re PR target/80695 (gratuitous use of stxvx to store multiple pointers)

[gcc]

2017-05-11  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	PR target/80695
	* config/rs6000/rs6000.c (rs6000_builtin_vectorization_cost):
	Account for direct move costs for vec_construct of integer
	vectors.

[gcc/testsuite]

2017-05-11  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	PR target/80695
	* gcc.target/powerpc/pr80695-p8.c: New file.
	* gcc.target/powerpc/pr80695-p9.c: New file.

From-SVN: r247928

gcc/ChangeLog

+2017-05-11  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	PR target/80695
+	* config/rs6000/rs6000.c (rs6000_builtin_vectorization_cost):
+	Account for direct move costs for vec_construct of integer
+	vectors.
+
 2017-05-11  Uros Bizjak  <ubizjak@gmail.com>
 
 	PR target/80706

gcc/config/rs6000/rs6000.c

@@ -5850,8 +5850,20 @@ rs6000_builtin_vectorization_cost (enum vect_cost_for_stmt type_of_cost,
 	if (SCALAR_FLOAT_TYPE_P (elem_type)
 	    && TYPE_PRECISION (elem_type) == 32)
 	  return 5;
+	/* On POWER9, integer vector types are built up in GPRs and then
+	   use a direct move (2 cycles).  For POWER8 this is even worse,
+	   as we need two direct moves and a merge, and the direct moves
+	   are five cycles.  */
+	else if (INTEGRAL_TYPE_P (elem_type))
+	  {
+	    if (TARGET_P9_VECTOR)
+	      return TYPE_VECTOR_SUBPARTS (vectype) - 1 + 2;
+	    else
+	      return TYPE_VECTOR_SUBPARTS (vectype) - 1 + 11;
+	  }
 	else
-	  return max (2, TYPE_VECTOR_SUBPARTS (vectype) - 1);
+	  /* V2DFmode doesn't need a direct move.  */
+	  return 2;
 
       default:
         gcc_unreachable ();

gcc/testsuite/ChangeLog

+2017-05-11  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	PR target/80695
+	* gcc.target/powerpc/pr80695-p8.c: New file.
+	* gcc.target/powerpc/pr80695-p9.c: New file.
+
 2017-05-11  Uros Bizjak  <ubizjak@gmail.com>
 	    Jakub Jelinek  <jakub@redhat.com>
 

gcc/testsuite/gcc.target/powerpc/pr80695-p8.c

+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-options "-mcpu=power8 -O3 -fdump-tree-slp-details" } */
+
+/* PR80695: Verify cost model for vec_construct on POWER8.  */
+
+long a[10] __attribute__((aligned(16)));
+
+void foo (long i, long j, long k, long l)
+{
+  a[6] = i;
+  a[7] = j;
+  a[8] = k;
+  a[9] = l;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorization is not profitable" 1 "slp2" } } */

gcc/testsuite/gcc.target/powerpc/pr80695-p9.c

+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-options "-mcpu=power9 -O3 -fdump-tree-slp-details" } */
+
+/* PR80695: Verify cost model for vec_construct on POWER9.  */
+
+long a[10] __attribute__((aligned(16)));
+
+void foo (long i, long j, long k, long l)
+{
+  a[6] = i;
+  a[7] = j;
+  a[8] = k;
+  a[9] = l;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorization is not profitable" 1 "slp2" } } */