diff options
| author | Michael Meissner <meissner@linux.ibm.com> | 2023-04-09 23:32:27 -0400 |
|---|---|---|
| committer | Michael Meissner <meissner@linux.ibm.com> | 2023-04-09 23:34:08 -0400 |
| commit | 725bcdeec60771cb9ee387978716028b64ea1b7f (patch) | |
| tree | 8efc92d73bcccbac46e0e8dfcbeff395ddf2d757 /gcc/tree-if-conv.cc | |
| parent | afa87bd5f7b126e20268aa959441cde2e02bba0e (diff) | |
| download | gcc-725bcdeec60771cb9ee387978716028b64ea1b7f.zip gcc-725bcdeec60771cb9ee387978716028b64ea1b7f.tar.gz gcc-725bcdeec60771cb9ee387978716028b64ea1b7f.tar.bz2 | |
Do not generate vmaddfp and vnmsubfp
This is version 3 of the patch. This is essentially version 1 with the removal
of changes to altivec.md, and cleanup of the comments.
Version 2 generated the vmaddfp and vnmsubfp instructions if -Ofast was used,
and those changes are deleted in this patch.
The Altivec instructions vmaddfp and vnmsubfp have different rounding behaviors
than the VSX xvmaddsp and xvnmsubsp instructions due to VSCR[NJ] and other
corner cases. In particular, generating these instructions seems to break
Eigen on big endian systems.
2023-04-09 Michael Meissner <meissner@linux.ibm.com>
gcc/
PR target/70243
* config/rs6000/vsx.md (vsx_fmav4sf4): Do not generate vmaddfp.
(vsx_nfmsv4sf4): Do not generate vnmsubfp.
gcc/testsuite/
PR target/70243
* gcc.target/powerpc/pr70243.c: New test.
Diffstat (limited to 'gcc/tree-if-conv.cc')
0 files changed, 0 insertions, 0 deletions