On 27/04/2022 15:03, Richard Biener wrote:
On Wed, 27 Apr 2022, Richard Biener wrote:
The following makes sure to take into account prologue peeling
when trying to narrow down the maximum number of iterations
computed for the epilogue of a vectorized epilogue.
Bootstrap & regtest running on x86_64-unknown-linux-gnu.
I did not verify this solves the original aarch64 testcase yet
but it looks like a simpler fix and explains why I don't see
the issue on the 11 branch which does otherwise the same transforms.
Can you verify the original aarch64 case is fixed and maybe add
a testcase for that to gcc.target/aarch64?
Your committed patch fixes the original testcase, but I'll stick to the
testcase you have as it's less fiddly, but I will add the options
required to make it originally fail for aarch64.
Is the attached patch OK for trunk?
gcc/ChangeLog:
PR tree-optimization/105219
* testsuite/gcc.dg/vect/pr105219.c: Add aarch64 target option.
diff --git a/gcc/testsuite/gcc.dg/vect/pr105219.c
b/gcc/testsuite/gcc.dg/vect/pr105219.c
index
0cb7ae2f4d6dc2a236740d34b59b771255b067b7..4bca5bbba30a9740a54e6205bc0d0c8011070977
100644
--- a/gcc/testsuite/gcc.dg/vect/pr105219.c
+++ b/gcc/testsuite/gcc.dg/vect/pr105219.c
@@ -1,6 +1,7 @@
/* { dg-do run } */
/* { dg-additional-options "-O3" } */
/* { dg-additional-options "-mtune=intel" { target x86_64-*-* i?86-*-* } } */
+/* { dg-additional-options "-mtune=thunderx" { target aarch64*-*-* } } */
#include "tree-vect.h"
