diff options
| author | liuhongt <hongtao.liu@intel.com> | 2024-05-31 14:38:07 +0800 |
|---|---|---|
| committer | liuhongt <hongtao.liu@intel.com> | 2024-06-03 15:18:10 +0800 |
| commit | ac306de7d5100d3682eae2270995a9abbe19db38 (patch) | |
| tree | 9d27ba0cc38a838211d05c0f6057c397cc6e8547 /gcc/tree-vect-loop.cc | |
| parent | 1f2ca510065a2033bac408eb5a960ef0126f25cc (diff) | |
| download | gcc-ac306de7d5100d3682eae2270995a9abbe19db38.zip gcc-ac306de7d5100d3682eae2270995a9abbe19db38.tar.gz gcc-ac306de7d5100d3682eae2270995a9abbe19db38.tar.bz2 | |
Add some preference for floating point rtl ifcvt when sse4.1 is not available
W/o TARGET_SSE4_1, it takes 3 instructions (pand, pandn and por) for
movdfcc/movsfcc, and could possibly fail cost comparison. Increase
branch cost could hurt performance for other modes, so specially add
some preference for floating point ifcvt.
gcc/ChangeLog:
PR target/115299
* config/i386/i386.cc (ix86_noce_conversion_profitable_p): Add
some preference for floating point ifcvt when SSE4.1 is not
available.
gcc/testsuite/ChangeLog:
* gcc.target/i386/pr115299.c: New test.
* gcc.target/i386/pr86722.c: Adjust testcase.
Diffstat (limited to 'gcc/tree-vect-loop.cc')
0 files changed, 0 insertions, 0 deletions