| Message ID | 20210629180859.1235662-5-pc@us.ibm.com |
|---|---|
| State | New |
| Headers | show |
| Series | rs6000: Add SSE4.1 "test" and "blend" intrinsics | expand |
Hi Paul, Please resubmit this when you resubmit 3/4, in case any adjustments are needed. Thanks! Bill On 6/29/21 1:08 PM, Paul A. Clarke via Gcc-patches wrote: > Copy the tests for _mm_blend_pd, _mm_blendv_pd, _mm_blend_ps, > _mm_blendv_ps from gcc/testsuite/gcc.target/i386. > > 2021-06-29 Paul A. Clarke <pc@us.ibm.com> > > gcc/testsuite/ChangeLog: > * gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c: Copy > from gcc/testsuite/gcc.target/i386. > * gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c: Likewise. > * gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c: Likewise. > * gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c: Likewise. > --- > .../gcc.target/powerpc/sse4_1-blendpd.c | 89 ++++++++++++++++++ > .../gcc.target/powerpc/sse4_1-blendps-2.c | 81 +++++++++++++++++ > .../gcc.target/powerpc/sse4_1-blendps.c | 90 +++++++++++++++++++ > .../gcc.target/powerpc/sse4_1-blendvpd.c | 65 ++++++++++++++ > 4 files changed, 325 insertions(+) > create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c > create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c > create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c > create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c > > diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c > new file mode 100644 > index 000000000000..ca1780471fa2 > --- /dev/null > +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c > @@ -0,0 +1,89 @@ > +/* { dg-do run } */ > +/* { dg-require-effective-target p8vector_hw } */ > +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ > + > +#ifndef CHECK_H > +#define CHECK_H "sse4_1-check.h" > +#endif > + > +#ifndef TEST > +#define TEST sse4_1_test > +#endif > + > +#include CHECK_H > + > +#include <smmintrin.h> > +#include <string.h> > + > +#define NUM 20 > + > +#ifndef MASK > +#define MASK 0x03 > +#endif > + > +static void > +init_blendpd (double *src1, double *src2) > +{ > + int i, sign = 1; > + > + for (i = 0; i < NUM * 2; i++) > + { > + src1[i] = i * i * sign; > + src2[i] = (i + 20) * sign; > + sign = -sign; > + } > +} > + > +static int > +check_blendpd (__m128d *dst, double *src1, double *src2) > +{ > + double tmp[2]; > + int j; > + > + memcpy (&tmp[0], src1, sizeof (tmp)); > + > + for(j = 0; j < 2; j++) > + if ((MASK & (1 << j))) > + tmp[j] = src2[j]; > + > + return memcmp (dst, &tmp[0], sizeof (tmp)); > +} > + > +static void > +TEST (void) > +{ > + __m128d x, y; > + union > + { > + __m128d x[NUM]; > + double d[NUM * 2]; > + } dst, src1, src2; > + union > + { > + __m128d x; > + double d[2]; > + } src3; > + int i; > + > + init_blendpd (src1.d, src2.d); > + > + /* Check blendpd imm8, m128, xmm */ > + for (i = 0; i < NUM; i++) > + { > + dst.x[i] = _mm_blend_pd (src1.x[i], src2.x[i], MASK); > + if (check_blendpd (&dst.x[i], &src1.d[i * 2], &src2.d[i * 2])) > + abort (); > + } > + > + /* Check blendpd imm8, xmm, xmm */ > + src3.x = _mm_setzero_pd (); > + > + x = _mm_blend_pd (dst.x[2], src3.x, MASK); > + y = _mm_blend_pd (src3.x, dst.x[2], MASK); > + > + if (check_blendpd (&x, &dst.d[4], &src3.d[0])) > + abort (); > + > + if (check_blendpd (&y, &src3.d[0], &dst.d[4])) > + abort (); > +} > diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c > new file mode 100644 > index 000000000000..768b6e64bbae > --- /dev/null > +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c > @@ -0,0 +1,81 @@ > +/* { dg-do run } */ > +/* { dg-require-effective-target p8vector_hw } */ > +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ > + > +#include "sse4_1-check.h" > + > +#include <smmintrin.h> > +#include <string.h> > +#include <stdlib.h> > + > +#define NUM 20 > + > +#undef MASK > +#define MASK 0xe > + > +static void > +init_blendps (float *src1, float *src2) > +{ > + int i, sign = 1; > + > + for (i = 0; i < NUM * 4; i++) > + { > + src1[i] = i * i * sign; > + src2[i] = (i + 20) * sign; > + sign = -sign; > + } > +} > + > +static int > +check_blendps (__m128 *dst, float *src1, float *src2) > +{ > + float tmp[4]; > + int j; > + > + memcpy (&tmp[0], src1, sizeof (tmp)); > + for (j = 0; j < 4; j++) > + if ((MASK & (1 << j))) > + tmp[j] = src2[j]; > + > + return memcmp (dst, &tmp[0], sizeof (tmp)); > +} > + > +static void > +sse4_1_test (void) > +{ > + __m128 x, y; > + union > + { > + __m128 x[NUM]; > + float f[NUM * 4]; > + } dst, src1, src2; > + union > + { > + __m128 x; > + float f[4]; > + } src3; > + int i; > + > + init_blendps (src1.f, src2.f); > + > + for (i = 0; i < 4; i++) > + src3.f[i] = (int) rand (); > + > + /* Check blendps imm8, m128, xmm */ > + for (i = 0; i < NUM; i++) > + { > + dst.x[i] = _mm_blend_ps (src1.x[i], src2.x[i], MASK); > + if (check_blendps (&dst.x[i], &src1.f[i * 4], &src2.f[i * 4])) > + abort (); > + } > + > + /* Check blendps imm8, xmm, xmm */ > + x = _mm_blend_ps (dst.x[2], src3.x, MASK); > + y = _mm_blend_ps (src3.x, dst.x[2], MASK); > + > + if (check_blendps (&x, &dst.f[8], &src3.f[0])) > + abort (); > + > + if (check_blendps (&y, &src3.f[0], &dst.f[8])) > + abort (); > +} > diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c > new file mode 100644 > index 000000000000..2f114b69a84b > --- /dev/null > +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c > @@ -0,0 +1,90 @@ > +/* { dg-do run } */ > +/* { dg-require-effective-target p8vector_hw } */ > +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ > + > +#ifndef CHECK_H > +#define CHECK_H "sse4_1-check.h" > +#endif > + > +#ifndef TEST > +#define TEST sse4_1_test > +#endif > + > +#include CHECK_H > + > +#include <smmintrin.h> > +#include <string.h> > +#include <stdlib.h> > + > +#define NUM 20 > + > +#ifndef MASK > +#define MASK 0x0f > +#endif > + > +static void > +init_blendps (float *src1, float *src2) > +{ > + int i, sign = 1; > + > + for (i = 0; i < NUM * 4; i++) > + { > + src1[i] = i * i * sign; > + src2[i] = (i + 20) * sign; > + sign = -sign; > + } > +} > + > +static int > +check_blendps (__m128 *dst, float *src1, float *src2) > +{ > + float tmp[4]; > + int j; > + > + memcpy (&tmp[0], src1, sizeof (tmp)); > + for (j = 0; j < 4; j++) > + if ((MASK & (1 << j))) > + tmp[j] = src2[j]; > + > + return memcmp (dst, &tmp[0], sizeof (tmp)); > +} > + > +static void > +TEST (void) > +{ > + __m128 x, y; > + union > + { > + __m128 x[NUM]; > + float f[NUM * 4]; > + } dst, src1, src2; > + union > + { > + __m128 x; > + float f[4]; > + } src3; > + int i; > + > + init_blendps (src1.f, src2.f); > + > + for (i = 0; i < 4; i++) > + src3.f[i] = (int) rand (); > + > + /* Check blendps imm8, m128, xmm */ > + for (i = 0; i < NUM; i++) > + { > + dst.x[i] = _mm_blend_ps (src1.x[i], src2.x[i], MASK); > + if (check_blendps (&dst.x[i], &src1.f[i * 4], &src2.f[i * 4])) > + abort (); > + } > + > + /* Check blendps imm8, xmm, xmm */ > + x = _mm_blend_ps (dst.x[2], src3.x, MASK); > + y = _mm_blend_ps (src3.x, dst.x[2], MASK); > + > + if (check_blendps (&x, &dst.f[8], &src3.f[0])) > + abort (); > + > + if (check_blendps (&y, &src3.f[0], &dst.f[8])) > + abort (); > +} > diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c > new file mode 100644 > index 000000000000..b82cd28848a6 > --- /dev/null > +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c > @@ -0,0 +1,65 @@ > +/* { dg-do run } */ > +/* { dg-require-effective-target p8vector_hw } */ > +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ > + > +#include "sse4_1-check.h" > + > +#include <smmintrin.h> > +#include <string.h> > + > +#define NUM 20 > + > +static void > +init_blendvpd (double *src1, double *src2, double *mask) > +{ > + int i, msk, sign = 1; > + > + msk = -1; > + for (i = 0; i < NUM * 2; i++) > + { > + if((i % 2) == 0) > + msk++; > + src1[i] = i* (i + 1) * sign; > + src2[i] = (i + 20) * sign; > + mask[i] = (i + 120) * i; > + if( (msk & (1 << (i % 2)))) > + mask[i] = -mask[i]; > + sign = -sign; > + } > +} > + > +static int > +check_blendvpd (__m128d *dst, double *src1, double *src2, > + double *mask) > +{ > + double tmp[2]; > + int j; > + > + memcpy (&tmp[0], src1, sizeof (tmp)); > + for (j = 0; j < 2; j++) > + if (mask [j] < 0.0) > + tmp[j] = src2[j]; > + > + return memcmp (dst, &tmp[0], sizeof (tmp)); > +} > + > +static void > +sse4_1_test (void) > +{ > + union > + { > + __m128d x[NUM]; > + double d[NUM * 2]; > + } dst, src1, src2, mask; > + int i; > + > + init_blendvpd (src1.d, src2.d, mask.d); > + > + for (i = 0; i < NUM; i++) > + { > + dst.x[i] = _mm_blendv_pd (src1.x[i], src2.x[i], mask.x[i]); > + if (check_blendvpd (&dst.x[i], &src1.d[i * 2], &src2.d[i * 2], > + &mask.d[i * 2])) > + abort (); > + } > +}
On Sun, Jul 11, 2021 at 11:19:56AM -0500, Bill Schmidt wrote: > Please resubmit this when you resubmit 3/4, in case any adjustments are > needed. It is testing if elsewhere-defined functions work according to its specification -- let's hope that doesn't change ;-) Segher
diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c new file mode 100644 index 000000000000..ca1780471fa2 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendpd.c @@ -0,0 +1,89 @@ +/* { dg-do run } */ +/* { dg-require-effective-target p8vector_hw } */ +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ + +#ifndef CHECK_H +#define CHECK_H "sse4_1-check.h" +#endif + +#ifndef TEST +#define TEST sse4_1_test +#endif + +#include CHECK_H + +#include <smmintrin.h> +#include <string.h> + +#define NUM 20 + +#ifndef MASK +#define MASK 0x03 +#endif + +static void +init_blendpd (double *src1, double *src2) +{ + int i, sign = 1; + + for (i = 0; i < NUM * 2; i++) + { + src1[i] = i * i * sign; + src2[i] = (i + 20) * sign; + sign = -sign; + } +} + +static int +check_blendpd (__m128d *dst, double *src1, double *src2) +{ + double tmp[2]; + int j; + + memcpy (&tmp[0], src1, sizeof (tmp)); + + for(j = 0; j < 2; j++) + if ((MASK & (1 << j))) + tmp[j] = src2[j]; + + return memcmp (dst, &tmp[0], sizeof (tmp)); +} + +static void +TEST (void) +{ + __m128d x, y; + union + { + __m128d x[NUM]; + double d[NUM * 2]; + } dst, src1, src2; + union + { + __m128d x; + double d[2]; + } src3; + int i; + + init_blendpd (src1.d, src2.d); + + /* Check blendpd imm8, m128, xmm */ + for (i = 0; i < NUM; i++) + { + dst.x[i] = _mm_blend_pd (src1.x[i], src2.x[i], MASK); + if (check_blendpd (&dst.x[i], &src1.d[i * 2], &src2.d[i * 2])) + abort (); + } + + /* Check blendpd imm8, xmm, xmm */ + src3.x = _mm_setzero_pd (); + + x = _mm_blend_pd (dst.x[2], src3.x, MASK); + y = _mm_blend_pd (src3.x, dst.x[2], MASK); + + if (check_blendpd (&x, &dst.d[4], &src3.d[0])) + abort (); + + if (check_blendpd (&y, &src3.d[0], &dst.d[4])) + abort (); +} diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c new file mode 100644 index 000000000000..768b6e64bbae --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps-2.c @@ -0,0 +1,81 @@ +/* { dg-do run } */ +/* { dg-require-effective-target p8vector_hw } */ +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ + +#include "sse4_1-check.h" + +#include <smmintrin.h> +#include <string.h> +#include <stdlib.h> + +#define NUM 20 + +#undef MASK +#define MASK 0xe + +static void +init_blendps (float *src1, float *src2) +{ + int i, sign = 1; + + for (i = 0; i < NUM * 4; i++) + { + src1[i] = i * i * sign; + src2[i] = (i + 20) * sign; + sign = -sign; + } +} + +static int +check_blendps (__m128 *dst, float *src1, float *src2) +{ + float tmp[4]; + int j; + + memcpy (&tmp[0], src1, sizeof (tmp)); + for (j = 0; j < 4; j++) + if ((MASK & (1 << j))) + tmp[j] = src2[j]; + + return memcmp (dst, &tmp[0], sizeof (tmp)); +} + +static void +sse4_1_test (void) +{ + __m128 x, y; + union + { + __m128 x[NUM]; + float f[NUM * 4]; + } dst, src1, src2; + union + { + __m128 x; + float f[4]; + } src3; + int i; + + init_blendps (src1.f, src2.f); + + for (i = 0; i < 4; i++) + src3.f[i] = (int) rand (); + + /* Check blendps imm8, m128, xmm */ + for (i = 0; i < NUM; i++) + { + dst.x[i] = _mm_blend_ps (src1.x[i], src2.x[i], MASK); + if (check_blendps (&dst.x[i], &src1.f[i * 4], &src2.f[i * 4])) + abort (); + } + + /* Check blendps imm8, xmm, xmm */ + x = _mm_blend_ps (dst.x[2], src3.x, MASK); + y = _mm_blend_ps (src3.x, dst.x[2], MASK); + + if (check_blendps (&x, &dst.f[8], &src3.f[0])) + abort (); + + if (check_blendps (&y, &src3.f[0], &dst.f[8])) + abort (); +} diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c new file mode 100644 index 000000000000..2f114b69a84b --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendps.c @@ -0,0 +1,90 @@ +/* { dg-do run } */ +/* { dg-require-effective-target p8vector_hw } */ +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ + +#ifndef CHECK_H +#define CHECK_H "sse4_1-check.h" +#endif + +#ifndef TEST +#define TEST sse4_1_test +#endif + +#include CHECK_H + +#include <smmintrin.h> +#include <string.h> +#include <stdlib.h> + +#define NUM 20 + +#ifndef MASK +#define MASK 0x0f +#endif + +static void +init_blendps (float *src1, float *src2) +{ + int i, sign = 1; + + for (i = 0; i < NUM * 4; i++) + { + src1[i] = i * i * sign; + src2[i] = (i + 20) * sign; + sign = -sign; + } +} + +static int +check_blendps (__m128 *dst, float *src1, float *src2) +{ + float tmp[4]; + int j; + + memcpy (&tmp[0], src1, sizeof (tmp)); + for (j = 0; j < 4; j++) + if ((MASK & (1 << j))) + tmp[j] = src2[j]; + + return memcmp (dst, &tmp[0], sizeof (tmp)); +} + +static void +TEST (void) +{ + __m128 x, y; + union + { + __m128 x[NUM]; + float f[NUM * 4]; + } dst, src1, src2; + union + { + __m128 x; + float f[4]; + } src3; + int i; + + init_blendps (src1.f, src2.f); + + for (i = 0; i < 4; i++) + src3.f[i] = (int) rand (); + + /* Check blendps imm8, m128, xmm */ + for (i = 0; i < NUM; i++) + { + dst.x[i] = _mm_blend_ps (src1.x[i], src2.x[i], MASK); + if (check_blendps (&dst.x[i], &src1.f[i * 4], &src2.f[i * 4])) + abort (); + } + + /* Check blendps imm8, xmm, xmm */ + x = _mm_blend_ps (dst.x[2], src3.x, MASK); + y = _mm_blend_ps (src3.x, dst.x[2], MASK); + + if (check_blendps (&x, &dst.f[8], &src3.f[0])) + abort (); + + if (check_blendps (&y, &src3.f[0], &dst.f[8])) + abort (); +} diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c new file mode 100644 index 000000000000..b82cd28848a6 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvpd.c @@ -0,0 +1,65 @@ +/* { dg-do run } */ +/* { dg-require-effective-target p8vector_hw } */ +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */ + +#include "sse4_1-check.h" + +#include <smmintrin.h> +#include <string.h> + +#define NUM 20 + +static void +init_blendvpd (double *src1, double *src2, double *mask) +{ + int i, msk, sign = 1; + + msk = -1; + for (i = 0; i < NUM * 2; i++) + { + if((i % 2) == 0) + msk++; + src1[i] = i* (i + 1) * sign; + src2[i] = (i + 20) * sign; + mask[i] = (i + 120) * i; + if( (msk & (1 << (i % 2)))) + mask[i] = -mask[i]; + sign = -sign; + } +} + +static int +check_blendvpd (__m128d *dst, double *src1, double *src2, + double *mask) +{ + double tmp[2]; + int j; + + memcpy (&tmp[0], src1, sizeof (tmp)); + for (j = 0; j < 2; j++) + if (mask [j] < 0.0) + tmp[j] = src2[j]; + + return memcmp (dst, &tmp[0], sizeof (tmp)); +} + +static void +sse4_1_test (void) +{ + union + { + __m128d x[NUM]; + double d[NUM * 2]; + } dst, src1, src2, mask; + int i; + + init_blendvpd (src1.d, src2.d, mask.d); + + for (i = 0; i < NUM; i++) + { + dst.x[i] = _mm_blendv_pd (src1.x[i], src2.x[i], mask.x[i]); + if (check_blendvpd (&dst.x[i], &src1.d[i * 2], &src2.d[i * 2], + &mask.d[i * 2])) + abort (); + } +}