diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2025-05-22 21:04:47 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-22 21:04:47 +0200 |
| commit | db0bac0ef2de92cf478977fbb5f48a0eabd8e9c2 (patch) | |
| tree | 9ca744bacffb07b2ba47fb9c3f90d7c416020f4e /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 57e9097ad28916f43a7d9ee07c66a7cffd02b0d5 (diff) | |
| download | llvm-db0bac0ef2de92cf478977fbb5f48a0eabd8e9c2.zip llvm-db0bac0ef2de92cf478977fbb5f48a0eabd8e9c2.tar.gz llvm-db0bac0ef2de92cf478977fbb5f48a0eabd8e9c2.tar.bz2 | |
AMDGPU: Form v_med_f32 from minimumnum/maximumnum immediate pattern (#141048)
This makes little difference in the final output, as we manage to form this
after these are lowered to the _ieee operations. This does result in fewer steps
in the DAG, and helps prepare for changing the handling of minnum/maxnum.
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions