public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "marko.makela at mariadb dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug middle-end/102566] [i386] GCC should emit LOCK BTS for simple bit-test-and-set operations with std::atomic Date: Sat, 29 Oct 2022 10:53:44 +0000 [thread overview] Message-ID: <bug-102566-4-mc4Kxfzncb@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-102566-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102566 Marko Mäkelä <marko.makela at mariadb dot com> changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |marko.makela at mariadb dot com --- Comment #31 from Marko Mäkelä <marko.makela at mariadb dot com> --- Much of this seems to work in GCC 12.2.0 as well as in clang++-15. For clang there is a related ticket https://github.com/llvm/llvm-project/issues/37322 I noticed a missed optimization in both g++-12 and clang++-15: Some operations involving bit 31 degrade to loops around lock cmpxchg. I compiled it with "-c -O2" (AMD64) or "-c -O2 -m32 -march=i686" (IA-32). #include <atomic> template<uint32_t b> void lock_bts(std::atomic<uint32_t> &a) { while (!(a.fetch_or(b) & b)); } template<uint32_t b> void lock_btr(std::atomic<uint32_t> &a) { while (a.fetch_and(~b) & b); } template<uint32_t b> void lock_btc(std::atomic<uint32_t> &a) { while (a.fetch_xor(b) & b); } template void lock_bts<1U<<30>(std::atomic<uint32_t> &a); template void lock_btr<1U<<30>(std::atomic<uint32_t> &a); template void lock_btc<1U<<30>(std::atomic<uint32_t> &a); // bug: uses lock cmpxchg template void lock_bts<1U<<31>(std::atomic<uint32_t> &a); template void lock_btr<1U<<31>(std::atomic<uint32_t> &a); template void lock_btc<1U<<31>(std::atomic<uint32_t> &a);
next prev parent reply other threads:[~2022-10-29 10:53 UTC|newest] Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-10-02 16:08 [Bug target/102566] New: " thiago at kde dot org 2021-10-02 20:30 ` [Bug target/102566] " pinskia at gcc dot gnu.org 2021-10-03 12:56 ` hjl.tools at gmail dot com 2021-10-03 13:06 ` hjl.tools at gmail dot com 2021-10-03 13:19 ` [Bug tree-optimization/102566] " hjl.tools at gmail dot com 2021-10-03 15:10 ` hjl.tools at gmail dot com 2021-10-03 16:45 ` [Bug middle-end/102566] " hjl.tools at gmail dot com 2021-10-03 22:36 ` hjl.tools at gmail dot com 2021-10-04 15:58 ` thiago at kde dot org 2021-10-04 16:10 ` thiago at kde dot org 2021-10-04 16:13 ` thiago at kde dot org 2021-10-04 21:46 ` hjl.tools at gmail dot com 2021-10-04 23:25 ` thiago at kde dot org 2021-10-04 23:26 ` thiago at kde dot org 2021-10-05 4:40 ` hjl.tools at gmail dot com 2021-10-05 15:23 ` hjl.tools at gmail dot com 2021-10-05 15:57 ` thiago at kde dot org 2021-10-05 16:02 ` pinskia at gcc dot gnu.org 2021-10-05 19:26 ` hjl.tools at gmail dot com 2021-10-05 19:30 ` hjl.tools at gmail dot com 2021-10-05 19:36 ` thiago at kde dot org 2021-10-06 8:00 ` jakub at gcc dot gnu.org 2021-10-06 15:40 ` thiago at kde dot org 2021-10-06 15:47 ` hjl.tools at gmail dot com 2021-10-06 15:54 ` thiago at kde dot org 2021-10-06 16:05 ` hjl.tools at gmail dot com 2021-10-07 15:18 ` thiago at kde dot org 2021-10-07 15:19 ` hjl.tools at gmail dot com 2021-10-07 15:35 ` thiago at kde dot org 2021-10-10 13:51 ` hjl.tools at gmail dot com 2021-10-22 3:31 ` crazylht at gmail dot com 2021-11-04 21:24 ` thiago at kde dot org 2021-11-10 9:17 ` cvs-commit at gcc dot gnu.org 2022-10-29 10:53 ` marko.makela at mariadb dot com [this message] 2022-10-31 2:42 ` crazylht at gmail dot com 2022-11-01 8:41 ` marko.makela at mariadb dot com 2022-11-01 16:46 ` hjl.tools at gmail dot com 2022-11-07 19:20 ` cvs-commit at gcc dot gnu.org 2023-01-18 18:49 ` hjl.tools at gmail dot com 2023-01-18 22:30 ` hjl.tools at gmail dot com
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-102566-4-mc4Kxfzncb@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: linkBe 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).