[nvptx] Force vl32 if calling vector-partitionable routines -- test-cases

Add test-cases for "[nvptx] Force vl32 if calling vector-partitionable
routines".

2019-01-12  Tom de Vries  <tdevries@suse.de>

	PR target/85486
	* testsuite/libgomp.oacc-c-c++-common/pr85486-3.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr85486.c: New test.

From-SVN: r267894

diff --git a/libgomp/ChangeLog b/libgomp/ChangeLog
index 7d56831e36a156faefc4851b22ad159029c34dc3..e6b1460917165fa6d2934a0508f917bb33099649 100644 (file)
--- a/libgomp/ChangeLog
+++ b/libgomp/ChangeLog
@@ -1,3 +1,9 @@
+2019-01-12  Tom de Vries  <tdevries@suse.de>
+
+       PR target/85486
+       * testsuite/libgomp.oacc-c-c++-common/pr85486-3.c: New test.
+       * testsuite/libgomp.oacc-c-c++-common/pr85486.c: New test.
+
 2019-01-12  Tom de Vries  <tdevries@suse.de>
 
        PR target/85381

diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/pr85486-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/pr85486-3.c
new file mode 100644 (file)
index 0000000..a959b90
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/pr85486-3.c
@@ -0,0 +1,54 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-set-target-env-var "GOMP_OPENACC_DIM" "::128" } */
+
+/* Minimized from ref-1.C.  */
+
+#include <stdio.h>
+
+#pragma acc routine vector
+void __attribute__((noinline, noclone))
+Vector (int *ptr, int n, const int inc)
+{
+  #pragma acc loop vector
+  for (unsigned ix = 0; ix < n; ix++)
+    ptr[ix] += inc;
+}
+
+int
+main (void)
+{
+  const int n = 32, m=32;
+
+  int ary[m][n];
+  unsigned ix,  iy;
+
+  for (ix = m; ix--;)
+    for (iy = n; iy--;)
+      ary[ix][iy] = (1 << 16) + (ix << 8) + iy;
+
+  int err = 0;
+
+#pragma acc parallel copy (ary)
+  {
+    Vector (&ary[0][0], m * n, (1 << 24) - (1 << 16));
+  }
+
+  for (ix = m; ix--;)
+    for (iy = n; iy--;)
+      if (ary[ix][iy] != ((1 << 24) + (ix << 8) + iy))
+       {
+         printf ("ary[%u][%u] = %x expected %x\n",
+                 ix, iy, ary[ix][iy], ((1 << 24) + (ix << 8) + iy));
+         err++;
+       }
+
+  if (err)
+    {
+      printf ("%d failed\n", err);
+      return 1;
+    }
+
+  return 0;
+}
+
+/* { dg-prune-output "using vector_length \\(32\\), ignoring runtime setting" } */

diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/pr85486.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/pr85486.c
new file mode 100644 (file)
index 0000000..99c0805
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/pr85486.c
@@ -0,0 +1,51 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+
+/* Minimized from ref-1.C.  */
+
+#include <stdio.h>
+
+#pragma acc routine vector
+void __attribute__((noinline, noclone))
+Vector (int *ptr, int n, const int inc)
+{
+  #pragma acc loop vector
+  for (unsigned ix = 0; ix < n; ix++)
+    ptr[ix] += inc;
+}
+
+int
+main (void)
+{
+  const int n = 32, m=32;
+
+  int ary[m][n];
+  unsigned ix,  iy;
+
+  for (ix = m; ix--;)
+    for (iy = n; iy--;)
+      ary[ix][iy] = (1 << 16) + (ix << 8) + iy;
+
+  int err = 0;
+
+#pragma acc parallel copy (ary) vector_length (128) /* { dg-warning "using vector_length \\(32\\) due to call to vector-partitionable routine, ignoring 128" } */
+  {
+    Vector (&ary[0][0], m * n, (1 << 24) - (1 << 16));
+  }
+
+  for (ix = m; ix--;)
+    for (iy = n; iy--;)
+      if (ary[ix][iy] != ((1 << 24) + (ix << 8) + iy))
+       {
+         printf ("ary[%u][%u] = %x expected %x\n",
+                 ix, iy, ary[ix][iy], ((1 << 24) + (ix << 8) + iy));
+         err++;
+       }
+
+  if (err)
+    {
+      printf ("%d failed\n", err);
+      return 1;
+    }
+
+  return 0;
+}