diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2021-06-15 18:51:06 -0400 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2021-06-22 13:42:49 -0400 |
| commit | 39f8a792f0ac4efed11ac906ba76137fc0c9f6a8 (patch) | |
| tree | f7c6afb259756716ae394997b2bb2418e7d2fcf3 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 317e92a3e82f88f111e04132195d9daa6b97f1ab (diff) | |
| download | llvm-39f8a792f0ac4efed11ac906ba76137fc0c9f6a8.zip llvm-39f8a792f0ac4efed11ac906ba76137fc0c9f6a8.tar.gz llvm-39f8a792f0ac4efed11ac906ba76137fc0c9f6a8.tar.bz2 | |
AMDGPU: Try to eliminate clearing of high bits of 16-bit instructions
These used to consistently be zeroed pre-gfx9, but gfx9 made the
situation complicated since now some still do and some don't. This
also manages to pick up a few cases that the pattern fails to optimize
away.
We handle some cases with instruction patterns, but some get
through. In particular this improves the integer cases.
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions