On Thu, Jun 2, 2022 at 5:04 PM Jan Beulich <jbeul...@suse.com> wrote: > > The 64-bit, 128-bit, and 512-bit variants have V<n>DI return type, in > line with instruction behavior. Make the 256-bit builtin match, thus > also making it match the insn it expands to (using VI8_AVX2_AVX512BW). > > gcc/ > > * config/i386/i386-builtin.def (__builtin_ia32_psadbw256): > Change type. > * config/i386/i386-builtin-types.def: New function type > (V4DI, V32QI, V32QI). > * config/i386/i386-expand.cc (ix86_expand_args_builtin): Handle > V4DI_FTYPE_V32QI_V32QI.
LGTM, but please let HJ have the final approval. Uros. > > --- a/gcc/config/i386/i386-builtin.def > +++ b/gcc/config/i386/i386-builtin.def > @@ -1217,7 +1217,7 @@ BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR > BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_mulv8si3, > "__builtin_ia32_pmulld256" , IX86_BUILTIN_PMULLD256 , UNKNOWN, (int) > V8SI_FTYPE_V8SI_V8SI) > BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_vec_widen_umult_even_v8si, > "__builtin_ia32_pmuludq256", IX86_BUILTIN_PMULUDQ256, UNKNOWN, (int) > V4DI_FTYPE_V8SI_V8SI) > BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_iorv4di3, "__builtin_ia32_por256", > IX86_BUILTIN_POR256, UNKNOWN, (int) V4DI_FTYPE_V4DI_V4DI) > -BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_psadbw, > "__builtin_ia32_psadbw256", IX86_BUILTIN_PSADBW256, UNKNOWN, (int) > V16HI_FTYPE_V32QI_V32QI) > +BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_psadbw, > "__builtin_ia32_psadbw256", IX86_BUILTIN_PSADBW256, UNKNOWN, (int) > V4DI_FTYPE_V32QI_V32QI) > BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_pshufbv32qi3, > "__builtin_ia32_pshufb256", IX86_BUILTIN_PSHUFB256, UNKNOWN, (int) > V32QI_FTYPE_V32QI_V32QI) > BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_pshufdv3, > "__builtin_ia32_pshufd256", IX86_BUILTIN_PSHUFD256, UNKNOWN, (int) > V8SI_FTYPE_V8SI_INT) > BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_pshufhwv3, > "__builtin_ia32_pshufhw256", IX86_BUILTIN_PSHUFHW256, UNKNOWN, (int) > V16HI_FTYPE_V16HI_INT) > --- a/gcc/config/i386/i386-builtin-types.def > +++ b/gcc/config/i386/i386-builtin-types.def > @@ -516,6 +516,7 @@ DEF_FUNCTION_TYPE (V8DI, V8DI, V2DI, INT > DEF_FUNCTION_TYPE (V8DI, V8DI, V2DI, INT, V8DI, UQI) > DEF_FUNCTION_TYPE (V8DI, V8DI, V4DI, INT, V8DI, UQI) > DEF_FUNCTION_TYPE (V4DI, V8SI, V8SI) > +DEF_FUNCTION_TYPE (V4DI, V32QI, V32QI) > DEF_FUNCTION_TYPE (V8DI, V64QI, V64QI) > DEF_FUNCTION_TYPE (V4DI, V4DI, V2DI) > DEF_FUNCTION_TYPE (V4DI, PCV4DI, V4DI) > --- a/gcc/config/i386/i386-expand.cc > +++ b/gcc/config/i386/i386-expand.cc > @@ -10359,6 +10359,7 @@ ix86_expand_args_builtin (const struct b > case V8SI_FTYPE_V16HI_V16HI: > case V4DI_FTYPE_V4DI_V4DI: > case V4DI_FTYPE_V8SI_V8SI: > + case V4DI_FTYPE_V32QI_V32QI: > case V8DI_FTYPE_V64QI_V64QI: > if (comparison == UNKNOWN) > return ix86_expand_binop_builtin (icode, exp, target); >