projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: b31d787) | patch
[mlir][Linalg] Add support for bufferization of SubTensorOp and SubTensorInsertOp
authorNicolas Vasilache <nicolas.vasilache@gmail.com>
Mon, 9 Nov 2020 11:57:42 +0000 (11:57 +0000)
committerNicolas Vasilache <nicolas.vasilache@gmail.com>
Mon, 9 Nov 2020 16:55:36 +0000 (16:55 +0000)
commit6fc3a4439493549df02ad11a84847bb73b2565e8
tree3082af7688fe23c3a00a1b28d74789bf7fc9804etree | snapshot
parentb31d78794998d313efe80472670602d0388fdbfacommit | diff
[mlir][Linalg] Add support for bufferization of SubTensorOp and SubTensorInsertOp

This revision adds support for bufferization by using a mix of `tensor_load`, `subview`, `linalg.copy` and `tensor_to_memref`.
mlir/integration_test/Dialect/Linalg/CPU/test-tensor-matmul.mlir diff | blob | history
mlir/lib/Dialect/Linalg/Transforms/Bufferize.cpp diff | blob | history
mlir/test/Dialect/Linalg/bufferize.mlir diff | blob | history
Domain: System / Toolchain;