projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: a9e90f7) | patch
[mlir][tensor][bufferize] Bufferize tensor.splat op
authorMatthias Springer <me@m-sp.org>
Mon, 22 May 2023 12:13:08 +0000 (14:13 +0200)
committerMatthias Springer <me@m-sp.org>
Mon, 22 May 2023 12:31:39 +0000 (14:31 +0200)
commit481b254e458bc195af16fef9625cf856ef87fced
treeca414e233eb704560955aab322ff6a739aed65dctree | snapshot
parenta9e90f7994222dde987154ed009504afbf3c2166commit | diff
[mlir][tensor][bufferize] Bufferize tensor.splat op

The op bufferizes similarly to tensor.generate: it is lowered to a linalg.map, which may then lower to a loop nest that fills the buffer.

Differential Revision: https://reviews.llvm.org/D150952
mlir/lib/Dialect/Tensor/Transforms/BufferizableOpInterfaceImpl.cpp diff | blob | history
mlir/test/Dialect/Tensor/bufferize.mlir diff | blob | history
Domain: System / Toolchain;