diff options
| author | Alex Zinenko <zinenko@google.com> | 2019-11-14 09:05:11 -0800 |
|---|---|---|
| committer | A. Unique TensorFlower <gardener@tensorflow.org> | 2019-11-14 09:05:42 -0800 |
| commit | bf5916e7a49b4f8279ee38c0fd20154a101ff026 (patch) | |
| tree | 7c6e2fb2ff93ef2497e9ff90bafa0a2c0c785ab5 /mlir/lib/Conversion/LoopsToGPU/LoopsToGPU.cpp | |
| parent | 62d5b1de45298d0ea3a1c7135555ca83cfa57353 (diff) | |
| download | bcm5719-llvm-bf5916e7a49b4f8279ee38c0fd20154a101ff026.tar.gz bcm5719-llvm-bf5916e7a49b4f8279ee38c0fd20154a101ff026.zip | |
Use MemRefDescriptor in Vector-to-LLVM convresion
Following up on the consolidation of MemRef descriptor conversion, update
Vector-to-LLVM conversion to use the helper class that abstracts away the
implementation details of the MemRef descriptor. This also makes the types of
the attributes in emitted llvm.insert/extractelement operations consistently
i64 instead of a mix of index and i64.
PiperOrigin-RevId: 280441451
Diffstat (limited to 'mlir/lib/Conversion/LoopsToGPU/LoopsToGPU.cpp')
0 files changed, 0 insertions, 0 deletions
