omp-low.c (struct omp_context): Add for_simd_scan_phase member.

	* omp-low.c (struct omp_context): Add for_simd_scan_phase member.
	(maybe_lookup_ctx): Add forward declaration.
	(omp_find_scan): Likewise.  Walk into body of simd if composited
	with worksharing loop.
	(scan_omp_simd_scan): New function.
	(scan_omp_1_stmt): Call it.
	(lower_rec_simd_input_clauses): Don't create rvar nor rvar2 if
	ctx->for_simd_scan_phase.
	(lower_rec_input_clauses): Do much less work for inscan reductions
	in ctx->for_simd_scan_phase is_simd regions.
	(lower_omp_scan): Set is_simd also on simd constructs composited
	with worksharing loop, unless ctx->for_simd_scan_phase.  Never emit
	a sorry message.  Don't change GIMPLE_OMP_SCAN stmts into nops and
	emit their body after in simd constructs composited with worksharing
	loop.
	(lower_omp_for_scan): Handle worksharing loop composited with simd.

	* c-c++-common/gomp/scan-4.c: Don't expect sorry message.

	* testsuite/libgomp.c/scan-11.c: New test.
	* testsuite/libgomp.c/scan-12.c: New test.
	* testsuite/libgomp.c/scan-13.c: New test.
	* testsuite/libgomp.c/scan-14.c: New test.
	* testsuite/libgomp.c/scan-15.c: New test.
	* testsuite/libgomp.c/scan-16.c: New test.
	* testsuite/libgomp.c/scan-17.c: New test.
	* testsuite/libgomp.c/scan-18.c: New test.
	* testsuite/libgomp.c++/scan-9.C: New test.
	* testsuite/libgomp.c++/scan-10.C: New test.
	* testsuite/libgomp.c++/scan-11.C: New test.
	* testsuite/libgomp.c++/scan-12.C: New test.
	* testsuite/libgomp.c++/scan-13.C: New test.
	* testsuite/libgomp.c++/scan-14.C: New test.
	* testsuite/libgomp.c++/scan-15.C: New test.
	* testsuite/libgomp.c++/scan-16.C: New test.

From-SVN: r273157

1 files changed, 120 insertions, 0 deletions

diff --git a/libgomp/testsuite/libgomp.c/scan-16.c b/libgomp/testsuite/libgomp.c/scan-16.c
new file mode 100644
index 0000000..53705d0
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/scan-16.c
@@ -0,0 +1,120 @@
+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+int r, a[1024], b[1024];
+
+#pragma omp declare reduction (foo: int: omp_out += omp_in) initializer (omp_priv = 0)
+
+__attribute__((noipa)) void
+foo (int *a, int *b)
+{
+  #pragma omp for simd reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int s = 0;
+  #pragma omp parallel
+  #pragma omp for simd simdlen (1) reduction (inscan, foo:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b)
+{
+  #pragma omp parallel for simd if (simd: 0) reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int s = 0;
+  #pragma omp parallel for simd reduction (inscan, foo:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+      s += i;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+      s += 2 * i;
+    }
+  r = 0;
+  baz (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+      s += i;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      s += 2 * i;
+    }
+  return 0;
+}