diff options
| author | Brox Chen <guochen2@amd.com> | 2025-09-04 18:08:18 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-09-04 18:08:18 -0400 |
| commit | dfdfc4e490f211155ffd581ea0ba8458e4290db6 (patch) | |
| tree | ac4ec2e4fb9b20dcf0932bd7210bb12a1e6e0617 /lldb/source/Commands/CommandObjectThread.cpp | |
| parent | 84b56202fbe150e06f92c855107489e08cc17bcd (diff) | |
| download | llvm-dfdfc4e490f211155ffd581ea0ba8458e4290db6.zip llvm-dfdfc4e490f211155ffd581ea0ba8458e4290db6.tar.gz llvm-dfdfc4e490f211155ffd581ea0ba8458e4290db6.tar.bz2 | |
[AMDGPU][True16][Codegen] remove another build_vector pattern from true16 (#149861)
Remove another build_vector pattern which takes a i16 but placed in a
VGPR_32 from true16 mode. This stop isel from generating illegal
"vgpr_32 = COPY vgpr_16".
ISel will use vgpr16 build vector pattern in true16 mode instead
Diffstat (limited to 'lldb/source/Commands/CommandObjectThread.cpp')
0 files changed, 0 insertions, 0 deletions