projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 8e5f57d) | patch
[mlir][tensor][bufferize] Lower tensor.generate to linalg.map
authorMatthias Springer <springerm@google.com>
Thu, 27 Oct 2022 09:54:01 +0000 (11:54 +0200)
committerMatthias Springer <springerm@google.com>
Thu, 27 Oct 2022 10:03:13 +0000 (12:03 +0200)
commitc1f0a15c65af3f9d2a140c4a73dcbfb3fcfc765d
treef5fab2a8b011bd2278bebe52d0fed2150cb3c6dbtree | snapshot
parent8e5f57d738d919ff7730036cc0628b533ece7ca8commit | diff
[mlir][tensor][bufferize] Lower tensor.generate to linalg.map

There is no memref equivalent of tensor.generate. The purpose of this change is to avoid creating scf.parallel loops during bufferization.

Differential Revision: https://reviews.llvm.org/D136767
mlir/lib/Dialect/Tensor/Transforms/BufferizableOpInterfaceImpl.cpp diff | blob | history
mlir/lib/Dialect/Tensor/Transforms/CMakeLists.txt diff | blob | history
mlir/test/Dialect/Tensor/bufferize.mlir diff | blob | history
mlir/test/Dialect/Tensor/one-shot-bufferize.mlir diff | blob | history
utils/bazel/llvm-project-overlay/mlir/BUILD.bazel diff | blob | history
Domain: System / Toolchain;