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/98348] [10 Regression] GCC 10.2 AVX512 Mask regression from GCC 9
Date: Fri, 16 Apr 2021 07:43:06 +0000 [thread overview]
Message-ID: <bug-98348-4-1o3wZ04pLR@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-98348-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98348
--- Comment #21 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to Dávid Bolvanský from comment #20)
> Some small regression (missed opportunity to use vptestnmd):
>
> Current trunk
>
> compare(unsigned int __vector(16)):
> vpxor xmm1, xmm1, xmm1
> vpcmpd k0, zmm0, zmm1, 0
> vpmovm2d zmm0, k0
> ret
>
> GCC 9.2
>
> compare(unsigned int __vector(16)):
> vptestnmd k0, zmm0, zmm0
> vpmovm2d zmm0, k0
> ret
>
>
> https://gcc.godbolt.org/z/5vK68jM3r
I'm testing
+(define_insn_and_split "*<avx512>_eq<mode>3"
+ [(set (match_operand:<avx512fmaskmode> 0 "register_operand")
+ (unspec:<avx512fmaskmode>
+ [(match_operand:VI_AVX512BW 1 "nonimm_or_0_operand")
+ (match_operand:VI_AVX512BW 2 "nonimm_or_0_operand")
+ (const_int 0)]
+ UNSPEC_PCMP_ITER))]
+ "TARGET_AVX512F && ix86_pre_reload_split ()
+ && (operands[1] == CONST0_RTX (<MODE>mode)
+ || operands[2] == CONST0_RTX (<MODE>mode))"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (unspec:<avx512fmaskmode>
+ [(match_dup 1) (match_dup 2)]
+ UNSPEC_MASKED_EQ))])
+
next prev parent reply other threads:[~2021-04-16 7:43 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-17 14:43 [Bug c++/98348] New: " danielhanchen at gmail dot com
2020-12-17 14:45 ` [Bug c++/98348] " danielhanchen at gmail dot com
2020-12-17 16:26 ` hjl.tools at gmail dot com
2020-12-17 19:34 ` jakub at gcc dot gnu.org
2020-12-18 1:37 ` crazylht at gmail dot com
2020-12-19 2:50 ` crazylht at gmail dot com
2020-12-19 10:22 ` jakub at gcc dot gnu.org
2020-12-19 10:47 ` jakub at gcc dot gnu.org
2020-12-19 11:22 ` jakub at gcc dot gnu.org
2020-12-21 11:23 ` crazylht at gmail dot com
2020-12-21 11:25 ` crazylht at gmail dot com
2020-12-21 11:32 ` jakub at gcc dot gnu.org
2020-12-21 12:12 ` crazylht at gmail dot com
2020-12-22 9:14 ` crazylht at gmail dot com
2021-01-04 6:51 ` crazylht at gmail dot com
2021-01-05 8:21 ` [Bug target/98348] [10/11 Regression] " rguenth at gcc dot gnu.org
2021-01-21 11:52 ` jakub at gcc dot gnu.org
2021-01-21 13:38 ` crazylht at gmail dot com
2021-01-22 4:37 ` cvs-commit at gcc dot gnu.org
2021-01-22 4:40 ` crazylht at gmail dot com
2021-04-08 12:02 ` [Bug target/98348] [10 " rguenth at gcc dot gnu.org
2021-04-11 13:17 ` david.bolvansky at gmail dot com
2021-04-16 7:43 ` crazylht at gmail dot com [this message]
2021-05-07 2:25 ` crazylht at gmail dot com
2022-01-12 1:14 ` crazylht at gmail dot com
2022-01-12 5:58 ` cvs-commit at gcc dot gnu.org
2022-01-12 5:59 ` crazylht at gmail dot com
2022-01-12 6:15 ` pinskia at gcc dot gnu.org
2022-01-12 6:15 ` pinskia 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-98348-4-1o3wZ04pLR@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).