diff options
| -rw-r--r-- | gcc/ChangeLog | 7 | ||||
| -rw-r--r-- | gcc/config/i386/i386.c | 5 | ||||
| -rw-r--r-- | gcc/config/i386/i386.h | 2 | ||||
| -rw-r--r-- | gcc/config/i386/x86-tune.def | 4 |
4 files changed, 16 insertions, 2 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 682816be898..c6fa5c08e5a 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,5 +1,12 @@ 2014-04-17 Evgeny Stupachenko <evstupac@gmail.com> + * config/i386/x86-tune.def (TARGET_SLOW_PSHUFB): New tune definition. + * config/i386/i386.h (TARGET_SLOW_PSHUFB): New tune flag. + * config/i386/i386.c (expand_vec_perm_even_odd_1): Avoid byte shuffles + for TARGET_SLOW_PSHUFB + +2014-04-17 Evgeny Stupachenko <evstupac@gmail.com> + * config/i386/i386.c (slm_cost): Adjust vec_to_scalar_cost. * config/i386/i386.c (intel_cost): Ditto. diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index bf4d5762c47..0ae3cdaf6ce 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -44026,7 +44026,7 @@ expand_vec_perm_even_odd_1 (struct expand_vec_perm_d *d, unsigned odd) gcc_unreachable (); case V8HImode: - if (TARGET_SSSE3) + if (TARGET_SSSE3 && !TARGET_SLOW_PSHUFB) return expand_vec_perm_pshufb2 (d); else { @@ -44049,7 +44049,7 @@ expand_vec_perm_even_odd_1 (struct expand_vec_perm_d *d, unsigned odd) break; case V16QImode: - if (TARGET_SSSE3) + if (TARGET_SSSE3 && !TARGET_SLOW_PSHUFB) return expand_vec_perm_pshufb2 (d); else { @@ -46318,6 +46318,7 @@ ix86_add_stmt_cost (void *data, int count, enum vect_cost_for_stmt kind, { unsigned *cost = (unsigned *) data; unsigned retval = 0; + tree vectype = stmt_info ? stmt_vectype (stmt_info) : NULL_TREE; int stmt_cost = ix86_builtin_vectorization_cost (kind, vectype, misalign); diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h index 51659deb309..1a884d86c35 100644 --- a/gcc/config/i386/i386.h +++ b/gcc/config/i386/i386.h @@ -425,6 +425,8 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST]; ix86_tune_features[X86_TUNE_USE_VECTOR_FP_CONVERTS] #define TARGET_USE_VECTOR_CONVERTS \ ix86_tune_features[X86_TUNE_USE_VECTOR_CONVERTS] +#define TARGET_SLOW_PSHUFB \ + ix86_tune_features[X86_TUNE_SLOW_PSHUFB] #define TARGET_FUSE_CMP_AND_BRANCH_32 \ ix86_tune_features[X86_TUNE_FUSE_CMP_AND_BRANCH_32] #define TARGET_FUSE_CMP_AND_BRANCH_64 \ diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def index 8399102671c..9b0ff360ab3 100644 --- a/gcc/config/i386/x86-tune.def +++ b/gcc/config/i386/x86-tune.def @@ -386,6 +386,10 @@ DEF_TUNE (X86_TUNE_USE_VECTOR_FP_CONVERTS, "use_vector_fp_converts", from integer to FP. */ DEF_TUNE (X86_TUNE_USE_VECTOR_CONVERTS, "use_vector_converts", m_AMDFAM10) +/* X86_TUNE_SLOW_SHUFB: Indicates tunings with slow pshufb instruction. */ +DEF_TUNE (X86_TUNE_SLOW_PSHUFB, "slow_pshufb", + m_BONNELL | m_SILVERMONT | m_INTEL) + /*****************************************************************************/ /* AVX instruction selection tuning (some of SSE flags affects AVX, too) */ /*****************************************************************************/ |