mirror of
https://github.com/autc04/Retro68.git
synced 2024-12-11 19:49:32 +00:00
59 lines
1.1 KiB
C
59 lines
1.1 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 ary[N];
|
||
|
int ix;
|
||
|
int exit = 0;
|
||
|
int ondev = 0;
|
||
|
|
||
|
for (ix = 0; ix < N;ix++)
|
||
|
ary[ix] = -1;
|
||
|
|
||
|
#pragma acc parallel vector_length(32) copy(ary) copy(ondev)
|
||
|
{
|
||
|
#pragma acc loop vector
|
||
|
for (unsigned ix = 0; ix < N; 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));
|
||
|
ary[ix] = (g << 16) | (w << 8) | v;
|
||
|
ondev = 1;
|
||
|
}
|
||
|
else
|
||
|
ary[ix] = ix;
|
||
|
}
|
||
|
}
|
||
|
|
||
|
for (ix = 0; ix < N; ix++)
|
||
|
{
|
||
|
int expected = ix;
|
||
|
if(ondev)
|
||
|
{
|
||
|
int g = 0;
|
||
|
int w = 0;
|
||
|
int v = ix % 32;
|
||
|
|
||
|
expected = (g << 16) | (w << 8) | v;
|
||
|
}
|
||
|
|
||
|
if (ary[ix] != expected)
|
||
|
{
|
||
|
exit = 1;
|
||
|
printf ("ary[%d]=%x expected %x\n", ix, ary[ix], expected);
|
||
|
}
|
||
|
}
|
||
|
|
||
|
return exit;
|
||
|
}
|