[PATCH] D80188: [mlir][Linalg] Avoid using scf.parallel for non-parallel loops in Linalg ops.

[Mahesh Ravishankar via Phabricator via llvm-commits]

mravishankar created this revision.
Herald added subscribers: llvm-commits, jurahul, Kayjukh, frgossen, grosul1, Joonsoo, stephenneuendorffer, liufengdb, aartbik, lucyrfox, mgester, arpith-jacob, nicolasvasilache, antiagainst, shauheen, jpienaar, rriddle, mehdi_amini.
Herald added a reviewer: nicolasvasilache.
Herald added a project: LLVM.
mravishankar added a reviewer: ftynse.

Modifying the loop nest builder for generating scf.parallel loops to
not generate scf.parallel loops for non-parallel iterator types in
Linalg operations. The existing implementation incorrectly generated
scf.parallel for all tiled loops. It is rectified by refactoring logic
used while lowering to loops that accounted for this.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D80188

Files:
  mlir/include/mlir/Dialect/Linalg/EDSC/Builders.h
  mlir/lib/Dialect/Linalg/EDSC/Builders.cpp
  mlir/lib/Dialect/Linalg/Transforms/Loops.cpp
  mlir/lib/Dialect/Linalg/Transforms/Tiling.cpp
  mlir/test/Dialect/Linalg/tile_parallel_reduce.mlir
  mlir/test/Dialect/Linalg/transform-patterns.mlir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D80188.264807.patch
Type: text/x-patch
Size: 10074 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200519/af205cd9/attachment.bin>