEDDED_ROUNDING);
+
+ return p0;
+ }
+ else
+ {
+ rtx *res = XALLOCAVEC (rtx, XVECLEN (pat, 0));
+ int i = 0;
+ int j = 0;
+
+ for (; i < XVECLEN (pat, 0); ++i)
+ {
+ rtx elem = XVECEXP (pat, 0, i);
+ if (GET_CODE (elem) != UNSPEC
+ || XINT (elem, 1) != UNSPEC_EMBEDDED_ROUNDING)
+ res [j++] = elem;
+ }
+
+ /* No more than 1 occurence was removed. */
+ gcc_assert (j >= XVECLEN (pat, 0) - 1);
+
+ return gen_rtx_PARALLEL (GET_MODE (pat), gen_rtvec_v (j, res));
+ }
+}
+
+/* Subroutine of ix86_expand_round_builtin to take care of comi insns
+ with rounding. */
+static rtx
+ix86_expand_sse_comi_round (const struct builtin_description *d,
+ tree exp, rtx target)
+{
+ rtx pat, set_dst;
+ tree arg0 = CALL_EXPR_ARG (exp, 0);
+ tree arg1 = CALL_EXPR_ARG (exp, 1);
+ tree arg2 = CALL_EXPR_ARG (exp, 2);
+ tree arg3 = CALL_EXPR_ARG (exp, 3);
+ rtx op0 = expand_normal (arg0);
+ rtx op1 = expand_normal (arg1);
+ rtx op2 = expand_normal (arg2);
+ rtx op3 = expand_normal (arg3);
+ enum insn_code icode = d->icode;
+ const struct insn_data_d *insn_p = &insn_data[icode];
+ enum machine_mode mode0 = insn_p->operand[0].mode;
+ enum machine_mode mode1 = insn_p->operand[1].mode;
+ enum rtx_code comparison = UNEQ;
+ bool need_ucomi = false;
+
+ /* See avxintrin.h for values. */
+ enum rtx_code comi_comparisons[32] =
+ {
+ UNEQ, GT, GE, UNORDERED, LTGT, UNLE, UNLT, ORDERED, UNEQ, UNLT,
+ UNLE, LT, LTGT, GE, GT, LT, UNEQ, GT, GE, UNORDERED, LTGT, UNLE,
+ UNLT, ORDERED, UNEQ, UNLT, UNLE, LT, LTGT, GE, GT, LT
+ };
+ bool need_ucomi_values[32] =
+ {
+ true, false, false, true, true, false, false, true,
+ true, false, false, true, true, false, false, true,
+ false, true, true, false, false, true, true, false,
+ false, true, true, false, false, true, true, false
+ };
+
+ if (!CONST_INT_P (op2))
+ {
+ error ("the third argument must be comparison constant");
+ return const0_rtx;
+ }
+ if (INTVAL (op2) < 0 || INTVAL (op2) >= 32)
+ {
+ error ("incorect comparison mode");
+ return const0_rtx;
+ }
+
+ if (!insn_p->operand[2].predicate (op3, SImode))
+ {
+ error ("incorrect rounding operand");
+ return const0_rtx;
+ }
+
+ comparison = comi_comparisons[INTVAL (op2)];
+ need_ucomi = need_ucomi_values[INTVAL (op2)];
+
+ if (VECTOR_MODE_P (mode0))
+ op0 = safe_vector_operand (op0, mode0);
+ if (VECTOR_MODE_P (mode1))
+ op1 = safe_vector_operand (op1, mode1);
+
+ target = gen_reg_rtx (SImode);
+ emit_move_insn (target, const0_rtx);
+ target = gen_rtx_SUBREG (QImode, target, 0);
+
+ if ((optimize && !register_operand (op0, mode0))
+ || !insn_p->operand[0].predicate (op0, mode0))
+ op0 = copy_to_mode_reg (mode0, op0);
+ if ((optimize && !register_operand (op1, mode1))
+ || !insn_p->operand[1].predicate (op1, mode1))
+ op1 = copy_to_mode_reg (mode1, op1);
+
+ if (need_ucomi)
+ icode = icode == CODE_FOR_sse_comi_round
+ ? CODE_FOR_sse_ucomi_round
+ : CODE_FOR_sse2_ucomi_round;
+
+ pat = GEN_FCN (icode) (op0, op1, op3);
+ if (! pat)
+ return 0;
+
+ /* Rounding operand can be either NO_ROUND or ROUND_SAE at this point. */
+ if (INTVAL (op3) == NO_ROUND)
+ {
+ pat = ix86_erase_embedded_rounding (pat);
+ if (! pat)
+ return 0;
+
+ set_dst = SET_DEST (pat);
+ }
+ else
+ {
+ gcc_assert (GET_CODE (XVECEXP (pat, 0, 0)) == SET);
+ set_dst = SET_DEST (XVECEXP (pat, 0, 0));
+ }
+
+ emit_insn (pat);
+ emit_insn (gen_rtx_SET (VOIDmode,
+ gen_rtx_STRICT_LOW_PART (VOIDmode, target),
+ gen_rtx_fmt_ee (comparison, QImode,
+ set_dst,
+ const0_rtx)));
+
+ return SUBREG_REG (target);
+}
+
+static rtx
+ix86_expand_round_builtin (const struct builtin_description *d,
+ tree exp, rtx target)
+{
+ rtx pat;
+ unsigned int i, nargs;
+ struct
+ {
+ rtx op;
+ enum machine_mode mode;
+ } args[6];
+ enum insn_code icode = d->icode;
+ const struct insn_data_d *insn_p = &insn_data[icode];
+ enum machine_mode tmode = insn_p->operand[0].mode;
+ unsigned int nargs_constant = 0;
+ unsigned int redundant_embed_rnd = 0;
+
+ switch ((enum ix86_builtin_func_type) d->flag)
+ {
+ case UINT64_FTYPE_V2DF_INT:
+ case UINT64_FTYPE_V4SF_INT:
+ case UINT_FTYPE_V2DF_INT:
+ case UINT_FTYPE_V4SF_INT:
+ case INT64_FTYPE_V2DF_INT:
+ case INT64_FTYPE_V4SF_INT:
+ case INT_FTYPE_V2DF_INT:
+ case INT_FTYPE_V4SF_INT:
+ nargs = 2;
+ break;
+ case V4SF_FTYPE_V4SF_UINT_INT:
+ case V4SF_FTYPE_V4SF_UINT64_INT:
+ case V2DF_FTYPE_V2DF_UINT64_INT:
+ case V4SF_FTYPE_V4SF_INT_INT:
+ case V4SF_FTYPE_V4SF_INT64_INT:
+ case V2DF_FTYPE_V2DF_INT64_INT:
+ nargs = 3;
+ break;
+ case V8SF_FTYPE_V8DF_V8SF_QI_INT:
+ case V8DF_FTYPE_V8DF_V8DF_QI_INT:
+ case V8SI_FTYPE_V8DF_V8SI_QI_INT:
+ case V16SF_FTYPE_V16SF_V16SF_HI_INT:
+ case V16SF_FTYPE_V16SI_V16SF_HI_INT:
+ case V16SI_FTYPE_V16SF_V16SI_HI_INT:
+ case V8DF_FTYPE_V8SF_V8DF_QI_INT:
+ case V16SF_FTYPE_V16HI_V16SF_HI_INT:
+ nargs = 4;
+ break;
+ case INT_FTYPE_V4SF_V4SF_INT_INT:
+ case INT_FTYPE_V2DF_V2DF_INT_INT:
+ return ix86_expand_sse_comi_round (d, exp, target);
+ case V8DF_FTYPE_V8DF_V8DF_V8DF_QI_INT:
+ case V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT:
+ case V2DF_FTYPE_V2DF_V2DF_V2DF_QI_INT:
+ case V2DF_FTYPE_V2DF_V4SF_V2DF_QI_INT:
+ case V4SF_FTYPE_V4SF_V4SF_V4SF_QI_INT:
+ case V4SF_FTYPE_V4SF_V2DF_V4SF_QI_INT:
+ nargs = 5;
+ break;
+ case V16SF_FTYPE_V16SF_INT_V16SF_HI_INT:
+ case V8DF_FTYPE_V8DF_INT_V8DF_QI_INT:
+ nargs_constant = 4;
+ nargs = 5;
+ break;
+ case QI_FTYPE_V8DF_V8DF_INT_QI_INT:
+ case QI_FTYPE_V2DF_V2DF_INT_QI_INT:
+ case HI_FTYPE_V16SF_V16SF_INT_HI_INT:
+ case QI_FTYPE_V4SF_V4SF_INT_QI_INT:
+ nargs_constant = 3;
+ nargs = 5;
+ break;
+ case V4SF_FTYPE_V4SF_V4SF_INT_V4SF_QI_INT:
+ case V2DF_FTYPE_V2DF_V2DF_INT_V2DF_QI_INT:
+ nargs = 6;
+ nargs_constant = 4;
+ break;
+ case V8DF_FTYPE_V8DF_V8DF_V8DI_INT_QI_INT:
+ case V16SF_FTYPE_V16SF_V16SF_V16SI_INT_HI_INT:
+ case V2DF_FTYPE_V2DF_V2DF_V2DI_INT_QI_INT:
+ case V4SF_FTYPE_V4SF_V4SF_V4SI_INT_QI_INT:
+ nargs = 6;
+ nargs_constant = 3;
+ break;
+ default:
+ gcc_unreachable ();
+ }
+ gcc_assert (nargs <= ARRAY_SIZE (args));
+
+ if (optimize
+ || target == 0
+ || GET_MODE (target) != tmode
+ || !insn_p->operand[0].predicate (target, tmode))
+ target = gen_reg_rtx (tmode);
+
+ for (i = 0; i < nargs; i++)
+ {
+ tree arg = CALL_EXPR_ARG (exp, i);
+ rtx op = expand_normal (arg);
+ enum machine_mode mode = insn_p->operand[i + 1].mode;
+ bool match = insn_p->operand[i + 1].predicate (op, mode);
+
+ if (i == nargs - nargs_constant)
+ {
+ if (!match)
+ {
+ switch (icode)
+ {
+ case CODE_FOR_avx512f_getmantv8df_mask_round:
+ case CODE_FOR_avx512f_getmantv16sf_mask_round:
+ error ("the immediate argument must be a 4-bit immediate");
+ return const0_rtx;
+ case CODE_FOR_avx512f_cmpv8df3_mask_round:
+ case CODE_FOR_avx512f_cmpv16sf3_mask_round:
+ case CODE_FOR_avx512f_vmcmpv2df3_mask_round:
+ case CODE_FOR_avx512f_vmcmpv4sf3_mask_round:
+ error ("the immediate argument must be a 5-bit immediate");
+ return const0_rtx;
+ default:
+ error ("the immediate argument must be an 8-bit immediate");
+ return const0_rtx;
+ }
+ }
+ }
+ else if (i == nargs-1)
+ {
+ if (!insn_p->operand[nargs].predicate (op, SImode))
+ {
+ error ("incorrect rounding operand");
+ return const0_rtx;
+ }
+
+ /* If there is no rounding use normal version of the pattern. */
+ if (INTVAL (op) == NO_ROUND)
+ redundant_embed_rnd = 1;
+ }
+ else
+ {
+ if (VECTOR_MODE_P (mode))
+ op = safe_vector_operand (op, mode);
+
+ if (GET_MODE (op) == mode || GET_MODE (op) == VOIDmode)
+ {
+ if (optimize || !match)
+ op = copy_to_mode_reg (mode, op);
+ }
+ else
+ {
+ op = copy_to_reg (op);
+ op = simplify_gen_subreg (mode, op, GET_MODE (op), 0);
+ }
+ }
+
+ args[i].op = op;
+ args[i].mode = mode;
+ }
+
+ switch (nargs)
+ {
+ case 1:
+ pat = GEN_FCN (icode) (target, args[0].op);
+ break;
+ case 2:
+ pat = GEN_FCN (icode) (target, args[0].op, args[1].op);
+ break;
+ case 3:
+ pat = GEN_FCN (icode) (target, args[0].op, args[1].op,
+ args[2].op);
+ break;
+ case 4:
+ pat = GEN_FCN (icode) (target, args[0].op, args[1].op,
+ args[2].op, args[3].op);
+ break;
+ case 5:
+ pat = GEN_FCN (icode) (target, args[0].op, args[1].op,
+ args[2].op, args[3].op, args[4].op);
+ case 6:
+ pat = GEN_FCN (icode) (target, args[0].op, args[1].op,
+ args[2].op, args[3].op, args[4].op,
+ args[5].op);
+ break;
+ default:
+ gcc_unreachable ();
+ }
+
+ if (!pat)
+ return 0;
+
+ if (redundant_embed_rnd)
+ pat = ix86_erase_embedded_rounding (pat);
+
+ emit_insn (pat);
+ return target;
+}
+
/* Subroutine of ix86_expand_builtin to take care of special insns
with variable number of operands. */
@@ -32882,6 +34239,10 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
case V4DF_FTYPE_PCDOUBLE:
case V2DF_FTYPE_PCDOUBLE:
case VOID_FTYPE_PVOID:
+ case V16SI_FTYPE_PV4SI:
+ case V16SF_FTYPE_PV4SF:
+ case V8DI_FTYPE_PV4DI:
+ case V8DF_FTYPE_PV4DF:
nargs = 1;
klass = load;
memory = 0;
@@ -32896,12 +34257,15 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
}
break;
case VOID_FTYPE_PV2SF_V4SF:
+ case VOID_FTYPE_PV8DI_V8DI:
case VOID_FTYPE_PV4DI_V4DI:
case VOID_FTYPE_PV2DI_V2DI:
case VOID_FTYPE_PCHAR_V32QI:
case VOID_FTYPE_PCHAR_V16QI:
+ case VOID_FTYPE_PFLOAT_V16SF:
case VOID_FTYPE_PFLOAT_V8SF:
case VOID_FTYPE_PFLOAT_V4SF:
+ case VOID_FTYPE_PDOUBLE_V8DF:
case VOID_FTYPE_PDOUBLE_V4DF:
case VOID_FTYPE_PDOUBLE_V2DF:
case VOID_FTYPE_PLONGLONG_LONGLONG:
@@ -32958,11 +34322,27 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
case VOID_FTYPE_PV4DI_V4DI_V4DI:
case VOID_FTYPE_PV4SI_V4SI_V4SI:
case VOID_FTYPE_PV2DI_V2DI_V2DI:
+ case VOID_FTYPE_PV8DF_V8DF_QI:
+ case VOID_FTYPE_PV16SF_V16SF_HI:
+ case VOID_FTYPE_PV8DI_V8DI_QI:
+ case VOID_FTYPE_PV16SI_V16SI_HI:
+ case VOID_FTYPE_PDOUBLE_V2DF_QI:
+ case VOID_FTYPE_PFLOAT_V4SF_QI:
nargs = 2;
klass = store;
/* Reserve memory operand for target. */
memory = ARRAY_SIZE (args);
break;
+ case V16SF_FTYPE_PCV16SF_V16SF_HI:
+ case V16SI_FTYPE_PCV16SI_V16SI_HI:
+ case V8DF_FTYPE_PCV8DF_V8DF_QI:
+ case V8DI_FTYPE_PCV8DI_V8DI_QI:
+ case V2DF_FTYPE_PCDOUBLE_V2DF_QI:
+ case V4SF_FTYPE_PCFLOAT_V4SF_QI:
+ nargs = 3;
+ klass = load;
+ memory = 0;
+ break;
case VOID_FTYPE_UINT_UINT_UINT:
case VOID_FTYPE_UINT64_UINT_UINT:
case UCHAR_FTYPE_UINT_UINT_UINT:
@@ -33061,9 +34441,13 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
if (VECTOR_MODE_P (mode))
op = safe_vector_operand (op, mode);
- gcc_assert (GET_MODE (op) == mode
- || GET_MODE (op) == VOIDmode);
- op = copy_to_mode_reg (mode, op);
+ if (GET_MODE (op) == mode || GET_MODE (op) == VOIDmode)
+ op = copy_to_mode_reg (mode, op);
+ else
+ {
+ op = copy_to_reg (op);
+ op = simplify_gen_subreg (mode, op, GET_MODE (op), 0);
+ }
}
}
@@ -33804,6 +35188,38 @@ addcarryx:
emit_insn (gen_pop (gen_rtx_REG (word_mode, FLAGS_REG)));
return 0;
+ case IX86_BUILTIN_KORTESTC16:
+ icode = CODE_FOR_kortestchi;
+ mode0 = HImode;
+ mode1 = CCCmode;
+ goto kortest;
+
+ case IX86_BUILTIN_KORTESTZ16:
+ icode = CODE_FOR_kortestzhi;
+ mode0 = HImode;
+ mode1 = CCZmode;
+
+ kortest:
+ arg0 = CALL_EXPR_ARG (exp, 0); /* Mask reg src1. */
+ arg1 = CALL_EXPR_ARG (exp, 1); /* Mask reg src2. */
+ op0 = expand_normal (arg0);
+ op1 = expand_normal (arg1);
+
+ op0 = copy_to_reg (op0);
+ op0 = simplify_gen_subreg (mode0, op0, GET_MODE (op0), 0);
+ op1 = copy_to_reg (op1);
+ op1 = simplify_gen_subreg (mode0, op1, GET_MODE (op1), 0);
+
+ target = gen_reg_rtx (QImode);
+ emit_insn (gen_rtx_SET (mode0, target, const0_rtx));
+
+ /* Emit kortest. */
+ emit_insn (GEN_FCN (icode) (op0, op1));
+ /* And use setcc to return result from flags. */
+ ix86_expand_setcc (target, EQ,
+ gen_rtx_REG (mode1, FLAGS_REG), const0_rtx);
+ return target;
+
case IX86_BUILTIN_GATHERSIV2DF:
icode = CODE_FOR_avx2_gathersiv2df;
goto gather_gen;
@@ -33864,8 +35280,83 @@ addcarryx:
case IX86_BUILTIN_GATHERALTDIV8SI:
icode = CODE_FOR_avx2_gatherdiv8si;
goto gather_gen;
+ case IX86_BUILTIN_GATHER3SIV16SF:
+ icode = CODE_FOR_avx512f_gathersiv16sf;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3SIV8DF:
+ icode = CODE_FOR_avx512f_gathersiv8df;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3DIV16SF:
+ icode = CODE_FOR_avx512f_gatherdiv16sf;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3DIV8DF:
+ icode = CODE_FOR_avx512f_gatherdiv8df;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3SIV16SI:
+ icode = CODE_FOR_avx512f_gathersiv16si;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3SIV8DI:
+ icode = CODE_FOR_avx512f_gathersiv8di;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3DIV16SI:
+ icode = CODE_FOR_avx512f_gatherdiv16si;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3DIV8DI:
+ icode = CODE_FOR_avx512f_gatherdiv8di;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3ALTSIV8DF:
+ icode = CODE_FOR_avx512f_gathersiv8df;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3ALTDIV16SF:
+ icode = CODE_FOR_avx512f_gatherdiv16sf;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3ALTSIV8DI:
+ icode = CODE_FOR_avx512f_gathersiv8di;
+ goto gather_gen;
+ case IX86_BUILTIN_GATHER3ALTDIV16SI:
+ icode = CODE_FOR_avx512f_gatherdiv16si;
+ goto gather_gen;
+ case IX86_BUILTIN_SCATTERSIV16SF:
+ icode = CODE_FOR_avx512f_scattersiv16sf;
+ goto scatter_gen;
+ case IX86_BUILTIN_SCATTERSIV8DF:
+ icode = CODE_FOR_avx512f_scattersiv8df;
+ goto scatter_gen;
+ case IX86_BUILTIN_SCATTERDIV16SF:
+ icode = CODE_FOR_avx512f_scatterdiv16sf;
+ goto scatter_gen;
+ case IX86_BUILTIN_SCATTERDIV8DF:
+ icode = CODE_FOR_avx512f_scatterdiv8df;
+ goto scatter_gen;
+ case IX86_BUILTIN_SCATTERSIV16SI:
+ icode = CODE_FOR_avx512f_scattersiv16si;
+ goto scatter_gen;
+ case IX86_BUILTIN_SCATTERSIV8DI:
+ icode = CODE_FOR_avx512f_scattersiv8di;
+ goto scatter_gen;
+ case IX86_BUILTIN_SCATTERDIV16SI:
+ icode = CODE_FOR_avx512f_scatterdiv16si;
+ goto scatter_gen;
+ case IX86_BUILTIN_SCATTERDIV8DI:
+ icode = CODE_FOR_avx512f_scatterdiv8di;
+ goto scatter_gen;
+ case IX86_BUILTIN_GATHERPFDPS:
+ icode = CODE_FOR_avx512pf_gatherpfv16si;
+ goto vec_prefetch_gen;
+ case IX86_BUILTIN_GATHERPFQPS:
+ icode = CODE_FOR_avx512pf_gatherpfv8di;
+ goto vec_prefetch_gen;
+ case IX86_BUILTIN_SCATTERPFDPS:
+ icode = CODE_FOR_avx512pf_scatterpfv16si;
+ goto vec_prefetch_gen;
+ case IX86_BUILTIN_SCATTERPFQPS:
+ icode = CODE_FOR_avx512pf_scatterpfv8di;
+ goto vec_prefetch_gen;
gather_gen:
+ rtx half;
+ rtx (*gen) (rtx, rtx);
+
arg0 = CALL_EXPR_ARG (exp, 0);
arg1 = CALL_EXPR_ARG (exp, 1);
arg2 = CALL_EXPR_ARG (exp, 2);
@@ -33888,20 +35379,46 @@ addcarryx:
else
subtarget = target;
- if (fcode == IX86_BUILTIN_GATHERALTSIV4DF
- || fcode == IX86_BUILTIN_GATHERALTSIV4DI)
+ switch (fcode)
{
- rtx half = gen_reg_rtx (V4SImode);
+ case IX86_BUILTIN_GATHER3ALTSIV8DF:
+ case IX86_BUILTIN_GATHER3ALTSIV8DI:
+ half = gen_reg_rtx (V8SImode);
+ if (!nonimmediate_operand (op2, V16SImode))
+ op2 = copy_to_mode_reg (V16SImode, op2);
+ emit_insn (gen_vec_extract_lo_v16si (half, op2));
+ op2 = half;
+ break;
+ case IX86_BUILTIN_GATHERALTSIV4DF:
+ case IX86_BUILTIN_GATHERALTSIV4DI:
+ half = gen_reg_rtx (V4SImode);
if (!nonimmediate_operand (op2, V8SImode))
op2 = copy_to_mode_reg (V8SImode, op2);
emit_insn (gen_vec_extract_lo_v8si (half, op2));
op2 = half;
- }
- else if (fcode == IX86_BUILTIN_GATHERALTDIV8SF
- || fcode == IX86_BUILTIN_GATHERALTDIV8SI)
- {
- rtx (*gen) (rtx, rtx);
- rtx half = gen_reg_rtx (mode0);
+ break;
+ case IX86_BUILTIN_GATHER3ALTDIV16SF:
+ case IX86_BUILTIN_GATHER3ALTDIV16SI:
+ half = gen_reg_rtx (mode0);
+ if (mode0 == V8SFmode)
+ gen = gen_vec_extract_lo_v16sf;
+ else
+ gen = gen_vec_extract_lo_v16si;
+ if (!nonimmediate_operand (op0, GET_MODE (op0)))
+ op0 = copy_to_mode_reg (GET_MODE (op0), op0);
+ emit_insn (gen (half, op0));
+ op0 = half;
+ if (GET_MODE (op3) != VOIDmode)
+ {
+ if (!nonimmediate_operand (op3, GET_MODE (op3)))
+ op3 = copy_to_mode_reg (GET_MODE (op3), op3);
+ emit_insn (gen (half, op3));
+ op3 = half;
+ }
+ break;
+ case IX86_BUILTIN_GATHERALTDIV8SF:
+ case IX86_BUILTIN_GATHERALTDIV8SI:
+ half = gen_reg_rtx (mode0);
if (mode0 == V4SFmode)
gen = gen_vec_extract_lo_v8sf;
else
@@ -33910,10 +35427,16 @@ addcarryx:
op0 = copy_to_mode_reg (GET_MODE (op0), op0);
emit_insn (gen (half, op0));
op0 = half;
- if (!nonimmediate_operand (op3, GET_MODE (op3)))
- op3 = copy_to_mode_reg (GET_MODE (op3), op3);
- emit_insn (gen (half, op3));
- op3 = half;
+ if (GET_MODE (op3) != VOIDmode)
+ {
+ if (!nonimmediate_operand (op3, GET_MODE (op3)))
+ op3 = copy_to_mode_reg (GET_MODE (op3), op3);
+ emit_insn (gen (half, op3));
+ op3 = half;
+ }
+ break;
+ default:
+ break;
}
/* Force memory operand only with base register here. But we
@@ -33927,11 +35450,19 @@ addcarryx:
op1 = copy_to_mode_reg (Pmode, op1);
if (!insn_data[icode].operand[3].predicate (op2, mode2))
op2 = copy_to_mode_reg (mode2, op2);
- if (!insn_data[icode].operand[4].predicate (op3, mode3))
- op3 = copy_to_mode_reg (mode3, op3);
+ if (GET_MODE (op3) == mode3 || GET_MODE (op3) == VOIDmode)
+ {
+ if (!insn_data[icode].operand[4].predicate (op3, mode3))
+ op3 = copy_to_mode_reg (mode3, op3);
+ }
+ else
+ {
+ op3 = copy_to_reg (op3);
+ op3 = simplify_gen_subreg (mode3, op3, GET_MODE (op3), 0);
+ }
if (!insn_data[icode].operand[5].predicate (op4, mode4))
{
- error ("last argument must be scale 1, 2, 4, 8");
+ error ("the last argument must be scale 1, 2, 4, 8");
return const0_rtx;
}
@@ -33941,7 +35472,12 @@ addcarryx:
previous contents. */
if (optimize)
{
- if (TREE_CODE (arg3) == VECTOR_CST)
+ if (TREE_CODE (arg3) == INTEGER_CST)
+ {
+ if (integer_all_onesp (arg3))
+ op0 = pc_rtx;
+ }
+ else if (TREE_CODE (arg3) == VECTOR_CST)
{
unsigned int negative = 0;
for (i = 0; i < VECTOR_CST_NELTS (arg3); ++i)
@@ -33957,7 +35493,8 @@ addcarryx:
if (negative == TYPE_VECTOR_SUBPARTS (TREE_TYPE (arg3)))
op0 = pc_rtx;
}
- else if (TREE_CODE (arg3) == SSA_NAME)
+ else if (TREE_CODE (arg3) == SSA_NAME
+ && TREE_CODE (TREE_TYPE (arg3)) == VECTOR_TYPE)
{
/* Recognize also when mask is like:
__v2df src = _mm_setzero_pd ();
@@ -34002,22 +35539,146 @@ addcarryx:
return const0_rtx;
emit_insn (pat);
- if (fcode == IX86_BUILTIN_GATHERDIV8SF
- || fcode == IX86_BUILTIN_GATHERDIV8SI)
+ switch (fcode)
{
- enum machine_mode tmode = GET_MODE (subtarget) == V8SFmode
- ? V4SFmode : V4SImode;
+ case IX86_BUILTIN_GATHER3DIV16SF:
if (target == NULL_RTX)
- target = gen_reg_rtx (tmode);
- if (tmode == V4SFmode)
- emit_insn (gen_vec_extract_lo_v8sf (target, subtarget));
- else
- emit_insn (gen_vec_extract_lo_v8si (target, subtarget));
+ target = gen_reg_rtx (V8SFmode);
+ emit_insn (gen_vec_extract_lo_v16sf (target, subtarget));
+ break;
+ case IX86_BUILTIN_GATHER3DIV16SI:
+ if (target == NULL_RTX)
+ target = gen_reg_rtx (V8SImode);
+ emit_insn (gen_vec_extract_lo_v16si (target, subtarget));
+ break;
+ case IX86_BUILTIN_GATHERDIV8SF:
+ if (target == NULL_RTX)
+ target = gen_reg_rtx (V4SFmode);
+ emit_insn (gen_vec_extract_lo_v8sf (target, subtarget));
+ break;
+ case IX86_BUILTIN_GATHERDIV8SI:
+ if (target == NULL_RTX)
+ target = gen_reg_rtx (V4SImode);
+ emit_insn (gen_vec_extract_lo_v8si (target, subtarget));
+ break;
+ default:
+ target = subtarget;
+ break;
+ }
+ return target;
+
+ scatter_gen:
+ arg0 = CALL_EXPR_ARG (exp, 0);
+ arg1 = CALL_EXPR_ARG (exp, 1);
+ arg2 = CALL_EXPR_ARG (exp, 2);
+ arg3 = CALL_EXPR_ARG (exp, 3);
+ arg4 = CALL_EXPR_ARG (exp, 4);
+ op0 = expand_normal (arg0);
+ op1 = expand_normal (arg1);
+ op2 = expand_normal (arg2);
+ op3 = expand_normal (arg3);
+ op4 = expand_normal (arg4);
+ mode1 = insn_data[icode].operand[1].mode;
+ mode2 = insn_data[icode].operand[2].mode;
+ mode3 = insn_data[icode].operand[3].mode;
+ mode4 = insn_data[icode].operand[4].mode;
+
+ /* Force memory operand only with base register here. But we
+ don't want to do it on memory operand for other builtin
+ functions. */
+ op0 = force_reg (Pmode, convert_to_mode (Pmode, op0, 1));
+
+ if (!insn_data[icode].operand[0].predicate (op0, Pmode))
+ op0 = copy_to_mode_reg (Pmode, op0);
+
+ if (GET_MODE (op1) == mode1 || GET_MODE (op1) == VOIDmode)
+ {
+ if (!insn_data[icode].operand[1].predicate (op1, mode1))
+ op1 = copy_to_mode_reg (mode1, op1);
}
else
- target = subtarget;
+ {
+ op1 = copy_to_reg (op1);
+ op1 = simplify_gen_subreg (mode1, op1, GET_MODE (op1), 0);
+ }
- return target;
+ if (!insn_data[icode].operand[2].predicate (op2, mode2))
+ op2 = copy_to_mode_reg (mode2, op2);
+
+ if (!insn_data[icode].operand[3].predicate (op3, mode3))
+ op3 = copy_to_mode_reg (mode3, op3);
+
+ if (!insn_data[icode].operand[4].predicate (op4, mode4))
+ {
+ error ("the last argument must be scale 1, 2, 4, 8");
+ return const0_rtx;
+ }
+
+ pat = GEN_FCN (icode) (op0, op1, op2, op3, op4);
+ if (! pat)
+ return const0_rtx;
+
+ emit_insn (pat);
+ return 0;
+
+ vec_prefetch_gen:
+ arg0 = CALL_EXPR_ARG (exp, 0);
+ arg1 = CALL_EXPR_ARG (exp, 1);
+ arg2 = CALL_EXPR_ARG (exp, 2);
+ arg3 = CALL_EXPR_ARG (exp, 3);
+ arg4 = CALL_EXPR_ARG (exp, 4);
+ op0 = expand_normal (arg0);
+ op1 = expand_normal (arg1);
+ op2 = expand_normal (arg2);
+ op3 = expand_normal (arg3);
+ op4 = expand_normal (arg4);
+ mode0 = insn_data[icode].operand[0].mode;
+ mode1 = insn_data[icode].operand[1].mode;
+ mode3 = insn_data[icode].operand[3].mode;
+ mode4 = insn_data[icode].operand[4].mode;
+
+ if (GET_MODE (op0) == mode0
+ || (GET_MODE (op0) == VOIDmode && op0 != constm1_rtx))
+ {
+ if (!insn_data[icode].operand[0].predicate (op0, mode0))
+ op0 = copy_to_mode_reg (mode0, op0);
+ }
+ else if (op0 != constm1_rtx)
+ {
+ op0 = copy_to_reg (op0);
+ op0 = simplify_gen_subreg (mode0, op0, GET_MODE (op0), 0);
+ }
+
+ if (!insn_data[icode].operand[1].predicate (op1, mode1))
+ op1 = copy_to_mode_reg (mode1, op1);
+
+ /* Force memory operand only with base register here. But we
+ don't want to do it on memory operand for other builtin
+ functions. */
+ op2 = force_reg (Pmode, convert_to_mode (Pmode, op2, 1));
+
+ if (!insn_data[icode].operand[2].predicate (op2, Pmode))
+ op2 = copy_to_mode_reg (Pmode, op2);
+
+ if (!insn_data[icode].operand[3].predicate (op3, mode3))
+ {
+ error ("the forth argument must be scale 1, 2, 4, 8");
+ return const0_rtx;
+ }
+
+ if (!insn_data[icode].operand[4].predicate (op4, mode4))
+ {
+ error ("the last argument must be hint 0 or 1");
+ return const0_rtx;
+ }
+
+ pat = GEN_FCN (icode) (op0, op1, op2, op3, op4);
+ if (! pat)
+ return const0_rtx;
+
+ emit_insn (pat);
+
+ return 0;
case IX86_BUILTIN_XABORT:
icode = CODE_FOR_xabort;
@@ -34061,6 +35722,10 @@ addcarryx:
if (d->code == fcode)
return ix86_expand_sse_comi (d, exp, target);
+ for (i = 0, d = bdesc_round_args; i < ARRAY_SIZE (bdesc_round_args); i++, d++)
+ if (d->code == fcode)
+ return ix86_expand_round_builtin (d, exp, target);
+
for (i = 0, d = bdesc_pcmpestr;
i < ARRAY_SIZE (bdesc_pcmpestr);
i++, d++)
diff --git a/gcc/config/i386/immintrin.h b/gcc/config/i386/immintrin.h
index e825c34a256..fa75a30ba79 100644
--- a/gcc/config/i386/immintrin.h
+++ b/gcc/config/i386/immintrin.h
@@ -42,6 +42,14 @@
#include <avx2intrin.h>
+#include <avx512fintrin.h>
+
+#include <avx512erintrin.h>
+
+#include <avx512pfintrin.h>
+
+#include <avx512cdintrin.h>
+
#include <lzcntintrin.h>
#include <bmiintrin.h>
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index ed9467b04bb..240a964a47e 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,12 +1,26 @@
2013-12-31 Alexander Ivchenko <alexander.ivchenko@intel.com>
- Maxim Kuznetsov <maxim.kuznetsov@intel.com>
- Sergey Lega <sergey.s.lega@intel.com>
- Anna Tikhonova <anna.tikhonova@intel.com>
- Ilya Tocar <ilya.tocar@intel.com>
- Andrey Turetskiy <andrey.turetskiy@intel.com>
- Ilya Verbin <ilya.verbin@intel.com>
- Kirill Yukhin <kirill.yukhin@intel.com>
- Michael Zolotukhin <michael.v.zolotukhin@intel.com>
+ Maxim Kuznetsov <maxim.kuznetsov@intel.com>
+ Sergey Lega <sergey.s.lega@intel.com>
+ Anna Tikhonova <anna.tikhonova@intel.com>
+ Ilya Tocar <ilya.tocar@intel.com>
+ Andrey Turetskiy <andrey.turetskiy@intel.com>
+ Ilya Verbin <ilya.verbin@intel.com>
+ Kirill Yukhin <kirill.yukhin@intel.com>
+ Michael Zolotukhin <michael.v.zolotukhin@intel.com>
+
+ * gcc.target/i386/avx-1.c: Extend to AVX-512.
+ * gcc.target/i386/sse-22.c: Ditto.
+ * gcc.target/i386/sse-23.c: Ditto.
+
+2013-12-31 Alexander Ivchenko <alexander.ivchenko@intel.com>
+ Maxim Kuznetsov <maxim.kuznetsov@intel.com>
+ Sergey Lega <sergey.s.lega@intel.com>
+ Anna Tikhonova <anna.tikhonova@intel.com>
+ Ilya Tocar <ilya.tocar@intel.com>
+ Andrey Turetskiy <andrey.turetskiy@intel.com>
+ Ilya Verbin <ilya.verbin@intel.com>
+ Kirill Yukhin <kirill.yukhin@intel.com>
+ Michael Zolotukhin <michael.v.zolotukhin@intel.com>
* gcc.target/i386/pr49002-2.c: allow vmovapd generation.
diff --git a/gcc/testsuite/gcc.target/i386/avx-1.c b/gcc/testsuite/gcc.target/i386/avx-1.c
index 7496746aec8..75b6f04e24b 100644
--- a/gcc/testsuite/gcc.target/i386/avx-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx-1.c
@@ -166,6 +166,181 @@
/* rtmintrin.h */
#define __builtin_ia32_xabort(I) __builtin_ia32_xabort(0)
+/* avx512fintrin.h */
+#define __builtin_ia32_addpd512_mask(A, B, C, D, E) __builtin_ia32_addpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_addps512_mask(A, B, C, D, E) __builtin_ia32_addps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_alignd512_mask(A, B, F, D, E) __builtin_ia32_alignd512_mask(A, B, 1, D, E)
+#define __builtin_ia32_alignq512_mask(A, B, F, D, E) __builtin_ia32_alignq512_mask(A, B, 1, D, E)
+#define __builtin_ia32_cmpd512_mask(A, B, E, D) __builtin_ia32_cmpd512_mask(A, B, 1, D)
+#define __builtin_ia32_cmppd512_mask(A, B, F, D, E) __builtin_ia32_cmppd512_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cmpps512_mask(A, B, F, D, E) __builtin_ia32_cmpps512_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cmpq512_mask(A, B, E, D) __builtin_ia32_cmpq512_mask(A, B, 1, D)
+#define __builtin_ia32_cmpsd_mask(A, B, F, D, E) __builtin_ia32_cmpsd_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cmpss_mask(A, B, F, D, E) __builtin_ia32_cmpss_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cvtdq2ps512_mask(A, B, C, D) __builtin_ia32_cvtdq2ps512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtpd2dq512_mask(A, B, C, D) __builtin_ia32_cvtpd2dq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtpd2ps512_mask(A, B, C, D) __builtin_ia32_cvtpd2ps512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtpd2udq512_mask(A, B, C, D) __builtin_ia32_cvtpd2udq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtps2dq512_mask(A, B, C, D) __builtin_ia32_cvtps2dq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtps2pd512_mask(A, B, C, D) __builtin_ia32_cvtps2pd512_mask(A, B, C, 5)
+#define __builtin_ia32_cvtps2udq512_mask(A, B, C, D) __builtin_ia32_cvtps2udq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtsd2ss_mask(A, B, C, D, E) __builtin_ia32_cvtsd2ss_mask(A, B, C, D, 1)
+#define __builtin_ia32_cvtsi2sd64(A, B, C) __builtin_ia32_cvtsi2sd64(A, B, 1)
+#define __builtin_ia32_cvtsi2ss32(A, B, C) __builtin_ia32_cvtsi2ss32(A, B, 1)
+#define __builtin_ia32_cvtsi2ss64(A, B, C) __builtin_ia32_cvtsi2ss64(A, B, 1)
+#define __builtin_ia32_cvtss2sd_mask(A, B, C, D, E) __builtin_ia32_cvtss2sd_mask(A, B, C, D, 5)
+#define __builtin_ia32_cvttpd2dq512_mask(A, B, C, D) __builtin_ia32_cvttpd2dq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvttpd2udq512_mask(A, B, C, D) __builtin_ia32_cvttpd2udq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvttps2dq512_mask(A, B, C, D) __builtin_ia32_cvttps2dq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvttps2udq512_mask(A, B, C, D) __builtin_ia32_cvttps2udq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvtudq2ps512_mask(A, B, C, D) __builtin_ia32_cvtudq2ps512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtusi2sd64(A, B, C) __builtin_ia32_cvtusi2sd64(A, B, 1)
+#define __builtin_ia32_cvtusi2ss32(A, B, C) __builtin_ia32_cvtusi2ss32(A, B, 1)
+#define __builtin_ia32_cvtusi2ss64(A, B, C) __builtin_ia32_cvtusi2ss64(A, B, 1)
+#define __builtin_ia32_divpd512_mask(A, B, C, D, E) __builtin_ia32_divpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_divps512_mask(A, B, C, D, E) __builtin_ia32_divps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_extractf32x4_mask(A, E, C, D) __builtin_ia32_extractf32x4_mask(A, 1, C, D)
+#define __builtin_ia32_extractf64x4_mask(A, E, C, D) __builtin_ia32_extractf64x4_mask(A, 1, C, D)
+#define __builtin_ia32_extracti32x4_mask(A, E, C, D) __builtin_ia32_extracti32x4_mask(A, 1, C, D)
+#define __builtin_ia32_extracti64x4_mask(A, E, C, D) __builtin_ia32_extracti64x4_mask(A, 1, C, D)
+#define __builtin_ia32_fixupimmpd512_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmpd512_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmpd512_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmpd512_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmps512_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmps512_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmps512_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmps512_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmsd_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmsd_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmsd_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmsd_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmss_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmss_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmss_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmss_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_gatherdiv8df(A, B, C, D, F) __builtin_ia32_gatherdiv8df(A, B, C, D, 1)
+#define __builtin_ia32_gatherdiv8di(A, B, C, D, F) __builtin_ia32_gatherdiv8di(A, B, C, D, 1)
+#define __builtin_ia32_gatherdiv16sf(A, B, C, D, F) __builtin_ia32_gatherdiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_gatherdiv16si(A, B, C, D, F) __builtin_ia32_gatherdiv16si(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv16sf(A, B, C, D, F) __builtin_ia32_gathersiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv16si(A, B, C, D, F) __builtin_ia32_gathersiv16si(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv8df(A, B, C, D, F) __builtin_ia32_gathersiv8df(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv8di(A, B, C, D, F) __builtin_ia32_gathersiv8di(A, B, C, D, 1)
+#define __builtin_ia32_getexppd512_mask(A, B, C, D) __builtin_ia32_getexppd512_mask(A, B, C, 5)
+#define __builtin_ia32_getexpps512_mask(A, B, C, D) __builtin_ia32_getexpps512_mask(A, B, C, 5)
+#define __builtin_ia32_getmantpd512_mask(A, F, C, D, E) __builtin_ia32_getmantpd512_mask(A, 1, C, D, 5)
+#define __builtin_ia32_getmantps512_mask(A, F, C, D, E) __builtin_ia32_getmantps512_mask(A, 1, C, D, 5)
+#define __builtin_ia32_insertf32x4_mask(A, B, F, D, E) __builtin_ia32_insertf32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_insertf64x4_mask(A, B, F, D, E) __builtin_ia32_insertf64x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_inserti32x4_mask(A, B, F, D, E) __builtin_ia32_inserti32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_inserti64x4_mask(A, B, F, D, E) __builtin_ia32_inserti64x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_maxpd512_mask(A, B, C, D, E) __builtin_ia32_maxpd512_mask(A, B, C, D, 5)
+#define __builtin_ia32_maxps512_mask(A, B, C, D, E) __builtin_ia32_maxps512_mask(A, B, C, D, 5)
+#define __builtin_ia32_minpd512_mask(A, B, C, D, E) __builtin_ia32_minpd512_mask(A, B, C, D, 5)
+#define __builtin_ia32_minps512_mask(A, B, C, D, E) __builtin_ia32_minps512_mask(A, B, C, D, 5)
+#define __builtin_ia32_mulpd512_mask(A, B, C, D, E) __builtin_ia32_mulpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_mulps512_mask(A, B, C, D, E) __builtin_ia32_mulps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_permdf512_mask(A, E, C, D) __builtin_ia32_permdf512_mask(A, 1, C, D)
+#define __builtin_ia32_permdi512_mask(A, E, C, D) __builtin_ia32_permdi512_mask(A, 1, C, D)
+#define __builtin_ia32_prold512_mask(A, E, C, D) __builtin_ia32_prold512_mask(A, 1, C, D)
+#define __builtin_ia32_prolq512_mask(A, E, C, D) __builtin_ia32_prolq512_mask(A, 1, C, D)
+#define __builtin_ia32_prord512_mask(A, E, C, D) __builtin_ia32_prord512_mask(A, 1, C, D)
+#define __builtin_ia32_prorq512_mask(A, E, C, D) __builtin_ia32_prorq512_mask(A, 1, C, D)
+#define __builtin_ia32_pshufd512_mask(A, E, C, D) __builtin_ia32_pshufd512_mask(A, 1, C, D)
+#define __builtin_ia32_pslldi512_mask(A, E, C, D) __builtin_ia32_pslldi512_mask(A, 1, C, D)
+#define __builtin_ia32_psllqi512_mask(A, E, C, D) __builtin_ia32_psllqi512_mask(A, 1, C, D)
+#define __builtin_ia32_psradi512_mask(A, E, C, D) __builtin_ia32_psradi512_mask(A, 1, C, D)
+#define __builtin_ia32_psraqi512_mask(A, E, C, D) __builtin_ia32_psraqi512_mask(A, 1, C, D)
+#define __builtin_ia32_psrldi512_mask(A, E, C, D) __builtin_ia32_psrldi512_mask(A, 1, C, D)
+#define __builtin_ia32_psrlqi512_mask(A, E, C, D) __builtin_ia32_psrlqi512_mask(A, 1, C, D)
+#define __builtin_ia32_pternlogd512_mask(A, B, C, F, E) __builtin_ia32_pternlogd512_mask(A, B, C, 1, E)
+#define __builtin_ia32_pternlogd512_maskz(A, B, C, F, E) __builtin_ia32_pternlogd512_maskz(A, B, C, 1, E)
+#define __builtin_ia32_pternlogq512_mask(A, B, C, F, E) __builtin_ia32_pternlogq512_mask(A, B, C, 1, E)
+#define __builtin_ia32_pternlogq512_maskz(A, B, C, F, E) __builtin_ia32_pternlogq512_maskz(A, B, C, 1, E)
+#define __builtin_ia32_rndscalepd_mask(A, F, C, D, E) __builtin_ia32_rndscalepd_mask(A, 1, C, D, 5)
+#define __builtin_ia32_rndscaleps_mask(A, F, C, D, E) __builtin_ia32_rndscaleps_mask(A, 1, C, D, 5)
+#define __builtin_ia32_rndscalesd_mask(A, B, I, D, E, F) __builtin_ia32_rndscalesd_mask(A, B, 1, D, E, 5)
+#define __builtin_ia32_rndscaless_mask(A, B, I, D, E, F) __builtin_ia32_rndscaless_mask(A, B, 1, D, E, 5)
+#define __builtin_ia32_scalefpd512_mask(A, B, C, D, E) __builtin_ia32_scalefpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_scalefps512_mask(A, B, C, D, E) __builtin_ia32_scalefps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv8df(A, B, C, D, F) __builtin_ia32_scatterdiv8df(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv8di(A, B, C, D, F) __builtin_ia32_scatterdiv8di(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv16sf(A, B, C, D, F) __builtin_ia32_scatterdiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv16si(A, B, C, D, F) __builtin_ia32_scatterdiv16si(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv16sf(A, B, C, D, F) __builtin_ia32_scattersiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv16si(A, B, C, D, F) __builtin_ia32_scattersiv16si(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv8df(A, B, C, D, F) __builtin_ia32_scattersiv8df(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv8di(A, B, C, D, F) __builtin_ia32_scattersiv8di(A, B, C, D, 1)
+#define __builtin_ia32_shuf_f32x4_mask(A, B, F, D, E) __builtin_ia32_shuf_f32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_shuf_f64x2_mask(A, B, F, D, E) __builtin_ia32_shuf_f64x2_mask(A, B, 1, D, E)
+#define __builtin_ia32_shuf_i32x4_mask(A, B, F, D, E) __builtin_ia32_shuf_i32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_shuf_i64x2_mask(A, B, F, D, E) __builtin_ia32_shuf_i64x2_mask(A, B, 1, D, E)
+#define __builtin_ia32_shufpd512_mask(A, B, F, D, E) __builtin_ia32_shufpd512_mask(A, B, 1, D, E)
+#define __builtin_ia32_shufps512_mask(A, B, F, D, E) __builtin_ia32_shufps512_mask(A, B, 1, D, E)
+#define __builtin_ia32_sqrtpd512_mask(A, B, C, D) __builtin_ia32_sqrtpd512_mask(A, B, C, 1)
+#define __builtin_ia32_sqrtps512_mask(A, B, C, D) __builtin_ia32_sqrtps512_mask(A, B, C, 1)
+#define __builtin_ia32_sqrtsd_mask(A, B, C, D, E) __builtin_ia32_sqrtsd_mask(A, B, C, D, 1)
+#define __builtin_ia32_sqrtss_mask(A, B, C, D, E) __builtin_ia32_sqrtss_mask(A, B, C, D, 1)
+#define __builtin_ia32_subpd512_mask(A, B, C, D, E) __builtin_ia32_subpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_subps512_mask(A, B, C, D, E) __builtin_ia32_subps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_ucmpd512_mask(A, B, E, D) __builtin_ia32_ucmpd512_mask(A, B, 1, D)
+#define __builtin_ia32_ucmpq512_mask(A, B, E, D) __builtin_ia32_ucmpq512_mask(A, B, 1, D)
+#define __builtin_ia32_vcomisd(A, B, C, D) __builtin_ia32_vcomisd(A, B, 1, 5)
+#define __builtin_ia32_vcomiss(A, B, C, D) __builtin_ia32_vcomiss(A, B, 1, 5)
+#define __builtin_ia32_vcvtph2ps512_mask(A, B, C, D) __builtin_ia32_vcvtph2ps512_mask(A, B, C, 5)
+#define __builtin_ia32_vcvtps2ph512_mask(A, E, C, D) __builtin_ia32_vcvtps2ph512_mask(A, 1, C, D)
+#define __builtin_ia32_vcvtsd2si32(A, B) __builtin_ia32_vcvtsd2si32(A, 1)
+#define __builtin_ia32_vcvtsd2si64(A, B) __builtin_ia32_vcvtsd2si64(A, 1)
+#define __builtin_ia32_vcvtsd2usi32(A, B) __builtin_ia32_vcvtsd2usi32(A, 1)
+#define __builtin_ia32_vcvtsd2usi64(A, B) __builtin_ia32_vcvtsd2usi64(A, 1)
+#define __builtin_ia32_vcvtss2si32(A, B) __builtin_ia32_vcvtss2si32(A, 1)
+#define __builtin_ia32_vcvtss2si64(A, B) __builtin_ia32_vcvtss2si64(A, 1)
+#define __builtin_ia32_vcvtss2usi32(A, B) __builtin_ia32_vcvtss2usi32(A, 1)
+#define __builtin_ia32_vcvtss2usi64(A, B) __builtin_ia32_vcvtss2usi64(A, 1)
+#define __builtin_ia32_vcvttsd2si32(A, B) __builtin_ia32_vcvttsd2si32(A, 5)
+#define __builtin_ia32_vcvttsd2si64(A, B) __builtin_ia32_vcvttsd2si64(A, 5)
+#define __builtin_ia32_vcvttsd2usi32(A, B) __builtin_ia32_vcvttsd2usi32(A, 5)
+#define __builtin_ia32_vcvttsd2usi64(A, B) __builtin_ia32_vcvttsd2usi64(A, 5)
+#define __builtin_ia32_vcvttss2si32(A, B) __builtin_ia32_vcvttss2si32(A, 5)
+#define __builtin_ia32_vcvttss2si64(A, B) __builtin_ia32_vcvttss2si64(A, 5)
+#define __builtin_ia32_vcvttss2usi32(A, B) __builtin_ia32_vcvttss2usi32(A, 5)
+#define __builtin_ia32_vcvttss2usi64(A, B) __builtin_ia32_vcvttss2usi64(A, 5)
+#define __builtin_ia32_vfmaddpd512_mask(A, B, C, D, E) __builtin_ia32_vfmaddpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddpd512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddpd512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddps512_mask(A, B, C, D, E) __builtin_ia32_vfmaddps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddps512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddps512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddps512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsd3_mask(A, B, C, D, E) __builtin_ia32_vfmaddsd3_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsd3_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsd3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsd3_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsd3_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddss3_mask(A, B, C, D, E) __builtin_ia32_vfmaddss3_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddss3_mask3(A, B, C, D, E) __builtin_ia32_vfmaddss3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddss3_maskz(A, B, C, D, E) __builtin_ia32_vfmaddss3_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubpd512_mask(A, B, C, D, E) __builtin_ia32_vfmaddsubpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsubpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubpd512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsubpd512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubps512_mask(A, B, C, D, E) __builtin_ia32_vfmaddsubps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubps512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsubps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubps512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsubps512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubaddpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubaddpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubaddps512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubaddps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubps512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubsd3_mask3(A, B, C, D, E) __builtin_ia32_vfmsubsd3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubss3_mask3(A, B, C, D, E) __builtin_ia32_vfmsubss3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfnmaddpd512_mask(A, B, C, D, E) __builtin_ia32_vfnmaddpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmaddps512_mask(A, B, C, D, E) __builtin_ia32_vfnmaddps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubpd512_mask(A, B, C, D, E) __builtin_ia32_vfnmsubpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubpd512_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubps512_mask(A, B, C, D, E) __builtin_ia32_vfnmsubps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubps512_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vpermilpd512_mask(A, E, C, D) __builtin_ia32_vpermilpd512_mask(A, 1, C, D)
+#define __builtin_ia32_vpermilps512_mask(A, E, C, D) __builtin_ia32_vpermilps512_mask(A, 1, C, D)
+#define __builtin_ia32_exp2ps_mask(A, B, C, D) __builtin_ia32_exp2ps_mask(A, B, C, 1)
+#define __builtin_ia32_exp2pd_mask(A, B, C, D) __builtin_ia32_exp2pd_mask(A, B, C, 1)
+#define __builtin_ia32_rcp28ps_mask(A, B, C, D) __builtin_ia32_exp2ps_mask(A, B, C, 1)
+#define __builtin_ia32_rcp28pd_mask(A, B, C, D) __builtin_ia32_exp2pd_mask(A, B, C, 1)
+#define __builtin_ia32_rsqrt28ps_mask(A, B, C, D) __builtin_ia32_rsqrt28ps_mask(A, B, C, 1)
+#define __builtin_ia32_rsqrt28pd_mask(A, B, C, D) __builtin_ia32_rsqrt28pd_mask(A, B, C, 1)
+#define __builtin_ia32_gatherpfdps(A, B, C, D, E) __builtin_ia32_gatherpfdps(A, B, C, 1, 1)
+#define __builtin_ia32_gatherpfqps(A, B, C, D, E) __builtin_ia32_gatherpfqps(A, B, C, 1, 1)
+#define __builtin_ia32_scatterpfdps(A, B, C, D, E) __builtin_ia32_scatterpfdps(A, B, C, 1, 1)
+#define __builtin_ia32_scatterpfqps(A, B, C, D, E) __builtin_ia32_scatterpfqps(A, B, C, 1, 1)
+
#include <wmmintrin.h>
#include <immintrin.h>
#include <mm3dnow.h>
diff --git a/gcc/testsuite/gcc.target/i386/sse-22.c b/gcc/testsuite/gcc.target/i386/sse-22.c
index 8e4c4bd3ebd..6f625ad11c9 100644
--- a/gcc/testsuite/gcc.target/i386/sse-22.c
+++ b/gcc/testsuite/gcc.target/i386/sse-22.c
@@ -30,6 +30,10 @@
type _CONCAT(_,func) (op1_type A, int const I, int const L) \
{ return func (A, imm1, imm2); }
+#define test_1y(func, type, op1_type, imm1, imm2, imm3) \
+ type _CONCAT(_,func) (op1_type A, int const I, int const L, int const R)\
+ { return func (A, imm1, imm2, imm3); }
+
#define test_2(func, type, op1_type, op2_type, imm) \
type _CONCAT(_,func) (op1_type A, op2_type B, int const I) \
{ return func (A, B, imm); }
@@ -38,19 +42,64 @@
type _CONCAT(_,func) (op1_type A, op2_type B, int const I, int const L) \
{ return func (A, B, imm1, imm2); }
+#define test_2y(func, type, op1_type, op2_type, imm1, imm2, imm3) \
+ type _CONCAT(_,func) (op1_type A, op2_type B, int const I, int const L,\
+ int const R) \
+ { return func (A, B, imm1, imm2, imm3); }
+
+#define test_2vx(func, op1_type, op2_type, imm1, imm2) \
+ _CONCAT(_,func) (op1_type A, op2_type B, int const I, int const L) \
+ { func (A, B, imm1, imm2); }
+
#define test_3(func, type, op1_type, op2_type, op3_type, imm) \
type _CONCAT(_,func) (op1_type A, op2_type B, \
op3_type C, int const I) \
{ return func (A, B, C, imm); }
+#define test_3x(func, type, op1_type, op2_type, op3_type, imm1, imm2) \
+ type _CONCAT(_,func) (op1_type A, op2_type B, \
+ op3_type C, int const I, int const L) \
+ { return func (A, B, C, imm1, imm2); }
+
+#define test_3y(func, type, op1_type, op2_type, op3_type, imm1, imm2, imm3) \
+ type _CONCAT(_,func) (op1_type A, op2_type B, \
+ op3_type C, int const I, int const L, int const R) \
+ { return func (A, B, C, imm1, imm2, imm3); }
+
+#define test_3v(func, op1_type, op2_type, op3_type, imm) \
+ _CONCAT(_,func) (op1_type A, op2_type B, \
+ op3_type C, int const I) \
+ { func (A, B, C, imm); }
+
+#define test_3vx(func, op1_type, op2_type, op3_type, imm1, imm2) \
+ _CONCAT(_,func) (op1_type A, op2_type B, \
+ op3_type C, int const I, int const L) \
+ { func (A, B, C, imm1, imm2); }
+
#define test_4(func, type, op1_type, op2_type, op3_type, op4_type, imm) \
type _CONCAT(_,func) (op1_type A, op2_type B, \
op3_type C, op4_type D, int const I) \
{ return func (A, B, C, D, imm); }
+#define test_4x(func, type, op1_type, op2_type, op3_type, op4_type, imm1, imm2) \
+ type _CONCAT(_,func) (op1_type A, op2_type B, \
+ op3_type C, op4_type D, int const I, int const L) \
+ { return func (A, B, C, D, imm1, imm2); }
+
+#define test_4y(func, type, op1_type, op2_type, op3_type, op4_type, imm1, imm2, imm3) \
+ type _CONCAT(_,func) (op1_type A, op2_type B, op3_type C, \
+ op4_type D, int const I, int const L, int const R) \
+ { return func (A, B, C, D, imm1, imm2, imm3); }
+
+
+#define test_4v(func, op1_type, op2_type, op3_type, op4_type, imm) \
+ _CONCAT(_,func) (op1_type A, op2_type B, \
+ op3_type C, op4_type D, int const I) \
+ { func (A, B, C, D, imm); }
+
#ifndef DIFFERENT_PRAGMAS
-#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,rtm,rdseed,prfchw,adx,fxsr,xsaveopt")
+#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512pf,avx512er,avx512cd")
#endif
/* Following intrinsics require immediate arguments. They
@@ -163,9 +212,9 @@ test_4 (_mm_cmpestro, int, __m128i, int, __m128i, int, 1)
test_4 (_mm_cmpestrs, int, __m128i, int, __m128i, int, 1)
test_4 (_mm_cmpestrz, int, __m128i, int, __m128i, int, 1)
-/* immintrin.h (AVX/AVX2/RDRND/FSGSBASE/F16C/RTM) */
+/* immintrin.h (AVX/AVX2/RDRND/FSGSBASE/F16C/RTM/AVX512F) */
#ifdef DIFFERENT_PRAGMAS
-#pragma GCC target ("avx,avx2,rdrnd,fsgsbase,f16c,rtm")
+#pragma GCC target ("avx,avx2,rdrnd,fsgsbase,f16c,rtm,avx512f,avx512er,avx512cd,avx512pf")
#endif
#include <immintrin.h>
test_1 (_cvtss_sh, unsigned short, float, 1)
@@ -248,6 +297,375 @@ test_2 ( _mm256_i64gather_epi32, __m128i, int const *, __m256i, 1)
/* rtmintrin.h */
test_0 ( _xabort, void, 1)
+/* avx512fintrin.h */
+test_1 (_mm512_cvt_roundepi32_ps, __m512, __m512i, 1)
+test_1 (_mm512_cvt_roundepu32_ps, __m512, __m512i, 1)
+test_1 (_mm512_cvt_roundpd_epi32, __m256i, __m512d, 1)
+test_1 (_mm512_cvt_roundpd_epu32, __m256i, __m512d, 1)
+test_1 (_mm512_cvt_roundpd_ps, __m256, __m512d, 1)
+test_1 (_mm512_cvt_roundph_ps, __m512, __m256i, 5)
+test_1 (_mm512_cvt_roundps_epi32, __m512i, __m512, 1)
+test_1 (_mm512_cvt_roundps_epu32, __m512i, __m512, 1)
+test_1 (_mm512_cvt_roundps_pd, __m512d, __m256, 5)
+test_1 (_mm512_cvtps_ph, __m256i, __m512, 1)
+test_1 (_mm512_cvtt_roundpd_epi32, __m256i, __m512d, 5)
+test_1 (_mm512_cvtt_roundpd_epu32, __m256i, __m512d, 5)
+test_1 (_mm512_cvtt_roundps_epi32, __m512i, __m512, 5)
+test_1 (_mm512_cvtt_roundps_epu32, __m512i, __m512, 5)
+test_1 (_mm512_extractf32x4_ps, __m128, __m512, 1)
+test_1 (_mm512_extractf64x4_pd, __m256d, __m512d, 1)
+test_1 (_mm512_extracti32x4_epi32, __m128i, __m512i, 1)
+test_1 (_mm512_extracti64x4_epi64, __m256i, __m512i, 1)
+test_1 (_mm512_getexp_round_pd, __m512d, __m512d, 5)
+test_1 (_mm512_getexp_round_ps, __m512, __m512, 5)
+test_1y (_mm512_getmant_round_pd, __m512d, __m512d, 1, 1, 5)
+test_1y (_mm512_getmant_round_ps, __m512, __m512, 1, 1, 5)
+test_1 (_mm512_permute_pd, __m512d, __m512d, 1)
+test_1 (_mm512_permute_ps, __m512, __m512, 1)
+test_1 (_mm512_permutex_epi64, __m512i, __m512i, 1)
+test_1 (_mm512_permutex_pd, __m512d, __m512d, 1)
+test_1 (_mm512_rol_epi32, __m512i, __m512i, 1)
+test_1 (_mm512_rol_epi64, __m512i, __m512i, 1)
+test_1 (_mm512_ror_epi32, __m512i, __m512i, 1)
+test_1 (_mm512_ror_epi64, __m512i, __m512i, 1)
+test_1 (_mm512_shuffle_epi32, __m512i, __m512i, 1)
+test_1 (_mm512_slli_epi32, __m512i, __m512i, 1)
+test_1 (_mm512_slli_epi64, __m512i, __m512i, 1)
+test_1 (_mm512_sqrt_round_pd, __m512d, __m512d, 1)
+test_1 (_mm512_sqrt_round_ps, __m512, __m512, 1)
+test_1 (_mm512_srai_epi32, __m512i, __m512i, 1)
+test_1 (_mm512_srai_epi64, __m512i, __m512i, 1)
+test_1 (_mm512_srli_epi32, __m512i, __m512i, 1)
+test_1 (_mm512_srli_epi64, __m512i, __m512i, 1)
+test_1 (_mm_cvt_roundsd_i32, int, __m128d, 1)
+test_1 (_mm_cvt_roundsd_u32, unsigned, __m128d, 1)
+test_1 (_mm_cvt_roundss_i32, int, __m128, 1)
+test_1 (_mm_cvt_roundss_u32, unsigned, __m128, 1)
+test_1 (_mm_cvtt_roundsd_i32, int, __m128d, 5)
+test_1 (_mm_cvtt_roundsd_u32, unsigned, __m128d, 5)
+test_1 (_mm_cvtt_roundss_i32, int, __m128, 5)
+test_1 (_mm_cvtt_roundss_u32, unsigned, __m128, 5)
+test_1x (_mm512_getmant_pd, __m512d, __m512d, 1, 1)
+test_1x (_mm512_getmant_ps, __m512, __m512, 1, 1)
+test_1x (_mm_cvt_roundi32_ss, __m128, __m128, 1, 1)
+test_2 (_mm512_add_round_pd, __m512d, __m512d, __m512d, 1)
+test_2 (_mm512_add_round_ps, __m512, __m512, __m512, 1)
+test_2 (_mm512_alignr_epi32, __m512i, __m512i, __m512i, 1)
+test_2 (_mm512_alignr_epi64, __m512i, __m512i, __m512i, 1)
+test_2 (_mm512_cmp_epi32_mask, __mmask16, __m512i, __m512i, 1)
+test_2 (_mm512_cmp_epi64_mask, __mmask8, __m512i, __m512i, 1)
+test_2 (_mm512_cmp_epu32_mask, __mmask16, __m512i, __m512i, 1)
+test_2 (_mm512_cmp_epu64_mask, __mmask8, __m512i, __m512i, 1)
+test_2 (_mm512_cmp_pd_mask, __mmask8, __m512d, __m512d, 1)
+test_2 (_mm512_cmp_ps_mask, __mmask16, __m512, __m512, 1)
+test_2 (_mm512_div_round_pd, __m512d, __m512d, __m512d, 1)
+test_2 (_mm512_div_round_ps, __m512, __m512, __m512, 1)
+test_2 (_mm512_i32gather_epi32, __m512i, __m512i, void const *, 1)
+test_2 (_mm512_i32gather_epi64, __m512i, __m256i, void const *, 1)
+test_2 (_mm512_i32gather_pd, __m512d, __m256i, void const *, 1)
+test_2 (_mm512_i32gather_ps, __m512, __m512i, void const *, 1)
+test_2 (_mm512_i64gather_epi32, __m256i, __m512i, void const *, 1)
+test_2 (_mm512_i64gather_epi64, __m512i, __m512i, void const *, 1)
+test_2 (_mm512_i64gather_pd, __m512d, __m512i, void const *, 1)
+test_2 (_mm512_i64gather_ps, __m256, __m512i, void const *, 1)
+test_2 (_mm512_insertf32x4, __m512, __m512, __m128, 1)
+test_2 (_mm512_insertf64x4, __m512d, __m512d, __m256d, 1)
+test_2 (_mm512_inserti32x4, __m512i, __m512i, __m128i, 1)
+test_2 (_mm512_inserti64x4, __m512i, __m512i, __m256i, 1)
+test_2 (_mm512_maskz_cvt_roundepi32_ps, __m512, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_cvt_roundepu32_ps, __m512, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_cvt_roundpd_epi32, __m256i, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_cvt_roundpd_epu32, __m256i, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_cvt_roundpd_ps, __m256, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_cvt_roundph_ps, __m512, __mmask16, __m256i, 5)
+test_2 (_mm512_maskz_cvt_roundps_epi32, __m512i, __mmask16, __m512, 1)
+test_2 (_mm512_maskz_cvt_roundps_epu32, __m512i, __mmask16, __m512, 1)
+test_2 (_mm512_maskz_cvt_roundps_pd, __m512d, __mmask8, __m256, 5)
+test_2 (_mm512_maskz_cvtps_ph, __m256i, __mmask16, __m512, 1)
+test_2 (_mm512_maskz_cvtt_roundpd_epi32, __m256i, __mmask8, __m512d, 5)
+test_2 (_mm512_maskz_cvtt_roundpd_epu32, __m256i, __mmask8, __m512d, 5)
+test_2 (_mm512_maskz_cvtt_roundps_epi32, __m512i, __mmask16, __m512, 5)
+test_2 (_mm512_maskz_cvtt_roundps_epu32, __m512i, __mmask16, __m512, 5)
+test_2 (_mm512_maskz_extractf32x4_ps, __m128, __mmask8, __m512, 1)
+test_2 (_mm512_maskz_extractf64x4_pd, __m256d, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_extracti32x4_epi32, __m128i, __mmask8, __m512i, 1)
+test_2 (_mm512_maskz_extracti64x4_epi64, __m256i, __mmask8, __m512i, 1)
+test_2 (_mm512_maskz_getexp_round_pd, __m512d, __mmask8, __m512d, 5)
+test_2 (_mm512_maskz_getexp_round_ps, __m512, __mmask16, __m512, 5)
+test_2y (_mm512_maskz_getmant_round_pd, __m512d, __mmask8, __m512d, 1, 1, 5)
+test_2y (_mm512_maskz_getmant_round_ps, __m512, __mmask16, __m512, 1, 1, 5)
+test_2 (_mm512_maskz_permute_pd, __m512d, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_permute_ps, __m512, __mmask16, __m512, 1)
+test_2 (_mm512_maskz_permutex_epi64, __m512i, __mmask8, __m512i, 1)
+test_2 (_mm512_maskz_permutex_pd, __m512d, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_rol_epi32, __m512i, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_rol_epi64, __m512i, __mmask8, __m512i, 1)
+test_2 (_mm512_maskz_ror_epi32, __m512i, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_ror_epi64, __m512i, __mmask8, __m512i, 1)
+test_2 (_mm512_maskz_shuffle_epi32, __m512i, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_slli_epi32, __m512i, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_slli_epi64, __m512i, __mmask8, __m512i, 1)
+test_2 (_mm512_maskz_sqrt_round_pd, __m512d, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_sqrt_round_ps, __m512, __mmask16, __m512, 1)
+test_2 (_mm512_maskz_srai_epi32, __m512i, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_srai_epi64, __m512i, __mmask8, __m512i, 1)
+test_2 (_mm512_maskz_srli_epi32, __m512i, __mmask16, __m512i, 1)
+test_2 (_mm512_maskz_srli_epi64, __m512i, __mmask8, __m512i, 1)
+test_2 (_mm512_max_round_pd, __m512d, __m512d, __m512d, 5)
+test_2 (_mm512_max_round_ps, __m512, __m512, __m512, 5)
+test_2 (_mm512_min_round_pd, __m512d, __m512d, __m512d, 5)
+test_2 (_mm512_min_round_ps, __m512, __m512, __m512, 5)
+test_2 (_mm512_mul_round_pd, __m512d, __m512d, __m512d, 1)
+test_2 (_mm512_mul_round_ps, __m512, __m512, __m512, 1)
+test_2 (_mm512_scalef_round_pd, __m512d, __m512d, __m512d, 1)
+test_2 (_mm512_scalef_round_ps, __m512, __m512, __m512, 1)
+test_2 (_mm512_shuffle_f32x4, __m512, __m512, __m512, 1)
+test_2 (_mm512_shuffle_f64x2, __m512d, __m512d, __m512d, 1)
+test_2 (_mm512_shuffle_i32x4, __m512i, __m512i, __m512i, 1)
+test_2 (_mm512_shuffle_i64x2, __m512i, __m512i, __m512i, 1)
+test_2 (_mm512_shuffle_pd, __m512d, __m512d, __m512d, 1)
+test_2 (_mm512_shuffle_ps, __m512, __m512, __m512, 1)
+test_2 (_mm512_sub_round_pd, __m512d, __m512d, __m512d, 1)
+test_2 (_mm512_sub_round_ps, __m512, __m512, __m512, 1)
+test_2 (_mm_cmp_sd_mask, __mmask8, __m128d, __m128d, 1)
+test_2 (_mm_cmp_ss_mask, __mmask8, __m128, __m128, 1)
+#ifdef __x86_64__
+test_2 (_mm_cvt_roundi64_sd, __m128d, __m128d, long long, 1)
+test_2 (_mm_cvt_roundi64_ss, __m128, __m128, long long, 1)
+#endif
+test_2 (_mm_cvt_roundu32_ss, __m128, __m128, unsigned, 1)
+#ifdef __x86_64__
+test_2 (_mm_cvt_roundu64_sd, __m128d, __m128d, unsigned long long, 1)
+test_2 (_mm_cvt_roundu64_ss, __m128, __m128, unsigned long long, 1)
+#endif
+test_2x (_mm512_cmp_round_pd_mask, __mmask8, __m512d, __m512d, 1, 5)
+test_2x (_mm512_cmp_round_ps_mask, __mmask16, __m512, __m512, 1, 5)
+test_2x (_mm512_maskz_roundscale_round_pd, __m512d, __mmask8, __m512d, 1, 5)
+test_2x (_mm512_maskz_roundscale_round_ps, __m512, __mmask16, __m512, 1, 5)
+test_2x (_mm_cmp_round_sd_mask, __mmask8, __m128d, __m128d, 1, 5)
+test_2x (_mm_cmp_round_ss_mask, __mmask8, __m128, __m128, 1, 5)
+test_2x (_mm_comi_round_sd, int, __m128d, __m128d, 1, 5)
+test_2x (_mm_comi_round_ss, int, __m128, __m128, 1, 5)
+test_3 (_mm512_fmadd_round_pd, __m512d, __m512d, __m512d, __m512d, 1)
+test_3 (_mm512_fmadd_round_ps, __m512, __m512, __m512, __m512, 1)
+test_3 (_mm512_fmaddsub_round_pd, __m512d, __m512d, __m512d, __m512d, 1)
+test_3 (_mm512_fmaddsub_round_ps, __m512, __m512, __m512, __m512, 1)
+test_3 (_mm512_fmsub_round_pd, __m512d, __m512d, __m512d, __m512d, 1)
+test_3 (_mm512_fmsub_round_ps, __m512, __m512, __m512, __m512, 1)
+test_3 (_mm512_fmsubadd_round_pd, __m512d, __m512d, __m512d, __m512d, 1)
+test_3 (_mm512_fmsubadd_round_ps, __m512, __m512, __m512, __m512, 1)
+test_3 (_mm512_fnmadd_round_pd, __m512d, __m512d, __m512d, __m512d, 1)
+test_3 (_mm512_fnmadd_round_ps, __m512, __m512, __m512, __m512, 1)
+test_3 (_mm512_fnmsub_round_pd, __m512d, __m512d, __m512d, __m512d, 1)
+test_3 (_mm512_fnmsub_round_ps, __m512, __m512, __m512, __m512, 1)
+test_3 (_mm512_mask_cmp_epi32_mask, __mmask16, __mmask16, __m512i, __m512i, 1)
+test_3 (_mm512_mask_cmp_epi64_mask, __mmask8, __mmask8, __m512i, __m512i, 1)
+test_3 (_mm512_mask_cmp_epu32_mask, __mmask16, __mmask16, __m512i, __m512i, 1)
+test_3 (_mm512_mask_cmp_epu64_mask, __mmask8, __mmask8, __m512i, __m512i, 1)
+test_3 (_mm512_mask_cmp_pd_mask, __mmask8, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_mask_cmp_ps_mask, __mmask16, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_mask_cvt_roundepi32_ps, __m512, __m512, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_cvt_roundepu32_ps, __m512, __m512, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_cvt_roundpd_epi32, __m256i, __m256i, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_cvt_roundpd_epu32, __m256i, __m256i, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_cvt_roundpd_ps, __m256, __m256, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_cvt_roundph_ps, __m512, __m512, __mmask16, __m256i, 5)
+test_3 (_mm512_mask_cvt_roundps_epi32, __m512i, __m512i, __mmask16, __m512, 1)
+test_3 (_mm512_mask_cvt_roundps_epu32, __m512i, __m512i, __mmask16, __m512, 1)
+test_3 (_mm512_mask_cvt_roundps_pd, __m512d, __m512d, __mmask8, __m256, 5)
+test_3 (_mm512_mask_cvtps_ph, __m256i, __m256i, __mmask16, __m512, 1)
+test_3 (_mm512_mask_cvtt_roundpd_epi32, __m256i, __m256i, __mmask8, __m512d, 5)
+test_3 (_mm512_mask_cvtt_roundpd_epu32, __m256i, __m256i, __mmask8, __m512d, 5)
+test_3 (_mm512_mask_cvtt_roundps_epi32, __m512i, __m512i, __mmask16, __m512, 5)
+test_3 (_mm512_mask_cvtt_roundps_epu32, __m512i, __m512i, __mmask16, __m512, 5)
+test_3 (_mm512_mask_extractf32x4_ps, __m128, __m128, __mmask8, __m512, 1)
+test_3 (_mm512_mask_extractf64x4_pd, __m256d, __m256d, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_extracti32x4_epi32, __m128i, __m128i, __mmask8, __m512i, 1)
+test_3 (_mm512_mask_extracti64x4_epi64, __m256i, __m256i, __mmask8, __m512i, 1)
+test_3 (_mm512_mask_getexp_round_pd, __m512d, __m512d, __mmask8, __m512d, 5)
+test_3 (_mm512_mask_getexp_round_ps, __m512, __m512, __mmask16, __m512, 5)
+test_3y (_mm512_mask_getmant_round_pd, __m512d, __m512d, __mmask8, __m512d, 1, 1, 5)
+test_3y (_mm512_mask_getmant_round_ps, __m512, __m512, __mmask16, __m512, 1, 1, 5)
+test_3 (_mm512_mask_permute_pd, __m512d, __m512d, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_permute_ps, __m512, __m512, __mmask16, __m512, 1)
+test_3 (_mm512_mask_permutex_epi64, __m512i, __m512i, __mmask8, __m512i, 1)
+test_3 (_mm512_mask_permutex_pd, __m512d, __m512d, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_rol_epi32, __m512i, __m512i, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_rol_epi64, __m512i, __m512i, __mmask8, __m512i, 1)
+test_3 (_mm512_mask_ror_epi32, __m512i, __m512i, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_ror_epi64, __m512i, __m512i, __mmask8, __m512i, 1)
+test_3 (_mm512_mask_shuffle_epi32, __m512i, __m512i, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_slli_epi32, __m512i, __m512i, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_slli_epi64, __m512i, __m512i, __mmask8, __m512i, 1)
+test_3 (_mm512_mask_sqrt_round_pd, __m512d, __m512d, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_sqrt_round_ps, __m512, __m512, __mmask16, __m512, 1)
+test_3 (_mm512_mask_srai_epi32, __m512i, __m512i, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_srai_epi64, __m512i, __m512i, __mmask8, __m512i, 1)
+test_3 (_mm512_mask_srli_epi32, __m512i, __m512i, __mmask16, __m512i, 1)
+test_3 (_mm512_mask_srli_epi64, __m512i, __m512i, __mmask8, __m512i, 1)
+test_3 (_mm512_maskz_add_round_pd, __m512d, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_maskz_add_round_ps, __m512, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_maskz_alignr_epi32, __m512i, __mmask16, __m512i, __m512i, 1)
+test_3 (_mm512_maskz_alignr_epi64, __m512i, __mmask8, __m512i, __m512i, 1)
+test_3 (_mm512_maskz_div_round_pd, __m512d, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_maskz_div_round_ps, __m512, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_maskz_insertf32x4, __m512, __mmask16, __m512, __m128, 1)
+test_3 (_mm512_maskz_insertf64x4, __m512d, __mmask8, __m512d, __m256d, 1)
+test_3 (_mm512_maskz_inserti32x4, __m512i, __mmask16, __m512i, __m128i, 1)
+test_3 (_mm512_maskz_inserti64x4, __m512i, __mmask8, __m512i, __m256i, 1)
+test_3 (_mm512_maskz_max_round_pd, __m512d, __mmask8, __m512d, __m512d, 5)
+test_3 (_mm512_maskz_max_round_ps, __m512, __mmask16, __m512, __m512, 5)
+test_3 (_mm512_maskz_min_round_pd, __m512d, __mmask8, __m512d, __m512d, 5)
+test_3 (_mm512_maskz_min_round_ps, __m512, __mmask16, __m512, __m512, 5)
+test_3 (_mm512_maskz_mul_round_pd, __m512d, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_maskz_mul_round_ps, __m512, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_maskz_scalef_round_pd, __m512d, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_maskz_scalef_round_ps, __m512, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_maskz_shuffle_f32x4, __m512, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_maskz_shuffle_f64x2, __m512d, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_maskz_shuffle_i32x4, __m512i, __mmask16, __m512i, __m512i, 1)
+test_3 (_mm512_maskz_shuffle_i64x2, __m512i, __mmask8, __m512i, __m512i, 1)
+test_3 (_mm512_maskz_shuffle_pd, __m512d, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_maskz_shuffle_ps, __m512, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_maskz_sub_round_pd, __m512d, __mmask8, __m512d, __m512d, 1)
+test_3 (_mm512_maskz_sub_round_ps, __m512, __mmask16, __m512, __m512, 1)
+test_3 (_mm512_ternarylogic_epi32, __m512i, __m512i, __m512i, __m512i, 1)
+test_3 (_mm512_ternarylogic_epi64, __m512i, __m512i, __m512i, __m512i, 1)
+test_3 (_mm_mask_cmp_sd_mask, __mmask8, __mmask8, __m128d, __m128d, 1)
+test_3 (_mm_mask_cmp_ss_mask, __mmask8, __mmask8, __m128, __m128, 1)
+test_3v (_mm512_i32scatter_epi32, void *, __m512i, __m512i, 1)
+test_3v (_mm512_i32scatter_epi64, void *, __m256i, __m512i, 1)
+test_3v (_mm512_i32scatter_pd, void *, __m256i, __m512d, 1)
+test_3v (_mm512_i32scatter_ps, void *, __m512i, __m512, 1)
+test_3v (_mm512_i64scatter_epi32, void *, __m512i, __m256i, 1)
+test_3v (_mm512_i64scatter_epi64, void *, __m512i, __m512i, 1)
+test_3v (_mm512_i64scatter_pd, void *, __m512i, __m512d, 1)
+test_3v (_mm512_i64scatter_ps, void *, __m512i, __m256, 1)
+test_3x (_mm512_mask_roundscale_round_pd, __m512d, __m512d, __mmask8, __m512d, 1, 5)
+test_3x (_mm512_mask_roundscale_round_ps, __m512, __m512, __mmask16, __m512, 1, 5)
+test_3x (_mm512_mask_cmp_round_pd_mask, __mmask8, __mmask8, __m512d, __m512d, 1, 5)
+test_3x (_mm512_mask_cmp_round_ps_mask, __mmask16, __mmask16, __m512, __m512, 1, 5)
+test_3x (_mm_fixupimm_round_sd, __m128d, __m128d, __m128d, __m128i, 1, 5)
+test_3x (_mm_fixupimm_round_ss, __m128, __m128, __m128, __m128i, 1, 5)
+test_3x (_mm_mask_cmp_round_sd_mask, __mmask8, __mmask8, __m128d, __m128d, 1, 5)
+test_3x (_mm_mask_cmp_round_ss_mask, __mmask8, __mmask8, __m128, __m128, 1, 5)
+test_4 (_mm512_mask3_fmadd_round_pd, __m512d, __m512d, __m512d, __m512d, __mmask8, 1)
+test_4 (_mm512_mask3_fmadd_round_ps, __m512, __m512, __m512, __m512, __mmask16, 1)
+test_4 (_mm512_mask3_fmaddsub_round_pd, __m512d, __m512d, __m512d, __m512d, __mmask8, 1)
+test_4 (_mm512_mask3_fmaddsub_round_ps, __m512, __m512, __m512, __m512, __mmask16, 1)
+test_4 (_mm512_mask3_fmsub_round_pd, __m512d, __m512d, __m512d, __m512d, __mmask8, 1)
+test_4 (_mm512_mask3_fmsub_round_ps, __m512, __m512, __m512, __m512, __mmask16, 1)
+test_4 (_mm512_mask3_fmsubadd_round_pd, __m512d, __m512d, __m512d, __m512d, __mmask8, 1)
+test_4 (_mm512_mask3_fmsubadd_round_ps, __m512, __m512, __m512, __m512, __mmask16, 1)
+test_4 (_mm512_mask3_fnmadd_round_pd, __m512d, __m512d, __m512d, __m512d, __mmask8, 1)
+test_4 (_mm512_mask3_fnmadd_round_ps, __m512, __m512, __m512, __m512, __mmask16, 1)
+test_4 (_mm512_mask3_fnmsub_round_pd, __m512d, __m512d, __m512d, __m512d, __mmask8, 1)
+test_4 (_mm512_mask3_fnmsub_round_ps, __m512, __m512, __m512, __m512, __mmask16, 1)
+test_4 (_mm512_mask_add_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_add_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_alignr_epi32, __m512i, __m512i, __mmask16, __m512i, __m512i, 1)
+test_4 (_mm512_mask_alignr_epi64, __m512i, __m512i, __mmask8, __m512i, __m512i, 1)
+test_4 (_mm512_mask_div_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_div_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_fmadd_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_fmadd_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_fmaddsub_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_fmaddsub_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_fmsub_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_fmsub_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_fmsubadd_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_fmsubadd_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_fnmadd_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_fnmadd_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_fnmsub_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_fnmsub_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_i32gather_epi32, __m512i, __m512i, __mmask16, __m512i, void const *, 1)
+test_4 (_mm512_mask_i32gather_epi64, __m512i, __m512i, __mmask8, __m256i, void const *, 1)
+test_4 (_mm512_mask_i32gather_pd, __m512d, __m512d, __mmask8, __m256i, void const *, 1)
+test_4 (_mm512_mask_i32gather_ps, __m512, __m512, __mmask16, __m512i, void const *, 1)
+test_4 (_mm512_mask_i64gather_epi32, __m256i, __m256i, __mmask8, __m512i, void const *, 1)
+test_4 (_mm512_mask_i64gather_epi64, __m512i, __m512i, __mmask8, __m512i, void const *, 1)
+test_4 (_mm512_mask_i64gather_pd, __m512d, __m512d, __mmask8, __m512i, void const *, 1)
+test_4 (_mm512_mask_i64gather_ps, __m256, __m256, __mmask8, __m512i, void const *, 1)
+test_4 (_mm512_mask_insertf32x4, __m512, __m512, __mmask16, __m512, __m128, 1)
+test_4 (_mm512_mask_insertf64x4, __m512d, __m512d, __mmask8, __m512d, __m256d, 1)
+test_4 (_mm512_mask_inserti32x4, __m512i, __m512i, __mmask16, __m512i, __m128i, 1)
+test_4 (_mm512_mask_inserti64x4, __m512i, __m512i, __mmask8, __m512i, __m256i, 1)
+test_4 (_mm512_mask_max_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 5)
+test_4 (_mm512_mask_max_round_ps, __m512, __m512, __mmask16, __m512, __m512, 5)
+test_4 (_mm512_mask_min_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 5)
+test_4 (_mm512_mask_min_round_ps, __m512, __m512, __mmask16, __m512, __m512, 5)
+test_4 (_mm512_mask_mul_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_mul_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_scalef_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_scalef_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_shuffle_f32x4, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_shuffle_f64x2, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_shuffle_i32x4, __m512i, __m512i, __mmask16, __m512i, __m512i, 1)
+test_4 (_mm512_mask_shuffle_i64x2, __m512i, __m512i, __mmask8, __m512i, __m512i, 1)
+test_4 (_mm512_mask_shuffle_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_shuffle_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_sub_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512d, 1)
+test_4 (_mm512_mask_sub_round_ps, __m512, __m512, __mmask16, __m512, __m512, 1)
+test_4 (_mm512_mask_ternarylogic_epi32, __m512i, __m512i, __mmask16, __m512i, __m512i, 1)
+test_4 (_mm512_mask_ternarylogic_epi64, __m512i, __m512i, __mmask8, __m512i, __m512i, 1)
+test_4 (_mm512_maskz_fmadd_round_pd, __m512d, __mmask8, __m512d, __m512d, __m512d, 1)
+test_4 (_mm512_maskz_fmadd_round_ps, __m512, __mmask16, __m512, __m512, __m512, 1)
+test_4 (_mm512_maskz_fmaddsub_round_pd, __m512d, __mmask8, __m512d, __m512d, __m512d, 1)
+test_4 (_mm512_maskz_fmaddsub_round_ps, __m512, __mmask16, __m512, __m512, __m512, 1)
+test_4 (_mm512_maskz_fmsub_round_pd, __m512d, __mmask8, __m512d, __m512d, __m512d, 1)
+test_4 (_mm512_maskz_fmsub_round_ps, __m512, __mmask16, __m512, __m512, __m512, 1)
+test_4 (_mm512_maskz_fmsubadd_round_pd, __m512d, __mmask8, __m512d, __m512d, __m512d, 1)
+test_4 (_mm512_maskz_fmsubadd_round_ps, __m512, __mmask16, __m512, __m512, __m512, 1)
+test_4 (_mm512_maskz_fnmadd_round_pd, __m512d, __mmask8, __m512d, __m512d, __m512d, 1)
+test_4 (_mm512_maskz_fnmadd_round_ps, __m512, __mmask16, __m512, __m512, __m512, 1)
+test_4 (_mm512_maskz_fnmsub_round_pd, __m512d, __mmask8, __m512d, __m512d, __m512d, 1)
+test_4 (_mm512_maskz_fnmsub_round_ps, __m512, __mmask16, __m512, __m512, __m512, 1)
+test_4 (_mm512_maskz_ternarylogic_epi32, __m512i, __mmask16, __m512i, __m512i, __m512i, 1)
+test_4 (_mm512_maskz_ternarylogic_epi64, __m512i, __mmask8, __m512i, __m512i, __m512i, 1)
+test_4v (_mm512_mask_i32scatter_epi32, void *, __mmask16, __m512i, __m512i, 1)
+test_4v (_mm512_mask_i32scatter_epi64, void *, __mmask8, __m256i, __m512i, 1)
+test_4v (_mm512_mask_i32scatter_pd, void *, __mmask8, __m256i, __m512d, 1)
+test_4v (_mm512_mask_i32scatter_ps, void *, __mmask16, __m512i, __m512, 1)
+test_4v (_mm512_mask_i64scatter_epi32, void *, __mmask8, __m512i, __m256i, 1)
+test_4v (_mm512_mask_i64scatter_epi64, void *, __mmask8, __m512i, __m512i, 1)
+test_4v (_mm512_mask_i64scatter_pd, void *, __mmask8, __m512i, __m512d, 1)
+test_4v (_mm512_mask_i64scatter_ps, void *, __mmask8, __m512i, __m256, 1)
+test_4x (_mm512_mask_fixupimm_round_pd, __m512d, __m512d, __mmask8, __m512d, __m512i, 1, 5)
+test_4x (_mm512_mask_fixupimm_round_ps, __m512, __m512, __mmask16, __m512, __m512i, 1, 5)
+test_4x (_mm512_maskz_fixupimm_round_pd, __m512d, __mmask8, __m512d, __m512d, __m512i, 1, 5)
+test_4x (_mm512_maskz_fixupimm_round_ps, __m512, __mmask16, __m512, __m512, __m512i, 1, 5)
+test_4x (_mm_mask_fixupimm_round_sd, __m128d, __m128d, __mmask8, __m128d, __m128i, 1, 5)
+test_4x (_mm_mask_fixupimm_round_ss, __m128, __m128, __mmask8, __m128, __m128i, 1, 5)
+test_4x (_mm_maskz_fixupimm_round_sd, __m128d, __mmask8, __m128d, __m128d, __m128i, 1, 5)
+test_4x (_mm_maskz_fixupimm_round_ss, __m128, __mmask8, __m128, __m128, __m128i, 1, 5)
+
+/* avx512pfintrin.h */
+test_3vx (_mm512_mask_prefetch_i32gather_ps, __m512i, __mmask16, void const *, 1, 1)
+test_3vx (_mm512_mask_prefetch_i32scatter_ps, void const *, __mmask16, __m512i, 1, 1)
+test_3vx (_mm512_mask_prefetch_i64gather_ps, __m512i, __mmask8, void const *, 1, 1)
+test_3vx (_mm512_mask_prefetch_i64scatter_ps, void const *, __mmask8, __m512i, 1, 1)
+
+/* avx512erintrin.h */
+test_1 (_mm512_exp2a23_round_pd, __m512d, __m512d, 1)
+test_1 (_mm512_exp2a23_round_ps, __m512, __m512, 1)
+test_1 (_mm512_rcp28_round_pd, __m512d, __m512d, 1)
+test_1 (_mm512_rcp28_round_ps, __m512, __m512, 1)
+test_1 (_mm512_rsqrt28_round_pd, __m512d, __m512d, 1)
+test_1 (_mm512_rsqrt28_round_ps, __m512, __m512, 1)
+test_2 (_mm512_maskz_exp2a23_round_pd, __m512d, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_exp2a23_round_ps, __m512, __mmask16, __m512, 1)
+test_2 (_mm512_maskz_rcp28_round_pd, __m512d, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_rcp28_round_ps, __m512, __mmask16, __m512, 1)
+test_2 (_mm512_maskz_rsqrt28_round_pd, __m512d, __mmask8, __m512d, 1)
+test_2 (_mm512_maskz_rsqrt28_round_ps, __m512, __mmask16, __m512, 1)
+test_3 (_mm512_mask_exp2a23_round_pd, __m512d, __m512d, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_exp2a23_round_ps, __m512, __m512, __mmask16, __m512, 1)
+test_3 (_mm512_mask_rcp28_round_pd, __m512d, __m512d, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_rcp28_round_ps, __m512, __m512, __mmask16, __m512, 1)
+test_3 (_mm512_mask_rsqrt28_round_pd, __m512d, __m512d, __mmask8, __m512d, 1)
+test_3 (_mm512_mask_rsqrt28_round_ps, __m512, __m512, __mmask16, __m512, 1)
+
/* wmmintrin.h (AES/PCLMUL). */
#ifdef DIFFERENT_PRAGMAS
#pragma GCC target ("aes,pclmul")
diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c b/gcc/testsuite/gcc.target/i386/sse-23.c
index 069f8e7cb80..f993c07cdf1 100644
--- a/gcc/testsuite/gcc.target/i386/sse-23.c
+++ b/gcc/testsuite/gcc.target/i386/sse-23.c
@@ -183,7 +183,180 @@
/* rtmintrin.h */
#define __builtin_ia32_xabort(M) __builtin_ia32_xabort(1)
-#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt")
+/* avx512fintrin.h */
+#define __builtin_ia32_addpd512_mask(A, B, C, D, E) __builtin_ia32_addpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_addps512_mask(A, B, C, D, E) __builtin_ia32_addps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_alignd512_mask(A, B, F, D, E) __builtin_ia32_alignd512_mask(A, B, 1, D, E)
+#define __builtin_ia32_alignq512_mask(A, B, F, D, E) __builtin_ia32_alignq512_mask(A, B, 1, D, E)
+#define __builtin_ia32_cmpd512_mask(A, B, E, D) __builtin_ia32_cmpd512_mask(A, B, 1, D)
+#define __builtin_ia32_cmppd512_mask(A, B, F, D, E) __builtin_ia32_cmppd512_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cmpps512_mask(A, B, F, D, E) __builtin_ia32_cmpps512_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cmpq512_mask(A, B, E, D) __builtin_ia32_cmpq512_mask(A, B, 1, D)
+#define __builtin_ia32_cmpsd_mask(A, B, F, D, E) __builtin_ia32_cmpsd_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cmpss_mask(A, B, F, D, E) __builtin_ia32_cmpss_mask(A, B, 1, D, 5)
+#define __builtin_ia32_cvtdq2ps512_mask(A, B, C, D) __builtin_ia32_cvtdq2ps512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtpd2dq512_mask(A, B, C, D) __builtin_ia32_cvtpd2dq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtpd2ps512_mask(A, B, C, D) __builtin_ia32_cvtpd2ps512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtpd2udq512_mask(A, B, C, D) __builtin_ia32_cvtpd2udq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtps2dq512_mask(A, B, C, D) __builtin_ia32_cvtps2dq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtps2pd512_mask(A, B, C, D) __builtin_ia32_cvtps2pd512_mask(A, B, C, 5)
+#define __builtin_ia32_cvtps2udq512_mask(A, B, C, D) __builtin_ia32_cvtps2udq512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtsi2sd64(A, B, C) __builtin_ia32_cvtsi2sd64(A, B, 1)
+#define __builtin_ia32_cvtsi2ss32(A, B, C) __builtin_ia32_cvtsi2ss32(A, B, 1)
+#define __builtin_ia32_cvtsi2ss64(A, B, C) __builtin_ia32_cvtsi2ss64(A, B, 1)
+#define __builtin_ia32_cvttpd2dq512_mask(A, B, C, D) __builtin_ia32_cvttpd2dq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvttpd2udq512_mask(A, B, C, D) __builtin_ia32_cvttpd2udq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvttps2dq512_mask(A, B, C, D) __builtin_ia32_cvttps2dq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvttps2udq512_mask(A, B, C, D) __builtin_ia32_cvttps2udq512_mask(A, B, C, 5)
+#define __builtin_ia32_cvtudq2ps512_mask(A, B, C, D) __builtin_ia32_cvtudq2ps512_mask(A, B, C, 1)
+#define __builtin_ia32_cvtusi2sd64(A, B, C) __builtin_ia32_cvtusi2sd64(A, B, 1)
+#define __builtin_ia32_cvtusi2ss32(A, B, C) __builtin_ia32_cvtusi2ss32(A, B, 1)
+#define __builtin_ia32_cvtusi2ss64(A, B, C) __builtin_ia32_cvtusi2ss64(A, B, 1)
+#define __builtin_ia32_divpd512_mask(A, B, C, D, E) __builtin_ia32_divpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_divps512_mask(A, B, C, D, E) __builtin_ia32_divps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_extractf32x4_mask(A, E, C, D) __builtin_ia32_extractf32x4_mask(A, 1, C, D)
+#define __builtin_ia32_extractf64x4_mask(A, E, C, D) __builtin_ia32_extractf64x4_mask(A, 1, C, D)
+#define __builtin_ia32_extracti32x4_mask(A, E, C, D) __builtin_ia32_extracti32x4_mask(A, 1, C, D)
+#define __builtin_ia32_extracti64x4_mask(A, E, C, D) __builtin_ia32_extracti64x4_mask(A, 1, C, D)
+#define __builtin_ia32_fixupimmpd512_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmpd512_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmpd512_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmpd512_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmps512_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmps512_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmps512_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmps512_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmsd_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmsd_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmsd_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmsd_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmss_mask(A, B, C, I, E, F) __builtin_ia32_fixupimmss_mask(A, B, C, 1, E, 5)
+#define __builtin_ia32_fixupimmss_maskz(A, B, C, I, E, F) __builtin_ia32_fixupimmss_maskz(A, B, C, 1, E, 5)
+#define __builtin_ia32_gatherdiv8df(A, B, C, D, F) __builtin_ia32_gatherdiv8df(A, B, C, D, 1)
+#define __builtin_ia32_gatherdiv8di(A, B, C, D, F) __builtin_ia32_gatherdiv8di(A, B, C, D, 1)
+#define __builtin_ia32_gatherdiv16sf(A, B, C, D, F) __builtin_ia32_gatherdiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_gatherdiv16si(A, B, C, D, F) __builtin_ia32_gatherdiv16si(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv16sf(A, B, C, D, F) __builtin_ia32_gathersiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv16si(A, B, C, D, F) __builtin_ia32_gathersiv16si(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv8df(A, B, C, D, F) __builtin_ia32_gathersiv8df(A, B, C, D, 1)
+#define __builtin_ia32_gathersiv8di(A, B, C, D, F) __builtin_ia32_gathersiv8di(A, B, C, D, 1)
+#define __builtin_ia32_getexppd512_mask(A, B, C, D) __builtin_ia32_getexppd512_mask(A, B, C, 5)
+#define __builtin_ia32_getexpps512_mask(A, B, C, D) __builtin_ia32_getexpps512_mask(A, B, C, 5)
+#define __builtin_ia32_getmantpd512_mask(A, F, C, D, E) __builtin_ia32_getmantpd512_mask(A, 1, C, D, 5)
+#define __builtin_ia32_getmantps512_mask(A, F, C, D, E) __builtin_ia32_getmantps512_mask(A, 1, C, D, 5)
+#define __builtin_ia32_insertf32x4_mask(A, B, F, D, E) __builtin_ia32_insertf32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_insertf64x4_mask(A, B, F, D, E) __builtin_ia32_insertf64x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_inserti32x4_mask(A, B, F, D, E) __builtin_ia32_inserti32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_inserti64x4_mask(A, B, F, D, E) __builtin_ia32_inserti64x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_maxpd512_mask(A, B, C, D, E) __builtin_ia32_maxpd512_mask(A, B, C, D, 5)
+#define __builtin_ia32_maxps512_mask(A, B, C, D, E) __builtin_ia32_maxps512_mask(A, B, C, D, 5)
+#define __builtin_ia32_minpd512_mask(A, B, C, D, E) __builtin_ia32_minpd512_mask(A, B, C, D, 5)
+#define __builtin_ia32_minps512_mask(A, B, C, D, E) __builtin_ia32_minps512_mask(A, B, C, D, 5)
+#define __builtin_ia32_mulpd512_mask(A, B, C, D, E) __builtin_ia32_mulpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_mulps512_mask(A, B, C, D, E) __builtin_ia32_mulps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_permdf512_mask(A, E, C, D) __builtin_ia32_permdf512_mask(A, 1, C, D)
+#define __builtin_ia32_permdi512_mask(A, E, C, D) __builtin_ia32_permdi512_mask(A, 1, C, D)
+#define __builtin_ia32_prold512_mask(A, E, C, D) __builtin_ia32_prold512_mask(A, 1, C, D)
+#define __builtin_ia32_prolq512_mask(A, E, C, D) __builtin_ia32_prolq512_mask(A, 1, C, D)
+#define __builtin_ia32_prord512_mask(A, E, C, D) __builtin_ia32_prord512_mask(A, 1, C, D)
+#define __builtin_ia32_prorq512_mask(A, E, C, D) __builtin_ia32_prorq512_mask(A, 1, C, D)
+#define __builtin_ia32_pshufd512_mask(A, E, C, D) __builtin_ia32_pshufd512_mask(A, 1, C, D)
+#define __builtin_ia32_pslldi512_mask(A, E, C, D) __builtin_ia32_pslldi512_mask(A, 1, C, D)
+#define __builtin_ia32_psllqi512_mask(A, E, C, D) __builtin_ia32_psllqi512_mask(A, 1, C, D)
+#define __builtin_ia32_psradi512_mask(A, E, C, D) __builtin_ia32_psradi512_mask(A, 1, C, D)
+#define __builtin_ia32_psraqi512_mask(A, E, C, D) __builtin_ia32_psraqi512_mask(A, 1, C, D)
+#define __builtin_ia32_psrldi512_mask(A, E, C, D) __builtin_ia32_psrldi512_mask(A, 1, C, D)
+#define __builtin_ia32_psrlqi512_mask(A, E, C, D) __builtin_ia32_psrlqi512_mask(A, 1, C, D)
+#define __builtin_ia32_pternlogd512_mask(A, B, C, F, E) __builtin_ia32_pternlogd512_mask(A, B, C, 1, E)
+#define __builtin_ia32_pternlogd512_maskz(A, B, C, F, E) __builtin_ia32_pternlogd512_maskz(A, B, C, 1, E)
+#define __builtin_ia32_pternlogq512_mask(A, B, C, F, E) __builtin_ia32_pternlogq512_mask(A, B, C, 1, E)
+#define __builtin_ia32_pternlogq512_maskz(A, B, C, F, E) __builtin_ia32_pternlogq512_maskz(A, B, C, 1, E)
+#define __builtin_ia32_rndscalepd_mask(A, F, C, D, E) __builtin_ia32_rndscalepd_mask(A, 1, C, D, 5)
+#define __builtin_ia32_rndscaleps_mask(A, F, C, D, E) __builtin_ia32_rndscaleps_mask(A, 1, C, D, 5)
+#define __builtin_ia32_scalefpd512_mask(A, B, C, D, E) __builtin_ia32_scalefpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_scalefps512_mask(A, B, C, D, E) __builtin_ia32_scalefps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv8df(A, B, C, D, F) __builtin_ia32_scatterdiv8df(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv8di(A, B, C, D, F) __builtin_ia32_scatterdiv8di(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv16sf(A, B, C, D, F) __builtin_ia32_scatterdiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_scatterdiv16si(A, B, C, D, F) __builtin_ia32_scatterdiv16si(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv16sf(A, B, C, D, F) __builtin_ia32_scattersiv16sf(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv16si(A, B, C, D, F) __builtin_ia32_scattersiv16si(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv8df(A, B, C, D, F) __builtin_ia32_scattersiv8df(A, B, C, D, 1)
+#define __builtin_ia32_scattersiv8di(A, B, C, D, F) __builtin_ia32_scattersiv8di(A, B, C, D, 1)
+#define __builtin_ia32_shuf_f32x4_mask(A, B, F, D, E) __builtin_ia32_shuf_f32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_shuf_f64x2_mask(A, B, F, D, E) __builtin_ia32_shuf_f64x2_mask(A, B, 1, D, E)
+#define __builtin_ia32_shuf_i32x4_mask(A, B, F, D, E) __builtin_ia32_shuf_i32x4_mask(A, B, 1, D, E)
+#define __builtin_ia32_shuf_i64x2_mask(A, B, F, D, E) __builtin_ia32_shuf_i64x2_mask(A, B, 1, D, E)
+#define __builtin_ia32_shufpd512_mask(A, B, F, D, E) __builtin_ia32_shufpd512_mask(A, B, 1, D, E)
+#define __builtin_ia32_shufps512_mask(A, B, F, D, E) __builtin_ia32_shufps512_mask(A, B, 1, D, E)
+#define __builtin_ia32_sqrtpd512_mask(A, B, C, D) __builtin_ia32_sqrtpd512_mask(A, B, C, 1)
+#define __builtin_ia32_sqrtps512_mask(A, B, C, D) __builtin_ia32_sqrtps512_mask(A, B, C, 1)
+#define __builtin_ia32_subpd512_mask(A, B, C, D, E) __builtin_ia32_subpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_subps512_mask(A, B, C, D, E) __builtin_ia32_subps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_ucmpd512_mask(A, B, E, D) __builtin_ia32_ucmpd512_mask(A, B, 1, D)
+#define __builtin_ia32_ucmpq512_mask(A, B, E, D) __builtin_ia32_ucmpq512_mask(A, B, 1, D)
+#define __builtin_ia32_vcomisd(A, B, C, D) __builtin_ia32_vcomisd(A, B, 1, 5)
+#define __builtin_ia32_vcomiss(A, B, C, D) __builtin_ia32_vcomiss(A, B, 1, 5)
+#define __builtin_ia32_vcvtph2ps512_mask(A, B, C, D) __builtin_ia32_vcvtph2ps512_mask(A, B, C, 5)
+#define __builtin_ia32_vcvtps2ph512_mask(A, E, C, D) __builtin_ia32_vcvtps2ph512_mask(A, 1, C, D)
+#define __builtin_ia32_vcvtsd2si32(A, B) __builtin_ia32_vcvtsd2si32(A, 1)
+#define __builtin_ia32_vcvtsd2si64(A, B) __builtin_ia32_vcvtsd2si64(A, 1)
+#define __builtin_ia32_vcvtsd2usi32(A, B) __builtin_ia32_vcvtsd2usi32(A, 1)
+#define __builtin_ia32_vcvtsd2usi64(A, B) __builtin_ia32_vcvtsd2usi64(A, 1)
+#define __builtin_ia32_vcvtss2si32(A, B) __builtin_ia32_vcvtss2si32(A, 1)
+#define __builtin_ia32_vcvtss2si64(A, B) __builtin_ia32_vcvtss2si64(A, 1)
+#define __builtin_ia32_vcvtss2usi32(A, B) __builtin_ia32_vcvtss2usi32(A, 1)
+#define __builtin_ia32_vcvtss2usi64(A, B) __builtin_ia32_vcvtss2usi64(A, 1)
+#define __builtin_ia32_vcvttsd2si32(A, B) __builtin_ia32_vcvttsd2si32(A, 5)
+#define __builtin_ia32_vcvttsd2si64(A, B) __builtin_ia32_vcvttsd2si64(A, 5)
+#define __builtin_ia32_vcvttsd2usi32(A, B) __builtin_ia32_vcvttsd2usi32(A, 5)
+#define __builtin_ia32_vcvttsd2usi64(A, B) __builtin_ia32_vcvttsd2usi64(A, 5)
+#define __builtin_ia32_vcvttss2si32(A, B) __builtin_ia32_vcvttss2si32(A, 5)
+#define __builtin_ia32_vcvttss2si64(A, B) __builtin_ia32_vcvttss2si64(A, 5)
+#define __builtin_ia32_vcvttss2usi32(A, B) __builtin_ia32_vcvttss2usi32(A, 5)
+#define __builtin_ia32_vcvttss2usi64(A, B) __builtin_ia32_vcvttss2usi64(A, 5)
+#define __builtin_ia32_vfmaddpd512_mask(A, B, C, D, E) __builtin_ia32_vfmaddpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddpd512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddpd512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddps512_mask(A, B, C, D, E) __builtin_ia32_vfmaddps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddps512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddps512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddps512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsd3_mask(A, B, C, D, E) __builtin_ia32_vfmaddsd3_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsd3_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsd3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsd3_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsd3_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddss3_mask(A, B, C, D, E) __builtin_ia32_vfmaddss3_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddss3_mask3(A, B, C, D, E) __builtin_ia32_vfmaddss3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddss3_maskz(A, B, C, D, E) __builtin_ia32_vfmaddss3_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubpd512_mask(A, B, C, D, E) __builtin_ia32_vfmaddsubpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsubpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubpd512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsubpd512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubps512_mask(A, B, C, D, E) __builtin_ia32_vfmaddsubps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubps512_mask3(A, B, C, D, E) __builtin_ia32_vfmaddsubps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmaddsubps512_maskz(A, B, C, D, E) __builtin_ia32_vfmaddsubps512_maskz(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubaddpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubaddpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubaddps512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubaddps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubpd512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubps512_mask3(A, B, C, D, E) __builtin_ia32_vfmsubps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubsd3_mask3(A, B, C, D, E) __builtin_ia32_vfmsubsd3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfmsubss3_mask3(A, B, C, D, E) __builtin_ia32_vfmsubss3_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfnmaddpd512_mask(A, B, C, D, E) __builtin_ia32_vfnmaddpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmaddps512_mask(A, B, C, D, E) __builtin_ia32_vfnmaddps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubpd512_mask(A, B, C, D, E) __builtin_ia32_vfnmsubpd512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubpd512_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubpd512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubps512_mask(A, B, C, D, E) __builtin_ia32_vfnmsubps512_mask(A, B, C, D, 1)
+#define __builtin_ia32_vfnmsubps512_mask3(A, B, C, D, E) __builtin_ia32_vfnmsubps512_mask3(A, B, C, D, 1)
+#define __builtin_ia32_vpermilpd512_mask(A, E, C, D) __builtin_ia32_vpermilpd512_mask(A, 1, C, D)
+#define __builtin_ia32_vpermilps512_mask(A, E, C, D) __builtin_ia32_vpermilps512_mask(A, 1, C, D)
+
+/* avx512pfintrin.h */
+#define __builtin_ia32_gatherpfdps(A, B, C, D, E) __builtin_ia32_gatherpfdps(A, B, C, 1, 1)
+#define __builtin_ia32_gatherpfqps(A, B, C, D, E) __builtin_ia32_gatherpfqps(A, B, C, 1, 1)
+#define __builtin_ia32_scatterpfdps(A, B, C, D, E) __builtin_ia32_scatterpfdps(A, B, C, 1, 1)
+#define __builtin_ia32_scatterpfqps(A, B, C, D, E) __builtin_ia32_scatterpfqps(A, B, C, 1, 1)
+
+/* avx512erintrin.h */
+#define __builtin_ia32_exp2pd_mask(A, B, C, D) __builtin_ia32_exp2pd_mask (A, B, C, 1)
+#define __builtin_ia32_exp2ps_mask(A, B, C, D) __builtin_ia32_exp2ps_mask (A, B, C, 1)
+#define __builtin_ia32_rcp28pd_mask(A, B, C, D) __builtin_ia32_rcp28pd_mask (A, B, C, 1)
+#define __builtin_ia32_rcp28ps_mask(A, B, C, D) __builtin_ia32_rcp28ps_mask (A, B, C, 1)
+#define __builtin_ia32_rsqrt28pd_mask(A, B, C, D) __builtin_ia32_rsqrt28pd_mask (A, B, C, 1)
+#define __builtin_ia32_rsqrt28ps_mask(A, B, C, D) __builtin_ia32_rsqrt28ps_mask (A, B, C, 1)
+
+#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,avx512f,avx512er,avx512pf,avx512cd")
#include <wmmintrin.h>
#include <smmintrin.h>
#include <mm3dnow.h>