diff options
| author | Julien Pagès <julien.pages@amd.com> | 2021-06-03 16:32:15 -0400 |
|---|---|---|
| committer | Julien Pagès <julien.pages@amd.com> | 2021-06-03 16:40:18 -0400 |
| commit | 37821155c972b06de1af20ffe2282d7476d7f157 (patch) | |
| tree | eac5cf3eed19104841037fdbdc9a99af7fe0b12c /llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp | |
| parent | ba1fb0ff8c9f9ef7f9b7d1fe43cb95c8d1363f78 (diff) | |
| download | llvm-37821155c972b06de1af20ffe2282d7476d7f157.zip llvm-37821155c972b06de1af20ffe2282d7476d7f157.tar.gz llvm-37821155c972b06de1af20ffe2282d7476d7f157.tar.bz2 | |
[AMDGPU] Fix a crash when selecting a particular case of buffer_load_format_d16
In this particular example, we had a crash when compiling it
for several architectures. This patch extends the legalization
of extract_subvector to avoid this problem.
Differential Revision: https://reviews.llvm.org/D103344
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp')
0 files changed, 0 insertions, 0 deletions