diff options
| author | Giuseppe Rossini <giuseppe.rossini@amd.com> | 2024-08-26 18:48:57 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-08-26 12:48:57 -0500 |
| commit | 1387ba48a312b6e9b174d850f8c9a1322f44c623 (patch) | |
| tree | b86dfa9bb9cc73e099608a1d6b73ffd0e2033b06 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 643bf6cb01bc3faa54c5510c904ea3bdcb4bf42f (diff) | |
| download | llvm-1387ba48a312b6e9b174d850f8c9a1322f44c623.zip llvm-1387ba48a312b6e9b174d850f8c9a1322f44c623.tar.gz llvm-1387ba48a312b6e9b174d850f8c9a1322f44c623.tar.bz2 | |
[MLIR][AMDGPU] Introduce fp16 packed arithmetic (#105688)
This PR is introducing rocdl.cvt.pkrtz in the ROCDL dialect and it is
using that instruction when lowering `arith::TruncFOp`.
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions