public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/98172] Update -mtune=generic for the current Intel and AMD processors
Date: Thu, 21 Jan 2021 01:55:23 +0000 [thread overview]
Message-ID: <bug-98172-4-feJGUcZijl@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-98172-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98172
--- Comment #10 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to Hongtao.liu from comment #9)
> > .L3:
> > vmovupd (%rcx,%rax), %xmm3
> > vmovupd (%rsi,%rax), %xmm4
> > vinsertf128 $0x1, 16(%rcx,%rax), %ymm3, %ymm0
> > vinsertf128 $0x1, 16(%rsi,%rax), %ymm4, %ymm2
> > vmovupd (%rdi,%rax), %xmm5
> > vinsertf128 $0x1, 16(%rdi,%rax), %ymm5, %ymm1
> > vfmadd132pd %ymm2, %ymm1, %ymm0
> > vmovupd %xmm0, (%rdx,%rax)
> > vextractf128 $0x1, %ymm0, 16(%rdx,%rax)
> > addq $32, %rax
> > cmpq $2048, %rax
> > jne .L3
> > vzeroupper
> > ret
>
> The kernel loop could be better as
>
> .L3:
> vmovupd (%rcx,%rax), %ymm0
> vmovupd (%rdi,%rax), %ymm1
> vfmadd132pd (%rsi,%rax), %ymm1, %ymm0
> vmovupd %ymm0, (%rdx,%rax)
> addq $32, %rax
> cmpq $2048, %rax
> jne .L3
It went into movmisalign<mode>, and finally be splitted into parts by
ix86_avx256_split_vector_move_misalign, and the differences between
-mtune=generic and -mtune=haswell matters here is
X86_TUNE_AVX256_UNALIGNED_LOAD_OPTIMAL and
X86_TUNE_AVX256_UNALIGNED_STORE_OPTIMAL
-------
/* X86_TUNE_AVX256_UNALIGNED_LOAD_OPTIMAL: if false, unaligned loads are
split. */
DEF_TUNE (X86_TUNE_AVX256_UNALIGNED_LOAD_OPTIMAL, "256_unaligned_load_optimal",
~(m_NEHALEM | m_SANDYBRIDGE | m_GENERIC))
/* X86_TUNE_AVX256_UNALIGNED_STORE_OPTIMAL: if false, unaligned stores are
split. */
DEF_TUNE (X86_TUNE_AVX256_UNALIGNED_STORE_OPTIMAL,
"256_unaligned_store_optimal",
~(m_NEHALEM | m_SANDYBRIDGE | m_BDVER | m_ZNVER1 | m_GENERIC))
--------
manually adding two tunes to generic
gcc -S -O3 y.c -mavx2 -mfma
-mtune-ctrl="256_unaligned_load_optimal,256_unaligned_store_optimal"
successfully generate optimial codes.
.L3:
vmovupd (%rcx,%rax), %ymm0
vmovupd (%rdi,%rax), %ymm1
vfmadd132pd (%rsi,%rax), %ymm1, %ymm0
vmovupd %ymm0, (%rdx,%rax)
addq $32, %rax
cmpq $2048, %rax
jne .L3
vzeroupper
ret
.L5:
next prev parent reply other threads:[~2021-01-21 1:55 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-07 13:01 [Bug target/98172] New: " hjl.tools at gmail dot com
2020-12-07 13:03 ` [Bug target/98172] " hubicka at gcc dot gnu.org
2020-12-07 13:12 ` hjl.tools at gmail dot com
2020-12-07 14:08 ` rguenth at gcc dot gnu.org
2020-12-07 14:08 ` hubicka at ucw dot cz
2020-12-07 14:10 ` hubicka at ucw dot cz
2020-12-07 14:44 ` hjl.tools at gmail dot com
2020-12-07 14:50 ` hjl.tools at gmail dot com
2021-01-20 23:09 ` hjl.tools at gmail dot com
2021-01-21 1:38 ` crazylht at gmail dot com
2021-01-21 1:55 ` crazylht at gmail dot com [this message]
2021-02-05 1:58 ` cvs-commit at gcc dot gnu.org
2021-04-27 11:39 ` jakub at gcc dot gnu.org
2021-07-28 7:05 ` rguenth at gcc dot gnu.org
2022-04-21 7:48 ` rguenth at gcc dot gnu.org
2023-05-29 10:03 ` jakub at gcc dot gnu.org
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=bug-98172-4-feJGUcZijl@http.gcc.gnu.org/bugzilla/ \
--to=gcc-bugzilla@gcc.gnu.org \
--cc=gcc-bugs@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).