[all-commits] [llvm/llvm-project] 6071f6: [mlir][sparse] Fix a problem in handling data type...

[Bixia Zheng via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6071f6fd67aa7ee7b9a29788118dc46be7f6cdcf
      https://github.com/llvm/llvm-project/commit/6071f6fd67aa7ee7b9a29788118dc46be7f6cdcf
  Author: bixia1 <bixia at google.com>
  Date:   2023-03-30 (Thu, 30 Mar 2023)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/CodegenUtils.cpp
    M mlir/test/Dialect/SparseTensor/codegen.mlir

  Log Message:
  -----------
  [mlir][sparse] Fix a problem in handling data type conversion.

Previously, the genCast function generates arith.trunci for converting f32 to
i32. Fix the function to use mlir::convertScalarToDtype to correctly handle
conversion cases beyond index casting.

Add a test case for codegen the sparse_tensor.convert op.

Reviewed By: aartbik, Peiming, wrengr

Differential Revision: https://reviews.llvm.org/D147272