From 459d21c6cffb2c74d2644e21db372ba8a0c27eb6 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Thu, 7 Mar 2019 20:10:21 +0100 Subject: [PATCH] re PR target/89602 (Missing AVX512 intrinsics) PR target/89602 * config/i386/sse.md (avx512f_mov_mask, *avx512f_load_mask, avx512f_store_mask): New define_insns. (avx512f_load_mask): New define_expand. * config/i386/i386-builtin.def (__builtin_ia32_loadsd_mask, __builtin_ia32_loadss_mask, __builtin_ia32_storesd_mask, __builtin_ia32_storess_mask, __builtin_ia32_movesd_mask, __builtin_ia32_movess_mask): New builtins. * config/i386/avx512fintrin.h (_mm_mask_load_ss, _mm_maskz_load_ss, _mm_mask_load_sd, _mm_maskz_load_sd, _mm_mask_move_ss, _mm_maskz_move_ss, _mm_mask_move_sd, _mm_maskz_move_sd, _mm_mask_store_ss, _mm_mask_store_sd): New intrinsics. * gcc.target/i386/avx512f-vmovss-1.c: New test. * gcc.target/i386/avx512f-vmovss-2.c: New test. * gcc.target/i386/avx512f-vmovss-3.c: New test. * gcc.target/i386/avx512f-vmovsd-1.c: New test. * gcc.target/i386/avx512f-vmovsd-2.c: New test. * gcc.target/i386/avx512f-vmovsd-3.c: New test. From-SVN: r269467 --- gcc/ChangeLog | 15 ++++ gcc/config/i386/avx512fintrin.h | 77 ++++++++++++++++ gcc/config/i386/i386-builtin.def | 6 ++ gcc/config/i386/sse.md | 61 +++++++++++++ gcc/testsuite/ChangeLog | 10 +++ .../gcc.target/i386/avx512f-vmovsd-1.c | 23 +++++ .../gcc.target/i386/avx512f-vmovsd-2.c | 87 +++++++++++++++++++ .../gcc.target/i386/avx512f-vmovsd-3.c | 84 ++++++++++++++++++ .../gcc.target/i386/avx512f-vmovss-1.c | 23 +++++ .../gcc.target/i386/avx512f-vmovss-2.c | 87 +++++++++++++++++++ .../gcc.target/i386/avx512f-vmovss-3.c | 84 ++++++++++++++++++ 11 files changed, 557 insertions(+) create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmovsd-1.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmovsd-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmovsd-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmovss-1.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmovss-2.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmovss-3.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 148360523ed..082e90b0126 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,18 @@ +2019-03-07 Jakub Jelinek + + PR target/89602 + * config/i386/sse.md (avx512f_mov_mask, + *avx512f_load_mask, avx512f_store_mask): New define_insns. + (avx512f_load_mask): New define_expand. + * config/i386/i386-builtin.def (__builtin_ia32_loadsd_mask, + __builtin_ia32_loadss_mask, __builtin_ia32_storesd_mask, + __builtin_ia32_storess_mask, __builtin_ia32_movesd_mask, + __builtin_ia32_movess_mask): New builtins. + * config/i386/avx512fintrin.h (_mm_mask_load_ss, _mm_maskz_load_ss, + _mm_mask_load_sd, _mm_maskz_load_sd, _mm_mask_move_ss, + _mm_maskz_move_ss, _mm_mask_move_sd, _mm_maskz_move_sd, + _mm_mask_store_ss, _mm_mask_store_sd): New intrinsics. + 2019-03-07 Martin Jambor PR lto/87525 diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h index 68320c28da5..3a4e0ad3c32 100644 --- a/gcc/config/i386/avx512fintrin.h +++ b/gcc/config/i386/avx512fintrin.h @@ -6273,6 +6273,83 @@ _mm512_mask_storeu_ps (void *__P, __mmask16 __U, __m512 __A) (__mmask16) __U); } +extern __inline __m128 +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_mask_load_ss (__m128 __W, __mmask8 __U, const float *__P) +{ + return (__m128) __builtin_ia32_loadss_mask (__P, (__v4sf) __W, __U); +} + +extern __inline __m128 +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_maskz_load_ss (__mmask8 __U, const float *__P) +{ + return (__m128) __builtin_ia32_loadss_mask (__P, (__v4sf) _mm_setzero_ps (), + __U); +} + +extern __inline __m128d +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_mask_load_sd (__m128d __W, __mmask8 __U, const double *__P) +{ + return (__m128d) __builtin_ia32_loadsd_mask (__P, (__v2df) __W, __U); +} + +extern __inline __m128d +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_maskz_load_sd (__mmask8 __U, const double *__P) +{ + return (__m128d) __builtin_ia32_loadsd_mask (__P, (__v2df) _mm_setzero_pd (), + __U); +} + +extern __inline __m128 +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_mask_move_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) +{ + return (__m128) __builtin_ia32_movess_mask ((__v4sf) __A, (__v4sf) __B, + (__v4sf) __W, __U); +} + +extern __inline __m128 +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_maskz_move_ss (__mmask8 __U, __m128 __A, __m128 __B) +{ + return (__m128) __builtin_ia32_movess_mask ((__v4sf) __A, (__v4sf) __B, + (__v4sf) _mm_setzero_ps (), __U); +} + +extern __inline __m128d +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_mask_move_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) +{ + return (__m128d) __builtin_ia32_movesd_mask ((__v2df) __A, (__v2df) __B, + (__v2df) __W, __U); +} + +extern __inline __m128d +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_maskz_move_sd (__mmask8 __U, __m128d __A, __m128d __B) +{ + return (__m128d) __builtin_ia32_movesd_mask ((__v2df) __A, (__v2df) __B, + (__v2df) _mm_setzero_pd (), + __U); +} + +extern __inline void +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_mask_store_ss (float *__P, __mmask8 __U, __m128 __A) +{ + __builtin_ia32_storess_mask (__P, (__v4sf) __A, (__mmask8) __U); +} + +extern __inline void +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_mask_store_sd (double *__P, __mmask8 __U, __m128d __A) +{ + __builtin_ia32_storesd_mask (__P, (__v2df) __A, (__mmask8) __U); +} + extern __inline __m512i __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) _mm512_mask_loadu_epi64 (__m512i __W, __mmask8 __U, void const *__P) diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def index 88005f4687f..eeef341726a 100644 --- a/gcc/config/i386/i386-builtin.def +++ b/gcc/config/i386/i386-builtin.def @@ -255,6 +255,10 @@ BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_storev16sf_mask, "__builtin_ BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_storev16si_mask, "__builtin_ia32_movdqa32store512_mask", IX86_BUILTIN_MOVDQA32STORE512, UNKNOWN, (int) VOID_FTYPE_PV16SI_V16SI_UHI) BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_storev8df_mask, "__builtin_ia32_storeapd512_mask", IX86_BUILTIN_STOREAPD512, UNKNOWN, (int) VOID_FTYPE_PV8DF_V8DF_UQI) BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_storev8di_mask, "__builtin_ia32_movdqa64store512_mask", IX86_BUILTIN_MOVDQA64STORE512, UNKNOWN, (int) VOID_FTYPE_PV8DI_V8DI_UQI) +BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_loaddf_mask, "__builtin_ia32_loadsd_mask", IX86_BUILTIN_LOADSD_MASK, UNKNOWN, (int) V2DF_FTYPE_PCDOUBLE_V2DF_UQI) +BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_loadsf_mask, "__builtin_ia32_loadss_mask", IX86_BUILTIN_LOADSS_MASK, UNKNOWN, (int) V4SF_FTYPE_PCFLOAT_V4SF_UQI) +BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_storedf_mask, "__builtin_ia32_storesd_mask", IX86_BUILTIN_STORESD_MASK, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V2DF_UQI) +BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_storesf_mask, "__builtin_ia32_storess_mask", IX86_BUILTIN_STORESS_MASK, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V4SF_UQI) BDESC (OPTION_MASK_ISA_LWP, 0, CODE_FOR_lwp_llwpcb, "__builtin_ia32_llwpcb", IX86_BUILTIN_LLWPCB, UNKNOWN, (int) VOID_FTYPE_PVOID) BDESC (OPTION_MASK_ISA_LWP, 0, CODE_FOR_lwp_slwpcb, "__builtin_ia32_slwpcb", IX86_BUILTIN_SLWPCB, UNKNOWN, (int) PVOID_FTYPE_VOID) @@ -1470,6 +1474,8 @@ BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_vternlogv16si_mask, "__built BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_vternlogv16si_maskz, "__builtin_ia32_pternlogd512_maskz", IX86_BUILTIN_VTERNLOGD512_MASKZ, UNKNOWN, (int) V16SI_FTYPE_V16SI_V16SI_V16SI_INT_UHI) BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_vternlogv8di_mask, "__builtin_ia32_pternlogq512_mask", IX86_BUILTIN_VTERNLOGQ512_MASK, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_INT_UQI) BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_vternlogv8di_maskz, "__builtin_ia32_pternlogq512_maskz", IX86_BUILTIN_VTERNLOGQ512_MASKZ, UNKNOWN, (int) V8DI_FTYPE_V8DI_V8DI_V8DI_INT_UQI) +BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_movdf_mask, "__builtin_ia32_movesd_mask", IX86_BUILTIN_MOVSD_MASK, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_V2DF_UQI) +BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_movsf_mask, "__builtin_ia32_movess_mask", IX86_BUILTIN_MOVSS_MASK, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_V4SF_UQI) BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_copysignv16sf3, "__builtin_ia32_copysignps512", IX86_BUILTIN_CPYSGNPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF) BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_copysignv8df3, "__builtin_ia32_copysignpd512", IX86_BUILTIN_CPYSGNPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF) diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index ac299495b2c..259063f7862 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -1151,6 +1151,67 @@ (set_attr "memory" "none,load") (set_attr "mode" "")]) +(define_insn "avx512f_mov_mask" + [(set (match_operand:VF_128 0 "register_operand" "=v") + (vec_merge:VF_128 + (vec_merge:VF_128 + (match_operand:VF_128 2 "register_operand" "v") + (match_operand:VF_128 3 "nonimm_or_0_operand" "0C") + (match_operand:QI 4 "register_operand" "Yk")) + (match_operand:VF_128 1 "register_operand" "v") + (const_int 1)))] + "TARGET_AVX512F" + "vmov\t{%2, %1, %0%{%4%}%N3|%0%{%4%}%N3, %1, %2}" + [(set_attr "type" "ssemov") + (set_attr "prefix" "evex") + (set_attr "mode" "")]) + +(define_expand "avx512f_load_mask" + [(set (match_operand: 0 "register_operand") + (vec_merge: + (vec_merge: + (vec_duplicate: + (match_operand:MODEF 1 "memory_operand")) + (match_operand: 2 "nonimm_or_0_operand") + (match_operand:QI 3 "register_operand")) + (match_dup 4) + (const_int 1)))] + "TARGET_AVX512F" + "operands[4] = CONST0_RTX (mode);") + +(define_insn "*avx512f_load_mask" + [(set (match_operand: 0 "register_operand" "=v") + (vec_merge: + (vec_merge: + (vec_duplicate: + (match_operand:MODEF 1 "memory_operand" "m")) + (match_operand: 2 "nonimm_or_0_operand" "0C") + (match_operand:QI 3 "register_operand" "Yk")) + (match_operand: 4 "const0_operand" "C") + (const_int 1)))] + "TARGET_AVX512F" + "vmov\t{%1, %0%{%3%}%N2|%0%{3%}%N2, %1}" + [(set_attr "type" "ssemov") + (set_attr "prefix" "evex") + (set_attr "memory" "load") + (set_attr "mode" "")]) + +(define_insn "avx512f_store_mask" + [(set (match_operand:MODEF 0 "memory_operand" "=m") + (if_then_else:MODEF + (and:QI (match_operand:QI 2 "register_operand" "Yk") + (const_int 1)) + (vec_select:MODEF + (match_operand: 1 "register_operand" "v") + (parallel [(const_int 0)])) + (match_dup 0)))] + "TARGET_AVX512F" + "vmov\t{%1, %0%{%2%}|%0%{%2%}, %1}" + [(set_attr "type" "ssemov") + (set_attr "prefix" "evex") + (set_attr "memory" "store") + (set_attr "mode" "")]) + (define_insn "_blendm" [(set (match_operand:V48_AVX512VL 0 "register_operand" "=v") (vec_merge:V48_AVX512VL diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index bf1546b639b..31b1f69b814 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,13 @@ +2019-03-07 Jakub Jelinek + + PR target/89602 + * gcc.target/i386/avx512f-vmovss-1.c: New test. + * gcc.target/i386/avx512f-vmovss-2.c: New test. + * gcc.target/i386/avx512f-vmovss-3.c: New test. + * gcc.target/i386/avx512f-vmovsd-1.c: New test. + * gcc.target/i386/avx512f-vmovsd-2.c: New test. + * gcc.target/i386/avx512f-vmovsd-3.c: New test. + 2019-03-07 Martin Jambor PR lto/87525 diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-1.c b/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-1.c new file mode 100644 index 00000000000..a7e136b7a14 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-1.c @@ -0,0 +1,23 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512f -O2 -masm=att" } */ +/* { dg-final { scan-assembler-times "vmovsd\[ \\t\]+\\(%\[a-z0-9,]*\\), %xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovsd\[ \\t\]+\\(%\[a-z0-9,]*\\), %xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovsd\[ \\t\]+%xmm\[0-9\]+, %xmm\[0-9\]+, %xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovsd\[ \\t\]+%xmm\[0-9\]+, %xmm\[0-9\]+, %xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovsd\[ \\t\]+%xmm\[0-9\]+, \\(%\[a-z0-9,]*\\)\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */ + +#include + +volatile __m128d x1, x2, x3; +volatile __mmask8 m; +double *volatile p; + +void extern +avx512f_test (void) +{ + x1 = _mm_mask_load_sd (x1, m, p); + x1 = _mm_maskz_load_sd (m, p); + x1 = _mm_mask_move_sd (x1, m, x2, x3); + x1 = _mm_maskz_move_sd (m, x2, x3); + _mm_mask_store_sd (p, m, x1); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-2.c b/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-2.c new file mode 100644 index 00000000000..fad298aaf4c --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-2.c @@ -0,0 +1,87 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -mavx512f" } */ +/* { dg-require-effective-target avx512f } */ + +#include "avx512f-check.h" + +#include "avx512f-helper.h" + +#define SIZE (128 / 64) +#include "avx512f-mask-type.h" + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2, src3; + volatile __mmask8 mask = 5; + double val[2] = { 35.5, 0.0 }; + double *volatile p = &val[0]; + double res_ref[SIZE]; + double zero[SIZE]; + + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + i; + src2.a[i] = 7.5 + i; + src3.a[i] = 4.5 + i; + zero[i] = 0.0; + } + + res1.x = _mm_mask_load_sd (src1.x, mask, p); + res2.x = _mm_maskz_load_sd (mask, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = val[0]; + if (check_union128d (res1, res_ref)) + abort (); + + if (check_union128d (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_sd (src1.x, mask, src2.x, src3.x); + res4.x = _mm_maskz_move_sd (mask, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src3.a[0]; + if (check_union128d (res3, res_ref)) + abort (); + + if (check_union128d (res4, res_ref)) + abort (); + + _mm_mask_store_sd (p + 1, mask, src1.x); + if (val[1] != src1.a[0]) + abort (); + + mask ^= 1; + + res1.x = _mm_mask_load_sd (src1.x, mask, p); + res2.x = _mm_maskz_load_sd (mask, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = src1.a[0]; + if (check_union128d (res1, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128d (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_sd (src1.x, mask, src2.x, src3.x); + res4.x = _mm_maskz_move_sd (mask, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src1.a[0]; + if (check_union128d (res3, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128d (res4, res_ref)) + abort (); + + val[1] = 42.0; + _mm_mask_store_sd (p + 1, mask, src1.x); + if (val[1] != 42.0) + abort (); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-3.c new file mode 100644 index 00000000000..d84aefcb59c --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmovsd-3.c @@ -0,0 +1,84 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -mavx512f" } */ +/* { dg-require-effective-target avx512f } */ + +#include "avx512f-check.h" + +#include "avx512f-helper.h" + +#define SIZE (128 / 64) +#include "avx512f-mask-type.h" + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2, src3; + double val[2] = { 35.5, 0.0 }; + double *volatile p = &val[0]; + double res_ref[SIZE]; + double zero[SIZE]; + + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + i; + src2.a[i] = 7.5 + i; + src3.a[i] = 4.5 + i; + zero[i] = 0.0; + } + + res1.x = _mm_mask_load_sd (src1.x, 1, p); + res2.x = _mm_maskz_load_sd (1, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = val[0]; + if (check_union128d (res1, res_ref)) + abort (); + + if (check_union128d (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_sd (src1.x, 1, src2.x, src3.x); + res4.x = _mm_maskz_move_sd (1, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src3.a[0]; + if (check_union128d (res3, res_ref)) + abort (); + + if (check_union128d (res4, res_ref)) + abort (); + + _mm_mask_store_sd (p + 1, 1, src1.x); + if (val[1] != src1.a[0]) + abort (); + + res1.x = _mm_mask_load_sd (src1.x, 0, p); + res2.x = _mm_maskz_load_sd (0, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = src1.a[0]; + if (check_union128d (res1, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128d (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_sd (src1.x, 0, src2.x, src3.x); + res4.x = _mm_maskz_move_sd (0, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src1.a[0]; + if (check_union128d (res3, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128d (res4, res_ref)) + abort (); + + val[1] = 42.0; + _mm_mask_store_sd (p + 1, 0, src1.x); + if (val[1] != 42.0) + abort (); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmovss-1.c b/gcc/testsuite/gcc.target/i386/avx512f-vmovss-1.c new file mode 100644 index 00000000000..85f40dcaa3e --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmovss-1.c @@ -0,0 +1,23 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512f -O2 -masm=att" } */ +/* { dg-final { scan-assembler-times "vmovss\[ \\t\]+\\(%\[a-z0-9,]*\\), %xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovss\[ \\t\]+\\(%\[a-z0-9,]*\\), %xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovss\[ \\t\]+%xmm\[0-9\]+, %xmm\[0-9\]+, %xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovss\[ \\t\]+%xmm\[0-9\]+, %xmm\[0-9\]+, %xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */ +/* { dg-final { scan-assembler-times "vmovss\[ \\t\]+%xmm\[0-9\]+, \\(%\[a-z0-9,]*\\)\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */ + +#include + +volatile __m128 x1, x2, x3; +volatile __mmask8 m; +float *volatile p; + +void extern +avx512f_test (void) +{ + x1 = _mm_mask_load_ss (x1, m, p); + x1 = _mm_maskz_load_ss (m, p); + x1 = _mm_mask_move_ss (x1, m, x2, x3); + x1 = _mm_maskz_move_ss (m, x2, x3); + _mm_mask_store_ss (p, m, x1); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmovss-2.c b/gcc/testsuite/gcc.target/i386/avx512f-vmovss-2.c new file mode 100644 index 00000000000..91721cf851e --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmovss-2.c @@ -0,0 +1,87 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -mavx512f" } */ +/* { dg-require-effective-target avx512f } */ + +#include "avx512f-check.h" + +#include "avx512f-helper.h" + +#define SIZE (128 / 32) +#include "avx512f-mask-type.h" + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2, src3; + volatile __mmask8 mask = 5; + float val[2] = { 35.5f, 0.0f }; + float *volatile p = &val[0]; + float res_ref[SIZE]; + float zero[SIZE]; + + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5f + i; + src2.a[i] = 7.5f + i; + src3.a[i] = 4.5f + i; + zero[i] = 0.0f; + } + + res1.x = _mm_mask_load_ss (src1.x, mask, p); + res2.x = _mm_maskz_load_ss (mask, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = val[0]; + if (check_union128 (res1, res_ref)) + abort (); + + if (check_union128 (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_ss (src1.x, mask, src2.x, src3.x); + res4.x = _mm_maskz_move_ss (mask, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src3.a[0]; + if (check_union128 (res3, res_ref)) + abort (); + + if (check_union128 (res4, res_ref)) + abort (); + + _mm_mask_store_ss (p + 1, mask, src1.x); + if (val[1] != src1.a[0]) + abort (); + + mask ^= 1; + + res1.x = _mm_mask_load_ss (src1.x, mask, p); + res2.x = _mm_maskz_load_ss (mask, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = src1.a[0]; + if (check_union128 (res1, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128 (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_ss (src1.x, mask, src2.x, src3.x); + res4.x = _mm_maskz_move_ss (mask, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src1.a[0]; + if (check_union128 (res3, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128 (res4, res_ref)) + abort (); + + val[1] = 42.0f; + _mm_mask_store_ss (p + 1, mask, src1.x); + if (val[1] != 42.0f) + abort (); +} diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmovss-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vmovss-3.c new file mode 100644 index 00000000000..bb05983b7a4 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmovss-3.c @@ -0,0 +1,84 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -mavx512f" } */ +/* { dg-require-effective-target avx512f } */ + +#include "avx512f-check.h" + +#include "avx512f-helper.h" + +#define SIZE (128 / 32) +#include "avx512f-mask-type.h" + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2, src3; + float val[2] = { 35.5f, 0.0f }; + float *volatile p = &val[0]; + float res_ref[SIZE]; + float zero[SIZE]; + + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5f + i; + src2.a[i] = 7.5f + i; + src3.a[i] = 4.5f + i; + zero[i] = 0.0f; + } + + res1.x = _mm_mask_load_ss (src1.x, 1, p); + res2.x = _mm_maskz_load_ss (1, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = val[0]; + if (check_union128 (res1, res_ref)) + abort (); + + if (check_union128 (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_ss (src1.x, 1, src2.x, src3.x); + res4.x = _mm_maskz_move_ss (1, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src3.a[0]; + if (check_union128 (res3, res_ref)) + abort (); + + if (check_union128 (res4, res_ref)) + abort (); + + _mm_mask_store_ss (p + 1, 1, src1.x); + if (val[1] != src1.a[0]) + abort (); + + res1.x = _mm_mask_load_ss (src1.x, 0, p); + res2.x = _mm_maskz_load_ss (0, p); + + __builtin_memcpy (res_ref, zero, sizeof (zero)); + res_ref[0] = src1.a[0]; + if (check_union128 (res1, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128 (res2, res_ref)) + abort (); + + res3.x = _mm_mask_move_ss (src1.x, 0, src2.x, src3.x); + res4.x = _mm_maskz_move_ss (0, src2.x, src3.x); + + __builtin_memcpy (res_ref, src2.a, sizeof (src2.a)); + res_ref[0] = src1.a[0]; + if (check_union128 (res3, res_ref)) + abort (); + + res_ref[0] = zero[0]; + if (check_union128 (res4, res_ref)) + abort (); + + val[1] = 42.0f; + _mm_mask_store_ss (p + 1, 0, src1.x); + if (val[1] != 42.0f) + abort (); +} -- 2.30.2