[all-commits] [llvm/llvm-project] 27dfb2: [mlir] [VectorOps] Correctly account for rank-0 af...

Aart Bik via All-commits all-commits at lists.llvm.org
Wed Mar 11 16:05:59 PDT 2020


  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 27dfb2257a0bbd11be8a86fa5894f1091481694b
      https://github.com/llvm/llvm-project/commit/27dfb2257a0bbd11be8a86fa5894f1091481694b
  Author: aartbik <ajcbik at google.com>
  Date:   2020-03-11 (Wed, 11 Mar 2020)

  Changed paths:
    M mlir/lib/Dialect/VectorOps/VectorOps.cpp
    M mlir/lib/Dialect/VectorOps/VectorTransforms.cpp

  Log Message:
  -----------
  [mlir] [VectorOps] Correctly account for rank-0 affine-map result in vector.contract

Summary:
Now that, thanks to ntv, we have the ability to parse and represent an affine
map with rank-0 results, viz. (i,j) -> (), we can pay off some engineering debt
in special casing the verification of such affine maps in dot-product flavored
vector.contract operations.

Reviewers: nicolasvasilache, andydavis1, rriddle

Reviewed By: nicolasvasilache

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76028




More information about the All-commits mailing list