diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2025-09-03 16:21:46 +0900 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-09-03 16:21:46 +0900 |
| commit | da8f692e3e6ecc7f91e4d0ff945613cabc103c28 (patch) | |
| tree | 1c8a92682e0ce0b7efe914623ce2a7dacb730cc7 /llvm/lib/Support/CommandLine.cpp | |
| parent | fba17cdee1830951867ecfc7d40f7b6caa78310a (diff) | |
| download | llvm-da8f692e3e6ecc7f91e4d0ff945613cabc103c28.zip llvm-da8f692e3e6ecc7f91e4d0ff945613cabc103c28.tar.gz llvm-da8f692e3e6ecc7f91e4d0ff945613cabc103c28.tar.bz2 | |
AMDGPU: Handle V->A MFMA copy from case with immediate src2 (#153023)
Handle a special case for copies from AGPR VGPR on the MFMA inputs.
If the "input" is really a subregister def, we will not see the
usual copy to VGPR for src2, only the read of the subregister def.
Not sure if this pattern appears in practice.
Diffstat (limited to 'llvm/lib/Support/CommandLine.cpp')
0 files changed, 0 insertions, 0 deletions