2015-11-09 Nathan Sidwell <nathan@codesourcery.com>
gcc/testsuite/
* c-c++-common/goacc/routine-1.c: New.
* c-c++-common/goacc/routine-2.c: New.
* c-c++-common/goacc/routine-3.c: New.
* c-c++-common/goacc/routine-4.c: New.
* c-c++-common/goacc/routine-5.c: New.
libgomp/
* testsuite/libgomp.oacc-c-c++-common/firstprivate-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/routine-g-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/routine-gwv-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/routine-v-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/routine-w-1.c: New.
* testsuite/libgomp.oacc-c-c++-common/routine-wv-1.c: New.
===================================================================
@@ -0,0 +1,34 @@
+
+#pragma acc routine gang
+void gang (void)
+{
+}
+
+#pragma acc routine worker
+void worker (void)
+{
+}
+
+#pragma acc routine vector
+void vector (void)
+{
+}
+
+#pragma acc routine seq
+void seq (void)
+{
+}
+
+int main ()
+{
+
+#pragma acc parallel num_gangs (32) num_workers (32) vector_length (32)
+ {
+ gang ();
+ worker ();
+ vector ();
+ seq ();
+ }
+
+ return 0;
+}
===================================================================
@@ -0,0 +1,21 @@
+#pragma acc routine gang worker /* { dg-error "multiple loop axes" } */
+void gang (void)
+{
+}
+
+#pragma acc routine worker vector /* { dg-error "multiple loop axes" } */
+void worker (void)
+{
+}
+
+#pragma acc routine vector seq /* { dg-error "multiple loop axes" } */
+void vector (void)
+{
+}
+
+#pragma acc routine seq gang /* { dg-error "multiple loop axes" } */
+void seq (void)
+{
+}
+
+#pragma acc routine (nothing) gang /* { dg-error "not been declared" } */
===================================================================
@@ -0,0 +1,53 @@
+#pragma acc routine gang
+void gang (void) /* { dg-message "declared here" 3 } */
+{
+}
+
+#pragma acc routine worker
+void worker (void) /* { dg-message "declared here" 2 } */
+{
+}
+
+#pragma acc routine vector
+void vector (void) /* { dg-message "declared here" 1 } */
+{
+}
+
+#pragma acc routine seq
+void seq (void)
+{
+}
+
+int main ()
+{
+
+#pragma acc parallel num_gangs (32) num_workers (32) vector_length (32)
+ {
+ #pragma acc loop gang /* { dg-message "loop here" 1 } */
+ for (int i = 0; i < 10; i++)
+ {
+ gang (); /* { dg-error "routine call uses same" } */
+ worker ();
+ vector ();
+ seq ();
+ }
+ #pragma acc loop worker /* { dg-message "loop here" 2 } */
+ for (int i = 0; i < 10; i++)
+ {
+ gang (); /* { dg-error "routine call uses same" } */
+ worker (); /* { dg-error "routine call uses same" } */
+ vector ();
+ seq ();
+ }
+ #pragma acc loop vector /* { dg-message "loop here" 3 } */
+ for (int i = 0; i < 10; i++)
+ {
+ gang (); /* { dg-error "routine call uses same" } */
+ worker (); /* { dg-error "routine call uses same" } */
+ vector (); /* { dg-error "routine call uses same" } */
+ seq ();
+ }
+ }
+
+ return 0;
+}
===================================================================
@@ -0,0 +1,41 @@
+
+void gang (void);
+void worker (void);
+void vector (void);
+
+#pragma acc routine (gang) gang
+#pragma acc routine (worker) worker
+#pragma acc routine (vector) vector
+
+#pragma acc routine seq
+void seq (void)
+{
+ gang (); /* { dg-error "routine call uses" } */
+ worker (); /* { dg-error "routine call uses" } */
+ vector (); /* { dg-error "routine call uses" } */
+ seq ();
+}
+
+void vector (void) /* { dg-message "declared here" 1 } */
+{
+ gang (); /* { dg-error "routine call uses" } */
+ worker (); /* { dg-error "routine call uses" } */
+ vector ();
+ seq ();
+}
+
+void worker (void) /* { dg-message "declared here" 2 } */
+{
+ gang (); /* { dg-error "routine call uses" } */
+ worker ();
+ vector ();
+ seq ();
+}
+
+void gang (void) /* { dg-message "declared here" 3 } */
+{
+ gang ();
+ worker ();
+ vector ();
+ seq ();
+}
===================================================================
@@ -0,0 +1,51 @@
+/* { dg-do compile } */
+
+#pragma acc routine /* { dg-error "not followed by" } */
+int a;
+
+#if 0 /* Disable for the moment. */
+#pragma acc routine /* dg-error "not followed by" */
+void fn1 (void), fn1b (void);
+#endif
+
+#pragma acc routine /* { dg-error "not followed by" } */
+int b, fn2 (void);
+
+#if 0 /* Disable for the moment. */
+#pragma acc routine /* dg-error "not followed by" */
+int fn3 (void), b2;
+#endif
+
+#pragma acc routine /* { dg-error "not followed by" } */
+typedef struct c c;
+
+#pragma acc routine /* { dg-error "not followed by" } */
+struct d {} d;
+
+#pragma acc routine /* { dg-error "not followed by" } */
+#pragma acc routine
+int fn4 (void);
+
+int fn5a (void);
+
+#pragma acc routine /* { dg-error "not followed by" } */
+#pragma acc routine (fn5a)
+int fn5 (void);
+
+#ifdef __cplusplus
+
+#pragma acc routine /* { dg-error "not followed by" "" { target c++ } } */
+namespace f {}
+
+namespace g {}
+
+#pragma acc routine /* { dg-error "not followed by" "" { target c++ } } */
+using namespace g;
+
+#pragma acc routine (g) /* { dg-error "does not refer to" "" { target c++ } } */
+
+#endif
+
+#pragma acc routine (a) /* { dg-error "does not refer to" } */
+
+#pragma acc routine (c) /* { dg-error "does not refer to" } */
===================================================================
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int main ()
+{
+ int ok = 1;
+ int val = 2;
+ int ary[32];
+ int ondev = 0;
+
+ for (int i = 0; i < 32; i++)
+ ary[i] = ~0;
+
+#pragma acc parallel num_gangs (32) copy (ok) firstprivate (val) copy(ary, ondev)
+ {
+ ondev = acc_on_device (acc_device_not_host);
+#pragma acc loop gang(static:1)
+ for (unsigned i = 0; i < 32; i++)
+ {
+ if (val != 2)
+ ok = 0;
+ val += i;
+ ary[i] = val;
+ }
+ }
+
+ if (ondev)
+ {
+ if (!ok)
+ return 1;
+ if (val != 2)
+ return 1;
+
+ for (int i = 0; i < 32; i++)
+ if (ary[i] != 2 + i)
+ return 1;
+ }
+
+ return 0;
+}
===================================================================
@@ -0,0 +1,64 @@
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+
+#pragma acc routine gang
+void __attribute__ ((noinline)) gang (int ary[N])
+{
+#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;
+ }
+ else
+ ary[ix] = ix;
+ }
+}
+
+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)
+ {
+ ondev = __builtin_acc_on_device (5);
+ gang (ary);
+ }
+
+ 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;
+}
===================================================================
@@ -0,0 +1,66 @@
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+
+#pragma acc routine gang
+void __attribute__ ((noinline)) gang (int ary[N])
+{
+#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;
+ }
+ else
+ ary[ix] = ix;
+ }
+}
+
+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)
+ {
+ ondev = __builtin_acc_on_device (5);
+ gang (ary);
+ }
+
+ 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;
+}
===================================================================
@@ -0,0 +1,64 @@
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+
+#pragma acc routine vector
+void __attribute__ ((noinline)) vector (int ary[N])
+{
+#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;
+ }
+ else
+ ary[ix] = ix;
+ }
+}
+
+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)
+ {
+ ondev = __builtin_acc_on_device (5);
+ vector (ary);
+ }
+
+ 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;
+}
===================================================================
@@ -0,0 +1,64 @@
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+
+#pragma acc routine worker
+void __attribute__ ((noinline)) worker (int ary[N])
+{
+#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;
+ }
+ else
+ ary[ix] = ix;
+ }
+}
+
+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)
+ {
+ ondev = __builtin_acc_on_device (5);
+ worker (ary);
+ }
+
+ 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;
+}
===================================================================
@@ -0,0 +1,64 @@
+/* { dg-do run } */
+/* { dg-additional-options "-O2" */
+
+#include <stdio.h>
+
+#define N (32*32*32+17)
+
+#pragma acc routine worker
+void __attribute__ ((noinline)) worker (int ary[N])
+{
+#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;
+ }
+ else
+ ary[ix] = ix;
+ }
+}
+
+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)
+ {
+ ondev = __builtin_acc_on_device (5);
+ worker (ary);
+ }
+
+ 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;
+}