Although the S/390 backend states that the machine supports unaligned
vector accesses the loop vectorizer still tries to peel loop
iterations to get higher alignments. Setting
vect_max_peeling_for_alignment to 0 prevents this.
gcc/ChangeLog:
2016-11-29 Andreas Krebbel <kreb...@linux.vnet.ibm.com>
* config/s390/s390.c (s390_option_override_internal): Set
vect_max_peeling_for_alignment to 0.
gcc/testsuite/ChangeLog:
2016-11-29 Andreas Krebbel <kreb...@linux.vnet.ibm.com>
* gcc.dg/tree-ssa/gen-vect-26.c: Disable peeling check for s390.
* gcc.dg/tree-ssa/gen-vect-28.c: Likewise.
---
gcc/config/s390/s390.c | 13 +++++++++++++
gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c | 5 ++---
gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c | 4 ++--
3 files changed, 17 insertions(+), 5 deletions(-)
diff --git a/gcc/config/s390/s390.c b/gcc/config/s390/s390.c
index dab4f43..2e71745 100644
--- a/gcc/config/s390/s390.c
+++ b/gcc/config/s390/s390.c
@@ -14586,6 +14586,19 @@ s390_option_override_internal (bool main_args_p,
opts->x_param_values,
opts_set->x_param_values);
+ /* S/390 can deal with unaligned accesses without a performance
+ penalty (as long as we do not cross a cache line boundary). This
+ setting prevents the vectorizer from generating expensive extra
+ code emitted to reach a better alignment.
+ Don't do this when vectorize_support_vector_misalignment falls
+ back to the default path in order to avoid effects on software
+ vectorization. */
+ if (TARGET_VX)
+ maybe_set_param_value (PARAM_VECT_MAX_PEELING_FOR_ALIGNMENT,
+ 0,
+ opts->x_param_values,
+ opts_set->x_param_values);
+
/* Call target specific restore function to do post-init work. At the
moment,
this just sets opts->x_s390_cost_pointer. */
s390_function_specific_restore (opts, NULL);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c
b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c
index 8e5f141..461a952 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c
@@ -28,7 +28,6 @@ int main ()
return 0;
}
-
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target {
! avr-*-* } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0
"vect" { target { ! avr-*-* } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" { target { ! avr-*-* } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0
"vect" { target { ! { avr-*-* s390*-*-* } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" { target { ! { avr-*-* s390*-*-* } } } } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c
b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c
index ce97e09..fe44e85 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c
@@ -38,5 +38,5 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target {
! avr-*-* } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0
"vect" { target { ! avr-*-* } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" { target { ! avr-*-* } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0
"vect" { target { ! { avr-*-* s390*-*-* } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using
peeling" 1 "vect" { target { ! { avr-*-* s390*-*-* } } } } } */
--
2.9.1
