projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 3b259a6) | patch
[mlir][linalg][bufferize] Support arith.index_cast bufferization
authorMatthias Springer <springerm@google.com>
Thu, 27 Jan 2022 10:37:58 +0000 (19:37 +0900)
committerMatthias Springer <springerm@google.com>
Thu, 27 Jan 2022 10:50:31 +0000 (19:50 +0900)
commitdbd1bbced9896d5caece9ee60a7953d2c80d939c
treed8ea1da35d02a24a2fb79cdc702a550d486b94c2tree | snapshot
parent3b259a68424b85142c8b1dc2ffdb7761920c1d8ccommit | diff
[mlir][linalg][bufferize] Support arith.index_cast bufferization

This is in preparation of switching `-tensor-constant-bufferize` and `-arith-bufferize` to BufferizableOpInterface-based implementations.

Differential Revision: https://reviews.llvm.org/D118324
mlir/lib/Dialect/Linalg/ComprehensiveBufferize/ArithInterfaceImpl.cpp diff | blob | history
mlir/test/Dialect/Linalg/comprehensive-function-bufferize.mlir diff | blob | history
Domain: System / Toolchain;