obtained gcc-4.6.4.tar.bz2 from upstream website;upstream

verified gcc-4.6.4.tar.bz2.sig;
imported gcc-4.6.4 source tree from verified upstream tarball.

downloading a git-generated archive based on the 'upstream' tag
should provide you with a source tree that is binary identical
to the one extracted from the above tarball.

if you have obtained the source via the command 'git clone',
however, do note that line-endings of files in your working
directory might differ from line-endings of the respective
files in the upstream repository.

1 files changed, 207 insertions, 0 deletions

diff --git a/gcc/testsuite/gcc.dg/vect/slp-21.c b/gcc/testsuite/gcc.dg/vect/slp-21.c
new file mode 100644
index 000000000..b4f4e24e0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/slp-21.c
@@ -0,0 +1,207 @@
+/* { dg-require-effective-target vect_int } */
+
+#include <stdarg.h>
+#include "tree-vect.h"
+
+#define N 128 
+
+int
+main1 ()
+{
+  unsigned short i;
+  unsigned short out[N*8], out2[N*8], b0, b1, b2, b3, b4, a0, a1, a2, a3, b5;
+  unsigned short in[N*8];
+
+  for (i = 0; i < N*8; i++)
+    {
+      in[i] = i;
+    }
+
+  /* Different operations in both cases - vectorization with interleaving.  */
+  for (i = 0; i < N; i++)
+    {
+      a0 = in[i*4];
+      a1 = in[i*4 + 1];
+      a2 = in[i*4 + 2];
+      a3 = in[i*4 + 3];
+
+      b0 = a0 * 8;
+      b1 = a1 + 7;
+      b2 = a2 + 6;
+      b3 = a3 * 5;
+      
+      b4 = a2 + 4;
+      b5 = a3 + 3;
+
+      out[i*4] = b0;
+      out[i*4 + 1] = b1;
+      out[i*4 + 2] = b2;
+      out[i*4 + 3] = b3;
+
+      out2[i*4] = b0;
+      out2[i*4 + 1] = b1;
+      out2[i*4 + 2] = b4;
+      out2[i*4 + 3] = b5;
+    }
+
+  /* check results:  */
+  for (i = 0; i < N; i++)
+    {
+      a0 = in[i*4];
+      a1 = in[i*4 + 1];
+      a2 = in[i*4 + 2];
+      a3 = in[i*4 + 3];
+
+      b0 = a0 * 8;
+      b1 = a1 + 7;
+      b2 = a2 + 6;
+      b3 = a3 * 5;
+
+      b4 = a2 + 4;
+      b5 = a3 + 3;
+
+      if (out[i*4] != b0 
+         || out[i*4 + 1] != b1
+         || out[i*4 + 2] != b2
+         || out[i*4 + 3] != b3)
+	abort ();
+
+      if (out2[i*4] != b0  
+         || out2[i*4 + 1] != b1
+         || out2[i*4 + 2] != b4
+         || out2[i*4 + 3] != b5)
+        abort ();
+    }
+
+  /* Different operations in the first case - vectorization with interleaving.  */
+  for (i = 0; i < N; i++)
+    {
+      a0 = in[i*4];
+      a1 = in[i*4 + 1];
+      a2 = in[i*4 + 2];
+      a3 = in[i*4 + 3];
+
+      b0 = a0 + 8;
+      b1 = a1 + 7;
+      b2 = a2 + 6;
+      b3 = a3 * 5;
+
+      b4 = a2 + 4;
+      b5 = a3 + 3;
+
+      out[i*4] = b0;
+      out[i*4 + 1] = b1;
+      out[i*4 + 2] = b2;
+      out[i*4 + 3] = b3;
+
+      out2[i*4] = b0;
+      out2[i*4 + 1] = b1;
+      out2[i*4 + 2] = b4;
+      out2[i*4 + 3] = b5;
+    }
+
+  /* check results:  */
+  for (i = 0; i < N; i++)
+    {
+      a0 = in[i*4];
+      a1 = in[i*4 + 1];
+      a2 = in[i*4 + 2];
+      a3 = in[i*4 + 3];
+
+      b0 = a0 + 8;
+      b1 = a1 + 7;
+      b2 = a2 + 6;
+      b3 = a3 * 5;
+
+      b4 = a2 + 4;
+      b5 = a3 + 3;
+
+      if (out[i*4] != b0
+         || out[i*4 + 1] != b1
+         || out[i*4 + 2] != b2
+         || out[i*4 + 3] != b3)
+        abort ();
+
+      if (out2[i*4] != b0
+         || out2[i*4 + 1] != b1
+         || out2[i*4 + 2] != b4
+         || out2[i*4 + 3] != b5)
+        abort ();
+    }
+
+
+  /* Different operations in the second case - vectorization with interleaving.  */
+  for (i = 0; i < N; i++) 
+    { 
+      a0 = in[i*4];
+      a1 = in[i*4 + 1];
+      a2 = in[i*4 + 2];
+      a3 = in[i*4 + 3];
+
+      b0 = a0 + 8;
+      b1 = a1 + 7;
+      b2 = a2 + 6;
+      b3 = a3 + 5;
+
+      b4 = a2 * 4;
+      b5 = a3 + 3;
+
+      out[i*4] = b0;
+      out[i*4 + 1] = b1;
+      out[i*4 + 2] = b2;
+      out[i*4 + 3] = b3;
+
+      out2[i*4] = b0;
+      out2[i*4 + 1] = b1;
+      out2[i*4 + 2] = b4;
+      out2[i*4 + 3] = b5;
+    }
+
+  /* check results:  */
+  for (i = 0; i < N; i++)
+    {
+      a0 = in[i*4];
+      a1 = in[i*4 + 1];
+      a2 = in[i*4 + 2];
+      a3 = in[i*4 + 3];
+
+      b0 = a0 + 8;
+      b1 = a1 + 7;
+      b2 = a2 + 6;
+      b3 = a3 + 5;
+
+      b4 = a2 * 4;
+      b5 = a3 + 3;
+
+      if (out[i*4] != b0
+         || out[i*4 + 1] != b1
+         || out[i*4 + 2] != b2
+         || out[i*4 + 3] != b3)
+        abort ();
+
+      if (out2[i*4] != b0
+         || out2[i*4 + 1] != b1
+         || out2[i*4 + 2] != b4
+         || out2[i*4 + 3] != b5)
+        abort ();
+    }
+
+
+  return 0;
+}
+
+int main (void)
+{
+  check_vect ();
+
+  main1 ();
+
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 4 loops" 1 "vect"  { target { vect_strided || vect_extract_even_odd } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect"  { target  { ! { vect_strided || vect_extract_even_odd } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target vect_strided }  } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 0 "vect"  { target { ! { vect_strided } } } } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
+