From: Hongtao Liu Date: Wed, 26 Jun 2019 04:46:29 +0000 (+0000) Subject: Enable GCC support for AVX512_VP2INTERSECT which will be in tigerlaker. X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=e21b52afe92f2596a5b0963d6efb5be44ab3b227;p=gcc.git Enable GCC support for AVX512_VP2INTERSECT which will be in tigerlaker. There are two instructions for AVX512_VP2INTERSECT: VP2INTERSECTD and VP2INTERSECTQ. gcc/ 2019-06-05 Hongtao Liu * common/config/i386/i386-common.c (OPTION_MASK_ISA_AVX512VP2INTERSECT_SET, OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET): New macros. (OPTION_MASK_ISA2_AVX512F_UNSET): Add OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET. (ix86_handle_option): Handle -mavx512vp2intersect. * config/i386/avx512vp2intersectintrin.h: New. * config/i386/avx512vp2intersectvlintrin.h: New. * config/i386/cpuid.h (bit_AVX512VP2INTERSECT): New. * config/i386/driver-i386.c (host_detect_local_cpu): Detect AVX512VP2INTERSECT. * config/i386/i386-builtin-types.def: Add new types. * config/i386/i386-builtin.def: Add new builtins. * config/i386/i386-builtins.c: (enum processor_features): Add F_AVX512VP2INTERSECT. (static const _isa_names_table isa_names_table): Ditto. * config/i386/i386-c.c (ix86_target_macros_internal): Define __AVX512VP2INTERSECT__. * config/i386/i386-expand.c (ix86_expand_builtin): Expand IX86_BUILTIN_2INTERSECTD512, IX86_BUILTIN_2INTERSECTQ512, IX86_BUILTIN_2INTERSECTD256, IX86_BUILTIN_2INTERSECTQ256, IX86_BUILTIN_2INTERSECTD128, IX86_BUILTIN_2INTERSECTQ128. * config/i386/i386-modes.def (P2QI, P2HI): New modes. * config/i386/i386-options.c (ix86_target_string): Add -mavx512vp2intersect. (ix86_option_override_internal): Handle AVX512VP2INTERSECT. * config/i386/i386.c (ix86_hard_regno_nregs): Allocate two regs for P2HImode and P2QImode. (ix86_hard_regno_mode_ok): Register pair only starts at even hardreg number for P2QImode and P2HImode. (ix86_regmode_natural_size): New function. * config/i386/i386.h (TARGET_AVX512VP2INTERSECT, TARGET_AVX512VP2INTERSECT_P, PTA_AVX512VP2INTERSECT REGMODE_NATURAL_SIZE, MASK_PAIR_REGNO_P): New. * config/i386/i386-protos.h (ix86_regmode_natural_size): Declare * config/i386/i386.opt: Add -mavx512vp2intersect. * config/i386/immintrin.h: Include avx512vp2intersectintrin.h and avx512vp2intersectvlintrin.h. * config/i386/sse.md (define_c_enum "unspec"): Add UNSPEC_VP2INTERSECT. (define_mode_iterator VI48_AVX512VP2VL): New. (avx512vp2intersect_2intersect, avx512vp2intersect_2intersectv16si): New define_insn patterns. * config.gcc: Add avx512vp2intersectvlintrin.h and avx512vp2intersectintrin.h to extra_headers. * doc/invoke.texi: Document -mavx512vp2intersect. gcc/testsuite 2019-06-06 Hongtao Liu Olga Makhotina * gcc.target/i386/avx512-check.h: Handle bit_AVX512VP2INTERSECT. * gcc.target/i386/avx512vp2intersect-2intersect-1a.c: New test. * gcc.target/i386/avx512vp2intersect-2intersect-1b.c: Likewise. * gcc.target/i386/avx512vp2intersect-2intersectvl-1a.c: Likewise. * gcc.target/i386/avx512vp2intersect-2intersectvl-1b.c: Likewise. * gcc.target/i386/sse-12.c: Add -mavx512vp2intersect. * gcc.target/i386/sse-13.c: Likewsie. * gcc.target/i386/sse-14.c: Likewise. * gcc.target/i386/sse-22.c: Likewise. * gcc.target/i386/sse-23.c: Likewise. * g++.dg/other/i386-2.C: Likewise. * g++.dg/other/i386-3.C: Likewise. Co-Authored-By: H.J. Lu Co-Authored-By: Olga Makhotina From-SVN: r272668 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 9d8d109ca0f..7945fdca7da 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,53 @@ +2019-06-25 Hongtao Liu + H.J. Lu + Olga Makhotina + + * common/config/i386/i386-common.c + (OPTION_MASK_ISA_AVX512VP2INTERSECT_SET, + OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET): New macros. + (OPTION_MASK_ISA2_AVX512F_UNSET): Add + OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET. + (ix86_handle_option): Handle -mavx512vp2intersect. + * config/i386/avx512vp2intersectintrin.h: New. + * config/i386/avx512vp2intersectvlintrin.h: New. + * config/i386/cpuid.h (bit_AVX512VP2INTERSECT): New. + * config/i386/driver-i386.c (host_detect_local_cpu): Detect + AVX512VP2INTERSECT. + * config/i386/i386-builtin-types.def: Add new types. + * config/i386/i386-builtin.def: Add new builtins. + * config/i386/i386-builtins.c: (enum processor_features): Add + F_AVX512VP2INTERSECT. + (static const _isa_names_table isa_names_table): Ditto. + * config/i386/i386-c.c (ix86_target_macros_internal): Define + __AVX512VP2INTERSECT__. + * config/i386/i386-expand.c (ix86_expand_builtin): Expand + IX86_BUILTIN_2INTERSECTD512, IX86_BUILTIN_2INTERSECTQ512, + IX86_BUILTIN_2INTERSECTD256, IX86_BUILTIN_2INTERSECTQ256, + IX86_BUILTIN_2INTERSECTD128, IX86_BUILTIN_2INTERSECTQ128. + * config/i386/i386-modes.def (P2QI, P2HI): New modes. + * config/i386/i386-options.c (ix86_target_string): Add + -mavx512vp2intersect. + (ix86_option_override_internal): Handle AVX512VP2INTERSECT. + * config/i386/i386.c (ix86_hard_regno_nregs): Allocate two regs for + P2HImode and P2QImode. + (ix86_hard_regno_mode_ok): Register pair only starts at even hardreg + number for P2QImode and P2HImode. + (ix86_regmode_natural_size): New function. + * config/i386/i386.h (TARGET_AVX512VP2INTERSECT, + TARGET_AVX512VP2INTERSECT_P, PTA_AVX512VP2INTERSECT + REGMODE_NATURAL_SIZE, MASK_PAIR_REGNO_P): New. + * config/i386/i386-protos.h (ix86_regmode_natural_size): Declare + * config/i386/i386.opt: Add -mavx512vp2intersect. + * config/i386/immintrin.h: Include avx512vp2intersectintrin.h and + avx512vp2intersectvlintrin.h. + * config/i386/sse.md (define_c_enum "unspec"): Add UNSPEC_VP2INTERSECT. + (define_mode_iterator VI48_AVX512VP2VL): New. + (avx512vp2intersect_2intersect, + avx512vp2intersect_2intersectv16si): New define_insn patterns. + * config.gcc: Add avx512vp2intersectvlintrin.h and + avx512vp2intersectintrin.h to extra_headers. + * doc/invoke.texi: Document -mavx512vp2intersect. + 2019-06-25 Iain Sandoe * config/rs6000/darwin.h (ENDFILE_SPEC): New. diff --git a/gcc/common/config/i386/i386-common.c b/gcc/common/config/i386/i386-common.c index 096aa3d4763..a394f874fe4 100644 --- a/gcc/common/config/i386/i386-common.c +++ b/gcc/common/config/i386/i386-common.c @@ -100,6 +100,7 @@ along with GCC; see the file COPYING3. If not see #define OPTION_MASK_ISA_XSAVEC_SET \ (OPTION_MASK_ISA_XSAVEC | OPTION_MASK_ISA_XSAVE_SET) #define OPTION_MASK_ISA_CLWB_SET OPTION_MASK_ISA_CLWB +#define OPTION_MASK_ISA_AVX512VP2INTERSECT_SET OPTION_MASK_ISA_AVX512VP2INTERSECT /* SSE4 includes both SSE4.1 and SSE4.2. -msse4 should be the same as -msse4.2. */ @@ -240,6 +241,7 @@ along with GCC; see the file COPYING3. If not see #define OPTION_MASK_ISA_WAITPKG_UNSET OPTION_MASK_ISA_WAITPKG #define OPTION_MASK_ISA_CLDEMOTE_UNSET OPTION_MASK_ISA_CLDEMOTE #define OPTION_MASK_ISA_ENQCMD_UNSET OPTION_MASK_ISA_ENQCMD +#define OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET OPTION_MASK_ISA_AVX512VP2INTERSECT /* SSE4 includes both SSE4.1 and SSE4.2. -mno-sse4 should the same as -mno-sse4.1. */ @@ -282,7 +284,8 @@ along with GCC; see the file COPYING3. If not see #define OPTION_MASK_ISA2_AVX512F_UNSET \ (OPTION_MASK_ISA_AVX512BF16_UNSET \ | OPTION_MASK_ISA_AVX5124FMAPS_UNSET \ - | OPTION_MASK_ISA_AVX5124VNNIW_UNSET) + | OPTION_MASK_ISA_AVX5124VNNIW_UNSET \ + | OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET) #define OPTION_MASK_ISA2_GENERAL_REGS_ONLY_UNSET \ (OPTION_MASK_ISA2_AVX512F_UNSET) @@ -880,6 +883,23 @@ ix86_handle_option (struct gcc_options *opts, } return true; + case OPT_mavx512vp2intersect: + if (value) + { + opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA_AVX512VP2INTERSECT_SET; + opts->x_ix86_isa_flags2_explicit |= + OPTION_MASK_ISA_AVX512VP2INTERSECT_SET; + opts->x_ix86_isa_flags |= OPTION_MASK_ISA_AVX512F_SET; + opts->x_ix86_isa_flags_explicit |= OPTION_MASK_ISA_AVX512F_SET; + } + else + { + opts->x_ix86_isa_flags2 &= ~OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET; + opts->x_ix86_isa_flags2_explicit |= + OPTION_MASK_ISA_AVX512VP2INTERSECT_UNSET; + } + return true; + case OPT_mfma: if (value) { diff --git a/gcc/config.gcc b/gcc/config.gcc index fd065c48a55..fe010d7e543 100644 --- a/gcc/config.gcc +++ b/gcc/config.gcc @@ -408,7 +408,7 @@ i[34567]86-*-*) avx512vpopcntdqvlintrin.h avx512bitalgintrin.h pconfigintrin.h wbnoinvdintrin.h movdirintrin.h waitpkgintrin.h cldemoteintrin.h avx512bf16vlintrin.h avx512bf16intrin.h - enqcmdintrin.h" + enqcmdintrin.h avx512vp2intersectintrin.h avx512vp2intersectvlintrin.h" ;; x86_64-*-*) cpu_type=i386 @@ -441,7 +441,7 @@ x86_64-*-*) avx512vpopcntdqvlintrin.h avx512bitalgintrin.h pconfigintrin.h wbnoinvdintrin.h movdirintrin.h waitpkgintrin.h cldemoteintrin.h avx512bf16vlintrin.h avx512bf16intrin.h - enqcmdintrin.h" + enqcmdintrin.h avx512vp2intersectintrin.h avx512vp2intersectvlintrin.h" ;; ia64-*-*) extra_headers=ia64intrin.h diff --git a/gcc/config/i386/avx512vp2intersectintrin.h b/gcc/config/i386/avx512vp2intersectintrin.h new file mode 100644 index 00000000000..60cb52c2ee0 --- /dev/null +++ b/gcc/config/i386/avx512vp2intersectintrin.h @@ -0,0 +1,35 @@ +#if !defined _IMMINTRIN_H_INCLUDED +#error "Never use directly; include instead." +#endif + +#ifndef _AVX512VP2INTERSECTINTRIN_H_INCLUDED +#define _AVX512VP2INTERSECTINTRIN_H_INCLUDED + +#if !defined(__AVX512VP2INTERSECT__) +#pragma GCC push_options +#pragma GCC target("avx512vp2intersect") +#define __DISABLE_AVX512VP2INTERSECT__ +#endif /* __AVX512VP2INTERSECT__ */ + +extern __inline void +__attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_2intersect_epi32 (__m512i __A, __m512i __B, __mmask16 *__U, + __mmask16 *__M) +{ + __builtin_ia32_2intersectd512 (__U, __M, (__v16si) __A, (__v16si) __B); +} + +extern __inline void +__attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_2intersect_epi64 (__m512i __A, __m512i __B, __mmask8 *__U, + __mmask8 *__M) +{ + __builtin_ia32_2intersectq512 (__U, __M, (__v8di) __A, (__v8di) __B); +} + +#ifdef __DISABLE_AVX512VP2INTERSECT__ +#undef __DISABLE_AVX512VP2INTERSECT__ +#pragma GCC pop_options +#endif /* __DISABLE_AVX512VP2INTERSECT__ */ + +#endif /* _AVX512VP2INTERSECTINTRIN_H_INCLUDED */ diff --git a/gcc/config/i386/avx512vp2intersectvlintrin.h b/gcc/config/i386/avx512vp2intersectvlintrin.h new file mode 100644 index 00000000000..26eee36602c --- /dev/null +++ b/gcc/config/i386/avx512vp2intersectvlintrin.h @@ -0,0 +1,49 @@ +#if !defined _IMMINTRIN_H_INCLUDED +#error "Never use directly; include instead." +#endif + +#ifndef _AVX512VP2INTERSECTVLINTRIN_H_INCLUDED +#define _AVX512VP2INTERSECTVLINTRIN_H_INCLUDED + +#if !defined(__AVX512VP2INTERSECT__) || !defined(__AVX512VL__) +#pragma GCC push_options +#pragma GCC target("avx512vp2intersect,avx512vl") +#define __DISABLE_AVX512VP2INTERSECTVL__ +#endif /* __AVX512VP2INTERSECTVL__ */ + +extern __inline void +__attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm_2intersect_epi32 (__m128i __A, __m128i __B, __mmask8 *__U, __mmask8 *__M) +{ + __builtin_ia32_2intersectd128 (__U, __M, (__v4si) __A, (__v4si) __B); +} + +extern __inline void +__attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm256_2intersect_epi32 (__m256i __A, __m256i __B, __mmask8 *__U, + __mmask8 *__M) +{ + __builtin_ia32_2intersectd256 (__U, __M, (__v8si) __A, (__v8si) __B); +} + +extern __inline void +__attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm_2intersect_epi64 (__m128i __A, __m128i __B, __mmask8 *__U, __mmask8 *__M) +{ + __builtin_ia32_2intersectq128 (__U, __M, (__v2di) __A, (__v2di) __B); +} + +extern __inline void +__attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm256_2intersect_epi64 (__m256i __A, __m256i __B, __mmask8 *__U, + __mmask8 *__M) +{ + __builtin_ia32_2intersectq256 (__U, __M, (__v4di) __A, (__v4di) __B); +} + +#ifdef __DISABLE_AVX512VP2INTERSECTVL__ +#undef __DISABLE_AVX512VP2INTERSECTVL__ +#pragma GCC pop_options +#endif /* __DISABLE_AVX512VP2INTERSECTVL__ */ + +#endif /* _AVX512VP2INTERSECTVLINTRIN_H_INCLUDED */ diff --git a/gcc/config/i386/cpuid.h b/gcc/config/i386/cpuid.h index 2fda7e73697..6108577cc3b 100644 --- a/gcc/config/i386/cpuid.h +++ b/gcc/config/i386/cpuid.h @@ -119,6 +119,7 @@ /* %edx */ #define bit_AVX5124VNNIW (1 << 2) #define bit_AVX5124FMAPS (1 << 3) +#define bit_AVX512VP2INTERSECT (1 << 8) #define bit_IBT (1 << 20) #define bit_PCONFIG (1 << 18) /* XFEATURE_ENABLED_MASK register bits (%eax == 13, %ecx == 0) */ diff --git a/gcc/config/i386/driver-i386.c b/gcc/config/i386/driver-i386.c index d5c62c07d56..a9d89817202 100644 --- a/gcc/config/i386/driver-i386.c +++ b/gcc/config/i386/driver-i386.c @@ -423,6 +423,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) unsigned int has_shstk = 0; unsigned int has_avx512vnni = 0, has_vaes = 0; unsigned int has_vpclmulqdq = 0; + unsigned int has_avx512vp2intersect = 0; unsigned int has_movdiri = 0, has_movdir64b = 0; unsigned int has_enqcmd = 0; unsigned int has_waitpkg = 0; @@ -532,6 +533,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) has_avx5124vnniw = edx & bit_AVX5124VNNIW; has_avx5124fmaps = edx & bit_AVX5124FMAPS; + has_avx512vp2intersect = edx & bit_AVX512VP2INTERSECT; has_shstk = ecx & bit_SHSTK; has_pconfig = edx & bit_PCONFIG; @@ -1143,6 +1145,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) const char *shstk = has_shstk ? " -mshstk" : " -mno-shstk"; const char *vaes = has_vaes ? " -mvaes" : " -mno-vaes"; const char *vpclmulqdq = has_vpclmulqdq ? " -mvpclmulqdq" : " -mno-vpclmulqdq"; + const char *avx512vp2intersect = has_avx512vp2intersect ? " -mavx512vp2intersect" : " -mno-avx512vp2intersect"; const char *avx512bitalg = has_avx512bitalg ? " -mavx512bitalg" : " -mno-avx512bitalg"; const char *movdiri = has_movdiri ? " -mmovdiri" : " -mno-movdiri"; const char *movdir64b = has_movdir64b ? " -mmovdir64b" : " -mno-movdir64b"; @@ -1165,7 +1168,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) clwb, mwaitx, clzero, pku, rdpid, gfni, shstk, avx512vbmi2, avx512vnni, vaes, vpclmulqdq, avx512bitalg, movdiri, movdir64b, waitpkg, cldemote, - ptwrite, avx512bf16, enqcmd, + ptwrite, avx512bf16, enqcmd, avx512vp2intersect, NULL); } diff --git a/gcc/config/i386/i386-builtin-types.def b/gcc/config/i386/i386-builtin-types.def index 4d190604904..221c0e7bb73 100644 --- a/gcc/config/i386/i386-builtin-types.def +++ b/gcc/config/i386/i386-builtin-types.def @@ -975,6 +975,13 @@ DEF_FUNCTION_TYPE (QI, V8SF, INT, UQI) DEF_FUNCTION_TYPE (QI, V4SF, INT, UQI) DEF_FUNCTION_TYPE (VOID, PV32QI, V32HI, USI) +DEF_FUNCTION_TYPE (VOID, PUHI, PUHI, V16SI, V16SI) +DEF_FUNCTION_TYPE (VOID, PUQI, PUQI, V8SI, V8SI) +DEF_FUNCTION_TYPE (VOID, PUQI, PUQI, V4SI, V4SI) +DEF_FUNCTION_TYPE (VOID, PUQI, PUQI, V8DI, V8DI) +DEF_FUNCTION_TYPE (VOID, PUQI, PUQI, V4DI, V4DI) +DEF_FUNCTION_TYPE (VOID, PUQI, PUQI, V2DI, V2DI) + DEF_FUNCTION_TYPE (V2DI, V2DI, V2DI, UINT, UINT) DEF_FUNCTION_TYPE (V4HI, HI, HI, HI, HI) diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def index e547dda80f1..aad62f3e401 100644 --- a/gcc/config/i386/i386-builtin.def +++ b/gcc/config/i386/i386-builtin.def @@ -288,6 +288,14 @@ BDESC (OPTION_MASK_ISA_AVX512BW, 0, CODE_FOR_avx512bw_loadv64qi_mask, "__builtin BDESC (OPTION_MASK_ISA_AVX512BW, 0, CODE_FOR_avx512bw_storev32hi_mask, "__builtin_ia32_storedquhi512_mask", IX86_BUILTIN_STOREDQUHI512_MASK, UNKNOWN, (int) VOID_FTYPE_PSHORT_V32HI_USI) BDESC (OPTION_MASK_ISA_AVX512BW, 0, CODE_FOR_avx512bw_storev64qi_mask, "__builtin_ia32_storedquqi512_mask", IX86_BUILTIN_STOREDQUQI512_MASK, UNKNOWN, (int) VOID_FTYPE_PCHAR_V64QI_UDI) +/* AVX512VP2INTERSECT */ +BDESC (0, OPTION_MASK_ISA_AVX512VP2INTERSECT, CODE_FOR_nothing, "__builtin_ia32_2intersectd512", IX86_BUILTIN_2INTERSECTD512, UNKNOWN, (int) VOID_FTYPE_PUHI_PUHI_V16SI_V16SI) +BDESC (0, OPTION_MASK_ISA_AVX512VP2INTERSECT, CODE_FOR_nothing, "__builtin_ia32_2intersectq512", IX86_BUILTIN_2INTERSECTQ512, UNKNOWN, (int) VOID_FTYPE_PUQI_PUQI_V8DI_V8DI) +BDESC (0, OPTION_MASK_ISA_AVX512VP2INTERSECT, CODE_FOR_nothing, "__builtin_ia32_2intersectd256", IX86_BUILTIN_2INTERSECTD256, UNKNOWN, (int) VOID_FTYPE_PUQI_PUQI_V8SI_V8SI) +BDESC (0, OPTION_MASK_ISA_AVX512VP2INTERSECT, CODE_FOR_nothing, "__builtin_ia32_2intersectq256", IX86_BUILTIN_2INTERSECTQ256, UNKNOWN, (int) VOID_FTYPE_PUQI_PUQI_V4DI_V4DI) +BDESC (0, OPTION_MASK_ISA_AVX512VP2INTERSECT, CODE_FOR_nothing, "__builtin_ia32_2intersectd128", IX86_BUILTIN_2INTERSECTD128, UNKNOWN, (int) VOID_FTYPE_PUQI_PUQI_V4SI_V4SI) +BDESC (0, OPTION_MASK_ISA_AVX512VP2INTERSECT, CODE_FOR_nothing, "__builtin_ia32_2intersectq128", IX86_BUILTIN_2INTERSECTQ128, UNKNOWN, (int) VOID_FTYPE_PUQI_PUQI_V2DI_V2DI) + /* AVX512VL */ BDESC (OPTION_MASK_ISA_AVX512BW | OPTION_MASK_ISA_AVX512VL, 0, CODE_FOR_avx512vl_loadv16hi_mask, "__builtin_ia32_loaddquhi256_mask", IX86_BUILTIN_LOADDQUHI256_MASK, UNKNOWN, (int) V16HI_FTYPE_PCSHORT_V16HI_UHI) BDESC (OPTION_MASK_ISA_AVX512BW | OPTION_MASK_ISA_AVX512VL, 0, CODE_FOR_avx512vl_loadv8hi_mask, "__builtin_ia32_loaddquhi128_mask", IX86_BUILTIN_LOADDQUHI128_MASK, UNKNOWN, (int) V8HI_FTYPE_PCSHORT_V8HI_UQI) diff --git a/gcc/config/i386/i386-builtins.c b/gcc/config/i386/i386-builtins.c index 9484b3d2daf..9b6a59dd136 100644 --- a/gcc/config/i386/i386-builtins.c +++ b/gcc/config/i386/i386-builtins.c @@ -1924,6 +1924,7 @@ enum processor_features F_VPCLMULQDQ, F_AVX512VNNI, F_AVX512BITALG, + F_AVX512VP2INTERSECT, F_AVX512BF16, F_MAX }; @@ -2070,6 +2071,7 @@ static const _isa_names_table isa_names_table[] = {"vpclmulqdq", F_VPCLMULQDQ, P_ZERO}, {"avx512vnni", F_AVX512VNNI, P_ZERO}, {"avx512bitalg", F_AVX512BITALG, P_ZERO}, + {"avx512vp2intersect",F_AVX512VP2INTERSECT, P_ZERO}, {"avx512bf16", F_AVX512BF16, P_ZERO} }; diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c index 0438a4266d4..ec5f15bee26 100644 --- a/gcc/config/i386/i386-c.c +++ b/gcc/config/i386/i386-c.c @@ -404,6 +404,8 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag, if (isa_flag2 & OPTION_MASK_ISA_WBNOINVD) def_or_undef (parse_in, "__WBNOINVD__"); + if (isa_flag2 & OPTION_MASK_ISA_AVX512VP2INTERSECT) + def_or_undef (parse_in, "__AVX512VP2INTERSECT__"); if (isa_flag & OPTION_MASK_ISA_MMX) def_or_undef (parse_in, "__MMX__"); if (isa_flag & OPTION_MASK_ISA_3DNOW) diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c index 72be1df0dac..d50b811d863 100644 --- a/gcc/config/i386/i386-expand.c +++ b/gcc/config/i386/i386-expand.c @@ -11339,6 +11339,79 @@ ix86_expand_builtin (tree exp, rtx target, rtx subtarget, emit_move_insn (target, op0); return target; + case IX86_BUILTIN_2INTERSECTD512: + case IX86_BUILTIN_2INTERSECTQ512: + case IX86_BUILTIN_2INTERSECTD256: + case IX86_BUILTIN_2INTERSECTQ256: + case IX86_BUILTIN_2INTERSECTD128: + case IX86_BUILTIN_2INTERSECTQ128: + arg0 = CALL_EXPR_ARG (exp, 0); + arg1 = CALL_EXPR_ARG (exp, 1); + arg2 = CALL_EXPR_ARG (exp, 2); + arg3 = CALL_EXPR_ARG (exp, 3); + op0 = expand_normal (arg0); + op1 = expand_normal (arg1); + op2 = expand_normal (arg2); + op3 = expand_normal (arg3); + + if (!address_operand (op0, VOIDmode)) + { + op0 = convert_memory_address (Pmode, op0); + op0 = copy_addr_to_reg (op0); + } + if (!address_operand (op1, VOIDmode)) + { + op1 = convert_memory_address (Pmode, op1); + op1 = copy_addr_to_reg (op1); + } + + switch (fcode) + { + case IX86_BUILTIN_2INTERSECTD512: + mode4 = P2HImode; + icode = CODE_FOR_avx512vp2intersect_2intersectv16si; + break; + case IX86_BUILTIN_2INTERSECTQ512: + mode4 = P2QImode; + icode = CODE_FOR_avx512vp2intersect_2intersectv8di; + break; + case IX86_BUILTIN_2INTERSECTD256: + mode4 = P2QImode; + icode = CODE_FOR_avx512vp2intersect_2intersectv8si; + break; + case IX86_BUILTIN_2INTERSECTQ256: + mode4 = P2QImode; + icode = CODE_FOR_avx512vp2intersect_2intersectv4di; + break; + case IX86_BUILTIN_2INTERSECTD128: + mode4 = P2QImode; + icode = CODE_FOR_avx512vp2intersect_2intersectv4si; + break; + case IX86_BUILTIN_2INTERSECTQ128: + mode4 = P2QImode; + icode = CODE_FOR_avx512vp2intersect_2intersectv2di; + break; + default: + gcc_unreachable (); + } + + mode2 = insn_data[icode].operand[1].mode; + mode3 = insn_data[icode].operand[2].mode; + if (!insn_data[icode].operand[1].predicate (op2, mode2)) + op2 = copy_to_mode_reg (mode2, op2); + if (!insn_data[icode].operand[2].predicate (op3, mode3)) + op3 = copy_to_mode_reg (mode3, op3); + + op4 = gen_reg_rtx (mode4); + emit_insn (GEN_FCN (icode) (op4, op2, op3)); + mode0 = mode4 == P2HImode ? HImode : QImode; + emit_move_insn (gen_rtx_MEM (mode0, op0), + gen_lowpart (mode0, op4)); + emit_move_insn (gen_rtx_MEM (mode0, op1), + gen_highpart (mode0, op4)); + + return 0; + case IX86_BUILTIN_RDPMC: case IX86_BUILTIN_RDTSC: case IX86_BUILTIN_RDTSCP: diff --git a/gcc/config/i386/i386-modes.def b/gcc/config/i386/i386-modes.def index d0ae469514e..e1b86c86310 100644 --- a/gcc/config/i386/i386-modes.def +++ b/gcc/config/i386/i386-modes.def @@ -101,6 +101,12 @@ VECTOR_MODE (INT, SI, 64); /* V64SI */ INT_MODE (OI, 32); INT_MODE (XI, 64); +/* Modes needs a consecutive register pair. + Note that Using PARTIAL_INT_MODE but not INT_MODE is to avoid mode promotion + issues. */ +PARTIAL_INT_MODE (HI, 16, P2QI); +PARTIAL_INT_MODE (SI, 32, P2HI); + /* Keep the OI and XI modes from confusing the compiler into thinking that these modes could actually be used for computation. They are only holders for vectors during data movement. */ diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c index a44b0d20384..6f8851aaf86 100644 --- a/gcc/config/i386/i386-options.c +++ b/gcc/config/i386/i386-options.c @@ -199,6 +199,7 @@ ix86_target_string (HOST_WIDE_INT isa, HOST_WIDE_INT isa2, { "-mrdpid", OPTION_MASK_ISA_RDPID }, { "-mpconfig", OPTION_MASK_ISA_PCONFIG }, { "-mwbnoinvd", OPTION_MASK_ISA_WBNOINVD }, + { "-mavx512vp2intersect", OPTION_MASK_ISA_AVX512VP2INTERSECT }, { "-msgx", OPTION_MASK_ISA_SGX }, { "-mavx5124vnniw", OPTION_MASK_ISA_AVX5124VNNIW }, { "-mavx5124fmaps", OPTION_MASK_ISA_AVX5124FMAPS }, @@ -852,6 +853,7 @@ ix86_valid_target_attribute_inner_p (tree fndecl, tree args, char *p_strings[], IX86_ATTR_ISA ("avx512vbmi2", OPT_mavx512vbmi2), IX86_ATTR_ISA ("avx512vnni", OPT_mavx512vnni), IX86_ATTR_ISA ("avx512bitalg", OPT_mavx512bitalg), + IX86_ATTR_ISA ("avx512vp2intersect", OPT_mavx512vp2intersect), IX86_ATTR_ISA ("avx512vbmi", OPT_mavx512vbmi), IX86_ATTR_ISA ("avx512ifma", OPT_mavx512ifma), @@ -2027,6 +2029,10 @@ ix86_option_override_internal (bool main_args_p, & OPTION_MASK_ISA_AVX512BITALG)) opts->x_ix86_isa_flags |= OPTION_MASK_ISA_AVX512BITALG; + if (((processor_alias_table[i].flags & PTA_AVX512VP2INTERSECT) != 0) + && !(opts->x_ix86_isa_flags2_explicit + & OPTION_MASK_ISA_AVX512VP2INTERSECT)) + opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA_AVX512VP2INTERSECT; if (((processor_alias_table[i].flags & PTA_AVX5124VNNIW) != 0) && !(opts->x_ix86_isa_flags2_explicit & OPTION_MASK_ISA_AVX5124VNNIW)) diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h index 80b6ee7cbbc..2faa9f15830 100644 --- a/gcc/config/i386/i386-protos.h +++ b/gcc/config/i386/i386-protos.h @@ -47,6 +47,7 @@ extern void ix86_reset_previous_fndecl (void); extern bool ix86_using_red_zone (void); +extern unsigned int ix86_regmode_natural_size (machine_mode); #ifdef RTX_CODE extern int standard_80387_constant_p (rtx); extern const char *standard_80387_constant_opcode (rtx); diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index 649a7e40af4..1ca1712183d 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -18674,11 +18674,23 @@ ix86_hard_regno_nregs (unsigned int regno, machine_mode mode) } if (COMPLEX_MODE_P (mode)) return 2; + /* Register pair for mask registers. */ + if (mode == P2QImode || mode == P2HImode) + return 2; if (mode == V64SFmode || mode == V64SImode) return 4; return 1; } +/* Implement REGMODE_NATURAL_SIZE(MODE). */ +unsigned int +ix86_regmode_natural_size (machine_mode mode) +{ + if (mode == P2HImode || mode == P2QImode) + return GET_MODE_SIZE (mode) / 2; + return UNITS_PER_WORD; +} + /* Implement TARGET_HARD_REGNO_MODE_OK. */ static bool @@ -18688,15 +18700,24 @@ ix86_hard_regno_mode_ok (unsigned int regno, machine_mode mode) if (CC_REGNO_P (regno)) return GET_MODE_CLASS (mode) == MODE_CC; if (GET_MODE_CLASS (mode) == MODE_CC - || GET_MODE_CLASS (mode) == MODE_RANDOM - || GET_MODE_CLASS (mode) == MODE_PARTIAL_INT) + || GET_MODE_CLASS (mode) == MODE_RANDOM) return false; if (STACK_REGNO_P (regno)) return VALID_FP_MODE_P (mode); if (MASK_REGNO_P (regno)) - return (VALID_MASK_REG_MODE (mode) - || (TARGET_AVX512BW - && VALID_MASK_AVX512BW_MODE (mode))); + { + /* Register pair only starts at even register number. */ + if ((mode == P2QImode || mode == P2HImode)) + return MASK_PAIR_REGNO_P(regno); + + return (VALID_MASK_REG_MODE (mode) + || (TARGET_AVX512BW + && VALID_MASK_AVX512BW_MODE (mode))); + } + + if (GET_MODE_CLASS (mode) == MODE_PARTIAL_INT) + return false; + if (SSE_REGNO_P (regno)) { /* We implement the move patterns for all vector modes into and diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h index 04cf7a77877..5e670b5fd11 100644 --- a/gcc/config/i386/i386.h +++ b/gcc/config/i386/i386.h @@ -93,6 +93,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see #define TARGET_AVX512VNNI_P(x) TARGET_ISA_AVX512VNNI_P(x) #define TARGET_AVX512BITALG TARGET_ISA_AVX512BITALG #define TARGET_AVX512BITALG_P(x) TARGET_ISA_AVX512BITALG_P(x) +#define TARGET_AVX512VP2INTERSECT TARGET_ISA_AVX512VP2INTERSECT +#define TARGET_AVX512VP2INTERSECT_P(x) TARGET_ISA_AVX512VP2INTERSECT_P(x) #define TARGET_FMA TARGET_ISA_FMA #define TARGET_FMA_P(x) TARGET_ISA_FMA_P(x) #define TARGET_SSE4A TARGET_ISA_SSE4A @@ -1125,6 +1127,8 @@ extern const char *host_detect_local_cpu (int argc, const char **argv); #define HARD_REGNO_NREGS_WITH_PADDING(REGNO, MODE) ((MODE) == XFmode ? 4 : 8) +#define REGMODE_NATURAL_SIZE(MODE) ix86_regmode_natural_size (MODE) + #define VALID_AVX256_REG_MODE(MODE) \ ((MODE) == V32QImode || (MODE) == V16HImode || (MODE) == V8SImode \ || (MODE) == V4DImode || (MODE) == V2TImode || (MODE) == V8SFmode \ @@ -1509,6 +1513,7 @@ enum reg_class #define MASK_REG_P(X) (REG_P (X) && MASK_REGNO_P (REGNO (X))) #define MASK_REGNO_P(N) IN_RANGE ((N), FIRST_MASK_REG, LAST_MASK_REG) +#define MASK_PAIR_REGNO_P(N) ((((N) - FIRST_MASK_REG) & 1) == 0) #define MMX_REG_P(X) (REG_P (X) && MMX_REGNO_P (REGNO (X))) #define MMX_REGNO_P(N) IN_RANGE ((N), FIRST_MMX_REG, LAST_MMX_REG) @@ -2362,6 +2367,7 @@ const wide_int_bitmask PTA_AVX512BITALG (0, HOST_WIDE_INT_1U << 5); const wide_int_bitmask PTA_RDPID (0, HOST_WIDE_INT_1U << 6); const wide_int_bitmask PTA_PCONFIG (0, HOST_WIDE_INT_1U << 7); const wide_int_bitmask PTA_WBNOINVD (0, HOST_WIDE_INT_1U << 8); +const wide_int_bitmask PTA_AVX512VP2INTERSECT (0, HOST_WIDE_INT_1U << 9); const wide_int_bitmask PTA_WAITPKG (0, HOST_WIDE_INT_1U << 9); const wide_int_bitmask PTA_PTWRITE (0, HOST_WIDE_INT_1U << 10); const wide_int_bitmask PTA_AVX512BF16 (0, HOST_WIDE_INT_1U << 11); diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt index b6e751f8793..599e799ea5e 100644 --- a/gcc/config/i386/i386.opt +++ b/gcc/config/i386/i386.opt @@ -749,6 +749,10 @@ mavx512bitalg Target Report Mask(ISA_AVX512BITALG) Var(ix86_isa_flags) Save Support MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2, AVX512F and AVX512BITALG built-in functions and code generation. +mavx512vp2intersect +Target Report Mask(ISA_AVX512VP2INTERSECT) Var(ix86_isa_flags2) Save +Support AVX512VP2INTERSECT built-in functions and code generation. + mfma Target Report Mask(ISA_FMA) Var(ix86_isa_flags) Save Support MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX and FMA built-in functions and code generation. diff --git a/gcc/config/i386/immintrin.h b/gcc/config/i386/immintrin.h index db98820a349..743aa7451bc 100644 --- a/gcc/config/i386/immintrin.h +++ b/gcc/config/i386/immintrin.h @@ -96,6 +96,10 @@ #include +#include + +#include + #include #include diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index a8d1fbf1fdd..abf7d987e12 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -188,6 +188,9 @@ ;; For AVX512BITALG support UNSPEC_VPSHUFBIT + ;; For VP2INTERSECT support + UNSPEC_VP2INTERSECT + ;; For AVX512BF16 support UNSPEC_VCVTNE2PS2BF16 UNSPEC_VCVTNEPS2BF16 @@ -22523,6 +22526,30 @@ [(set_attr "prefix" "evex") (set_attr "mode" "")]) +(define_mode_iterator VI48_AVX512VP2VL + [V8DI + (V4DI "TARGET_AVX512VL") (V2DI "TARGET_AVX512VL") + (V8SI "TARGET_AVX512VL") (V4SI "TARGET_AVX512VL")]) + +(define_insn "avx512vp2intersect_2intersect" + [(set (match_operand:P2QI 0 "register_operand" "=k") + (unspec:P2QI + [(match_operand:VI48_AVX512VP2VL 1 "register_operand" "v") + (match_operand:VI48_AVX512VP2VL 2 "vector_operand" "vm")] + UNSPEC_VP2INTERSECT))] + "TARGET_AVX512VP2INTERSECT" + "vp2intersect\t{%2, %1, %0|%0, %1, %2}" + [(set_attr ("prefix") ("evex"))]) + +(define_insn "avx512vp2intersect_2intersectv16si" + [(set (match_operand:P2HI 0 "register_operand" "=k") + (unspec:P2HI [(match_operand:V16SI 1 "register_operand" "v") + (match_operand:V16SI 2 "vector_operand" "vm")] + UNSPEC_VP2INTERSECT))] + "TARGET_AVX512VP2INTERSECT" + "vp2intersectd\t{%2, %1, %0|%0, %1, %2}" + [(set_attr ("prefix") ("evex"))]) + (define_mode_iterator BF16 [V32HI (V16HI "TARGET_AVX512VL") (V8HI "TARGET_AVX512VL")]) ;; Converting from BF to SF (define_mode_attr bf16_cvt_2sf diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index 7c096804881..e6d591cc13d 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -1284,7 +1284,7 @@ See RS/6000 and PowerPC Options. -mshstk -mmanual-endbr -mforce-indirect-call -mavx512vbmi2 -mavx512bf16 -menqcmd @gol -mvpclmulqdq -mavx512bitalg -mmovdiri -mmovdir64b -mavx512vpopcntdq @gol -mavx5124fmaps -mavx512vnni -mavx5124vnniw -mprfchw -mrdpid @gol --mrdseed -msgx @gol +-mrdseed -msgx -mavx512vp2intersect@gol -mcldemote -mms-bitfields -mno-align-stringops -minline-all-stringops @gol -minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol -mmemcpy-strategy=@var{strategy} -mmemset-strategy=@var{strategy} @gol @@ -28192,6 +28192,9 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}. @itemx -mavx512vpopcntdq @opindex mavx512vpopcntdq @need 200 +@itemx -mavx512vp2intersect +@opindex mavx512vp2intersect +@need 200 @itemx -mavx5124fmaps @opindex mavx5124fmaps @need 200 diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 1270f44fac3..fd34b5eceab 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,19 @@ +2019-06-06 Hongtao Liu + Olga Makhotina + + * gcc.target/i386/avx512-check.h: Handle bit_AVX512VP2INTERSECT. + * gcc.target/i386/avx512vp2intersect-2intersect-1a.c: New test. + * gcc.target/i386/avx512vp2intersect-2intersect-1b.c: Likewise. + * gcc.target/i386/avx512vp2intersect-2intersectvl-1a.c: Likewise. + * gcc.target/i386/avx512vp2intersect-2intersectvl-1b.c: Likewise. + * gcc.target/i386/sse-12.c: Add -mavx512vp2intersect. + * gcc.target/i386/sse-13.c: Likewsie. + * gcc.target/i386/sse-14.c: Likewise. + * gcc.target/i386/sse-22.c: Likewise. + * gcc.target/i386/sse-23.c: Likewise. + * g++.dg/other/i386-2.C: Likewise. + * g++.dg/other/i386-3.C: Likewise. + 2019-06-25 Jakub Jelinek PR c++/90969 diff --git a/gcc/testsuite/g++.dg/other/i386-2.C b/gcc/testsuite/g++.dg/other/i386-2.C index 841a12cc972..b83248044e4 100644 --- a/gcc/testsuite/g++.dg/other/i386-2.C +++ b/gcc/testsuite/g++.dg/other/i386-2.C @@ -1,12 +1,13 @@ /* { dg-do compile { target i?86-*-* x86_64-*-* } } */ -/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd" } */ +/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect" } */ /* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h, xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h, popcntintrin.h, fmaintrin.h, pkuintrin.h, avx5124fmapsintrin.h, avx5124vnniwintrin.h, avx512vpopcntdqintrin.h gfniintrin.h - avx512bitalgintrin.h and mm_malloc.h.h are usable with -O - -pedantic-errors. */ + avx512bitalgintrin.h, avx512vp2intersectintrin.h, + avx512vp2intersectvlintrin.h and mm_malloc.h.h are usable + with -O -pedantic-errors. */ #include diff --git a/gcc/testsuite/g++.dg/other/i386-3.C b/gcc/testsuite/g++.dg/other/i386-3.C index a70f00fc5ac..303bef47816 100644 --- a/gcc/testsuite/g++.dg/other/i386-3.C +++ b/gcc/testsuite/g++.dg/other/i386-3.C @@ -1,11 +1,12 @@ /* { dg-do compile { target i?86-*-* x86_64-*-* } } */ -/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd" } */ +/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect" } */ /* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h, xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h, popcntintrin.h, fmaintrin.h, pkuintrin.h, avx5124fmapsintrin.h, avx5124vnniwintrin.h, avx512vpopcntdqintrin.h gfniintrin.h - avx512bitalgintrin.h and mm_malloc.h are usable with -O - -fkeep-inline-functions. */ + avx512bitalgintrin.h, avx512vp2intersectintrin.h, + avx512vp2intersectvlintrin.h and mm_malloc.h are usable + with -O -fkeep-inline-functions. */ #include diff --git a/gcc/testsuite/gcc.target/i386/avx512-check.h b/gcc/testsuite/gcc.target/i386/avx512-check.h index 234e60c818b..0a377dba1d5 100644 --- a/gcc/testsuite/gcc.target/i386/avx512-check.h +++ b/gcc/testsuite/gcc.target/i386/avx512-check.h @@ -92,6 +92,9 @@ main () #endif #ifdef VPCLMULQDQ && (ecx & bit_VPCLMULQDQ) +#endif +#ifdef AVX512VP2INTERSECT + && (edx & bit_AVX512VP2INTERSECT) #endif && avx512f_os_support ()) { diff --git a/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersect-1a.c b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersect-1a.c new file mode 100644 index 00000000000..4ce04002fbd --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersect-1a.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -mavx512vp2intersect" } */ +/* { dg-final { scan-assembler "vp2intersectq\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\]*%k\[0-7\]"} } */ +/* { dg-final { scan-assembler "vp2intersectd\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\]*%k\[0-7\]"} } */ + +#include + +__m512i a1, b1; +__m512i a2, b2; +__mmask8 m8, u8; +__mmask16 m16, u16; + +int foo () +{ + _mm512_2intersect_epi64 (a1, b1, &u8, &m8); + _mm512_2intersect_epi32 (a2, b2, &u16, &m16); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersect-1b.c b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersect-1b.c new file mode 100644 index 00000000000..5d718d30588 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersect-1b.c @@ -0,0 +1,28 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -mavx512vp2intersect" } */ + +#define AVX512F +#include +#include "avx512f-helper.h" + +void +TEST (void) +{ + __m512i a1 = _mm512_set_epi64 (10, 43, 253, 3566, 25, -253, -243, 3456); + __m512i b1 = _mm512_set_epi64 (43, 100, 3566, 2353, -253, -25, 3456, 243); + __m512i a2 = _mm512_set_epi32 (21, 22, 23, 24, 25, 26, 27, 28, + 11, 12, 13, 14, 15, 16, 17, 18); + __m512i b2 = _mm512_set_epi32 (22, 211, 24, 213, 26, 215, 28, 217, + 12, 111, 14, 113, 16, 115, 18, 117); + __mmask8 u8 = 0, m8 = 0; + __mmask16 u16 = 0, m16 = 0; + + _mm512_2intersect_epi64 (a1, b1, &u8, &m8); + /* u8 = 01010101, m8 = 10101010. */ + if (u8 != 0x55 || m8 != 0xaa) + abort(); + _mm512_2intersect_epi32 (a2, b2, &u16, &m16); + /* u8 = 0101010101010101, m8 = 1010101010101010. */ + if (u16 != 0x5555 || m16 != 0xaaaa) + abort(); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersectvl-1a.c b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersectvl-1a.c new file mode 100644 index 00000000000..555f5aba477 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersectvl-1a.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -mavx512vp2intersect -mavx512vl" } */ +/* { dg-final { scan-assembler "vp2intersectd\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%k\[0-7\]" } } */ +/* { dg-final { scan-assembler "vp2intersectd\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\]*%k\[0-7\]" } } */ +/* { dg-final { scan-assembler "vp2intersectq\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%k\[0-7\]" } } */ +/* { dg-final { scan-assembler "vp2intersectq\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\]*%k\[0-7\]" } } */ + +#include + +__m256i a2, b2; +__m128i a3, b3; +__mmask8 m0, m1, m2, m3, m4, m5, m6, m7; + +int foo () +{ + _mm_2intersect_epi64 (a3, b3, &m0, &m1); + _mm_2intersect_epi32 (a3, b3, &m2, &m3); + + _mm256_2intersect_epi64 (a2, b2, &m4, &m5); + _mm256_2intersect_epi32 (a2, b2, &m6, &m7); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersectvl-1b.c b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersectvl-1b.c new file mode 100644 index 00000000000..ee3d237c86e --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512vp2intersect-2intersectvl-1b.c @@ -0,0 +1,41 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -mavx512vp2intersect -mavx512vl" } */ + +#define AVX512F +#include +#include "avx512f-helper.h" + + void + TEST (void) +{ + __m256i a1 = _mm256_set_epi64x (1, 2, 3, 4); + __m256i b1 = _mm256_set_epi64x (2, 11, 4, 33); + __m256i a2 = _mm256_set_epi32 (1, 2, 3, 4, 5, 6, 7, 8); + __m256i b2 = _mm256_set_epi32 (2, 11, 4, 33, 6, 55, 8, 77); + __m128i a3 = _mm_set_epi64x (13, 22); + __m128i b3 = _mm_set_epi64x (22, 1434); + __m128i a4 = _mm_set_epi32 (1, 2, 3, 4); + __m128i b4 = _mm_set_epi32 (2, 11, 4, 33); + __mmask8 m0, m1, m2, m3, m4, m5, m6, m7; + m0 = m1 = m2 = m3 = m4 = m5 = m6 = m7 = 0; + + _mm_2intersect_epi64 (a3, b3, &m0, &m1); + /* m0 = ******01, m1 = ******10. */ + if (m0 != 0x1 || m1 != 0x2) + abort(); + + _mm_2intersect_epi32 (a4, b4, &m2, &m3); + /* m2 = ****0101, m3 = ****1010. */ + if (m2 != 0x5 || m3 != 0xa) + abort(); + + _mm256_2intersect_epi64 (a1, b1, &m4, &m5); + /* m4 = ****0101, m5 = ****1010. */ + if (m4 != 0x5 || m5 != 0xa) + abort(); + + _mm256_2intersect_epi32 (a2, b2, &m6, &m7); + /* m0 = 01010101, m1 = 10101010. */ + if (m6 != 0x55 || m7 != 0xaa) + abort(); +} diff --git a/gcc/testsuite/gcc.target/i386/sse-12.c b/gcc/testsuite/gcc.target/i386/sse-12.c index 28d994ccd20..222675e98c6 100644 --- a/gcc/testsuite/gcc.target/i386/sse-12.c +++ b/gcc/testsuite/gcc.target/i386/sse-12.c @@ -3,7 +3,7 @@ popcntintrin.h gfniintrin.h and mm_malloc.h are usable with -O -std=c89 -pedantic-errors. */ /* { dg-do compile } */ -/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512bw -mavx512dq -mavx512vl -mavx512vbmi -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd" } */ +/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512bw -mavx512dq -mavx512vl -mavx512vbmi -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd -mavx512vp2intersect" } */ #include diff --git a/gcc/testsuite/gcc.target/i386/sse-13.c b/gcc/testsuite/gcc.target/i386/sse-13.c index 91da5da0b96..39b2d31578c 100644 --- a/gcc/testsuite/gcc.target/i386/sse-13.c +++ b/gcc/testsuite/gcc.target/i386/sse-13.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd" } */ +/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512vl -mavx512dq -mavx512bw -mavx512vbmi -mavx512ifma -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mavx512vp2intersect -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mavx512bitalg -mpconfig -mwbnoinvd -mavx512bf16 -menqcmd" } */ /* { dg-add-options bind_pic_locally } */ #include diff --git a/gcc/testsuite/gcc.target/i386/sse-14.c b/gcc/testsuite/gcc.target/i386/sse-14.c index 40ec3f90bf8..8795109e1b8 100644 --- a/gcc/testsuite/gcc.target/i386/sse-14.c +++ b/gcc/testsuite/gcc.target/i386/sse-14.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mpconfig -mwbnoinvd -mavx512vl -mavx512bf16 -menqcmd" } */ +/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mbmi2 -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c -mfma -mrtm -mrdseed -mprfchw -madx -mfxsr -mxsaveopt -mavx512f -mavx512er -mavx512cd -mavx512pf -msha -mprefetchwt1 -mxsavec -mxsaves -mclflushopt -mavx512dq -mavx512bw -mavx512vl -mavx512ifma -mavx512vbmi -mavx5124fmaps -mavx5124vnniw -mavx512vpopcntdq -mclwb -mmwaitx -mclzero -mpku -msgx -mrdpid -mgfni -mpconfig -mwbnoinvd -mavx512vl -mavx512bf16 -menqcmd -mavx512vp2intersect" } */ /* { dg-add-options bind_pic_locally } */ #include diff --git a/gcc/testsuite/gcc.target/i386/sse-22.c b/gcc/testsuite/gcc.target/i386/sse-22.c index 733c67011ea..1c786bb9392 100644 --- a/gcc/testsuite/gcc.target/i386/sse-22.c +++ b/gcc/testsuite/gcc.target/i386/sse-22.c @@ -10,8 +10,9 @@ mm3dnow.h, fma4intrin.h, xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h, popcntintrin.h, fmaintrin.h, avx5124fmapsintrin.h, avx5124vnniwintrin.h, avx512vpopcntdqintrin.h, - avx512bitalgintrin.h and mm_malloc.h that reference the proper builtin - functions. + avx512bitalgintrin.h, avx512vp2intersectintrin.h, + avx512vp2intersectvlintrin.h and mm_malloc.h that reference the proper + builtin functions. Defining away "extern" and "__inline" results in all of them being compiled as proper functions. */ @@ -101,7 +102,7 @@ #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,avx512f,avx512er,avx512cd,avx512pf,sha,prefetchwt1,avx512vl,avx512bw,avx512dq,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16") +#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,avx512er,avx512cd,avx512pf,sha,prefetchwt1,avx512vl,avx512bw,avx512dq,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16,avx512vp2intersect") #endif /* Following intrinsics require immediate arguments. They @@ -218,7 +219,7 @@ test_4 (_mm_cmpestrz, int, __m128i, int, __m128i, int, 1) /* immintrin.h (AVX/AVX2/RDRND/FSGSBASE/F16C/RTM/AVX512F/SHA) */ #ifdef DIFFERENT_PRAGMAS -#pragma GCC target ("avx,avx2,rdrnd,fsgsbase,f16c,rtm,avx512f,avx512er,avx512cd,avx512pf,sha,avx512vl,avx512bw,avx512dq,avx512ifma,avx512vbmi,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16") +#pragma GCC target ("avx,avx2,rdrnd,fsgsbase,f16c,rtm,avx512f,avx512er,avx512cd,avx512pf,sha,avx512vl,avx512bw,avx512dq,avx512ifma,avx512vbmi,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,gfni,avx512bitalg,avx512bf16,avx512vp2intersect") #endif #include test_1 (_cvtss_sh, unsigned short, float, 1) diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c b/gcc/testsuite/gcc.target/i386/sse-23.c index 8b809acd71f..7ea665de747 100644 --- a/gcc/testsuite/gcc.target/i386/sse-23.c +++ b/gcc/testsuite/gcc.target/i386/sse-23.c @@ -9,8 +9,9 @@ mm3dnow.h, fma4intrin.h, xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h, popcntintrin.h, fmaintrin.h, avx5124fmapsintrin.h, avx5124vnniwintrin.h, avx512vpopcntdqintrin.h, - avx512bitalgintrin.h and mm_malloc.h that reference the proper builtin - functions. + avx512bitalgintrin.h, avx512vp2intersectintrin.h, + avx512vp2intersectvlintrin.h and mm_malloc.h that reference the proper + builtin functions. Defining away "extern" and "__inline" results in all of them being compiled as proper functions. */ @@ -696,6 +697,6 @@ #define __builtin_ia32_vpclmulqdq_v2di(A, B, C) __builtin_ia32_vpclmulqdq_v2di(A, B, 1) #define __builtin_ia32_vpclmulqdq_v8di(A, B, C) __builtin_ia32_vpclmulqdq_v8di(A, B, 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,avx512cd,avx512pf,sha,prefetchwt1,xsavec,xsaves,clflushopt,avx512bw,avx512dq,avx512vl,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,clwb,mwaitx,clzero,pku,sgx,rdpid,gfni,avx512vbmi2,vpclmulqdq,avx512bitalg,pconfig,wbnoinvd,avx512bf16,enqcmd") +#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,avx512cd,avx512pf,sha,prefetchwt1,xsavec,xsaves,clflushopt,avx512bw,avx512dq,avx512vl,avx512vbmi,avx512ifma,avx5124fmaps,avx5124vnniw,avx512vpopcntdq,clwb,mwaitx,clzero,pku,sgx,rdpid,gfni,avx512vbmi2,vpclmulqdq,avx512bitalg,pconfig,wbnoinvd,avx512bf16,enqcmd,avx512vp2intersect") #include