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, 93 insertions, 0 deletions

diff --git a/gcc/testsuite/gcc.target/i386/fma4-256-vector.c b/gcc/testsuite/gcc.target/i386/fma4-256-vector.c
new file mode 100644
index 000000000..1bd2ce4dd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/fma4-256-vector.c
@@ -0,0 +1,93 @@
+/* Test that the compiler properly optimizes floating point multiply and add
+   instructions vector into vfmaddps on FMA4 systems.  */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mfma4 -ftree-vectorize -mtune=generic" } */
+
+extern void exit (int);
+
+typedef float     __m256  __attribute__ ((__vector_size__ (32), __may_alias__));
+typedef double    __m256d __attribute__ ((__vector_size__ (32), __may_alias__));
+
+#define SIZE 10240
+
+union {
+  __m256 f_align;
+  __m256d d_align;
+  float f[SIZE];
+  double d[SIZE];
+} a, b, c, d;
+
+void
+flt_mul_add (void)
+{
+  int i;
+
+  for (i = 0; i < SIZE; i++)
+    a.f[i] = (b.f[i] * c.f[i]) + d.f[i];
+}
+
+void
+dbl_mul_add (void)
+{
+  int i;
+
+  for (i = 0; i < SIZE; i++)
+    a.d[i] = (b.d[i] * c.d[i]) + d.d[i];
+}
+
+void
+flt_mul_sub (void)
+{
+  int i;
+
+  for (i = 0; i < SIZE; i++)
+    a.f[i] = (b.f[i] * c.f[i]) - d.f[i];
+}
+
+void
+dbl_mul_sub (void)
+{
+  int i;
+
+  for (i = 0; i < SIZE; i++)
+    a.d[i] = (b.d[i] * c.d[i]) - d.d[i];
+}
+
+void
+flt_neg_mul_add (void)
+{
+  int i;
+
+  for (i = 0; i < SIZE; i++)
+    a.f[i] = (-(b.f[i] * c.f[i])) + d.f[i];
+}
+
+void
+dbl_neg_mul_add (void)
+{
+  int i;
+
+  for (i = 0; i < SIZE; i++)
+    a.d[i] = (-(b.d[i] * c.d[i])) + d.d[i];
+}
+
+int main ()
+{
+  flt_mul_add ();
+  flt_mul_sub ();
+  flt_neg_mul_add ();
+
+  dbl_mul_add ();
+  dbl_mul_sub ();
+  dbl_neg_mul_add ();
+  exit (0);
+}
+
+/* { dg-final { scan-assembler "vfmaddps" } } */
+/* { dg-final { scan-assembler "vfmaddpd" } } */
+/* { dg-final { scan-assembler "vfmsubps" } } */
+/* { dg-final { scan-assembler "vfmsubpd" } } */
+/* { dg-final { scan-assembler "vfnmaddps" } } */
+/* { dg-final { scan-assembler "vfnmaddpd" } } */