There was a reported regression on x86-64 with -march=cascadelake
and -m32 where epilogue vectorization causes a different number of
SLPed loops. Fixed by disabling epilogue vectorization for the
testcase.
tested on x86_64-unknown-linux-gnu, pushed.
* gcc.dg/vect/fast-math-vect-call-2.c: Disable epilogue
vectorization.
---
gcc/testsuite/gcc.dg/vect/fast-math-vect-call-2.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/gcc/testsuite/gcc.dg/vect/fast-math-vect-call-2.c
b/gcc/testsuite/gcc.dg/vect/fast-math-vect-call-2.c
index ed42a21cedc..e52ffe435d3 100644
--- a/gcc/testsuite/gcc.dg/vect/fast-math-vect-call-2.c
+++ b/gcc/testsuite/gcc.dg/vect/fast-math-vect-call-2.c
@@ -1,4 +1,5 @@
/* { dg-require-effective-target vect_double } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "tree-vect.h"
--
2.43.0
