public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug target/66925] New: [3.9 optimization regression] _mm_cvtsi32_si128 spilling to memory
@ 2015-07-18 6:35 thiago at kde dot org
2015-07-18 6:45 ` [Bug target/66925] [4.9 " pinskia at gcc dot gnu.org
2015-07-18 15:04 ` hjl.tools at gmail dot com
0 siblings, 2 replies; 3+ messages in thread
From: thiago at kde dot org @ 2015-07-18 6:35 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66925
Bug ID: 66925
Summary: [3.9 optimization regression] _mm_cvtsi32_si128
spilling to memory
Product: gcc
Version: 5.2.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: thiago at kde dot org
Target Milestone: ---
Consider the following function:
float __attribute__((target("f16c"))) fromf16(unsigned short v)
{
__m128i m = _mm_cvtsi32_si128(v);
return _mm_cvtss_f32(_mm_cvtph_ps(m));
}
With GCC 4.9, this generates:
movzwl %di, %edi
vmovd %edi, %xmm0
vcvtph2ps %xmm0, %xmm0
ret
With GCC 5.2.1, it became:
movzwl %di, %edi
movl %edi, -12(%rsp)
vmovd -12(%rsp), %xmm0
vcvtph2ps %xmm0, %xmm0
ret
The same still applies to GCC 6.
Note that the problem disappears if -march=sandybridge or -march=ivybridge are
active
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug target/66925] [4.9 optimization regression] _mm_cvtsi32_si128 spilling to memory
2015-07-18 6:35 [Bug target/66925] New: [3.9 optimization regression] _mm_cvtsi32_si128 spilling to memory thiago at kde dot org
@ 2015-07-18 6:45 ` pinskia at gcc dot gnu.org
2015-07-18 15:04 ` hjl.tools at gmail dot com
1 sibling, 0 replies; 3+ messages in thread
From: pinskia at gcc dot gnu.org @ 2015-07-18 6:45 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66925
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |RESOLVED
Resolution|--- |INVALID
--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Some processors moving between the GPR via vmovd is slower than moving via
memory. So that is the reason why using -march=sandybridge or -march=ivybridge
makes the issue go away.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug target/66925] [4.9 optimization regression] _mm_cvtsi32_si128 spilling to memory
2015-07-18 6:35 [Bug target/66925] New: [3.9 optimization regression] _mm_cvtsi32_si128 spilling to memory thiago at kde dot org
2015-07-18 6:45 ` [Bug target/66925] [4.9 " pinskia at gcc dot gnu.org
@ 2015-07-18 15:04 ` hjl.tools at gmail dot com
1 sibling, 0 replies; 3+ messages in thread
From: hjl.tools at gmail dot com @ 2015-07-18 15:04 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66925
--- Comment #2 from H.J. Lu <hjl.tools at gmail dot com> ---
(In reply to Andrew Pinski from comment #1)
> Some processors moving between the GPR via vmovd is slower than moving via
> memory. So that is the reason why using -march=sandybridge or
> -march=ivybridge makes the issue go away.
You can also use -mtune=intel.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-07-18 15:04 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-07-18 6:35 [Bug target/66925] New: [3.9 optimization regression] _mm_cvtsi32_si128 spilling to memory thiago at kde dot org
2015-07-18 6:45 ` [Bug target/66925] [4.9 " pinskia at gcc dot gnu.org
2015-07-18 15:04 ` hjl.tools at gmail dot com
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).