* libgomp.oacc-c-c++-common/loop-red-g-1.c: New.
* libgomp.oacc-c-c++-common/loop-red-gwv-1.c: New.
* libgomp.oacc-c-c++-common/loop-red-v-1.c: New.
* libgomp.oacc-c-c++-common/loop-red-v-2.c: New.
* libgomp.oacc-c-c++-common/loop-red-w-1.c: New.
* libgomp.oacc-c-c++-common/loop-red-w-2.c: New.
* libgomp.oacc-c-c++-common/loop-red-wv-1.c: New.
* libgomp.oacc-fortran/reduction-5.f90: Avoid reference var.
From-SVN: r229770
+2015-11-04 Nathan Sidwell <nathan@codesourcery.com>
+
+ * libgomp.oacc-c-c++-common/loop-red-g-1.c: New.
+ * libgomp.oacc-c-c++-common/loop-red-gwv-1.c: New.
+ * libgomp.oacc-c-c++-common/loop-red-v-1.c: New.
+ * libgomp.oacc-c-c++-common/loop-red-v-2.c: New.
+ * libgomp.oacc-c-c++-common/loop-red-w-1.c: New.
+ * libgomp.oacc-c-c++-common/loop-red-w-2.c: New.
+ * libgomp.oacc-c-c++-common/loop-red-wv-1.c: New.
+ * libgomp.oacc-fortran/reduction-5.f90: Avoid reference var.
+
2015-11-03 Nathan Sidwell <nathan@codesourcery.com>
* libgomp.h (struct acc_dispatch_t): Remove args from exec_func.
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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) vector_length(32) copy(t) copy(ondev)
+ {
+#pragma acc loop gang 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 g = ix / ((N + 31) / 32);
+ int w = 0;
+ int v = 0;
+
+ val = (g << 16) | (w << 8) | v;
+ }
+ h += val;
+ }
+ if (t != h)
+ {
+ printf ("t=%x expected %x\n", t, h);
+ return 1;
+ }
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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(t) 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;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+
+int main ()
+{
+ int ix;
+ int ondev = 0;
+ int t = 0, h = 0;
+
+#pragma acc parallel vector_length(32) copy(t) copy(ondev)
+ {
+#pragma acc loop 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 g = 0;
+ int w = 0;
+ 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;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+
+int main ()
+{
+ int ix;
+ int ondev = 0;
+ int q = 0, h = 0;
+
+#pragma acc parallel vector_length(32) copy(q) copy(ondev)
+ {
+ int t = q;
+
+#pragma acc loop 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;
+ }
+ q = t;
+ }
+
+ for (ix = 0; ix < N; ix++)
+ {
+ int val = ix;
+ if (ondev)
+ {
+ int g = 0;
+ int w = 0;
+ int v = ix % 32;
+
+ val = (g << 16) | (w << 8) | v;
+ }
+ h += val;
+ }
+
+ if (q != h)
+ {
+ printf ("t=%x expected %x\n", q, h);
+ return 1;
+ }
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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_workers(32) vector_length(32) copy(t) copy(ondev)
+ {
+#pragma acc loop worker 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 g = 0;
+ int w = ix % 32;
+ int v = 0;
+
+ val = (g << 16) | (w << 8) | v;
+ }
+ h += val;
+ }
+ if (t != h)
+ {
+ printf ("t=%x expected %x\n", t, h);
+ return 1;
+ }
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+int main ()
+{
+ int ix;
+ int ondev = 0;
+ int q = 0, h = 0;
+
+#pragma acc parallel num_workers(32) vector_length(32) copy(q) copy(ondev)
+ {
+ int t = q;
+
+#pragma acc loop worker 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;
+ }
+ q = t;
+ }
+
+ for (ix = 0; ix < N; ix++)
+ {
+ int val = ix;
+ if(ondev)
+ {
+ int g = 0;
+ int w = ix % 32;
+ int v = 0;
+
+ val = (g << 16) | (w << 8) | v;
+ }
+ h += val;
+ }
+ if (q != h)
+ {
+ printf ("t=%x expected %x\n", q, h);
+ return 1;
+ }
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#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_workers(32) vector_length(32) copy(t) copy(ondev)
+ {
+#pragma acc loop 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 g = 0;
+ 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;
+}
subroutine redsub(sum, n, c)
integer :: sum, n, c
- sum = 0
+ integer :: s
+ s = 0
- !$acc parallel vector_length(n) copyin (n, c) num_gangs(1)
- !$acc loop reduction(+:sum)
+ !$acc parallel vector_length(32) copyin (n, c) copy (s) num_gangs(1)
+ !$acc loop reduction(+:s)
do i = 1, n
- sum = sum + c
+ s = s + c
end do
!$acc end parallel
+
+ sum = s
end subroutine redsub