[mlir][sparse] lower number of entries op to actual code
authorAart Bik <ajcbik@google.com>
Thu, 20 Oct 2022 23:01:37 +0000 (16:01 -0700)
committerAart Bik <ajcbik@google.com>
Fri, 21 Oct 2022 17:48:37 +0000 (10:48 -0700)
commit0f3e4d1afaa1dc330c374b729269f2ff8422e8dd
treeeb1f5b0735eb612fc623c078ad9e7d95b3d10b66
parent4c7218e7702651bb8dd2ef7734ca05ac0ada32fd
[mlir][sparse] lower number of entries op to actual code

works both along runtime path and pure codegen path

Reviewed By: Peiming

Differential Revision: https://reviews.llvm.org/D136389
mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorCodegen.cpp
mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorConversion.cpp
mlir/test/Dialect/SparseTensor/codegen.mlir
mlir/test/Dialect/SparseTensor/conversion.mlir
mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_dot.mlir