Merge "[4.8, 4.9] Backport of additional SLM tuning."

4 files changed, 115 insertions, 0 deletions

diff --git a/gcc-4.9/gcc/testsuite/gcc.dg/vect/pr52252-ld.c b/gcc-4.9/gcc/testsuite/gcc.dg/vect/pr52252-ld.c
new file mode 100644
index 0000000..6e3cb52
--- /dev/null
+++ b/gcc-4.9/gcc/testsuite/gcc.dg/vect/pr52252-ld.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -g -ftree-vectorize -mssse3 -fdump-tree-vect-details" { target { i?86-*-* x86_64-*-* } } } */
+
+#define byte unsigned char
+
+void
+matrix_mul (byte *in, byte *out, int size)
+{
+  int i;
+  for (i = 0; i < size; i++)
+    {
+      byte in0 = in[0];
+      byte in1 = in[1];
+      byte in2 = in[2];
+      byte out0, out1, out2, out3;
+      out0 = in0 + in1;
+      out1 = in0 + in2;
+      out2 = in1 + in2;
+      out3 = in0 + in1 + in2;
+      out[0] = out0;
+      out[1] = out1;
+      out[2] = out2;
+      out[3] = out3;
+      in += 3;
+      out += 4;
+    }
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
diff --git a/gcc-4.9/gcc/testsuite/gcc.target/i386/pr52252-atom.c b/gcc-4.9/gcc/testsuite/gcc.target/i386/pr52252-atom.c
new file mode 100644
index 0000000..715b459
--- /dev/null
+++ b/gcc-4.9/gcc/testsuite/gcc.target/i386/pr52252-atom.c
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target ssse3 } */
+/* { dg-options "-O2 -ftree-vectorize -mssse3 -mtune=slm" } */
+#define byte unsigned char
+
+void
+matrix_mul (byte *in, byte *out, int size)
+{
+  int i;
+  for (i = 0; i < size; i++)
+    {
+      byte in0 = in[0];
+      byte in1 = in[1];
+      byte in2 = in[2];
+      byte out0, out1, out2, out3;
+      out0 = in0 + in1;
+      out1 = in0 + in2;
+      out2 = in1 + in2;
+      out3 = in0 + in1 + in2;
+      out[0] = out0;
+      out[1] = out1;
+      out[2] = out2;
+      out[3] = out3;
+      in += 3;
+      out += 4;
+    }
+}
+
+/* { dg-final { scan-assembler "palignr" } } */
diff --git a/gcc-4.9/gcc/testsuite/gcc.target/i386/pr52252-core.c b/gcc-4.9/gcc/testsuite/gcc.target/i386/pr52252-core.c
new file mode 100644
index 0000000..ac857a5
--- /dev/null
+++ b/gcc-4.9/gcc/testsuite/gcc.target/i386/pr52252-core.c
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target ssse3 } */
+/* { dg-options "-O2 -ftree-vectorize -mssse3 -mtune=corei7" } */
+#define byte unsigned char
+
+void
+matrix_mul (byte *in, byte *out, int size)
+{
+  int i;
+  for (i = 0; i < size; i++)
+    {
+      byte in0 = in[0];
+      byte in1 = in[1];
+      byte in2 = in[2];
+      byte out0, out1, out2, out3;
+      out0 = in0 + in1;
+      out1 = in0 + in2;
+      out2 = in1 + in2;
+      out3 = in0 + in1 + in2;
+      out[0] = out0;
+      out[1] = out1;
+      out[2] = out2;
+      out[3] = out3;
+      in += 3;
+      out += 4;
+    }
+}
+
+/* { dg-final { scan-assembler "pshufb" } } */
diff --git a/gcc-4.9/gcc/testsuite/gcc.target/i386/pr61403.c b/gcc-4.9/gcc/testsuite/gcc.target/i386/pr61403.c
new file mode 100644
index 0000000..84cc5c5
--- /dev/null
+++ b/gcc-4.9/gcc/testsuite/gcc.target/i386/pr61403.c
@@ -0,0 +1,27 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target sse4 } */
+/* { dg-options "-O2 -ffast-math -ftree-vectorize -msse4.2 -mtune=corei7" } */
+
+#include <math.h>
+
+struct XYZ
+{
+  float x;
+  float y;
+  float z;
+};
+
+void
+norm (struct XYZ *in, struct XYZ *out, int size)
+{
+  int i;
+  for (i = 0; i < size; ++i)
+    {
+      float n = sqrt (in[i].x * in[i].x + in[i].y * in[i].y + in[i].z * in[i].z);
+      out[i].x = in[i].x / n;
+      out[i].y = in[i].y / n;
+      out[i].z = in[i].z / n;
+    }
+}
+
+/* { dg-final { scan-assembler "blend" } } */