[i386,11/8,AVX512,2/2] Add missing packed PF gathers/scatters.

Message ID	20140127100900.GA65215@msticlxl57.ims.intel.com
State	New
Headers	show Return-Path: <gcc-patches-return-360437-incoming=patchwork.ozlabs.org@gcc.gnu.org> DomainKey-Signature: a=rsa-sha1; c=nofws; d=gcc.gnu.org; h=list-id :list-unsubscribe:list-archive:list-post:list-help:sender:date :from:to:cc:subject:message-id:references:mime-version :content-type:in-reply-to; q=dns; s=default; b=fLjr4+mgibexWl+KU bNcbcKwdyCK8FQNsqfQ5oLmdzTqo1mFjZ0f3o8+PAoyxJh1ZTilvOUtU+8h80H0+ urIULRSg4uQOFRhjLhrRQYcRd3lrY1IpZhp51sKv1EMUcrfvkU6g6SJYtcg26Ld8 HdvvtPsKJQ51BqKdgbk2vtWaXs= Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk Sender: gcc-patches-owner@gcc.gnu.org Date: Mon, 27 Jan 2014 13:09:08 +0300 From: Kirill Yukhin <kirill.yukhin@gmail.com> To: Uros Bizjak <ubizjak@gmail.com> Cc: Jakub Jelinek <jakub@redhat.com>, GCC Patches <gcc-patches@gcc.gnu.org> Subject: Re: [PATCH i386 11/8] [AVX512] [2/2] Add missing packed PF gathers/scatters. Message-ID: <20140127100900.GA65215@msticlxl57.ims.intel.com> References: <20140114061303.GA57893@msticlxl57.ims.intel.com> <CAFULd4aVig-4X7iCJyYO3XCxPn-+LDJF3ymUZt=0K2-0Zhk-bQ@mail.gmail.com> <20140116045745.GA31714@msticlxl57.ims.intel.com> <CAFULd4ZsBn3gPViBRRE43VLV2VzCmi4XGGr-bWaz1=fKBKLfbA@mail.gmail.com> <20140121185217.GB49359@msticlxl57.ims.intel.com> <CAFULd4Yz_0RxwChuaL19aw52VGAnJEwbAv3L0+miEwj9cmedAg@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <CAFULd4Yz_0RxwChuaL19aw52VGAnJEwbAv3L0+miEwj9cmedAg@mail.gmail.com> User-Agent: Mutt/1.5.21 (2010-09-15)

diff --git a/gcc/config/i386/avx512pfintrin.h b/gcc/config/i386/avx512pfintrin.h index b8c0110..bc7598e 100644 --- a/gcc/config/i386/avx512pfintrin.h +++ b/gcc/config/i386/avx512pfintrin.h @@ -48,74 +48,157 @@ typedef unsigned short __mmask16; #ifdef __OPTIMIZE__ extern __inline void __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_mask_prefetch_i32gather_pd (__m256i index, __mmask8 mask, + void *addr, int scale, int hint) +{ + __builtin_ia32_gatherpfdpd (mask, (__v8si) index, (long long const *) addr, + scale, hint); +} + +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) + void *addr, int scale, int hint) +{ + __builtin_ia32_gatherpfdps (mask, (__v16si) index, (int const *) addr, + scale, hint); +} + +extern __inline void +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_mask_prefetch_i64gather_pd (__m512i index, __mmask8 mask, + void *addr, int scale, int hint) { - __builtin_ia32_gatherpfdps (mask, (__v16si) index, addr, scale, hint); + __builtin_ia32_gatherpfqpd (mask, (__v8di) index, (long long const *) 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) + void *addr, int scale, int hint) { - __builtin_ia32_gatherpfqps (mask, (__v8di) index, addr, scale, hint); + __builtin_ia32_gatherpfqps (mask, (__v8di) index, (int const *) addr, + scale, hint); } extern __inline void __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_prefetch_i32scatter_ps (int const *addr, __m512i index, int scale, +_mm512_prefetch_i32scatter_pd (void *addr, __m256i index, int scale, int hint) { - __builtin_ia32_scatterpfdps ((__mmask16) 0xFFFF, (__v16si) index, addr, scale, - hint); + __builtin_ia32_scatterpfdpd ((__mmask8) 0xFF, (__v8si) index, + (long long const *)addr, scale, hint); +} + +extern __inline void +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_prefetch_i32scatter_ps (void *addr, __m512i index, int scale, + int hint) +{ + __builtin_ia32_scatterpfdps ((__mmask16) 0xFFFF, (__v16si) index, (int const *) addr, + scale, hint); +} + +extern __inline void +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_mask_prefetch_i32scatter_pd (void *addr, __mmask8 mask, + __m256i index, int scale, int hint) +{ + __builtin_ia32_scatterpfdpd (mask, (__v8si) index, (long long const *) addr, + scale, hint); } extern __inline void __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_mask_prefetch_i32scatter_ps (int const *addr, __mmask16 mask, +_mm512_mask_prefetch_i32scatter_ps (void *addr, __mmask16 mask, __m512i index, int scale, int hint) { - __builtin_ia32_scatterpfdps (mask, (__v16si) index, addr, scale, hint); + __builtin_ia32_scatterpfdps (mask, (__v16si) index, (int const *) addr, + scale, hint); +} + +extern __inline void +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_prefetch_i64scatter_pd (void *addr, __m512i index, int scale, + int hint) +{ + __builtin_ia32_scatterpfqpd ((__mmask8) 0xFF, (__v8di) index, (long long const *) addr, + scale, hint); } extern __inline void __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_prefetch_i64scatter_ps (int const *addr, __m512i index, int scale, +_mm512_prefetch_i64scatter_ps (void *addr, __m512i index, int scale, int hint) { - __builtin_ia32_scatterpfqps ((__mmask8) 0xFF, (__v8di) index, addr, scale, - hint); + __builtin_ia32_scatterpfqps ((__mmask8) 0xFF, (__v8di) index, (int const *) addr, + scale, hint); +} + +extern __inline void +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_mask_prefetch_i64scatter_pd (void *addr, __mmask16 mask, + __m512i index, int scale, int hint) +{ + __builtin_ia32_scatterpfqpd (mask, (__v8di) index, (long long const *) addr, + scale, hint); } extern __inline void __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) -_mm512_mask_prefetch_i64scatter_ps (int const *addr, __mmask16 mask, +_mm512_mask_prefetch_i64scatter_ps (void *addr, __mmask16 mask, __m512i index, int scale, int hint) { - __builtin_ia32_scatterpfqps (mask, (__v8di) index, addr, scale, hint); + __builtin_ia32_scatterpfqps (mask, (__v8di) index, (int const *) addr, + scale, hint); } + #else +#define _mm512_mask_prefetch_i32gather_pd(INDEX, MASK, ADDR, SCALE, HINT) \ + __builtin_ia32_gatherpfdpd ((__mmask8)MASK, (__v8si)(__m256i)INDEX, \ + (long long const *)ADDR, (int)SCALE, (int)HINT) + #define _mm512_mask_prefetch_i32gather_ps(INDEX, MASK, ADDR, SCALE, HINT) \ - __builtin_ia32_gatherpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \ + __builtin_ia32_gatherpfdps ((__mmask16)MASK, (__v16si)(__m512i)INDEX, \ (int const *)ADDR, (int)SCALE, (int)HINT) +#define _mm512_mask_prefetch_i64gather_pd(INDEX, MASK, ADDR, SCALE, HINT) \ + __builtin_ia32_gatherpfqpd ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \ + (long long 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_pd(ADDR, INDEX, SCALE, HINT) \ + __builtin_ia32_scatterpfdpd ((__mmask8)0xFF, (__v8si)(__m256i)INDEX, \ + (long long 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_pd(ADDR, MASK, INDEX, SCALE, HINT) \ + __builtin_ia32_scatterpfdpd ((__mmask8)MASK, (__v8si)(__m256i)INDEX, \ + (long long 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_pd(ADDR, INDEX, SCALE, HINT) \ + __builtin_ia32_scatterpfqpd ((__mmask8)0xFF, (__v8di)(__m512i)INDEX, \ + (long long 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_pd(ADDR, MASK, INDEX, SCALE, HINT) \ + __builtin_ia32_scatterpfqpd ((__mmask8)MASK, (__v8di)(__m512i)INDEX, \ + (long long 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) diff --git a/gcc/config/i386/i386-builtin-types.def b/gcc/config/i386/i386-builtin-types.def index acf2f32..f3c658b 100644 --- a/gcc/config/i386/i386-builtin-types.def +++ b/gcc/config/i386/i386-builtin-types.def @@ -733,7 +733,9 @@ 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, QI, V8SI, PCINT64, INT, INT) DEF_FUNCTION_TYPE (VOID, HI, V16SI, PCINT, INT, INT) +DEF_FUNCTION_TYPE (VOID, QI, V8DI, PCINT64, INT, INT) DEF_FUNCTION_TYPE (VOID, QI, V8DI, PCINT, INT, INT) DEF_FUNCTION_TYPE_ALIAS (V2DF_FTYPE_V2DF, ROUND) diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index 1a4d568..49e153c 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -28397,9 +28397,13 @@ enum ix86_builtins IX86_BUILTIN_SCATTERSIV8DI, /* AVX512PF */ + IX86_BUILTIN_GATHERPFQPD, IX86_BUILTIN_GATHERPFDPS, + IX86_BUILTIN_GATHERPFDPD, IX86_BUILTIN_GATHERPFQPS, + IX86_BUILTIN_SCATTERPFDPD, IX86_BUILTIN_SCATTERPFDPS, + IX86_BUILTIN_SCATTERPFQPD, IX86_BUILTIN_SCATTERPFQPS, /* AVX-512ER */ @@ -30929,15 +30933,27 @@ ix86_init_mmx_sse_builtins (void) IX86_BUILTIN_SCATTERDIV8DI); /* AVX512PF */ + def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_gatherpfdpd", + VOID_FTYPE_QI_V8SI_PCINT64_INT_INT, + IX86_BUILTIN_GATHERPFDPD); 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_gatherpfqpd", + VOID_FTYPE_QI_V8DI_PCINT64_INT_INT, + IX86_BUILTIN_GATHERPFQPD); 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_scatterpfdpd", + VOID_FTYPE_QI_V8SI_PCINT64_INT_INT, + IX86_BUILTIN_SCATTERPFDPD); 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_scatterpfqpd", + VOID_FTYPE_QI_V8DI_PCINT64_INT_INT, + IX86_BUILTIN_SCATTERPFQPD); def_builtin (OPTION_MASK_ISA_AVX512PF, "__builtin_ia32_scatterpfqps", VOID_FTYPE_QI_V8DI_PCINT_INT_INT, IX86_BUILTIN_SCATTERPFQPS); @@ -35583,17 +35599,30 @@ addcarryx: case IX86_BUILTIN_SCATTERDIV8DI: icode = CODE_FOR_avx512f_scatterdiv8di; goto scatter_gen; + + case IX86_BUILTIN_GATHERPFDPD: + icode = CODE_FOR_avx512pf_gatherpfv8sidf; + goto vec_prefetch_gen; case IX86_BUILTIN_GATHERPFDPS: - icode = CODE_FOR_avx512pf_gatherpfv16si; + icode = CODE_FOR_avx512pf_gatherpfv16sisf; + goto vec_prefetch_gen; + case IX86_BUILTIN_GATHERPFQPD: + icode = CODE_FOR_avx512pf_gatherpfv8didf; goto vec_prefetch_gen; case IX86_BUILTIN_GATHERPFQPS: - icode = CODE_FOR_avx512pf_gatherpfv8di; + icode = CODE_FOR_avx512pf_gatherpfv8disf; + goto vec_prefetch_gen; + case IX86_BUILTIN_SCATTERPFDPD: + icode = CODE_FOR_avx512pf_scatterpfv8sidf; goto vec_prefetch_gen; case IX86_BUILTIN_SCATTERPFDPS: - icode = CODE_FOR_avx512pf_scatterpfv16si; + icode = CODE_FOR_avx512pf_scatterpfv16sisf; + goto vec_prefetch_gen; + case IX86_BUILTIN_SCATTERPFQPD: + icode = CODE_FOR_avx512pf_scatterpfv8didf; goto vec_prefetch_gen; case IX86_BUILTIN_SCATTERPFQPS: - icode = CODE_FOR_avx512pf_scatterpfv8di; + icode = CODE_FOR_avx512pf_scatterpfv8disf; goto vec_prefetch_gen; gather_gen: diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 2e68fb6..24eec40 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -417,6 +417,7 @@ [V32QI V16HI V8SI (V8DI "TARGET_AVX512F") (V16SI "TARGET_AVX512F")]) (define_mode_iterator VI48_256 [V8SI V4DI]) (define_mode_iterator VI48_512 [V16SI V8DI]) +(define_mode_iterator VI4_256_8_512 [V8SI V8DI]) ;; Int-float size matches (define_mode_iterator VI4F_128 [V4SI V4SF]) @@ -12495,10 +12496,16 @@ (set_attr "btver2_decode" "vector,vector,vector,vector") (set_attr "mode" "TI")]) -(define_expand "avx512pf_gatherpf<mode>" +;; Packed float variants +(define_mode_attr GATHER_SCATTER_SF_MEM_MODE + [(V8DI "V8SF") (V16SI "V16SF")]) +(define_mode_attr GATHER_SCATTER_DF_MEM_MODE + [(V8DI "V8DF") (V8SI "V8DF")]) + +(define_expand "avx512pf_gatherpf<mode>sf" [(unspec [(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand") - (mem:<ssescalarmode> + (mem:<GATHER_SCATTER_SF_MEM_MODE> (match_par_dup 5 [(match_operand 2 "vsib_address_operand") (match_operand:VI48_512 1 "register_operand") @@ -12512,10 +12519,10 @@ operands[3]), UNSPEC_VSIBADDR); }) -(define_insn "*avx512pf_gatherpf<mode>_mask" +(define_insn "*avx512pf_gatherpf<mode>sf_mask" [(unspec [(match_operand:<avx512fmaskmode> 0 "register_operand" "k") - (match_operator:<ssescalarmode> 5 "vsib_mem_operator" + (match_operator:<GATHER_SCATTER_SF_MEM_MODE> 5 "vsib_mem_operator" [(unspec:P [(match_operand:P 2 "vsib_address_operand" "Tv") (match_operand:VI48_512 1 "register_operand" "v") @@ -12539,10 +12546,10 @@ (set_attr "prefix" "evex") (set_attr "mode" "XI")]) -(define_insn "*avx512pf_gatherpf<mode>" +(define_insn "*avx512pf_gatherpf<mode>sf" [(unspec [(const_int -1) - (match_operator:<ssescalarmode> 4 "vsib_mem_operator" + (match_operator:<GATHER_SCATTER_SF_MEM_MODE> 4 "vsib_mem_operator" [(unspec:P [(match_operand:P 1 "vsib_address_operand" "Tv") (match_operand:VI48_512 0 "register_operand" "v") @@ -12566,10 +12573,83 @@ (set_attr "prefix" "evex") (set_attr "mode" "XI")]) -(define_expand "avx512pf_scatterpf<mode>" +;; Packed double variants +(define_expand "avx512pf_gatherpf<mode>df" + [(unspec + [(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand") + (mem:<GATHER_SCATTER_DF_MEM_MODE> + (match_par_dup 5 + [(match_operand 2 "vsib_address_operand") + (match_operand:VI4_256_8_512 1 "register_operand") + (match_operand:SI 3 "const1248_operand")])) + (match_operand:SI 4 "const_0_to_1_operand")] + UNSPEC_GATHER_PREFETCH)] + "TARGET_AVX512PF" +{ + operands[5] + = gen_rtx_UNSPEC (Pmode, gen_rtvec (3, operands[2], operands[1], + operands[3]), UNSPEC_VSIBADDR); +}) + +(define_insn "*avx512pf_gatherpf<mode>df_mask" + [(unspec + [(match_operand:<avx512fmaskmode> 0 "register_operand" "k") + (match_operator:<GATHER_SCATTER_DF_MEM_MODE> 5 "vsib_mem_operator" + [(unspec:P + [(match_operand:P 2 "vsib_address_operand" "Tv") + (match_operand:VI4_256_8_512 1 "register_operand" "v") + (match_operand:SI 3 "const1248_operand" "n")] + UNSPEC_VSIBADDR)]) + (match_operand:SI 4 "const_0_to_1_operand" "n")] + UNSPEC_GATHER_PREFETCH)] + "TARGET_AVX512PF" +{ + switch (INTVAL (operands[4])) + { + case 0: + return "vgatherpf0<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}"; + case 1: + return "vgatherpf1<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}"; + default: + gcc_unreachable (); + } +} + [(set_attr "type" "sse") + (set_attr "prefix" "evex") + (set_attr "mode" "XI")]) + +(define_insn "*avx512pf_gatherpf<mode>df" + [(unspec + [(const_int -1) + (match_operator:<GATHER_SCATTER_DF_MEM_MODE> 4 "vsib_mem_operator" + [(unspec:P + [(match_operand:P 1 "vsib_address_operand" "Tv") + (match_operand:VI4_256_8_512 0 "register_operand" "v") + (match_operand:SI 2 "const1248_operand" "n")] + UNSPEC_VSIBADDR)]) + (match_operand:SI 3 "const_0_to_1_operand" "n")] + UNSPEC_GATHER_PREFETCH)] + "TARGET_AVX512PF" +{ + switch (INTVAL (operands[3])) + { + case 0: + return "vgatherpf0<ssemodesuffix>pd\t{%4|%4}"; + case 1: + return "vgatherpf1<ssemodesuffix>pd\t{%4|%4}"; + default: + gcc_unreachable (); + } +} + [(set_attr "type" "sse") + (set_attr "prefix" "evex") + (set_attr "mode" "XI")]) + +;; Packed float variants +(define_expand "avx512pf_scatterpf<mode>sf" [(unspec [(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand") - (mem:<ssescalarmode> + (mem:<GATHER_SCATTER_SF_MEM_MODE> (match_par_dup 5 [(match_operand 2 "vsib_address_operand") (match_operand:VI48_512 1 "register_operand") @@ -12583,10 +12663,10 @@ operands[3]), UNSPEC_VSIBADDR); }) -(define_insn "*avx512pf_scatterpf<mode>_mask" +(define_insn "*avx512pf_scatterpf<mode>sf_mask" [(unspec [(match_operand:<avx512fmaskmode> 0 "register_operand" "k") - (match_operator:<ssescalarmode> 5 "vsib_mem_operator" + (match_operator:<GATHER_SCATTER_SF_MEM_MODE> 5 "vsib_mem_operator" [(unspec:P [(match_operand:P 2 "vsib_address_operand" "Tv") (match_operand:VI48_512 1 "register_operand" "v") @@ -12610,10 +12690,10 @@ (set_attr "prefix" "evex") (set_attr "mode" "XI")]) -(define_insn "*avx512pf_scatterpf<mode>" +(define_insn "*avx512pf_scatterpf<mode>sf" [(unspec [(const_int -1) - (match_operator:<ssescalarmode> 4 "vsib_mem_operator" + (match_operator:<GATHER_SCATTER_SF_MEM_MODE> 4 "vsib_mem_operator" [(unspec:P [(match_operand:P 1 "vsib_address_operand" "Tv") (match_operand:VI48_512 0 "register_operand" "v") @@ -12637,6 +12717,78 @@ (set_attr "prefix" "evex") (set_attr "mode" "XI")]) +;; Packed double variants +(define_expand "avx512pf_scatterpf<mode>df" + [(unspec + [(match_operand:<avx512fmaskmode> 0 "register_or_constm1_operand") + (mem:<GATHER_SCATTER_DF_MEM_MODE> + (match_par_dup 5 + [(match_operand 2 "vsib_address_operand") + (match_operand:VI4_256_8_512 1 "register_operand") + (match_operand:SI 3 "const1248_operand")])) + (match_operand:SI 4 "const_0_to_1_operand")] + UNSPEC_SCATTER_PREFETCH)] + "TARGET_AVX512PF" +{ + operands[5] + = gen_rtx_UNSPEC (Pmode, gen_rtvec (3, operands[2], operands[1], + operands[3]), UNSPEC_VSIBADDR); +}) + +(define_insn "*avx512pf_scatterpf<mode>df_mask" + [(unspec + [(match_operand:<avx512fmaskmode> 0 "register_operand" "k") + (match_operator:<GATHER_SCATTER_DF_MEM_MODE> 5 "vsib_mem_operator" + [(unspec:P + [(match_operand:P 2 "vsib_address_operand" "Tv") + (match_operand:VI4_256_8_512 1 "register_operand" "v") + (match_operand:SI 3 "const1248_operand" "n")] + UNSPEC_VSIBADDR)]) + (match_operand:SI 4 "const_0_to_1_operand" "n")] + UNSPEC_SCATTER_PREFETCH)] + "TARGET_AVX512PF" +{ + switch (INTVAL (operands[4])) + { + case 0: + return "vscatterpf0<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}"; + case 1: + return "vscatterpf1<ssemodesuffix>pd\t{%5%{%0%}|%5%{%0%}}"; + default: + gcc_unreachable (); + } +} + [(set_attr "type" "sse") + (set_attr "prefix" "evex") + (set_attr "mode" "XI")]) + +(define_insn "*avx512pf_scatterpf<mode>df" + [(unspec + [(const_int -1) + (match_operator:<GATHER_SCATTER_DF_MEM_MODE> 4 "vsib_mem_operator" + [(unspec:P + [(match_operand:P 1 "vsib_address_operand" "Tv") + (match_operand:VI4_256_8_512 0 "register_operand" "v") + (match_operand:SI 2 "const1248_operand" "n")] + UNSPEC_VSIBADDR)]) + (match_operand:SI 3 "const_0_to_1_operand" "n")] + UNSPEC_SCATTER_PREFETCH)] + "TARGET_AVX512PF" +{ + switch (INTVAL (operands[3])) + { + case 0: + return "vscatterpf0<ssemodesuffix>pd\t{%4|%4}"; + case 1: + return "vscatterpf1<ssemodesuffix>pd\t{%4|%4}"; + default: + gcc_unreachable (); + } +} + [(set_attr "type" "sse") + (set_attr "prefix" "evex") + (set_attr "mode" "XI")]) + (define_insn "avx512er_exp2<mode><mask_name><round_saeonly_name>" [(set (match_operand:VF_512 0 "register_operand" "=v") (unspec:VF_512 diff --git a/gcc/testsuite/gcc.target/i386/avx-1.c b/gcc/testsuite/gcc.target/i386/avx-1.c index 12674ad..8fb6fb88 100644 --- a/gcc/testsuite/gcc.target/i386/avx-1.c +++ b/gcc/testsuite/gcc.target/i386/avx-1.c @@ -362,6 +362,10 @@ #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) +#define __builtin_ia32_gatherpfdpd(A, B, C, D, E) __builtin_ia32_gatherpfdpd(A, B, C, 1, 1) +#define __builtin_ia32_gatherpfqpd(A, B, C, D, E) __builtin_ia32_gatherpfqpd(A, B, C, 1, 1) +#define __builtin_ia32_scatterpfdpd(A, B, C, D, E) __builtin_ia32_scatterpfdpd(A, B, C, 1, 1) +#define __builtin_ia32_scatterpfqpd(A, B, C, D, E) __builtin_ia32_scatterpfqpd(A, B, C, 1, 1) /* shaintrin.h */ #define __builtin_ia32_sha1rnds4(A, B, C) __builtin_ia32_sha1rnds4(A, B, 1) diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf0dpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf0dpd-1.c new file mode 100644 index 0000000..1368b7a --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf0dpd-1.c @@ -0,0 +1,15 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vgatherpf0dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m256i idx; +volatile __mmask8 m8; +void *base; + +void extern +avx512pf_test (void) +{ + _mm512_mask_prefetch_i32gather_pd (idx, m8, base, 8, 0); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf0qpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf0qpd-1.c new file mode 100644 index 0000000..61a81bb --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf0qpd-1.c @@ -0,0 +1,15 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vgatherpf0qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m512i idx; +volatile __mmask8 m8; +int *base; + +void extern +avx512pf_test (void) +{ + _mm512_mask_prefetch_i64gather_pd (idx, m8, base, 8, 0); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf1dpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf1dpd-1.c new file mode 100644 index 0000000..5bc7599 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf1dpd-1.c @@ -0,0 +1,15 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vgatherpf1dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m256i idx; +volatile __mmask8 m8; +int *base; + +void extern +avx512pf_test (void) +{ + _mm512_mask_prefetch_i32gather_pd (idx, m8, base, 8, 1); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf1qpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf1qpd-1.c new file mode 100644 index 0000000..96610db --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vgatherpf1qpd-1.c @@ -0,0 +1,15 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vgatherpf1qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m512i idx; +volatile __mmask8 m8; +int *base; + +void extern +avx512pf_test (void) +{ + _mm512_mask_prefetch_i64gather_pd (idx, m8, base, 8, 1); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf0dpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf0dpd-1.c new file mode 100644 index 0000000..83c31cc --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf0dpd-1.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vscatterpf0dpd\[ \\t\]+\[^\n\]*%ymm\[0-9\]" 2 } } */ +/* { dg-final { scan-assembler-times "vscatterpf0dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m256i idx; +volatile __mmask8 m8; +void *base; + +void extern +avx512pf_test (void) +{ + _mm512_prefetch_i32scatter_pd (base, idx, 8, 0); + _mm512_mask_prefetch_i32scatter_pd (base, m8, idx, 8, 0); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf0qpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf0qpd-1.c new file mode 100644 index 0000000..31172f8 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf0qpd-1.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vscatterpf0qpd\[ \\t\]+\[^\n\]*%zmm\[0-9\]" 2 } } */ +/* { dg-final { scan-assembler-times "vscatterpf0qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m512i idx; +volatile __mmask8 m8; +void *base; + +void extern +avx512pf_test (void) +{ + _mm512_prefetch_i64scatter_pd (base, idx, 8, 0); + _mm512_mask_prefetch_i64scatter_pd (base, m8, idx, 8, 0); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf1dpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf1dpd-1.c new file mode 100644 index 0000000..205505b --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf1dpd-1.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vscatterpf1dpd\[ \\t\]+\[^\n\]*%ymm\[0-9\]" 2 } } */ +/* { dg-final { scan-assembler-times "vscatterpf1dpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m256i idx; +volatile __mmask8 m8; +void *base; + +void extern +avx512pf_test (void) +{ + _mm512_prefetch_i32scatter_pd (base, idx, 8, 1); + _mm512_mask_prefetch_i32scatter_pd (base, m8, idx, 8, 1); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf1qpd-1.c b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf1qpd-1.c new file mode 100644 index 0000000..64d7dfa --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512pf-vscatterpf1qpd-1.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512pf -O2" } */ +/* { dg-final { scan-assembler-times "vscatterpf1qpd\[ \\t\]+\[^\n\]*%zmm\[0-9\]" 2 } } */ +/* { dg-final { scan-assembler-times "vscatterpf1qpd\[ \\t\]+\[^\n\]*\{%k\[1-7\]" 1 } } */ + +#include <immintrin.h> + +volatile __m512i idx; +volatile __mmask8 m8; +int *base; + +void extern +avx512pf_test (void) +{ + _mm512_prefetch_i64scatter_pd (base, idx, 8, 1); + _mm512_mask_prefetch_i64scatter_pd (base, m8, idx, 8, 1); +} diff --git a/gcc/testsuite/gcc.target/i386/sse-14.c b/gcc/testsuite/gcc.target/i386/sse-14.c index ad7ca76..643eb99 100644 --- a/gcc/testsuite/gcc.target/i386/sse-14.c +++ b/gcc/testsuite/gcc.target/i386/sse-14.c @@ -523,6 +523,10 @@ test_3vx (_mm512_mask_prefetch_i32gather_ps, __m512i, __mmask16, void const *, 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) +test_3vx (_mm512_mask_prefetch_i32gather_pd, __m256i, __mmask8, void const *, 1, 1) +test_3vx (_mm512_mask_prefetch_i32scatter_pd, void const *, __mmask8, __m256i, 1, 1) +test_3vx (_mm512_mask_prefetch_i64gather_pd, __m512i, __mmask8, void const *, 1, 1) +test_3vx (_mm512_mask_prefetch_i64scatter_pd, void const *, __mmask8, __m512i, 1, 1) /* avx512erintrin.h */ test_1 (_mm512_exp2a23_round_pd, __m512d, __m512d, 5) diff --git a/gcc/testsuite/gcc.target/i386/sse-22.c b/gcc/testsuite/gcc.target/i386/sse-22.c index 630c952..7d68be1 100644 --- a/gcc/testsuite/gcc.target/i386/sse-22.c +++ b/gcc/testsuite/gcc.target/i386/sse-22.c @@ -646,6 +646,11 @@ test_3vx (_mm512_mask_prefetch_i32scatter_ps, void const *, __mmask16, __m512i, 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) +test_3vx (_mm512_mask_prefetch_i32gather_pd, __m256i, __mmask8, void const *, 1, 1) +test_3vx (_mm512_mask_prefetch_i32scatter_pd, void const *, __mmask8, __m256i, 1, 1) +test_3vx (_mm512_mask_prefetch_i64gather_pd, __m512i, __mmask8, long long *, 1, 1) +test_3vx (_mm512_mask_prefetch_i64scatter_pd, void const *, __mmask8, __m512i, 1, 1) + /* avx512erintrin.h */ test_1 (_mm512_exp2a23_round_pd, __m512d, __m512d, 5) test_1 (_mm512_exp2a23_round_ps, __m512, __m512, 5) diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c b/gcc/testsuite/gcc.target/i386/sse-23.c index 309cd73..77c8d67 100644 --- a/gcc/testsuite/gcc.target/i386/sse-23.c +++ b/gcc/testsuite/gcc.target/i386/sse-23.c @@ -365,6 +365,10 @@ #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) +#define __builtin_ia32_gatherpfdpd(A, B, C, D, E) __builtin_ia32_gatherpfdpd(A, B, C, 1, 1) +#define __builtin_ia32_gatherpfqpd(A, B, C, D, E) __builtin_ia32_gatherpfqpd(A, B, C, 1, 1) +#define __builtin_ia32_scatterpfdpd(A, B, C, D, E) __builtin_ia32_scatterpfdpd(A, B, C, 1, 1) +#define __builtin_ia32_scatterpfqpd(A, B, C, D, E) __builtin_ia32_scatterpfqpd(A, B, C, 1, 1) /* avx512erintrin.h */ #define __builtin_ia32_exp2pd_mask(A, B, C, D) __builtin_ia32_exp2pd_mask (A, B, C, 5)

[i386,11/8,AVX512,2/2] Add missing packed PF gathers/scatters.

Commit Message

Comments

Patch