This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug target/68923] SSE/AVX movq load (_mm_cvtsi64_si128) not being folded into pmovzx
- From: "peter at cordes dot ca" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: Tue, 15 Dec 2015 20:24:00 +0000
- Subject: [Bug target/68923] SSE/AVX movq load (_mm_cvtsi64_si128) not being folded into pmovzx
- Auto-submitted: auto-generated
- References: <bug-68923-4 at http dot gcc dot gnu dot org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68923
Peter Cordes <peter at cordes dot ca> changed:
What |Removed |Added
----------------------------------------------------------------------------
Keywords| |missed-optimization, ssemmx
Target| |x86_64-linux-gnu
URL| |http://stackoverflow.com/qu
| |estions/34279513/loading-8-
| |chars-from-memory-into-an-m
| |256-variable-as-packed-sing
| |le-precision-f
--- Comment #1 from Peter Cordes <peter at cordes dot ca> ---
The other issue (that there's no intrinsic to generate a movq m64, %xmm in
32bit mode), is addressed in
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68924.
This bug is just about the optimization failure to fold the load into pmovzx.