diff options
author | Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> | 2023-03-01 22:05:48 +0000 |
---|---|---|
committer | Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> | 2023-03-07 16:06:18 +0000 |
commit | 723979efc8638d192a680d2a0f814f758274a046 (patch) | |
tree | 8ce08f965ef65be21f2c616199b700f4cc3ae102 /flang/lib/Frontend/CompilerInvocation.cpp | |
parent | af682f0df83f3364dac7ab92f39c7209dfbce28a (diff) | |
download | llvm-723979efc8638d192a680d2a0f814f758274a046.zip llvm-723979efc8638d192a680d2a0f814f758274a046.tar.gz llvm-723979efc8638d192a680d2a0f814f758274a046.tar.bz2 |
Move tosa.reshape lowering patterns from TosaToLinalg to TosaToTensor
Converting tosa.reshape to tensor.expand_shape and
tensor.collapse_shape logically belongs in the tosa-to-tensor
conversion process. In addition, we (rocMLIR downstream) want to use
the reshape -> expand/collapse_shape logic to simplify parts of our
Tosa integration without using the full tosa-to-linalg flow, further
motivating moving these patterns.
The downside to this change is that it means you need to run
tosa-to-tensor after tosa-to-linalg, which is probably a breaking
change.
Reviewed By: rsuderman
Differential Revision: https://reviews.llvm.org/D145119
Diffstat (limited to 'flang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions