gcc/testsuite/gcc.target/i386/avx512vl-vmovaps-1.c

   1 /* { dg-do compile } */
   2 /* { dg-options "-mavx512vl -O2" } */
   3 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
   4 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
   5 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
   6 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
   7 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*\\)\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
   8 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*\\)\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
   9 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*\\)\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
  10 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*\\)\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
  11 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\]*\\)\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
  12 /* { dg-final { scan-assembler-times "vmovaps\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*\\)\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
  13
  14 #include <immintrin.h>
  15
  16 float __attribute__ ((aligned (32))) *p;
  17 volatile __m256 yy, y2;
  18 volatile __m128 xx, x2;
  19 volatile __mmask8 m;
  20
  21 void extern
  22 avx512vl_test (void)
  23 {
  24   yy = _mm256_mask_mov_ps (yy, m, y2);
  25   xx = _mm_mask_mov_ps (xx, m, x2);
  26
  27   yy = _mm256_maskz_mov_ps (m, y2);
  28   xx = _mm_maskz_mov_ps (m, x2);
  29
  30   yy = _mm256_mask_load_ps (yy, m, p);
  31   xx = _mm_mask_load_ps (xx, m, p);
  32
  33   yy = _mm256_maskz_load_ps (m, p);
  34   xx = _mm_maskz_load_ps (m, p);
  35
  36   _mm256_mask_store_ps (p, m, yy);
  37   _mm_mask_store_ps (p, m, xx);
  38 }