re PR target/65787 (Miscompile due to bad vector swap optimization for little endian)

[gcc]

2015-04-17  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	PR target/65787
	* config/rs6000/rs6000.c (rtx_is_swappable_p): Ensure that a
	subsequent SH_NONE operand does not overwrite an existing *special
	value.
	(adjust_extract): Handle case where a vec_extract operation is
	wrapped in a PARALLEL.

[gcc/testsuite]

2015-04-17  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	PR target/65787
	* gcc.target/powerpc/pr65787.c: New.

From-SVN: r222205

4 files changed, 45 insertions, 5 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 99f2d08..5da0cd2 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,12 @@
+2015-04-17  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	PR target/65787
+	* config/rs6000/rs6000.c (rtx_is_swappable_p): Ensure that a
+	subsequent SH_NONE operand does not overwrite an existing *special
+	value.
+	(adjust_extract): Handle case where a vec_extract operation is
+	wrapped in a PARALLEL.
+
 2015-04-17  H.J. Lu  <hongjiu.lu@intel.com>
 
 	PR target/65780
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index a96a774..10aa40b 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -34285,10 +34285,11 @@ rtx_is_swappable_p (rtx op, unsigned int *special)
       {
 	unsigned int special_op = SH_NONE;
 	ok &= rtx_is_swappable_p (XEXP (op, i), &special_op);
+	if (special_op == SH_NONE)
+	  continue;
 	/* Ensure we never have two kinds of special handling
 	   for the same insn.  */
-	if (*special != SH_NONE && special_op != SH_NONE
-	    && *special != special_op)
+	if (*special != SH_NONE && *special != special_op)
 	  return 0;
 	*special = special_op;
       }
@@ -34297,10 +34298,11 @@ rtx_is_swappable_p (rtx op, unsigned int *special)
 	{
 	  unsigned int special_op = SH_NONE;
 	  ok &= rtx_is_swappable_p (XVECEXP (op, i, j), &special_op);
+	if (special_op == SH_NONE)
+	  continue;
 	  /* Ensure we never have two kinds of special handling
 	     for the same insn.  */
-	  if (*special != SH_NONE && special_op != SH_NONE
-	      && *special != special_op)
+	  if (*special != SH_NONE && *special != special_op)
 	    return 0;
 	  *special = special_op;
 	}
@@ -34603,7 +34605,10 @@ permute_store (rtx_insn *insn)
 static void
 adjust_extract (rtx_insn *insn)
 {
-  rtx src = SET_SRC (PATTERN (insn));
+  rtx pattern = PATTERN (insn);
+  if (GET_CODE (pattern) == PARALLEL)
+    pattern = XVECEXP (pattern, 0, 0);
+  rtx src = SET_SRC (pattern);
   /* The vec_select may be wrapped in a vec_duplicate for a splat, so
      account for that.  */
   rtx sel = GET_CODE (src) == VEC_DUPLICATE ? XEXP (src, 0) : src;
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index cec5fa1..ee4f05f 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2015-04-17  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	PR target/65787
+	* gcc.target/powerpc/pr65787.c: New.
+
 2015-04-17  Jakub Jelinek  <jakub@redhat.com>
 
 	PR target/65689
diff --git a/gcc/testsuite/gcc.target/powerpc/pr65787.c b/gcc/testsuite/gcc.target/powerpc/pr65787.c
new file mode 100644
index 0000000..c819be9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr65787.c
@@ -0,0 +1,21 @@
+/* { dg-do compile { target { powerpc64le-*-* } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
+/* { dg-options "-mcpu=power8 -O3" } */
+/* { dg-final { scan-assembler "xxsldwi \[0-9\]*,\[0-9\]*,\[0-9\]*,3" } } */
+/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* This test verifies that a vector extract operand properly has its
+   lane changed by the swap optimization.  Element 2 of LE corresponds
+   to element 1 of BE.  When doublewords are swapped, this becomes
+   element 3 of BE, so we need to shift the vector left by 3 words
+   to be able to extract the correct value from BE element zero.  */
+
+typedef float  v4f32 __attribute__ ((__vector_size__ (16)));
+
+void foo (float);
+extern v4f32 x, y;
+
+int main() {
+  v4f32 z = x + y;
+  foo (z[2]);
+}