rs6000.c (altivec_expand_vec_perm_const): Reverse meaning of merge-high and merge-low masks for little endian...

gcc:

2013-10-22  Bill Schmidt  <wschmidt@vnet.ibm.com>

	* config/rs6000/rs6000.c (altivec_expand_vec_perm_const): Reverse
	meaning of merge-high and merge-low masks for little endian; avoid
	use of vector-pack masks for little endian for mismatched modes.

gcc/testsuite:

2013-10-22  Bill Schmidt  <wschmidt@vnet.ibm.com>

	* gcc.target/powerpc/altivec-perm-1.c: Move the two vector pack
	tests into...
	* gcc.target/powerpc/altivec-perm-3.c: ...this new test, which is
	restricted to big-endian targets.

From-SVN: r203930

5 files changed, 68 insertions, 21 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index cfb6187..c1d3ba8 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2013-10-22  Bill Schmidt  <wschmidt@vnet.ibm.com>
+
+	* config/rs6000/rs6000.c (altivec_expand_vec_perm_const): Reverse
+	meaning of merge-high and merge-low masks for little endian; avoid
+	use of vector-pack masks for little endian for mismatched modes.
+
 2013-10-22  Jan-Benedict Glaw  <jbglaw@lug-owl.de>
 
 	* config/tilepro/tilepro.c: Include "tree.h".
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index e054585..afd6db2 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -28838,17 +28838,23 @@ altivec_expand_vec_perm_const (rtx operands[4])
       {  1,  3,  5,  7,  9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 } },
     { OPTION_MASK_ALTIVEC, CODE_FOR_altivec_vpkuwum,
       {  2,  3,  6,  7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 } },
-    { OPTION_MASK_ALTIVEC, CODE_FOR_altivec_vmrghb,
+    { OPTION_MASK_ALTIVEC, 
+      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghb : CODE_FOR_altivec_vmrglb,
       {  0, 16,  1, 17,  2, 18,  3, 19,  4, 20,  5, 21,  6, 22,  7, 23 } },
-    { OPTION_MASK_ALTIVEC, CODE_FOR_altivec_vmrghh,
+    { OPTION_MASK_ALTIVEC,
+      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghh : CODE_FOR_altivec_vmrglh,
       {  0,  1, 16, 17,  2,  3, 18, 19,  4,  5, 20, 21,  6,  7, 22, 23 } },
-    { OPTION_MASK_ALTIVEC, CODE_FOR_altivec_vmrghw,
+    { OPTION_MASK_ALTIVEC,
+      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghw : CODE_FOR_altivec_vmrglw,
       {  0,  1,  2,  3, 16, 17, 18, 19,  4,  5,  6,  7, 20, 21, 22, 23 } },
-    { OPTION_MASK_ALTIVEC, CODE_FOR_altivec_vmrglb,
+    { OPTION_MASK_ALTIVEC,
+      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglb : CODE_FOR_altivec_vmrghb,
       {  8, 24,  9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 } },
-    { OPTION_MASK_ALTIVEC, CODE_FOR_altivec_vmrglh,
+    { OPTION_MASK_ALTIVEC,
+      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglh : CODE_FOR_altivec_vmrghh,
       {  8,  9, 24, 25, 10, 11, 26, 27, 12, 13, 28, 29, 14, 15, 30, 31 } },
-    { OPTION_MASK_ALTIVEC, CODE_FOR_altivec_vmrglw,
+    { OPTION_MASK_ALTIVEC,
+      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglw : CODE_FOR_altivec_vmrghw,
       {  8,  9, 10, 11, 24, 25, 26, 27, 12, 13, 14, 15, 28, 29, 30, 31 } },
     { OPTION_MASK_P8_VECTOR, CODE_FOR_p8_vmrgew,
       {  0,  1,  2,  3, 16, 17, 18, 19,  8,  9, 10, 11, 24, 25, 26, 27 } },
@@ -28981,6 +28987,26 @@ altivec_expand_vec_perm_const (rtx operands[4])
 	  enum machine_mode omode = insn_data[icode].operand[0].mode;
 	  enum machine_mode imode = insn_data[icode].operand[1].mode;
 
+	  /* For little-endian, don't use vpkuwum and vpkuhum if the
+	     underlying vector type is not V4SI and V8HI, respectively.
+	     For example, using vpkuwum with a V8HI picks up the even
+	     halfwords (BE numbering) when the even halfwords (LE
+	     numbering) are what we need.  */
+	  if (!BYTES_BIG_ENDIAN
+	      && icode == CODE_FOR_altivec_vpkuwum
+	      && ((GET_CODE (op0) == REG
+		   && GET_MODE (op0) != V4SImode)
+		  || (GET_CODE (op0) == SUBREG
+		      && GET_MODE (XEXP (op0, 0)) != V4SImode)))
+	    continue;
+	  if (!BYTES_BIG_ENDIAN
+	      && icode == CODE_FOR_altivec_vpkuhum
+	      && ((GET_CODE (op0) == REG
+		   && GET_MODE (op0) != V8HImode)
+		  || (GET_CODE (op0) == SUBREG
+		      && GET_MODE (XEXP (op0, 0)) != V8HImode)))
+	    continue;
+
           /* For little-endian, the two input operands must be swapped
              (or swapped back) to ensure proper right-to-left numbering
              from 0 to 2N-1.  */
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index ff48a24..446183d 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,10 @@
+2013-10-22  Bill Schmidt  <wschmidt@vnet.ibm.com>
+
+	* gcc.target/powerpc/altivec-perm-1.c: Move the two vector pack
+	tests into...
+	* gcc.target/powerpc/altivec-perm-3.c: ...this new test, which is
+	restricted to big-endian targets.
+
 2013-10-22  Paul Thomas  <pault@gcc.gnu.org>
 
 	PR fortran 57893
diff --git a/gcc/testsuite/gcc.target/powerpc/altivec-perm-1.c b/gcc/testsuite/gcc.target/powerpc/altivec-perm-1.c
index ee5c5ee..c3cf67e 100644
--- a/gcc/testsuite/gcc.target/powerpc/altivec-perm-1.c
+++ b/gcc/testsuite/gcc.target/powerpc/altivec-perm-1.c
@@ -19,19 +19,6 @@ V b4(V x)
   return __builtin_shuffle(x, (V){ 4,5,6,7, 4,5,6,7, 4,5,6,7, 4,5,6,7, });
 }
 
-V p2(V x, V y)
-{
-  return __builtin_shuffle(x, y,
-	(V){ 1,  3,  5,  7,  9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
-
-}
-
-V p4(V x, V y)
-{
-  return __builtin_shuffle(x, y,
-	(V){ 2,  3,  6,  7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 });
-}
-
 V h1(V x, V y)
 {
   return __builtin_shuffle(x, y,
@@ -72,5 +59,3 @@ V l4(V x, V y)
 /* { dg-final { scan-assembler "vspltb" } } */
 /* { dg-final { scan-assembler "vsplth" } } */
 /* { dg-final { scan-assembler "vspltw" } } */
-/* { dg-final { scan-assembler "vpkuhum" } } */
-/* { dg-final { scan-assembler "vpkuwum" } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/altivec-perm-3.c b/gcc/testsuite/gcc.target/powerpc/altivec-perm-3.c
new file mode 100644
index 0000000..d0b671e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/altivec-perm-3.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-skip-if "" { powerpc*le-*-* } { "*" } { "" } } */
+/* { dg-options "-O -maltivec -mno-vsx" } */
+
+typedef unsigned char V __attribute__((vector_size(16)));
+
+V p2(V x, V y)
+{
+  return __builtin_shuffle(x, y,
+	(V){ 1,  3,  5,  7,  9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
+
+}
+
+V p4(V x, V y)
+{
+  return __builtin_shuffle(x, y,
+	(V){ 2,  3,  6,  7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 });
+}
+
+/* { dg-final { scan-assembler-not "vperm" } } */
+/* { dg-final { scan-assembler "vpkuhum" } } */
+/* { dg-final { scan-assembler "vpkuwum" } } */