public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug tree-optimization/93771] SLP produces VEC_PERM when should have used vector generation
[not found] <bug-93771-4@http.gcc.gnu.org/bugzilla/>
@ 2023-05-12 6:01 ` pinskia at gcc dot gnu.org
0 siblings, 0 replies; only message in thread
From: pinskia at gcc dot gnu.org @ 2023-05-12 6:01 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93771
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Resolution|--- |FIXED
Status|NEW |RESOLVED
Target Milestone|--- |11.0
--- Comment #5 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Note the aarch64 code generation for this code is not so bad right now:
ldp q0, q2, [x1]
ldr q1, [x2]
ins v0.d[1], v2.d[1]
fadd v0.2d, v0.2d, v1.2d
str q0, [x0]
Because the PERM
vect__1.7_17 = VEC_PERM_EXPR <vect__1.5_14, vect__1.6_16, { 0, 3 }>;
does the correct thing of doing just the ins now (by
r11-2192-gc9c87e6f9c795bb36e4570a07 )
x86_64 code generation is not bad either:
movupd 16(%rsi), %xmm0
movupd (%rdx), %xmm1
movlpd (%rsi), %xmm0
addpd %xmm1, %xmm0
movups %xmm0, (%rdi)
So I am just going to close this as fixed really.
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2023-05-12 6:01 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <bug-93771-4@http.gcc.gnu.org/bugzilla/>
2023-05-12 6:01 ` [Bug tree-optimization/93771] SLP produces VEC_PERM when should have used vector generation pinskia at gcc dot gnu.org
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).