re PR target/71186 (PowerPC64: Autovectorised code hits ICE with -O3 -mpower9 -mlra)

[gcc]
2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>

	PR target/71186
	* config/rs6000/vsx.md (xxspltib_<mode>_nosplit): Add alternatives
	for loading up all 0's or all 1's.

[gcc/testsuite]
2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>

	PR target/71186
	* gcc.target/powerpc/pr71186.c: New test.

Index: gcc/config/rs6000/vsx.md
===================================================================
--- gcc/config/rs6000/vsx.md	(.../svn+ssh://meissner@gcc.gnu.org/svn/gcc/trunk/gcc/config/rs6000)	(revision 236935)
+++ gcc/config/rs6000/vsx.md	(.../gcc/config/rs6000)	(working copy)
@@ -776,8 +776,8 @@ (define_insn "xxspltib_v16qi"
   [(set_attr "type" "vecperm")])
 
 (define_insn "xxspltib_<mode>_nosplit"
-  [(set (match_operand:VSINT_842 0 "vsx_register_operand" "=wa")
-	(match_operand:VSINT_842 1 "xxspltib_constant_nosplit" "wE"))]
+  [(set (match_operand:VSINT_842 0 "vsx_register_operand" "=wa,wa")
+	(match_operand:VSINT_842 1 "xxspltib_constant_nosplit" "jwM,wE"))]
   "TARGET_P9_VECTOR"
 {
   rtx op1 = operands[1];

[gcc]
2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>

	* config/rs6000/vsx.md (vsx_splat_<mode>, V2DI/V2DF): Simplify
	alternatives, eliminating preferred register class.  Add support
	for the MTVSRDD instruction in ISA 3.0.
	(vsx_splat_v4si_internal): Use splat_input_operand instead of
	reg_or_indexed_operand.
	(vsx_splat_v4sf_internal): Likewise.

[gcc/testsuite]
2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>

	* gcc.target/powerpc/p9-splat-4.c: New test.

From-SVN: r237006

5 files changed, 74 insertions, 11 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 45ae2f9..8fb0bab 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,18 @@
+2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>
+
+	* config/rs6000/vsx.md (vsx_splat_<mode>, V2DI/V2DF): Simplify
+	alternatives, eliminating preferred register class.  Add support
+	for the MTVSRDD instruction in ISA 3.0.
+	(vsx_splat_v4si_internal): Use splat_input_operand instead of
+	reg_or_indexed_operand.
+	(vsx_splat_v4sf_internal): Likewise.
+
+2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>
+
+	PR target/71186
+	* config/rs6000/vsx.md (xxspltib_<mode>_nosplit): Add alternatives
+	for loading up all 0's or all 1's.
+
 2016-06-01  Thomas Preud'homme  <thomas.preudhomme@arm.com>
 
 	* doc/sourcebuild.texi (arm_acq_rel): Document new effective target.
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index 2b6963b..58e1cb5 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -776,8 +776,8 @@
   [(set_attr "type" "vecperm")])
 
 (define_insn "xxspltib_<mode>_nosplit"
-  [(set (match_operand:VSINT_842 0 "vsx_register_operand" "=wa")
-	(match_operand:VSINT_842 1 "xxspltib_constant_nosplit" "wE"))]
+  [(set (match_operand:VSINT_842 0 "vsx_register_operand" "=wa,wa")
+	(match_operand:VSINT_842 1 "xxspltib_constant_nosplit" "jwM,wE"))]
   "TARGET_P9_VECTOR"
 {
   rtx op1 = operands[1];
@@ -2384,18 +2384,15 @@
 
 ;; V2DF/V2DI splat
 (define_insn "vsx_splat_<mode>"
-  [(set (match_operand:VSX_D 0 "vsx_register_operand" "=wd,wd,wd,?<VSa>,?<VSa>,?<VSa>")
+  [(set (match_operand:VSX_D 0 "vsx_register_operand" "=<VSa>,<VSa>,we")
 	(vec_duplicate:VSX_D
-	 (match_operand:<VS_scalar> 1 "splat_input_operand" "<VS_64reg>,f,Z,<VSa>,<VSa>,Z")))]
+	 (match_operand:<VS_scalar> 1 "splat_input_operand" "<VS_64reg>,Z,b")))]
   "VECTOR_MEM_VSX_P (<MODE>mode)"
   "@
    xxpermdi %x0,%x1,%x1,0
-   xxpermdi %x0,%x1,%x1,0
    lxvdsx %x0,%y1
-   xxpermdi %x0,%x1,%x1,0
-   xxpermdi %x0,%x1,%x1,0
-   lxvdsx %x0,%y1"
-  [(set_attr "type" "vecperm,vecperm,vecload,vecperm,vecperm,vecload")])
+   mtvsrdd %x0,%1,%1"
+  [(set_attr "type" "vecperm,vecload,mftgpr")])
 
 ;; V4SI splat (ISA 3.0)
 ;; When SI's are allowed in VSX registers, add XXSPLTW support
@@ -2414,7 +2411,7 @@
 (define_insn "*vsx_splat_v4si_internal"
   [(set (match_operand:V4SI 0 "vsx_register_operand" "=wa,wa")
 	(vec_duplicate:V4SI
-	 (match_operand:SI 1 "reg_or_indexed_operand" "r,Z")))]
+	 (match_operand:SI 1 "splat_input_operand" "r,Z")))]
   "TARGET_P9_VECTOR"
   "@
    mtvsrws %x0,%1
@@ -2425,7 +2422,7 @@
 (define_insn_and_split "*vsx_splat_v4sf_internal"
   [(set (match_operand:V4SF 0 "vsx_register_operand" "=wa,wa,wa")
 	(vec_duplicate:V4SF
-	 (match_operand:SF 1 "reg_or_indexed_operand" "Z,wy,r")))]
+	 (match_operand:SF 1 "splat_input_operand" "Z,wy,r")))]
   "TARGET_P9_VECTOR"
   "@
    lxvwsx %x0,%y1
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 7ee77b6..6d5ee16 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>
+
+	* gcc.target/powerpc/p9-splat-4.c: New test.
+
+2016-05-31  Michael Meissner  <meissner@linux.vnet.ibm.com>
+
+	PR target/71186
+	* gcc.target/powerpc/pr71186.c: New test.
+
 2016-06-01  Jerry DeLisle  <jvdelisle@gcc.gnu.org>
 
 	PR fortran/52393
diff --git a/gcc/testsuite/gcc.target/powerpc/p9-splat-4.c b/gcc/testsuite/gcc.target/powerpc/p9-splat-4.c
new file mode 100644
index 0000000..d643324
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/p9-splat-4.c
@@ -0,0 +1,10 @@
+/* { dg-do compile { target { powerpc64*-*-* && lp64 } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-options "-mcpu=power9 -O2" } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+
+#include <altivec.h>
+
+vector long long foo (long long a) { return (vector long long) { a, a }; }
+
+/* { dg-final { scan-assembler "mtvsrdd" } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/pr71186.c b/gcc/testsuite/gcc.target/powerpc/pr71186.c
new file mode 100644
index 0000000..22762cc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr71186.c
@@ -0,0 +1,32 @@
+/* { dg-do compile { target { powerpc64*-*-* && lp64 } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-options "-mcpu=power9 -O2" } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+
+static unsigned short x[(16384/sizeof(unsigned short))] __attribute__ ((aligned (16)));
+static unsigned short y[(16384/sizeof(unsigned short))] __attribute__ ((aligned (16)));
+static unsigned short a;
+
+void obfuscate(void *a, ...);
+
+static void __attribute__((noinline)) do_one(void)
+{
+ unsigned long i;
+
+ obfuscate(x, y, &a);
+
+ for (i = 0; i < (16384/sizeof(unsigned short)); i++)
+  y[i] = a * x[i];
+
+ obfuscate(x, y, &a);
+}
+
+int main(void)
+{
+ unsigned long i;
+
+ for (i = 0; i < 1000000; i++)
+  do_one();
+
+ return 0;
+}