[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 Uroš Bizjak changed: What|Removed |Added Status|ASSIGNED|RESOLVED Resolution|--- |FIXED --- Comment #7 from Uroš Bizjak --- Fixed.
[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 --- Comment #6 from uros at gcc dot gnu.org --- Author: uros Date: Mon Jun 17 18:40:22 2019 New Revision: 272396 URL: https://gcc.gnu.org/viewcvs?rev=272396=gcc=rev Log: PR target/62055 * config/i386/i386.md (*nabstf2_1): New insn pattern. (*nabs2_1): Ditto. (nabs sse-reg splitter): New splitter. * config/i386/sse.md (*nabs2): New insn_and_split pattern. testsuite/ChangeLog: PR target/62055 * gcc.target/i386/fnabs.c: New test. Added: trunk/gcc/testsuite/gcc.target/i386/fnabs.c Modified: trunk/gcc/ChangeLog trunk/gcc/config/i386/i386.md trunk/gcc/config/i386/sse.md trunk/gcc/testsuite/ChangeLog
[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 Uroš Bizjak changed: What|Removed |Added Status|NEW |ASSIGNED Assignee|unassigned at gcc dot gnu.org |ubizjak at gmail dot com Target Milestone|--- |10.0
[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 Uroš Bizjak changed: What|Removed |Added Attachment #46464|0 |1 is obsolete|| --- Comment #5 from Uroš Bizjak --- Created attachment 46492 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=46492=edit Proposed patch Patch in testing.
[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 --- Comment #4 from Marc Glisse --- (In reply to Uroš Bizjak from comment #3) > The patch is OK, but please let me cleanup this (and scalar) part a bit > first. Of course, thanks. And you are more than welcome to take over if you feel like it ;-)
[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 --- Comment #3 from Uroš Bizjak --- (In reply to Marc Glisse from comment #2) > Created attachment 46464 [details] > for vectors > > A naive try to handle it for vectors (because it seems a bit easier), > copying the existing pattern for neg or abs. On a trivial testcase, it seems > to work, but I don't really understand how the "use" part works, and in > particular if it is safe to assume that it is always the constant I expect. The patch is OK, but please let me cleanup this (and scalar) part a bit first.
[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 --- Comment #2 from Marc Glisse --- Created attachment 46464 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=46464=edit for vectors A naive try to handle it for vectors (because it seems a bit easier), copying the existing pattern for neg or abs. On a trivial testcase, it seems to work, but I don't really understand how the "use" part works, and in particular if it is safe to assume that it is always the constant I expect.
[Bug target/62055] missed optimization: recognize fnabs (FP negative absolute value) (x86-64)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62055 Richard Biener rguenth at gcc dot gnu.org changed: What|Removed |Added Keywords||missed-optimization Target||x86_64-*-*, i?86-*-* Status|UNCONFIRMED |NEW Last reconfirmed||2014-08-08 Ever confirmed|0 |1 --- Comment #1 from Richard Biener rguenth at gcc dot gnu.org --- Confirmed also with -ffast-math.