Retro68/gcc/libgomp/testsuite/libgomp.oacc-c-c++-common/loop-red-gwv-1.c
2017-04-10 13:32:00 +02:00

58 lines
1.2 KiB
C

/* This code uses nvptx inline assembly guarded with acc_on_device, which is
not optimized away at -O0, and then confuses the target assembler.
{ dg-skip-if "" { *-*-* } { "-O0" } { "" } } */
#include <stdio.h>
#define N (32*32*32+17)
int main ()
{
int ix;
int ondev = 0;
int t = 0, h = 0;
#pragma acc parallel num_gangs(32) num_workers(32) vector_length(32) copy(ondev)
{
#pragma acc loop gang worker vector reduction(+:t)
for (unsigned ix = 0; ix < N; ix++)
{
int val = ix;
if (__builtin_acc_on_device (5))
{
int g = 0, w = 0, v = 0;
__asm__ volatile ("mov.u32 %0,%%ctaid.x;" : "=r" (g));
__asm__ volatile ("mov.u32 %0,%%tid.y;" : "=r" (w));
__asm__ volatile ("mov.u32 %0,%%tid.x;" : "=r" (v));
val = (g << 16) | (w << 8) | v;
ondev = 1;
}
t += val;
}
}
for (ix = 0; ix < N; ix++)
{
int val = ix;
if(ondev)
{
int chunk_size = (N + 32*32*32 - 1) / (32*32*32);
int g = ix / (chunk_size * 32 * 32);
int w = ix / 32 % 32;
int v = ix % 32;
val = (g << 16) | (w << 8) | v;
}
h += val;
}
if (t != h)
{
printf ("t=%x expected %x\n", t, h);
return 1;
}
return 0;
}