User Details
- User Since
- Feb 27 2022, 6:44 PM (23 w, 17 h)
Fri, Aug 5
Address Review comments.
Thu, Aug 4
Move codegen tests to CodeGen, add IR test for InferAddressSpace flat_atomic.
Rework approach of fix.
Wed, Aug 3
Hey Matt, Jay,
Tue, Aug 2
Address Review Comments.
Mon, Aug 1
Fri, Jul 29
Thu, Jul 28
Remove unnecessary local var
Tue, Jul 26
LGTM
Thu, Jul 14
Address review comments.
Wed, Jul 13
Include test which which minimally reproduces the SmallVector error reported.
Jul 6 2022
Remove unnecessary debug code.
Addressed review comments.
Jul 1 2022
Hey Austin -- I like the removal of canAddMIs. In the original design, I was leaving open the possibility for users to pass in canAddMIs rather than a mask / SchedGroup name, but it looks like this isn't the direction we're going, and the classification functions defined in a general canAddMI makes things easier.
Jun 30 2022
Remove accidental files
Run instnamer on testfile, explicitly use "source" (RRList) scheduler for InstSelection Scheduler in test.
Jun 28 2022
Jun 27 2022
Broke up logic in ScheduleDAGFast CheckForLiveRegDef to remove redundancy.
Ported over to phab review to land in Trunk. Addressed the requests in initial review, renamed test file to better align with naming of previous test.
Jun 16 2022
Fix naming of the parser.
Jun 13 2022
Thanks for addressing the post-commit requests in D125997. LGTM
May 26 2022
Write back the changes that were accidentally overwritten
Testing on CK uncovered an edge case error w/ the way bundle iteration was done.
May 25 2022
Addressed Review comments:
- Command line option naming.
- Included comments where code was potentially confusing
May 23 2022
Addressed review comments:
- Added options for sizing of specific instruction groups
- Renamed the DAG Mutation -- renaming suggestions welcomed.
- Minor details
May 19 2022
May 10 2022
May 6 2022
Resolve NITs
May 4 2022
Fix algorithmic flaws:
- Use chain as cluster shape (A->B->C->D) instead of fanout (A->{B,C,D}). With a chain, the scheduler will not miss cluster edges due to multiple cluster succs.
- Create artificial edges in the cluster. This will coerce the scheduler to start from either the root or leaf of the cluster rather than potentially selecting the middle. In post RA scheduling, if the scheduler selects the middle, it will lose the cluster prefix.
May 3 2022
Remove extraneous file
Add test to MIR after both scheduling passes in sequence to confirm clustering results hold.
Resolve silly arcconfig issue.
May 2 2022
Updating D124678: [AMDGPU] Allow for MFMA Inst Clustering