[all-commits] [llvm/llvm-project] b1d44e: [mlir][sparse] add affine subscripts to sparse com...

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b1d44e59020a2a7adfc81bffb07577fd091d0778
      https://github.com/llvm/llvm-project/commit/b1d44e59020a2a7adfc81bffb07577fd091d0778
  Author: Aart Bik <ajcbik at google.com>
  Date:   2021-09-15 (Wed, 15 Sep 2021)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/Sparsification.cpp
    A mlir/test/Dialect/SparseTensor/sparse_affine.mlir
    A mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_filter_conv2d.mlir

  Log Message:
  -----------
  [mlir][sparse] add affine subscripts to sparse compilation pass

This enables the sparsification of more kernels, such as convolutions
where there is a x(i+j) subscript. It also enables more tensor invariants
such as x(1) or other affine subscripts such as x(i+1). Currently, we
reject sparsity altogether for such tensors. Despite this restriction,
however, we can already handle a lot more kernels with compound subscripts
for dense access (viz. convolution with dense input and sparse filter).
Some unit tests and an integration test demonstrate new capability.

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D109783