Page MenuHomePhabricator
Feed Advanced Search

Yesterday

jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Rebase on top of precommitted tests.

Fri, Sep 30, 1:08 PM · Restricted Project, Restricted Project
jrbyrnes committed rG5a61340eb435: [AMDGPU] Fix tests in f6a2e6afed2 (authored by jrbyrnes).
[AMDGPU] Fix tests in f6a2e6afed2
Fri, Sep 30, 12:54 PM · Restricted Project, Restricted Project
jrbyrnes committed rGf6a2e6afed21: [AMDGPU] Precommit test case for D133584 (authored by jrbyrnes).
[AMDGPU] Precommit test case for D133584
Fri, Sep 30, 12:44 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Extend ByteProvider / VectorOffset handling to support vectorScalarTypes > 1 Byte.

Fri, Sep 30, 12:10 PM · Restricted Project, Restricted Project

Thu, Sep 29

jrbyrnes added inline comments to D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).
Thu, Sep 29, 4:45 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

Add pattern to select V_AND v1, 0xffff000 in the case where buildvector produces bits V1.hi : 0

Thu, Sep 29, 4:44 PM · Restricted Project, Restricted Project
jrbyrnes added inline comments to D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).
Thu, Sep 29, 11:11 AM · Restricted Project, Restricted Project

Wed, Sep 28

jrbyrnes added inline comments to D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).
Wed, Sep 28, 12:03 PM · Restricted Project, Restricted Project
jrbyrnes added a comment to D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

One small point in favor of BFI is the bitmask you need is more likely CSEable for unrelated uses

Wed, Sep 28, 11:35 AM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

Use V_BFI for V[1].hi : V[0].low . This allows for a bitmask which is more likely to be reused by other instructions (0xffff vs 0x7060100), potentially enabling other optimizations (e.g. CSE)

Wed, Sep 28, 11:35 AM · Restricted Project, Restricted Project

Tue, Sep 27

jrbyrnes added a comment to D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

Can't you use v_alignbit for all the cases where you need the upper 16 bits of one register and the lower 16 bits of the other? It should be smaller than v_perm because the shift amount (16) is an inline constant.

Tue, Sep 27, 12:26 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

Precommit generated test + Rebase

Tue, Sep 27, 12:26 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Rebase

Tue, Sep 27, 11:37 AM · Restricted Project, Restricted Project
jrbyrnes added a comment to D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

I'm still not confident in my understanding of the various index values even with the added code comments.
I'll try to step through some of these tests in the debugger to get a better idea, but it would be good if another reviewer can have a look too for a second opinion.

Tue, Sep 27, 10:03 AM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

replace setOffset with addToOffset

Tue, Sep 27, 10:02 AM · Restricted Project, Restricted Project

Mon, Sep 26

jrbyrnes committed rGe6c29c033899: [AMDGPU] Precommit switching test to generated checks for D134463 (authored by Jeff).
[AMDGPU] Precommit switching test to generated checks for D134463
Mon, Sep 26, 8:14 AM · Restricted Project, Restricted Project

Fri, Sep 23

jrbyrnes updated the diff for D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

Address review comments.

Fri, Sep 23, 5:29 PM · Restricted Project, Restricted Project
jrbyrnes committed rG33ab74ac466f: [AMDGPU] Precommit switching test to generated checks for D134463 (authored by Jeff).
[AMDGPU] Precommit switching test to generated checks for D134463
Fri, Sep 23, 3:13 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

Fix attributes in test

Fri, Sep 23, 10:32 AM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).

Precommit generated tests pack.v2f16.ll, rebase

Fri, Sep 23, 10:26 AM · Restricted Project, Restricted Project
jrbyrnes committed rG5787d4446288: [AMDGPU] Precommit switching test to generated checks for D134463 (authored by Jeff).
[AMDGPU] Precommit switching test to generated checks for D134463
Fri, Sep 23, 10:16 AM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Address review comments (remove unnecessary "Root" parameter).

Fri, Sep 23, 8:34 AM · Restricted Project, Restricted Project

Thu, Sep 22

jrbyrnes added inline comments to D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.
Thu, Sep 22, 2:39 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Address review comments.

Thu, Sep 22, 2:38 PM · Restricted Project, Restricted Project
jrbyrnes added reviewers for D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK): arsenm, rampitec, kerbowa.

Hey Matt, thanks for the comments. I'll address them soon, for now I'll add you as reviewer.

Thu, Sep 22, 12:41 PM · Restricted Project, Restricted Project
jrbyrnes updated the summary of D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).
Thu, Sep 22, 12:18 PM · Restricted Project, Restricted Project
jrbyrnes updated the summary of D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).
Thu, Sep 22, 12:18 PM · Restricted Project, Restricted Project
jrbyrnes requested review of D134463: [AMDGPU] Use V_PERM to match buildvectors when inputs are not canonicalized (i.e. can't use V_PACK).
Thu, Sep 22, 11:26 AM · Restricted Project, Restricted Project

Wed, Sep 21

jrbyrnes added a comment to D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Sure - I didn't look at the diffs closely, but I don't object to improving the SDAG implementation. Just wanted to let you know that there are potential other places to try this kind of transform.

Wed, Sep 21, 2:46 PM · Restricted Project, Restricted Project

Mon, Sep 19

jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Address review comments -- update usage of Optional API.

Mon, Sep 19, 12:46 PM · Restricted Project, Restricted Project
jrbyrnes committed rG1bb293f6582b: [AMDGPU] [DAGCombiner] Precommit test for D133584 (authored by Jeff).
[AMDGPU] [DAGCombiner] Precommit test for D133584
Mon, Sep 19, 11:39 AM · Restricted Project, Restricted Project
jrbyrnes added a comment to D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

LLVM has gone back and forth on this. There was a general load combine pass for IR, but it was removed because it interfered with other transforms in IR. So we started hacking away at codegen instead, but there are programs where doing the transform in codegen is too late to get the optimal results. So we have some limited transforms in the vectorization passes, and now we're trying to reintroduce load combining as a canonicalization (but in very limited cases and gated by target-specific legality checks).

Mon, Sep 19, 11:20 AM · Restricted Project, Restricted Project
jrbyrnes added a comment to D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Both SLP and VectorCombine should try to make patterns like this better in IR, so there might be some target cost/legality checks that need adjusting.
There's also an in-progress patch for -aggressive-instcombine that could be relevant:
D127392

Would it be better to transform this before codegen?
https://alive2.llvm.org/ce/z/uyxHSW

Mon, Sep 19, 10:59 AM · Restricted Project, Restricted Project

Thu, Sep 15

jrbyrnes added inline comments to D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.
Thu, Sep 15, 3:39 PM · Restricted Project, Restricted Project
jrbyrnes committed rGf90cf68003bd: [NFC] Fix tests in commit 20cf170e68def (authored by jrbyrnes).
[NFC] Fix tests in commit 20cf170e68def
Thu, Sep 15, 3:38 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133731: [AMDGPU] Add Lower Bound to PipelineSolver.

Address review comments

Thu, Sep 15, 3:08 PM · Restricted Project, Restricted Project
jrbyrnes added reviewers for D133964: [AMDGPU] Implement dependency heuristic for prioritizing candidate SchedGroups for a given pipeline instruction.: arsenm, vangthao95, rampitec, kerbowa.
Thu, Sep 15, 2:32 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133964: [AMDGPU] Implement dependency heuristic for prioritizing candidate SchedGroups for a given pipeline instruction..

Add comment for new function

Thu, Sep 15, 12:22 PM · Restricted Project, Restricted Project
jrbyrnes requested review of D133964: [AMDGPU] Implement dependency heuristic for prioritizing candidate SchedGroups for a given pipeline instruction..
Thu, Sep 15, 12:19 PM · Restricted Project, Restricted Project

Wed, Sep 14

jrbyrnes updated the diff for D133731: [AMDGPU] Add Lower Bound to PipelineSolver.

A few optimizations to improve general performance, and perf of LB.

Wed, Sep 14, 8:30 AM · Restricted Project, Restricted Project

Tue, Sep 13

jrbyrnes added a comment to D133731: [AMDGPU] Add Lower Bound to PipelineSolver.

Thanks for implementing this!

Tue, Sep 13, 4:44 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133731: [AMDGPU] Add Lower Bound to PipelineSolver.

Address Review Comments

Tue, Sep 13, 4:43 PM · Restricted Project, Restricted Project

Mon, Sep 12

jrbyrnes added reviewers for D133731: [AMDGPU] Add Lower Bound to PipelineSolver: kerbowa, rampitec, arsenm, vangthao95.
Mon, Sep 12, 3:30 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133731: [AMDGPU] Add Lower Bound to PipelineSolver.

Avoid a very small number of calls to calculateLowerBound

Mon, Sep 12, 3:28 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133731: [AMDGPU] Add Lower Bound to PipelineSolver.

Fix incomplete comment

Mon, Sep 12, 3:24 PM · Restricted Project, Restricted Project
jrbyrnes requested review of D133731: [AMDGPU] Add Lower Bound to PipelineSolver.
Mon, Sep 12, 3:19 PM · Restricted Project, Restricted Project
jrbyrnes added reviewers for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine: bogner, RKSimon, spatel.

Adding reviewers for increased perspective.

Mon, Sep 12, 10:53 AM · Restricted Project, Restricted Project

Fri, Sep 9

jrbyrnes added a comment to D131959: [AMDGPU] Fix SDST operand of V_DIV_SCALE to always be VCC.

Check D133593, it tries to address a similar problem, but with SCC.

Fri, Sep 9, 5:55 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.

Address comments.

Fri, Sep 9, 3:57 PM · Restricted Project, Restricted Project
jrbyrnes added a comment to D131959: [AMDGPU] Fix SDST operand of V_DIV_SCALE to always be VCC.

+ @jrbyrnes who did some work on implicit vs explicit uses of $scc in D128681.

Fri, Sep 9, 11:16 AM · Restricted Project, Restricted Project
jrbyrnes added reviewers for D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine: kerbowa, rampitec, arsenm.
Fri, Sep 9, 9:02 AM · Restricted Project, Restricted Project
jrbyrnes requested review of D133584: [DAGCombiner] [AMDGPU] Allow vector loads in MatchLoadCombine.
Fri, Sep 9, 8:59 AM · Restricted Project, Restricted Project

Aug 19 2022

jrbyrnes closed D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.

Thanks Stas

Aug 19 2022, 3:48 PM · Restricted Project, Restricted Project
jrbyrnes accepted D132079: [AMDGPU] Add iglp_opt builtin and MFMA GEMM Opt strategy.

LGTM

Aug 19 2022, 12:58 PM · Restricted Project, Restricted Project, Restricted Project
jrbyrnes added a comment to D132079: [AMDGPU] Add iglp_opt builtin and MFMA GEMM Opt strategy.

Just a couple nitpicks

Aug 19 2022, 12:27 PM · Restricted Project, Restricted Project, Restricted Project
jrbyrnes added a comment to rG20cf170e68de: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.

Code review: https://reviews.llvm.org/D130729

Aug 19 2022, 11:45 AM · Restricted Project, Restricted Project
jrbyrnes committed rG20cf170e68de: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics (authored by jrbyrnes).
[InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics
Aug 19 2022, 11:38 AM · Restricted Project, Restricted Project
jrbyrnes added a comment to D132079: [AMDGPU] Add iglp_opt builtin and MFMA GEMM Opt strategy.

LGTM again

Aug 19 2022, 11:23 AM · Restricted Project, Restricted Project, Restricted Project
jrbyrnes added inline comments to D132079: [AMDGPU] Add iglp_opt builtin and MFMA GEMM Opt strategy.
Aug 19 2022, 7:23 AM · Restricted Project, Restricted Project, Restricted Project

Aug 17 2022

jrbyrnes added a comment to D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.

Does anyone have any concerns about this patch?

Aug 17 2022, 4:45 PM · Restricted Project, Restricted Project
jrbyrnes added a comment to D132079: [AMDGPU] Add iglp_opt builtin and MFMA GEMM Opt strategy.

Hey Austin --

Aug 17 2022, 4:43 PM · Restricted Project, Restricted Project, Restricted Project
jrbyrnes committed rG1c8d7ea97329: [AMDGPU] Implement pipeline solver for non-trivial pipelines (authored by jrbyrnes).
[AMDGPU] Implement pipeline solver for non-trivial pipelines
Aug 17 2022, 4:22 PM · Restricted Project, Restricted Project
jrbyrnes closed D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.
Aug 17 2022, 4:22 PM · Restricted Project, Restricted Project

Aug 16 2022

jrbyrnes added a comment to D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.

Not sure how much effort you are willing to put into the exact algorithm. But maybe you can improve the performance by adding some lower bounds on future costs to improve pruning?

More specifically, when evaluating a partial solution S with cost C, and comparing it against the currently best solution BS with cost BC, you currently prune if C > BC.
I'm proposing to compute some lower bound LC on the cost of the decisions that have not yet been made (e.g. adding the costs of cheapest assignments), and pruning if C + LC > BC.

I did not review the algorithm in enough detail to make a more concrete proposal, and it could very well be that computing a non-trivial lower bound (i.e. one that is not zero) is difficult.
However, in similar problems the technique above often helps a lot.

Aug 16 2022, 11:14 AM · Restricted Project, Restricted Project

Aug 10 2022

jrbyrnes updated the diff for D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.

Replace timeout feature with deterministic max branches explored feature, and properly handle early termination condition.

Aug 10 2022, 8:19 AM · Restricted Project, Restricted Project

Aug 9 2022

jrbyrnes updated the diff for D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.

Add some features to help performance / usability of exact PipelineSolver, including:

Timeout feature (& corresponding CLI option)
Guiding heuristic, choosing the fit with fewest missed edges first (& corresponding CLI option)
Run the greedy algorithm before exact to improve pruning (useful if not using cost heuristic)
Aug 9 2022, 1:30 PM · Restricted Project, Restricted Project

Aug 8 2022

jrbyrnes added inline comments to D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.
Aug 8 2022, 5:47 PM · Restricted Project, Restricted Project

Aug 5 2022

jrbyrnes updated the diff for D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.

Address Review comments.

Aug 5 2022, 2:15 PM · Restricted Project, Restricted Project
jrbyrnes added inline comments to D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.
Aug 5 2022, 8:35 AM · Restricted Project, Restricted Project

Aug 4 2022

jrbyrnes added inline comments to D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.
Aug 4 2022, 1:38 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.

Move codegen tests to CodeGen, add IR test for InferAddressSpace flat_atomic.

Aug 4 2022, 1:21 PM · Restricted Project, Restricted Project
jrbyrnes retitled D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics from [SeparateConstOffsetFromGEP] [AMDGPU] Check legality for all uses of transformed GEP to [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.
Aug 4 2022, 12:19 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.

Rework approach of fix.

Aug 4 2022, 12:17 PM · Restricted Project, Restricted Project

Aug 3 2022

jrbyrnes added a comment to D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.

Hey Matt, Jay,

Aug 3 2022, 3:35 PM · Restricted Project, Restricted Project
jrbyrnes committed rGe0b16aaaf997: [AMDGPU] Precommit test case for D130729 (authored by jrbyrnes).
[AMDGPU] Precommit test case for D130729
Aug 3 2022, 3:23 PM · Restricted Project, Restricted Project

Aug 2 2022

jrbyrnes added a reviewer for D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics: foad.
Aug 2 2022, 2:27 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.

Address Review Comments.

Aug 2 2022, 2:21 PM · Restricted Project, Restricted Project

Aug 1 2022

jrbyrnes added a comment to D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.

Thanks! I like the idea behind the greedy solver. Not sure about SchedGroupSU. Maybe just a map between SUs and lists of schedgroups? I think trying to track sched_group_barriers by their order and assigning that an index is a bit confusing.

Aug 1 2022, 1:31 PM · Restricted Project, Restricted Project

Jul 29 2022

jrbyrnes requested review of D130797: [AMDGPU] Implement pipeline solver for non-trivial pipelines.
Jul 29 2022, 1:07 PM · Restricted Project, Restricted Project

Jul 28 2022

jrbyrnes updated the diff for D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.

Remove unnecessary local var

Jul 28 2022, 1:53 PM · Restricted Project, Restricted Project
jrbyrnes requested review of D130729: [InferAddressSpaces] [AMDGPU] Add inference for flat_atomic intrinsics.
Jul 28 2022, 1:52 PM · Restricted Project, Restricted Project
jrbyrnes accepted D128158: [AMDGPU] Add amdgcn_sched_group_barrier builtin.
Jul 28 2022, 9:37 AM · Restricted Project, Restricted Project, Restricted Project

Jul 26 2022

jrbyrnes added a comment to D128158: [AMDGPU] Add amdgcn_sched_group_barrier builtin.

LGTM

Jul 26 2022, 2:30 PM · Restricted Project, Restricted Project, Restricted Project

Jul 14 2022

jrbyrnes committed rG8a12f20ef773: [AMDGPU] Update the mechanism used to check for cycles and add eges in power… (authored by jrbyrnes).
[AMDGPU] Update the mechanism used to check for cycles and add eges in power…
Jul 14 2022, 4:25 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D129667: [AMDGPU] Update the mechanism used to check for cycles and add eges in power-sched mutation.

Address review comments.

Jul 14 2022, 10:14 AM · Restricted Project, Restricted Project

Jul 13 2022

jrbyrnes updated the diff for D129667: [AMDGPU] Update the mechanism used to check for cycles and add eges in power-sched mutation.

Include test which which minimally reproduces the SmallVector error reported.

Jul 13 2022, 4:41 PM · Restricted Project, Restricted Project
jrbyrnes requested review of D129667: [AMDGPU] Update the mechanism used to check for cycles and add eges in power-sched mutation.
Jul 13 2022, 10:45 AM · Restricted Project, Restricted Project

Jul 6 2022

jrbyrnes updated the diff for D127994: [AMDGPU] Expose CLI controls for IGroup ordering.

Remove unnecessary debug code.

Jul 6 2022, 11:09 AM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D127994: [AMDGPU] Expose CLI controls for IGroup ordering.

Addressed review comments.

Jul 6 2022, 11:03 AM · Restricted Project, Restricted Project

Jul 1 2022

jrbyrnes added a comment to D128158: [AMDGPU] Add amdgcn_sched_group_barrier builtin.

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.

Jul 1 2022, 11:45 AM · Restricted Project, Restricted Project, Restricted Project

Jun 30 2022

jrbyrnes committed rG09424f802c8f: [AMDGPU] Check for CopyToReg PhysReg clobbers in pre-RA-sched (authored by jrbyrnes).
[AMDGPU] Check for CopyToReg PhysReg clobbers in pre-RA-sched
Jun 30 2022, 9:18 AM · Restricted Project, Restricted Project
jrbyrnes closed D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.
Jun 30 2022, 9:18 AM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.

Remove accidental files

Jun 30 2022, 7:43 AM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.

Run instnamer on testfile, explicitly use "source" (RRList) scheduler for InstSelection Scheduler in test.

Jun 30 2022, 7:41 AM · Restricted Project, Restricted Project

Jun 28 2022

jrbyrnes added inline comments to D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.
Jun 28 2022, 4:13 PM · Restricted Project, Restricted Project

Jun 27 2022

jrbyrnes updated the diff for D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.

Broke up logic in ScheduleDAGFast CheckForLiveRegDef to remove redundancy.

Jun 27 2022, 4:44 PM · Restricted Project, Restricted Project
jrbyrnes retitled D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched from [AMDGPU] Check for CopyToReg PhysReg clobbers in pre-RA-sched to [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.
Jun 27 2022, 2:05 PM · Restricted Project, Restricted Project
jrbyrnes added reviewers for D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched: arsenm, rampitec, kerbowa, foad, Hipony.
Jun 27 2022, 2:04 PM · Restricted Project, Restricted Project
jrbyrnes updated the diff for D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.

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 27 2022, 2:02 PM · Restricted Project, Restricted Project
jrbyrnes updated the summary of D128681: [AMDGPU][ScheduleDAG] Check for CopyToReg PhysReg clobbers in pre-RA-sched.
Jun 27 2022, 1:58 PM · Restricted Project, Restricted Project