gcc/

        * config/i386/avx512erintrin.h (_mm_rcp28_round_sd): New.
        (_mm_rcp28_round_ss): Ditto.
        (_mm_rsqrt28_round_sd): Ditto.
        (_mm_rsqrt28_round_ss): Ditto.
        (_mm_rcp28_sd): Ditto.
        (_mm_rcp28_ss): Ditto.
        (_mm_rsqrt28_sd): Ditto.
        (_mm_rsqrt28_ss): Ditto.
        * config/i386/avx512fintrin.h (_mm512_stream_load_si512): Ditto.
        * config/i386/i386-builtin-types.def (V8DI_FTYPE_PV8DI): Ditto.
        * config/i386/i386.c (IX86_BUILTIN_MOVNTDQA512): Ditto.
        (IX86_BUILTIN_RCP28SD): Ditto.
        (IX86_BUILTIN_RCP28SS): Ditto.
        (IX86_BUILTIN_RSQRT28SD): Ditto.
        (IX86_BUILTIN_RSQRT28SS): Ditto.
        (bdesc_special_args): Define __builtin_ia32_movntdqa512,
        __builtin_ia32_rcp28sd_round, __builtin_ia32_rcp28ss_round,
        __builtin_ia32_rsqrt28sd_round, __builtin_ia32_rsqrt28ss_round.
        (ix86_expand_special_args_builtin): Expand new FTYPE.
        * config/i386/sse.md (define_mode_attr "sse4_1_avx2"): Expand to V8DI.
        (srcp14<mode>): Make insn unary.
        (avx512f_vmscalef<mode><round_name>): Use substed predicate.
        (avx512f_sgetexp<mode><round_saeonly_name>): Ditto.
        (avx512f_rndscale<mode><round_saeonly_name>): Ditto.
        (<sse4_1_avx2>_movntdqa): Extend to 512 bits.
        (avx512er_exp2<mode><mask_name><round_saeonly_name>):
        Fix rounding: make it SAE only.
        (<mask_codefor>avx512er_rcp28<mode><mask_name><round_saeonly_name>): Ditto.
        (<mask_codefor>avx512er_rsqrt28<mode><mask_name><round_saeonly_name>): Ditto.
        (avx512er_vmrcp28<mode><round_saeonly_name>): Ditto.
        (avx512er_vmrsqrt28<mode><round_saeonly_name>): Ditto.
        (avx512f_getmant<mode><mask_name><round_saeonly_name>): Ditto.
        * config/i386/subst.md (round_saeonly_mask_scalar_operand3): Remove.
        (round_saeonly_mask_scalar_operand4): Ditto.
        (round_saeonly_mask_scalar_op3): Ditto.
        (round_saeonly_mask_scalar_op4): Ditto.

gcc/testsuite/
        * gcc.target/i386/avx-1.c: Fix __builtin_ia32_exp2ps_mask,
        __builtin_ia32_exp2pd_mask, __builtin_ia32_rcp28ps_mask,
        __builtin_ia32_rcp28pd_mask, __builtin_ia32_rsqrt28ps_mask,
        __builtin_ia32_rsqrt28pd_mask. Add __builtin_ia32_rcp28ss_round,
        __builtin_ia32_rcp28sd_round, __builtin_ia32_rsqrt28ss_round,
        __builtin_ia32_rsqrt28sd_round.
        * gcc.target/i386/avx512er-vexp2pd-1.c: Fix rounding mode.
        * gcc.target/i386/avx512er-vexp2ps-1.c: Ditto.
        * gcc.target/i386/avx512er-vrcp28pd-1.c: Ditto.
        * gcc.target/i386/avx512er-vrcp28ps-1.c: Ditto.
        * gcc.target/i386/avx512er-vrsqrt28pd-1.c: Ditto.
        * gcc.target/i386/avx512er-vrsqrt28ps-1.c: Ditto.
        * gcc.target/i386/avx512er-vrcp28sd-1.c: New.
        * gcc.target/i386/avx512er-vrcp28sd-2.c: Ditto.
        * gcc.target/i386/avx512er-vrcp28ss-1.c: Ditto.
        * gcc.target/i386/avx512er-vrcp28ss-2.c: Ditto.
        * gcc.target/i386/avx512er-vrsqrt28sd-1.c: Ditto.
        * gcc.target/i386/avx512er-vrsqrt28sd-2.c: Ditto.
        * gcc.target/i386/avx512er-vrsqrt28ss-1.c: Ditto.
        * gcc.target/i386/avx512er-vrsqrt28ss-2.c: Ditto.
        * gcc.target/i386/avx512f-vmovntdqa-1.c: Ditto.
        * gcc.target/i386/avx512f-vmovntdqa-2.c: Ditto.
        * gcc.target/i386/avx512f-vrcp14sd-2.c: Fix.
        * gcc.target/i386/avx512f-vrcp14ss-2.c: Ditto.
        * gcc.target/i386/sse-22.c: Extend with new built-ins,
        fix wrong rounding mode (see above).
        * gcc.target/i386/sse-23.c: Ditto.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@206596 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 62 insertions, 0 deletions

diff --git a/gcc/config/i386/avx512erintrin.h b/gcc/config/i386/avx512erintrin.h
index f442f2bec94..6fe05bc6608 100644
--- a/gcc/config/i386/avx512erintrin.h
+++ b/gcc/config/i386/avx512erintrin.h
@@ -159,6 +159,24 @@ _mm512_maskz_rcp28_round_ps (__mmask16 __U, __m512 __A, int __R)
 					       (__mmask16) __U, __R);
 }
 
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rcp28_round_sd (__m128d __A, __m128d __B, int __R)
+{
+  return (__m128d) __builtin_ia32_rcp28sd_round ((__v2df) __A,
+						 (__v2df) __B,
+						 __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rcp28_round_ss (__m128 __A, __m128 __B, int __R)
+{
+  return (__m128) __builtin_ia32_rcp28ss_round ((__v4sf) __A,
+						(__v4sf) __B,
+						__R);
+}
+
 extern __inline __m512d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm512_rsqrt28_round_pd (__m512d __A, int __R)
@@ -214,6 +232,25 @@ _mm512_maskz_rsqrt28_round_ps (__mmask16 __U, __m512 __A, int __R)
 						 (__v16sf) _mm512_setzero_ps (),
 						 (__mmask16) __U, __R);
 }
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rsqrt28_round_sd (__m128d __A, __m128d __B, int __R)
+{
+  return (__m128d) __builtin_ia32_rsqrt28sd_round ((__v2df) __A,
+						   (__v2df) __B,
+						   __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_rsqrt28_round_ss (__m128 __A, __m128 __B, int __R)
+{
+  return (__m128) __builtin_ia32_rsqrt28ss_round ((__v4sf) __A,
+						  (__v4sf) __B,
+						  __R);
+}
+
 #else
 #define _mm512_exp2a23_round_pd(A, C)            \
     __builtin_ia32_exp2pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
@@ -268,6 +305,19 @@ _mm512_maskz_rsqrt28_round_ps (__mmask16 __U, __m512 __A, int __R)
 
 #define _mm512_maskz_rsqrt28_round_ps(U, A, C)   \
     __builtin_ia32_rsqrt28ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
+
+#define _mm_rcp28_round_sd(A, B, R)	\
+    __builtin_ia32_rcp28sd_round(A, B, R)
+
+#define _mm_rcp28_round_ss(A, B, R)	\
+    __builtin_ia32_rcp28ss_round(A, B, R)
+
+#define _mm_rsqrt28_round_sd(A, B, R)	\
+    __builtin_ia32_rsqrt28sd_round(A, B, R)
+
+#define _mm_rsqrt28_round_ss(A, B, R)	\
+    __builtin_ia32_rsqrt28ss_round(A, B, R)
+
 #endif
 
 #define _mm512_exp2a23_pd(A)                    \
@@ -324,6 +374,18 @@ _mm512_maskz_rsqrt28_round_ps (__mmask16 __U, __m512 __A, int __R)
 #define _mm512_maskz_rsqrt28_ps(U, A)     \
     _mm512_maskz_rsqrt28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
 
+#define _mm_rcp28_sd(A, B)	\
+    __builtin_ia32_rcp28sd_round(A, B, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm_rcp28_ss(A, B)	\
+    __builtin_ia32_rcp28ss_round(A, B, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm_rsqrt28_sd(A, B)	\
+    __builtin_ia32_rsqrt28sd_round(A, B, _MM_FROUND_CUR_DIRECTION)
+
+#define _mm_rsqrt28_ss(A, B)	\
+    __builtin_ia32_rsqrt28ss_round(A, B, _MM_FROUND_CUR_DIRECTION)
+
 #ifdef __DISABLE_AVX512ER__
 #undef __DISABLE_AVX512ER__
 #pragma GCC pop_options