* testsuite/libgomp.oacc-c-c++-common/loop-g-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/loop-g-2.c: New.
* testsuite/libgomp.oacc-c-c++-common/loop-gwv-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/loop-v-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/loop-w-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/loop-wv-1.c: New.
From-SVN: r229487
+2015-10-28 Nathan Sidwell <nathan@codesourcery.com>
+
+ * testsuite/libgomp.oacc-c-c++-common/loop-g-1.c: New.
+ * testsuite/libgomp.oacc-c-c++-common/loop-g-2.c: New.
+ * testsuite/libgomp.oacc-c-c++-common/loop-gwv-1.c: New.
+ * testsuite/libgomp.oacc-c-c++-common/loop-v-1.c: New.
+ * testsuite/libgomp.oacc-c-c++-common/loop-w-1.c: New.
+ * testsuite/libgomp.oacc-c-c++-common/loop-wv-1.c: New.
+
2015-10-27 Nathan Sidwell <nathan@codesourcery.com>
* plugin/plugin-nvptx.c (nvptx_exec): Remove check on compute
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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 num_gangs(32) vector_length(32) copy(ary) copy(ondev)
+ {
+#pragma acc loop gang
+ 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 = ix / ((N + 31) / 32);
+ int w = 0;
+ int v = 0;
+
+ 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;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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 num_gangs(32) vector_length(32) copy(ary) copy(ondev)
+ {
+#pragma acc loop gang (static:1)
+ 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 = ix % 32;
+ int w = 0;
+ int v = 0;
+
+ 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;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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 num_gangs(32) num_workers(32) vector_length(32) copy(ary) copy(ondev)
+ {
+#pragma acc loop gang worker 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 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;
+
+ 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;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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 num_workers(32) vector_length(32) copy(ary) copy(ondev)
+ {
+#pragma acc loop worker
+ 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 = ix % 32;
+ int v = 0;
+
+ 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;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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 num_workers(32) vector_length(32) copy(ary) copy(ondev)
+ {
+#pragma acc loop worker 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 = (ix / 32) % 32;
+ 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;
+}