https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117875
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target|x86_64-*-*, aarch64* |x86_64-*-*, aarch64*,
| |loongarch
Assignee|unassigned at gcc dot gnu.org |rguenth at gcc dot
gnu.org
Status|NEW |ASSIGNED
--- Comment #17 from Richard Biener <rguenth at gcc dot gnu.org> ---
My bisect on a Zen2 machine lands on r15-5340-g4b8c5b337e007e ...
So --param vect-force-slp=0 vs 1 shows the regression there. Re-confirmed
also on trunk head with that.
The interesting difference is probably
-fast_algorithms.c:133:19: optimized: loop vectorized using 32 byte vectors
-fast_algorithms.c:133:19: optimized: loop versioned for vectorization because
of possible aliasing
-fast_algorithms.c:133:19: optimized: loop vectorized using 16 byte vectors
but there's also
-plan7.c:137:17: optimized: loop vectorized using 16 byte vectors
-sre_math.c:174:17: optimized: loop vectorized using 16 byte vectors
-sre_math.c:192:17: optimized: loop vectorized using 16 byte vectors
I will have a closer look.
