projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 04caa7c) | patch
[mlir] Support tensor types in non-unrolled VectorToSCF
authorMatthias Springer <springerm@google.com>
Wed, 2 Jun 2021 01:29:07 +0000 (10:29 +0900)
committerMatthias Springer <springerm@google.com>
Wed, 2 Jun 2021 01:37:58 +0000 (10:37 +0900)
commit558e740170681c723ecb04156f7177d6dfebff13
tree28e3472363174918ff05bc39746315db44ea3ae5tree | snapshot
parent04caa7c3e02f0e2f96881b2b9b5ae5fec6e59aa9commit | diff
[mlir] Support tensor types in non-unrolled VectorToSCF

Support for tensor types in the unrolled version will follow in a separate commit.

Add a new pass option to activate lowering of transfer ops with tensor types (default: deactivated).

Differential Revision: https://reviews.llvm.org/D102666
mlir/include/mlir/Conversion/Passes.td diff | blob | history
mlir/include/mlir/Conversion/VectorToSCF/VectorToSCF.h diff | blob | history
mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp diff | blob | history
mlir/test/Conversion/VectorToSCF/tensor-transfer-ops.mlir [new file with mode: 0644] blob
Domain: System / Toolchain;