File: mul-vectorize-1.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 (27 lines) | stat: -rw-r--r-- 803 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
 
/* { dg-require-effective-target powerpc_p8vector_ok } */
/* { dg-options "-mdejagnu-cpu=power8 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fdump-tree-vect-details" } */

/* Test vectorizer can exploit ISA 2.07 instruction vmuluwm (Vector Multiply
   Unsigned Word Modulo) for both signed and unsigned word multiplication.  */

#define N 128

extern signed int si_a[N], si_b[N], si_c[N];
extern unsigned int ui_a[N], ui_b[N], ui_c[N];

__attribute__ ((noipa)) void
test_si ()
{
  for (int i = 0; i < N; i++)
    si_c[i] = si_a[i] * si_b[i];
}

__attribute__ ((noipa)) void
test_ui ()
{
  for (int i = 0; i < N; i++)
    ui_c[i] = ui_a[i] * ui_b[i];
}

/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" } } */
/* { dg-final { scan-assembler-times {\mvmuluwm\M} 2 } } */