[mlir][bufferization][sparse] put restriction on sparse tensor allocation
authorAart Bik <ajcbik@google.com>
Thu, 23 Jun 2022 19:17:01 +0000 (12:17 -0700)
committerAart Bik <ajcbik@google.com>
Fri, 24 Jun 2022 17:58:43 +0000 (10:58 -0700)
commit9a3d60e0d30a3a659f4040e3c424d82115c4219e
tree8e34aa07b58eb1acee5fb2bf5e13833b528d83ff
parent5a08280659125b6196e1ca83d5d9d6ba412674fe
[mlir][bufferization][sparse] put restriction on sparse tensor allocation

Putting some direct use restrictions on tensor allocations in the
sparse case enables the use of simplifying assumptions in the
bufferization analysis.

Reviewed By: springerm

Differential Revision: https://reviews.llvm.org/D128463
mlir/include/mlir/Dialect/Bufferization/IR/BufferizationOps.td
mlir/lib/Dialect/Bufferization/IR/BufferizationOps.cpp
mlir/lib/Dialect/Bufferization/IR/CMakeLists.txt
mlir/test/Dialect/Bufferization/invalid.mlir
mlir/test/Dialect/SparseTensor/conversion.mlir
utils/bazel/llvm-project-overlay/mlir/BUILD.bazel