[PATCH] D74954: Add a basic tiling pass for parallel loops
Stephan Herhut via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Feb 21 06:24:08 PST 2020
herhut added inline comments.
================
Comment at: mlir/lib/Dialect/LoopOps/Transforms/ParallelLoopTiling.cpp:67
+ for (auto bounds : llvm::zip(op.upperBound(), op.lowerBound())) {
+ newBounds.push_back(b.create<AffineMinOp>(
+ op.getLoc(), b.getIndexType(), minMap,
----------------
herhut wrote:
> I do not understand this part. We want the min of either the step size or dim - upperbound_of_outer.
I always get confused by this myself. I think it needs to be `upper_bound - current_index_of_outer_loop` to get the number of remaining iterations. And then the min with the tiling size.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D74954/new/
https://reviews.llvm.org/D74954
More information about the llvm-commits
mailing list