https://gcc.gnu.org/g:c77b1c833e84b62928a729556c502e1311782b2d
commit r12-10733-gc77b1c833e84b62928a729556c502e1311782b2d
Author: Richard Biener <rguent...@suse.de>
Date: Tue Jul 16 10:45:27 2024 +0200
Fixup unaligned load/store cost for znver5
Currently unaligned YMM and ZMM load and store costs are cheaper than
aligned which causes the vectorizer to purposely mis-align accesses
by adding an alignment prologue. It looks like the unaligned costs
were simply copied from the bogus znver4 costs. The following makes
the unaligned costs equal to the aligned costs like in the fixed znver4
version.
* config/i386/x86-tune-costs.h (znver5_cost): Update unaligned
load and store cost from the aligned costs.
(cherry picked from commit 896393791ee34ffc176c87d232dfee735db3aaab)
Diff:
---
gcc/config/i386/x86-tune-costs.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h
index 11a9dd0ff9ed..b8e7ab9372ea 100644
--- a/gcc/config/i386/x86-tune-costs.h
+++ b/gcc/config/i386/x86-tune-costs.h
@@ -2028,8 +2028,8 @@ struct processor_costs znver5_cost = {
in 32bit, 64bit, 128bit, 256bit and
512bit */
{8, 8, 8, 12, 12}, /* cost of storing SSE register
in 32bit, 64bit, 128bit, 256bit and
512bit */
- {6, 6, 6, 6, 6}, /* cost of unaligned loads. */
- {8, 8, 8, 8, 8}, /* cost of unaligned stores. */
+ {6, 6, 10, 10, 12}, /* cost of unaligned loads. */
+ {8, 8, 8, 12, 12}, /* cost of unaligned stores. */
2, 2, 2, /* cost of moving XMM,YMM,ZMM
register. */
6, /* cost of moving SSE register to
integer. */
