projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: bc02a3d) | patch
[mlir][Linalg] NFC - Add support to specify that a tensor value is known to bufferize...
authorNicolas Vasilache <nicolas.vasilache@gmail.com>
Tue, 5 Oct 2021 06:58:53 +0000 (06:58 +0000)
committerNicolas Vasilache <nicolas.vasilache@gmail.com>
Tue, 5 Oct 2021 08:37:34 +0000 (08:37 +0000)
commit8096759519f2930dc9ba2ceddada1100fee34a0b
treedfa064bbc216cc8130a84e2af9f71a7c754c3f82tree | snapshot
parentbc02a3d4281cd7a6535c657d3981af8b096a3aabcommit | diff
[mlir][Linalg] NFC - Add support to specify that a tensor value is known to bufferize to writeable memory

This change allows better interop with external clients of comprehensive bufferization functions
but is otherwise NFC for the MLIR pass itself.

Differential Revision: https://reviews.llvm.org/D111121
mlir/include/mlir/Dialect/Linalg/Transforms/ComprehensiveBufferize.h diff | blob | history
mlir/lib/Dialect/Linalg/Transforms/ComprehensiveBufferize.cpp diff | blob | history
Domain: System / Toolchain;