File: sad-vectorize-2.c

package info (click to toggle)
gcc-arm-none-eabi 15%3A12.2.rel1-1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 959,712 kB
  • sloc: cpp: 3,275,382; ansic: 2,061,766; ada: 840,956; f90: 208,513; makefile: 76,132; asm: 73,433; xml: 50,448; exp: 34,146; sh: 32,436; objc: 15,637; fortran: 14,012; python: 11,991; pascal: 6,787; awk: 4,779; perl: 3,054; yacc: 338; ml: 285; lex: 201; haskell: 122
file content (34 lines) | stat: -rw-r--r-- 927 bytes parent folder | download 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
 
/* { dg-do compile } */
/* { dg-require-effective-target powerpc_p9vector_ok } */
/* { dg-options "-O3 -mdejagnu-cpu=power9" } */

/* Verify that we vectorize this SAD loop using vabsduh. */

extern int abs (int __x) __attribute__ ((__nothrow__, __leaf__)) __attribute__ ((__const__));

static int
foo (unsigned short *w, int i, unsigned short *x, int j)
{
  int tot = 0;
  for (int a = 0; a < 16; a++)
    {
      for (int b = 0; b < 8; b++)
	tot += abs (w[b] - x[b]);
      w += i;
      x += j;
    }
  return tot;
}

void
bar (unsigned short *w, unsigned short *x, int i, int *result)
{
  *result = foo (w, 8, x, i);
}

/* { dg-final { scan-assembler-times "vabsduh" 16 } } */
/* { dg-final { scan-assembler-times "vsum4shs" 16 } } */
/* { dg-final { scan-assembler-times "vadduwm" 17 } } */

/* Note: One of the 16 adds is optimized out (add with zero),
   leaving 15.  The extra two adds are for the final reduction.  */