From f8aa2b2c434483559d93ffa7b56643caecd276da Mon Sep 17 00:00:00 2001 From: Sebastian Peryt Date: Wed, 5 Jul 2017 18:44:18 +0200 Subject: [PATCH] Scalar mask and round RTL templates gcc/ * config/i386/subst.md (mask_scalar, round_scalar, round_saeonly_scalar): New meta-templates. (mask_scalar_name, mask_scalar_operand3, round_scalar_name, round_scalar_mask_operand3, round_scalar_mask_op3, round_scalar_constraint, round_scalar_prefix, round_saeonly_scalar_name, round_saeonly_scalar_mask_operand3, round_saeonly_scalar_mask_op3, round_saeonly_scalar_constraint, round_saeonly_scalar_prefix): New subst attribute. * config/i386/sse.md (_vm3): Renamed to ... _vm3 ... this. (_vm3): Renamed to ... _vm3 ... this. (_vm3): Renamed to ... _vm3 ... this. (v \t{%2, %1, %0| %0, %1, %2}): Changed to ... v \t{%2, %1, %0| %0, %1, %2} ... this. (v \t{%2, %1, %0| %0, %1, %2}): Changed to ... v \t{%2, %1, %0| %0, %1, %2} ... this. (v \t{%2, %1, %0| %0, %1, %2}): Changed to ... v \t{%2, %1, %0| %0, %1, %2 } ... this. gcc/testsuite/ * gcc.target/i386/avx512f-vaddsd-3.c: New test for mask 0 verification. * gcc.target/i386/avx512f-vaddss-3.c: Ditto. * gcc.target/i386/avx512f-vdivsd-3.c: Ditto. * gcc.target/i386/avx512f-vdivss-3.c: Ditto. * gcc.target/i386/avx512f-vmaxsd-3.c: Ditto. * gcc.target/i386/avx512f-vmaxss-3.c: Ditto. * gcc.target/i386/avx512f-vminsd-3.c: Ditto. * gcc.target/i386/avx512f-vminss-3.c: Ditto. * gcc.target/i386/avx512f-vmulsd-3.c: Ditto. * gcc.target/i386/avx512f-vmulss-3.c: Ditto. * gcc.target/i386/avx512f-vsubsd-3.c: Ditto. * gcc.target/i386/avx512f-vsubss-3.c: Ditto. From-SVN: r250006 --- gcc/ChangeLog | 40 +++++++++++ gcc/config/i386/sse.md | 24 +++---- gcc/config/i386/subst.md | 63 ++++++++++++++++++ gcc/testsuite/ChangeLog | 15 +++++ .../gcc.target/i386/avx512f-vaddsd-3.c | 62 +++++++++++++++++ .../gcc.target/i386/avx512f-vaddss-3.c | 65 ++++++++++++++++++ .../gcc.target/i386/avx512f-vdivsd-3.c | 62 +++++++++++++++++ .../gcc.target/i386/avx512f-vdivss-3.c | 64 ++++++++++++++++++ .../gcc.target/i386/avx512f-vmaxsd-3.c | 62 +++++++++++++++++ .../gcc.target/i386/avx512f-vmaxss-3.c | 66 +++++++++++++++++++ .../gcc.target/i386/avx512f-vminsd-3.c | 62 +++++++++++++++++ .../gcc.target/i386/avx512f-vminss-3.c | 66 +++++++++++++++++++ .../gcc.target/i386/avx512f-vmulsd-3.c | 62 +++++++++++++++++ .../gcc.target/i386/avx512f-vmulss-3.c | 64 ++++++++++++++++++ .../gcc.target/i386/avx512f-vsubsd-3.c | 62 +++++++++++++++++ .../gcc.target/i386/avx512f-vsubss-3.c | 64 ++++++++++++++++++ 16 files changed, 891 insertions(+), 12 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vaddsd-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vaddss-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vdivsd-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vdivss-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmaxsd-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmaxss-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vminsd-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vminss-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmulsd-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vmulss-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vsubsd-3.c create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-vsubss-3.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 41ee99c4af4..3c66d2f4ad0 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,43 @@ +2017-07-05 Sebastian Peryt + + * config/i386/subst.md (mask_scalar, round_scalar, + round_saeonly_scalar): New meta-templates. + (mask_scalar_name, mask_scalar_operand3, round_scalar_name, + round_scalar_mask_operand3, round_scalar_mask_op3, + round_scalar_constraint, round_scalar_prefix, round_saeonly_scalar_name, + round_saeonly_scalar_mask_operand3, round_saeonly_scalar_mask_op3, + round_saeonly_scalar_constraint, + round_saeonly_scalar_prefix): New subst attribute. + * config/i386/sse.md + (_vm3): Renamed to ... + _vm3 + ... this. + (_vm3): Renamed to ... + _vm3 + ... this. + (_vm3): Renamed to ... + _vm3 + ... this. + (v + \t{%2, %1, %0| + %0, %1, %2}): Changed to ... + v + \t{%2, %1, %0| + %0, %1, %2} ... this. + (v + \t{%2, %1, %0| + %0, %1, %2}): Changed to ... + v + \t{%2, %1, %0| + %0, %1, %2} ... this. + (v + \t{%2, %1, %0| + %0, %1, %2}): Changed to ... + v + \t{%2, %1, %0| + %0, %1, %2 + } ... this. + 2017-07-05 Richard Earnshaw * config/arm/arm.c (arm_fixed_condition_code_regs): New function. diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 5cf6c928bfb..e557b35cd1e 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -1568,21 +1568,21 @@ (set_attr "prefix" "") (set_attr "mode" "")]) -(define_insn "_vm3" +(define_insn "_vm3" [(set (match_operand:VF_128 0 "register_operand" "=x,v") (vec_merge:VF_128 (plusminus:VF_128 (match_operand:VF_128 1 "register_operand" "0,v") - (match_operand:VF_128 2 "vector_operand" "xBm,")) + (match_operand:VF_128 2 "vector_operand" "xBm,")) (match_dup 1) (const_int 1)))] "TARGET_SSE" "@ \t{%2, %0|%0, %2} - v\t{%2, %1, %0|%0, %1, %2}" + v\t{%2, %1, %0|%0, %1, %2}" [(set_attr "isa" "noavx,avx") (set_attr "type" "sseadd") - (set_attr "prefix" "") + (set_attr "prefix" "") (set_attr "mode" "")]) (define_expand "mul3" @@ -1608,21 +1608,21 @@ (set_attr "btver2_decode" "direct,double") (set_attr "mode" "")]) -(define_insn "_vm3" +(define_insn "_vm3" [(set (match_operand:VF_128 0 "register_operand" "=x,v") (vec_merge:VF_128 (multdiv:VF_128 (match_operand:VF_128 1 "register_operand" "0,v") - (match_operand:VF_128 2 "vector_operand" "xBm,")) + (match_operand:VF_128 2 "vector_operand" "xBm,")) (match_dup 1) (const_int 1)))] "TARGET_SSE" "@ \t{%2, %0|%0, %2} - v\t{%2, %1, %0|%0, %1, %2}" + v\t{%2, %1, %0|%0, %1, %2}" [(set_attr "isa" "noavx,avx") (set_attr "type" "sse") - (set_attr "prefix" "") + (set_attr "prefix" "") (set_attr "btver2_decode" "direct,double") (set_attr "mode" "")]) @@ -1944,22 +1944,22 @@ (set_attr "prefix" "") (set_attr "mode" "")]) -(define_insn "_vm3" +(define_insn "_vm3" [(set (match_operand:VF_128 0 "register_operand" "=x,v") (vec_merge:VF_128 (smaxmin:VF_128 (match_operand:VF_128 1 "register_operand" "0,v") - (match_operand:VF_128 2 "vector_operand" "xBm,")) + (match_operand:VF_128 2 "vector_operand" "xBm,")) (match_dup 1) (const_int 1)))] "TARGET_SSE" "@ \t{%2, %0|%0, %2} - v\t{%2, %1, %0|%0, %1, %2}" + v\t{%2, %1, %0|%0, %1, %2}" [(set_attr "isa" "noavx,avx") (set_attr "type" "sse") (set_attr "btver2_sse_attr" "maxmin") - (set_attr "prefix" "") + (set_attr "prefix" "") (set_attr "mode" "")]) (define_insn "avx_addsubv4df3" diff --git a/gcc/config/i386/subst.md b/gcc/config/i386/subst.md index 4685db302b9..1c7306efd3e 100644 --- a/gcc/config/i386/subst.md +++ b/gcc/config/i386/subst.md @@ -236,3 +236,66 @@ (match_dup 3) (match_operand:SUBST_V 4 "vector_move_operand") (match_operand: 5 "register_operand")]) + +(define_subst_attr "mask_scalar_name" "mask_scalar" "" "_mask") +(define_subst_attr "mask_scalar_operand3" "mask_scalar" "" "%{%4%}%N3") + +(define_subst "mask_scalar" + [(set (match_operand:SUBST_V 0) + (vec_merge:SUBST_V + (match_operand:SUBST_V 1) + (match_operand:SUBST_V 2) + (const_int 1)))] + "TARGET_AVX512F" + [(set (match_dup 0) + (vec_merge:SUBST_V + (vec_merge:SUBST_V + (match_dup 1) + (match_operand:SUBST_V 3 "vector_move_operand" "0C") + (match_operand: 4 "register_operand" "Yk")) + (match_dup 2) + (const_int 1)))]) + +(define_subst_attr "round_scalar_name" "round_scalar" "" "_round") +(define_subst_attr "round_scalar_mask_operand3" "mask_scalar" "%R3" "%R5") +(define_subst_attr "round_scalar_mask_op3" "round_scalar" "" "") +(define_subst_attr "round_scalar_constraint" "round_scalar" "vm" "v") +(define_subst_attr "round_scalar_prefix" "round_scalar" "vex" "evex") + +(define_subst "round_scalar" + [(set (match_operand:SUBST_V 0) + (vec_merge:SUBST_V + (match_operand:SUBST_V 1) + (match_operand:SUBST_V 2) + (const_int 1)))] + "TARGET_AVX512F" + [(set (match_dup 0) + (unspec:SUBST_V [ + (vec_merge:SUBST_V + (match_dup 1) + (match_dup 2) + (const_int 1)) + (match_operand:SI 3 "const_4_or_8_to_11_operand")] + UNSPEC_EMBEDDED_ROUNDING))]) + +(define_subst_attr "round_saeonly_scalar_name" "round_saeonly_scalar" "" "_round") +(define_subst_attr "round_saeonly_scalar_mask_operand3" "mask_scalar" "%r3" "%r5") +(define_subst_attr "round_saeonly_scalar_mask_op3" "round_saeonly_scalar" "" "") +(define_subst_attr "round_saeonly_scalar_constraint" "round_saeonly_scalar" "vm" "v") +(define_subst_attr "round_saeonly_scalar_prefix" "round_saeonly_scalar" "vex" "evex") + +(define_subst "round_saeonly_scalar" + [(set (match_operand:SUBST_V 0) + (vec_merge:SUBST_V + (match_operand:SUBST_V 1) + (match_operand:SUBST_V 2) + (const_int 1)))] + "TARGET_AVX512F" + [(set (match_dup 0) + (unspec:SUBST_V [ + (vec_merge:SUBST_V + (match_dup 1) + (match_dup 2) + (const_int 1)) + (match_operand:SI 3 "const48_operand")] + UNSPEC_EMBEDDED_ROUNDING))]) diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 60159669d53..90092cfec7e 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,18 @@ +2017-07-05 Sebastian Peryt + + * gcc.target/i386/avx512f-vaddsd-3.c: New test for mask 0 verification. + * gcc.target/i386/avx512f-vaddss-3.c: Ditto. + * gcc.target/i386/avx512f-vdivsd-3.c: Ditto. + * gcc.target/i386/avx512f-vdivss-3.c: Ditto. + * gcc.target/i386/avx512f-vmaxsd-3.c: Ditto. + * gcc.target/i386/avx512f-vmaxss-3.c: Ditto. + * gcc.target/i386/avx512f-vminsd-3.c: Ditto. + * gcc.target/i386/avx512f-vminss-3.c: Ditto. + * gcc.target/i386/avx512f-vmulsd-3.c: Ditto. + * gcc.target/i386/avx512f-vmulss-3.c: Ditto. + * gcc.target/i386/avx512f-vsubsd-3.c: Ditto. + * gcc.target/i386/avx512f-vsubss-3.c: Ditto. + 2017-07-05 Georg-Johann Lay PR target/81305 diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vaddsd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vaddsd-3.c new file mode 100644 index 00000000000..fbe09b1220b --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vaddsd-3.c @@ -0,0 +1,62 @@ +/* { 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" + +static void +calc_add (double *r, double *s1, double *s2) +{ + r[0] = s1[0] + s2[0]; + r[1] = s1[1]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + double res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_add_sd (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_add_sd (mask, src1.x, src2.x); + res3.x = _mm_mask_add_round_sd (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_add_round_sd (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_add (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res1, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res2, res_ref)) + abort (); + + calc_add (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res3, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vaddss-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vaddss-3.c new file mode 100644 index 00000000000..45fb29594e5 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vaddss-3.c @@ -0,0 +1,65 @@ +/* { 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" + +static void +calc_add (float *r, float *s1, float *s2) +{ + r[0] = s1[0] + s2[0]; + + int i; + for (i = 1; i < SIZE; i++) + r[i] = s1[i]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + float res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_add_ss (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_add_ss (mask, src1.x, src2.x); + res3.x = _mm_mask_add_round_ss (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_add_round_ss (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_add (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res1, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res2, res_ref)) + abort (); + + calc_add (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res3, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vdivsd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vdivsd-3.c new file mode 100644 index 00000000000..0baaf75e194 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vdivsd-3.c @@ -0,0 +1,62 @@ +/* { 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" + +static void +calc_div (double *r, double *s1, double *s2) +{ + r[0] = s1[0] / s2[0]; + r[1] = s1[1]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + double res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_div_sd (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_div_sd (mask, src1.x, src2.x); + res3.x = _mm_mask_div_round_sd (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_div_round_sd (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_div (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res1, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res2, res_ref)) + abort (); + + calc_div (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res3, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vdivss-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vdivss-3.c new file mode 100644 index 00000000000..d337bb21182 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vdivss-3.c @@ -0,0 +1,64 @@ +/* { 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" + +static void +calc_div (float *r, float *s1, float *s2) +{ + r[0] = s1[0] / s2[0]; + int i; + for (i = 1; i < SIZE; i++) + r[i] = s1[i]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + float res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_div_ss (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_div_ss (mask, src1.x, src2.x); + res3.x = _mm_mask_div_round_ss (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_div_round_ss (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_div (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res1, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res2, res_ref)) + abort (); + + calc_div (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res3, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmaxsd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vmaxsd-3.c new file mode 100644 index 00000000000..95c9c6335af --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmaxsd-3.c @@ -0,0 +1,62 @@ +/* { 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" + +static void +calc_max (double *r, double *s1, double *s2) +{ + r[0] = s1[0] > s2[0] ? s1[0] : s2[0]; + r[1] = s1[1]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + double res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_max_sd (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_max_sd (mask, src1.x, src2.x); + res3.x = _mm_mask_max_round_sd (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_max_round_sd (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_max (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res1, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res2, res_ref)) + abort (); + + calc_max (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res3, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmaxss-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vmaxss-3.c new file mode 100644 index 00000000000..e40c891001b --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmaxss-3.c @@ -0,0 +1,66 @@ +/* { 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" + +static void +calc_max (float *r, float *s1, float *s2) +{ + r[0] = s1[0] > s2[0] ? s1[0] : s2[0]; + int i; + for (i = 1; i < SIZE; i++) + { + r[i] = s1[i]; + } +} + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + float res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_max_ss (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_max_ss (mask, src1.x, src2.x); + res3.x = _mm_mask_max_round_ss (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_max_round_ss (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_max (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res1, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res2, res_ref)) + abort (); + + calc_max (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res3, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vminsd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vminsd-3.c new file mode 100644 index 00000000000..eac806b0f23 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vminsd-3.c @@ -0,0 +1,62 @@ +/* { 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" + +static void +calc_min (double *r, double *s1, double *s2) +{ + r[0] = s1[0] < s2[0] ? s1[0] : s2[0]; + r[1] = s1[1]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + double res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_min_sd (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_min_sd (mask, src1.x, src2.x); + res3.x = _mm_mask_min_round_sd (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_min_round_sd (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_min (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res1, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res2, res_ref)) + abort (); + + calc_min (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res3, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vminss-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vminss-3.c new file mode 100644 index 00000000000..0ecddd6803e --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vminss-3.c @@ -0,0 +1,66 @@ +/* { 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" + +static void +calc_min (float *r, float *s1, float *s2) +{ + r[0] = s1[0] < s2[0] ? s1[0] : s2[0]; + int i; + for (i = 1; i < SIZE; i++) + { + r[i] = s1[i]; + } +} + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + float res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_min_ss (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_min_ss (mask, src1.x, src2.x); + res3.x = _mm_mask_min_round_ss (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_min_round_ss (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_min (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res1, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res2, res_ref)) + abort (); + + calc_min (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res3, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmulsd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vmulsd-3.c new file mode 100644 index 00000000000..f6afb693e68 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmulsd-3.c @@ -0,0 +1,62 @@ +/* { 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" + +static void +calc_mul (double *r, double *s1, double *s2) +{ + r[0] = s1[0] * s2[0]; + r[1] = s1[1]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + double res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_mul_sd (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_mul_sd (mask, src1.x, src2.x); + res3.x = _mm_mask_mul_round_sd (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_mul_round_sd (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_mul (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res1, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res2, res_ref)) + abort (); + + calc_mul (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res3, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vmulss-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vmulss-3.c new file mode 100644 index 00000000000..3d579905bae --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vmulss-3.c @@ -0,0 +1,64 @@ +/* { 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" + +static void +calc_mul (float *r, float *s1, float *s2) +{ + r[0] = s1[0] * s2[0]; + int i; + for (i = 1; i < SIZE; i++) + r[i] = s1[i]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + float res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_mul_ss (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_mul_ss (mask, src1.x, src2.x); + res3.x = _mm_mask_mul_round_ss (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_mul_round_ss (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_mul (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res1, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res2, res_ref)) + abort (); + + calc_mul (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res3, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vsubsd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vsubsd-3.c new file mode 100644 index 00000000000..d9f79133937 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vsubsd-3.c @@ -0,0 +1,62 @@ +/* { 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" + +static void +calc_sub (double *r, double *s1, double *s2) +{ + r[0] = s1[0] - s2[0]; + r[1] = s1[1]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128d res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + double res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_sub_sd (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_sub_sd (mask, src1.x, src2.x); + res3.x = _mm_mask_sub_round_sd (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_sub_round_sd (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_sub (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res1, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res2, res_ref)) + abort (); + + calc_sub (res_ref, src1.a, src2.a); + + MASK_MERGE (d) (res_ref, mask, 1); + if (check_union128d (res3, res_ref)) + abort (); + + MASK_ZERO (d) (res_ref, mask, 1); + if (check_union128d (res4, res_ref)) + abort (); +} + diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vsubss-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vsubss-3.c new file mode 100644 index 00000000000..bd597c959a6 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-vsubss-3.c @@ -0,0 +1,64 @@ +/* { 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" + +static void +calc_sub (float *r, float *s1, float *s2) +{ + r[0] = s1[0] - s2[0]; + int i; + for (i = 1; i < SIZE; i++) + r[i] = s1[i]; +} + +void +avx512f_test (void) +{ + int i, sign; + union128 res1, res2, res3, res4, src1, src2; + MASK_TYPE mask = 0; + float res_ref[SIZE]; + + sign = -1; + for (i = 0; i < SIZE; i++) + { + src1.a[i] = 1.5 + 34.67 * i * sign; + src2.a[i] = -22.17 * i * sign + 1.0; + res1.a[i] = DEFAULT_VALUE; + res3.a[i] = DEFAULT_VALUE; + sign = sign * -1; + } + + res1.x = _mm_mask_sub_ss (res1.x, mask, src1.x, src2.x); + res2.x = _mm_maskz_sub_ss (mask, src1.x, src2.x); + res3.x = _mm_mask_sub_round_ss (res3.x, mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + res4.x = _mm_maskz_sub_round_ss (mask, src1.x, src2.x, _MM_FROUND_NO_EXC); + + calc_sub (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res1, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res2, res_ref)) + abort (); + + calc_sub (res_ref, src1.a, src2.a); + + MASK_MERGE () (res_ref, mask, 1); + if (check_union128 (res3, res_ref)) + abort (); + + MASK_ZERO () (res_ref, mask, 1); + if (check_union128 (res4, res_ref)) + abort (); +} + -- 2.30.2