Please use GitHub pull requests for new patches. Phabricator shutdown timeline

Differential D142927

[mlir][sparse] add new sparisification option for dependent index reduction-based codegen
ClosedPublic
Actions

Authored by Peiming on Jan 30 2023, 1:23 PM.

Tags

Subscribers

View All 29 Subscribers

Details

Reviewers

aartbik
nicolasvasilache
bixia
wrengr

Commits

rGee928fcde2b0: [mlir][sparse] add new sparisification option for dependent index reduction…

Diff Detail

Repository: rG LLVM Github Monorepo

Event Timeline

Peiming created this revision.Jan 30 2023, 1:23 PM

Herald added a reviewer: aartbik. · View Herald TranscriptJan 30 2023, 1:23 PM

Herald added a project: Restricted Project. · View Herald Transcript

Herald added subscribers: hanchung, jsetoain, Moerafaat and 23 others. · View Herald Transcript

Peiming requested review of this revision.Jan 30 2023, 1:23 PM

Herald added a reviewer: nicolasvasilache. · View Herald TranscriptJan 30 2023, 1:23 PM

Herald added a project: Restricted Project. · View Herald Transcript

Herald added subscribers: stephenneuendorffer, nicolasvasilache. · View Herald Transcript

Peiming added a child revision: D142928: [mlir][sparse] add merger/topo sort support for slice-based affine sparse index codegen.Jan 30 2023, 1:31 PM

Peiming added a parent revision: D141532: [mlir][sparse] support dynamic sparse tensor slices..

Peiming added reviewers: bixia, wrengr.Jan 30 2023, 1:33 PM

Harbormaster completed remote builds in B210841: Diff 493393.Jan 30 2023, 1:44 PM

Peiming retitled this revision from [mlir][sparse] add new sparisification option for slice-based codegen to [mlir][sparse] add new sparisification option for dependent index reduction-based codegen.Mar 10 2023, 2:55 PM

Herald added a subscriber: arphaman. · View Herald TranscriptMar 10 2023, 2:55 PM

aartbik accepted this revision.Mar 16 2023, 11:30 AM

aartbik added inline comments.

mlir/include/mlir/Dialect/SparseTensor/Pipelines/Passes.h
58	I would move (experimental) to the end, so e.g. Enable slice-based algorithm to generate affine indices on sparse inputs (experimental feature)
mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.td
85	same

This revision is now accepted and ready to land.Mar 16 2023, 11:30 AM

address comment, rename terminologies

Harbormaster completed remote builds in B219939: Diff 505904.Mar 16 2023, 1:08 PM

This revision was landed with ongoing or failed builds.Mar 16 2023, 1:11 PM

Closed by commit rGee928fcde2b0: [mlir][sparse] add new sparisification option for dependent index reduction… (authored by Peiming). · Explain Why

This revision was automatically updated to reflect the committed changes.

Peiming added a commit: rGee928fcde2b0: [mlir][sparse] add new sparisification option for dependent index reduction….

Revision Contents
Changeset List

Path

Size

mlir/

include/

mlir/

Dialect/

SparseTensor/

Pipelines/

9 lines

Transforms/

7 lines

3 lines

lib/

Dialect/

SparseTensor/

Transforms/

SparseTensorPasses.cpp

3 lines

Sparsification.cpp

137 lines

Diff 505910

mlir/include/mlir/Dialect/SparseTensor/Pipelines/Passes.h

Loading...

mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.h

Loading...

mlir/include/mlir/Dialect/SparseTensor/Transforms/Passes.td

Loading...

mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorPasses.cpp

Loading...

mlir/lib/Dialect/SparseTensor/Transforms/Sparsification.cpp

Loading...