diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2020-02-11 15:13:42 -0500 |
|---|---|---|
| committer | Matt Arsenault <arsenm2@gmail.com> | 2020-02-11 23:11:30 -0500 |
| commit | 6d4ebada797f22f1bdb9bf07f7e51671d6af458c (patch) | |
| tree | a796df51ebb36ce784810a7407f273677909a4c6 /llvm/lib/Support/ErrorHandling.cpp | |
| parent | a5153dbc368e1a484e179fafce7a260410d20569 (diff) | |
| download | llvm-6d4ebada797f22f1bdb9bf07f7e51671d6af458c.zip llvm-6d4ebada797f22f1bdb9bf07f7e51671d6af458c.tar.gz llvm-6d4ebada797f22f1bdb9bf07f7e51671d6af458c.tar.bz2 | |
AMDGPU: Use conditions directly in division expansion
This was creating a select on true/false values, and then comparing
that later. This produced more work for later combines, which can be
avoided by just using the boolean values. This was copied from the
original DAG expansion, which also has the same problem. This doesn't
have a observable change using SelectionDAG, but since GlobalISel is
missing these optimizations, the final code was noticeably longer.
Diffstat (limited to 'llvm/lib/Support/ErrorHandling.cpp')
0 files changed, 0 insertions, 0 deletions