public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "linkw at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug target/115355] [12/13/14/15 Regression] vectorization exposes wrong code on P9 LE starting from r12-4496 Date: Thu, 06 Jun 2024 06:35:59 +0000 [thread overview] Message-ID: <bug-115355-4-dn40myEPvu@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-115355-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115355 --- Comment #9 from Kewen Lin <linkw at gcc dot gnu.org> --- (In reply to Peter Bergner from comment #7) > The test fails when setToIdentityBAD's index var is unsigned int. It passes > when using unsigned long long, unsigned long, unsigned short and unsigned > char. When using unsigned long long/unsigned long, we do no vectorize the unsigned {long ,}long fails to vectorize due to cost modeling: missed: cost model: the vector iteration cost = 2 divided by the scalar iteration cost = 1 is greater or equal to the vectorization factor = 2. missed: not vectorized: vectorization not profitable. it can be forced with -fno-vect-cost-model. > loop. We vectorize the loop when using unsigned int/short/char. The > vectorized code is a little strange, in that the smaller the integer type we > use for the index var, the more code we generate. > > The vectorized code for unsigned char is truly huge! ...although it does > seem to work correctly. I'm attaching the "unsigned char i" code gen for > setToIdentityBAD for people to examine. Even though it gives "correct" > results, it can't really be the code we want to generate, correct??? It's due to aggressive unrolling, as it has one early check on the loop bound between 16 and 255, then cunroll completely unrolls it for each 16 multiples (totally 15 loops). A compact version of code can be generated with -fdisable-tree-cunroll.
next prev parent reply other threads:[~2024-06-06 6:36 UTC|newest] Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top 2024-06-05 10:39 [Bug target/115355] New: PPCLE: Auto-vectorization creates wrong code for Power9 jens.seifert at de dot ibm.com 2024-06-05 11:55 ` [Bug target/115355] " jens.seifert at de dot ibm.com 2024-06-05 12:30 ` rguenth at gcc dot gnu.org 2024-06-05 13:03 ` bergner at gcc dot gnu.org 2024-06-05 13:43 ` linkw at gcc dot gnu.org 2024-06-05 14:59 ` bergner at gcc dot gnu.org 2024-06-05 15:42 ` [Bug target/115355] [12/13/14/15 Regression] " pinskia at gcc dot gnu.org 2024-06-05 21:05 ` bergner at gcc dot gnu.org 2024-06-05 21:05 ` bergner at gcc dot gnu.org 2024-06-06 4:36 ` [Bug target/115355] [12/13/14/15 Regression] vectorization exposes wrong code on P9 LE starting from r12-4496 linkw at gcc dot gnu.org 2024-06-06 6:30 ` rguenth at gcc dot gnu.org 2024-06-06 6:35 ` linkw at gcc dot gnu.org [this message] 2024-06-07 6:53 ` jens.seifert at de dot ibm.com 2024-06-07 8:14 ` linkw at gcc dot gnu.org 2024-06-20 9:15 ` rguenth at gcc dot gnu.org 2024-06-21 1:27 ` cvs-commit at gcc dot gnu.org 2024-06-26 7:17 ` cvs-commit at gcc dot gnu.org 2024-06-26 7:17 ` cvs-commit at gcc dot gnu.org 2024-06-28 1:13 ` cvs-commit at gcc dot gnu.org 2024-06-28 1:14 ` cvs-commit at gcc dot gnu.org 2024-06-28 1:17 ` cvs-commit 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-115355-4-dn40myEPvu@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).