diff options
| author | Alex Zinenko <zinenko@google.com> | 2021-02-12 12:53:12 +0100 |
|---|---|---|
| committer | Alex Zinenko <zinenko@google.com> | 2021-02-12 14:09:24 +0100 |
| commit | 4c4876c314577e253a198ca3868b26fd35ec8a6e (patch) | |
| tree | 1780488e06c5fd3eb6b718fa3398e4926e44f86a /llvm/lib/Transforms/Utils/LoopUtils.cpp | |
| parent | 85fe5c93456776f313e25efaf49d3ae9e8703c86 (diff) | |
| download | llvm-4c4876c314577e253a198ca3868b26fd35ec8a6e.zip llvm-4c4876c314577e253a198ca3868b26fd35ec8a6e.tar.gz llvm-4c4876c314577e253a198ca3868b26fd35ec8a6e.tar.bz2 | |
[mlir] Use target-specific GPU kernel attributes in lowering pipelines
Until now, the GPU translation to NVVM or ROCDL intrinsics relied on the
presence of the generic `gpu.kernel` attribute to attach additional LLVM IR
metadata to the relevant functions. This would be problematic if each dialect
were to handle the conversion of its own options, which is the intended
direction for the translation infrastructure. Introduce `nvvm.kernel` and
`rocdl.kernel` in addition to `gpu.kernel` and base translation on these new
attributes instead.
Reviewed By: herhut
Differential Revision: https://reviews.llvm.org/D96591
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUtils.cpp')
0 files changed, 0 insertions, 0 deletions