[all-commits] [llvm/llvm-project] ff6c84: [mlir][sparse] generalize sparse storage format to...

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ff6c84b803c6a7f5e79dcdbad25332dc7936303c
      https://github.com/llvm/llvm-project/commit/ff6c84b803c6a7f5e79dcdbad25332dc7936303c
  Author: Aart Bik <ajcbik at google.com>
  Date:   2021-02-17 (Wed, 17 Feb 2021)

  Changed paths:
    A mlir/integration_test/Sparse/CPU/sparse_sampled_matmul.mlir
    M mlir/integration_test/Sparse/CPU/sparse_sum.mlir
    M mlir/lib/Dialect/Linalg/Transforms/SparseLowering.cpp
    M mlir/lib/ExecutionEngine/SparseUtils.cpp
    M mlir/test/Dialect/Linalg/sparse_lower.mlir
    M mlir/test/Dialect/Linalg/sparse_lower_calls.mlir

  Log Message:
  -----------
  [mlir][sparse] generalize sparse storage format to many more types

Rationale:
Narrower types for overhead storage yield a smaller memory footprint for
sparse tensors and thus needs to be supported. Also, more value types
need to be supported to deal with all kinds of kernels. Since the
"one-size-fits-all" sparse storage scheme implementation is used
instead of actual codegen, the library needs to be able to support
all combinations of desired types. With some crafty templating and
overloading, the actual code for this is kept reasonably sized though.

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D96819