Page MenuHomePhabricator

tpopp (Theodore Popp)
User

Projects

User does not belong to any projects.

User Details

User Since
Jan 3 2020, 4:17 AM (76 w, 4 d)

Recent Activity

Mon, Jun 14

tpopp updated the diff for D103513: Support buffers in LinalgFoldUnitExtentDims.

Rebase, add tests, and extract reshape logic into separate methods.

Mon, Jun 14, 2:58 AM · Restricted Project

Sun, Jun 13

tpopp accepted D104103: [mlir] Remove traits that require vector type support from ops in Complex dialect..
Sun, Jun 13, 9:58 PM · Restricted Project

Mon, Jun 7

tpopp updated the diff for D103513: Support buffers in LinalgFoldUnitExtentDims.

Create a single method to support both Tensor and MemRef operands.

Mon, Jun 7, 3:08 AM · Restricted Project
tpopp added a comment to D103513: Support buffers in LinalgFoldUnitExtentDims.

Have a comment above (clicked enter early there). Will review more, but if we are going down this path, do we just replicate all the tests here for tensors with memrefs as well?

Mon, Jun 7, 3:05 AM · Restricted Project

Wed, Jun 2

tpopp added a reviewer for D103513: Support buffers in LinalgFoldUnitExtentDims: mravishankar.
Wed, Jun 2, 4:53 AM · Restricted Project
tpopp updated the diff for D103513: Support buffers in LinalgFoldUnitExtentDims.

Update a comment

Wed, Jun 2, 4:53 AM · Restricted Project
tpopp requested review of D103513: Support buffers in LinalgFoldUnitExtentDims.
Wed, Jun 2, 4:51 AM · Restricted Project

Tue, Jun 1

tpopp requested review of D103447: [mlir] Use interfaces in MathToLibm.
Tue, Jun 1, 4:04 AM · Restricted Project

Mon, May 31

tpopp added a comment to D103388: [mlir][NFC] Remove illegal TanhOp in LLVMConversionTarget.

Do this let us also remove the build/link dependency on the math dialect from this conversion?

Mon, May 31, 1:40 AM · Restricted Project

Sun, May 30

tpopp requested review of D103388: [mlir][NFC] Remove illegal TanhOp in LLVMConversionTarget.
Sun, May 30, 11:42 PM · Restricted Project

Tue, May 25

tpopp updated the diff for D102681: [mlir] Support buffer hoisting on allocas.

Remove hoisting of allocas in non-loop cases.

Tue, May 25, 5:19 AM · Restricted Project
tpopp requested review of D103076: [mlir] Fold memref.dim of OffsetSizeAndStrideOpInterface outputs.
Tue, May 25, 2:38 AM · Restricted Project

May 21 2021

tpopp added inline comments to D102681: [mlir] Support buffer hoisting on allocas.
May 21 2021, 12:16 AM · Restricted Project

May 18 2021

tpopp requested review of D102681: [mlir] Support buffer hoisting on allocas.
May 18 2021, 3:12 AM · Restricted Project

May 11 2021

tpopp updated the diff for D102157: Support VectorTransfer splitting on writes also..

Respond to comments.

May 11 2021, 1:32 AM · Restricted Project

May 10 2021

tpopp requested review of D102157: Support VectorTransfer splitting on writes also..
May 10 2021, 2:12 AM · Restricted Project

May 7 2021

tpopp updated the diff for D100838: [mlir] Split BufferAliasAnalysis into 2 classes.

Change this patch to just a rename and expanded documentation.

May 7 2021, 7:10 AM · Restricted Project

May 6 2021

tpopp added a comment to D100838: [mlir] Split BufferAliasAnalysis into 2 classes.

I have to admit that my comment regarding all aliases of A was a bit misleading :-( At the time of writing, I accidentally had the "flow"-property (required by the BufferDeallocation phase) in mind. My comment was meant to address potentially "inconsistent" results of two "alias analyses" (of course, aliasing is a symmetric property!) :-)

Regarding the name: I really like BufferViewFlowAnalysis, as it expresses the property of data flow between different Value nodes.

This alias analysis should indeed not exist. It is broken in several different ways, and only works now because well.. luck mostly

This also sounds a bit misleading. At the time of implementing, we had to introduce a specialized and domain-specific version that collects all aliases depending on the "flow" of a given value. This analysis was never intended to serve as a universal global program analysis. However, I agree that it might be beneficial to replace this analysis implementation by the ones available right now.

May 6 2021, 6:48 AM · Restricted Project

Apr 30 2021

tpopp added a comment to D100838: [mlir] Split BufferAliasAnalysis into 2 classes.

I agree though that "Dependency" is a bad name. I'm just struggling to find a name to encode this concept of BufferViewFlowAnalysis.

Apr 30 2021, 1:22 AM · Restricted Project
tpopp added a comment to D100838: [mlir] Split BufferAliasAnalysis into 2 classes.

I am not convinced that DependencyAnalysis is the better name here. For dependencies, I think of read-after-write, etc.. This only computes the flow of buffers through control flow.

Apr 30 2021, 1:19 AM · Restricted Project

Apr 29 2021

tpopp added a comment to D97667: [loop-idiom] Hoist loop memcpys to loop preheader.

Describing what the code is intended to do (https://github.com/tensorflow/tensorflow/blob/master/tensorflow/compiler/xla/tests/reverse_test.cc#L146).

Apr 29 2021, 1:37 AM · Restricted Project
tpopp added a comment to D97667: [loop-idiom] Hoist loop memcpys to loop preheader.
; ModuleID = '__compute_module' 
source_filename = "__compute_module"                                                                                               
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"                                       
target triple = "x86_64-grtev4-linux-gnu"
Apr 29 2021, 1:23 AM · Restricted Project

Apr 28 2021

tpopp added a reviewer for D100838: [mlir] Split BufferAliasAnalysis into 2 classes: pifon2a.
Apr 28 2021, 1:59 PM · Restricted Project
tpopp accepted D101456: [MLIR][Shape] Fix `shape.broadcast` to standard lowering.
Apr 28 2021, 7:20 AM · Restricted Project
tpopp added a comment to D101385: tsan: refactor fork handling.

I'm reverting this due to test failures and emailing you a more in depth reproducer for the failures. It seems like you expected the possibility of failures, so I hope this is okay.

Apr 28 2021, 5:11 AM · Restricted Project
tpopp added a comment to D97667: [loop-idiom] Hoist loop memcpys to loop preheader.

lebedev.ri's concerns seem to have been valid, so I'll be rolling this back. A test case in XLA that reverses data across certain dimensions in a multidimensional change fails with this patch. A sequence of loads and stores is converted into a single memcpy even though the ordering should be different across loads and stores.

Apr 28 2021, 4:13 AM · Restricted Project

Apr 23 2021

tpopp added a comment to D100838: [mlir] Split BufferAliasAnalysis into 2 classes.

Friendly ping.

Apr 23 2021, 4:57 AM · Restricted Project
tpopp added a comment to D99939: [mlir] Support complex numbers in Linalg promotion.

Friendly ping.

Apr 23 2021, 4:57 AM · Restricted Project

Apr 21 2021

tpopp accepted D100634: [MLIR][Shape] Add canonicalizations for `shape.broadcast`.
Apr 21 2021, 6:51 AM · Restricted Project
tpopp added a comment to D100634: [MLIR][Shape] Add canonicalizations for `shape.broadcast`.

A few places you checked that *.isa<ShapeType>() == *.isa<ShapeType>(). Out of curiosity, why not just compare the types?

Apr 21 2021, 12:46 AM · Restricted Project
tpopp added a comment to D100634: [MLIR][Shape] Add canonicalizations for `shape.broadcast`.

Arc diff doesn't update the description, so FYI in case you didn't, update to mention the additional features you added.

Apr 21 2021, 12:23 AM · Restricted Project

Apr 20 2021

tpopp updated the diff for D100838: [mlir] Split BufferAliasAnalysis into 2 classes.

Update cmake file and remove friendliness between Analyses

Apr 20 2021, 11:54 PM · Restricted Project
tpopp requested review of D100838: [mlir] Split BufferAliasAnalysis into 2 classes.
Apr 20 2021, 3:52 AM · Restricted Project
tpopp added a comment to D99939: [mlir] Support complex numbers in Linalg promotion.

I forwarded the DataLayout through several layers of functions. I started at the last point that the call sequence has the originating LinalgOp and passed it through as an additional argument rather than inside of any of the LinalgPromotionOption data structures. Please let me know what you think.

Apr 20 2021, 3:27 AM · Restricted Project
tpopp updated the diff for D99939: [mlir] Support complex numbers in Linalg promotion.

Forward DataLayout object to buffer allocation.

Apr 20 2021, 3:26 AM · Restricted Project

Apr 19 2021

tpopp added a comment to D100367: [mlir] Add patterns to lower Math operations to LLVM based libm calls..

It may not exist, it just sounds like a useful thing to have so I thought somebody could have added it. Feel free to have a local version or suggest one at Vector level. There's already VectorUnrollPattern that could be helpful.

Apr 19 2021, 11:33 PM · Restricted Project
tpopp updated the diff for D100367: [mlir] Add patterns to lower Math operations to LLVM based libm calls..

Add test case to convert vectors to scalars.

Apr 19 2021, 11:32 PM · Restricted Project

Apr 16 2021

tpopp added inline comments to D100634: [MLIR][Shape] Add canonicalizations for `shape.broadcast`.
Apr 16 2021, 7:16 AM · Restricted Project

Apr 14 2021

tpopp updated the diff for D100367: [mlir] Add patterns to lower Math operations to LLVM based libm calls..

Convert to StandardOpsDialect instead of LLVMDialect.

Apr 14 2021, 6:53 AM · Restricted Project
tpopp added a comment to D100367: [mlir] Add patterns to lower Math operations to LLVM based libm calls..

On a second thought, does this even need to target LLVM dialect directly? I'd expect us to have vector insert/extract in the vector dialect (hopefully, there is also a facility to unpack vectors; I see a naive combination of vector-to-loops and loop-unroll, but there may be something more specific) and we can call functions at the std level. The std->llvm conversion will do the rest.

Apr 14 2021, 6:37 AM · Restricted Project
tpopp updated the diff for D99939: [mlir] Support complex numbers in Linalg promotion.

Rebase onto parent commit

Apr 14 2021, 1:44 AM · Restricted Project
tpopp added a comment to D100289: Add default DataLayout support for complex numbers.

Please let me know what you think of my interpretation of the default sizes for complex types.

Apr 14 2021, 1:33 AM · Restricted Project
tpopp updated the diff for D100289: Add default DataLayout support for complex numbers.

Change complex DataLayout size computation to include alignment padding between elements.

Apr 14 2021, 1:25 AM · Restricted Project

Apr 13 2021

tpopp requested review of D100390: [mlir] Change verification order to prevent null dereference.
Apr 13 2021, 8:32 AM · Restricted Project
tpopp requested review of D100367: [mlir] Add patterns to lower Math operations to LLVM based libm calls..
Apr 13 2021, 1:21 AM · Restricted Project

Apr 12 2021

tpopp added a comment to D99197: [MLIR][Shape] Derive more concrete type for `shape.shape_of`.

Is this no longer needed?

Apr 12 2021, 2:24 AM · Restricted Project
tpopp added inline comments to D99939: [mlir] Support complex numbers in Linalg promotion.
Apr 12 2021, 1:30 AM · Restricted Project
tpopp requested review of D100289: Add default DataLayout support for complex numbers.
Apr 12 2021, 1:29 AM · Restricted Project
tpopp added inline comments to D99939: [mlir] Support complex numbers in Linalg promotion.
Apr 12 2021, 1:09 AM · Restricted Project
tpopp updated the diff for D99939: [mlir] Support complex numbers in Linalg promotion.

Switch to using DataLayout.

Apr 12 2021, 1:08 AM · Restricted Project

Apr 9 2021

tpopp accepted D100042: [MLIR] Do not yield values from an assuming op that are never used.

Nice code.

Apr 9 2021, 1:49 AM · Restricted Project
tpopp added inline comments to D100042: [MLIR] Do not yield values from an assuming op that are never used.
Apr 9 2021, 1:49 AM · Restricted Project

Apr 6 2021

tpopp requested review of D99939: [mlir] Support complex numbers in Linalg promotion.
Apr 6 2021, 3:41 AM · Restricted Project

Mar 23 2021

tpopp added inline comments to D99161: [MLIR][Shape] Canonicalize casted dynamic extent tensor.
Mar 23 2021, 7:36 AM · Restricted Project

Mar 15 2021

tpopp accepted D98402: [MLIR] Add canonicalization for `shape.broadcast`.
Mar 15 2021, 2:00 AM · Restricted Project

Mar 10 2021

tpopp updated the diff for D98331: [mlir] Correct verifyCompatibleShapes.

Add test case.

Mar 10 2021, 6:00 AM · Restricted Project
tpopp added inline comments to D98331: [mlir] Correct verifyCompatibleShapes.
Mar 10 2021, 5:48 AM · Restricted Project
tpopp updated the diff for D98331: [mlir] Correct verifyCompatibleShapes.

Respond to feedback.

Mar 10 2021, 5:41 AM · Restricted Project
tpopp updated the diff for D98331: [mlir] Correct verifyCompatibleShapes.

Add a missing newline and remove an unneeded include.

Mar 10 2021, 4:00 AM · Restricted Project
tpopp requested review of D98331: [mlir] Correct verifyCompatibleShapes.
Mar 10 2021, 3:57 AM · Restricted Project

Mar 3 2021

tpopp accepted D97860: [mlir][Shape] Lower cstr_eq to shape_eq + assert.
Mar 3 2021, 7:48 AM · Restricted Project
tpopp accepted D97728: [mlir][Shape] Make shape_eq nary.
Mar 3 2021, 5:30 AM · Restricted Project
tpopp added inline comments to D97728: [mlir][Shape] Make shape_eq nary.
Mar 3 2021, 5:30 AM · Restricted Project
tpopp accepted D97716: [mlir][Shape] Make cstr_eq more like cstr_broadcastable.
Mar 3 2021, 5:17 AM · Restricted Project

Feb 22 2021

tpopp accepted D97206: [mlir][Shape] Fix a crash when folding nary broadcast ops.

Whoops. That's definitely a better choice than what I did.

Feb 22 2021, 10:53 AM · Restricted Project

Feb 18 2021

tpopp requested review of D96951: [mlir] Mark std.subview as NoSideEffect.
Feb 18 2021, 5:27 AM · Restricted Project
tpopp added inline comments to D96739: [mlir] Add math polynomial approximation pass.
Feb 18 2021, 1:02 AM · Restricted Project

Feb 17 2021

tpopp accepted D96800: [mlir][Shape] Generalize cstr_broadcastable folding for n-ary broadcasts.
Feb 17 2021, 1:48 AM · Restricted Project

Feb 16 2021

tpopp accepted D96797: [mlir][Shape] Mark BroadcastOp as not having side effects.
Feb 16 2021, 11:41 PM · Restricted Project
tpopp requested review of D96764: [mlir] Don't return nullptrs from scf::IfOp::getSuccessorRegions.
Feb 16 2021, 2:32 AM · Restricted Project

Feb 15 2021

tpopp updated the diff for D96401: Make shape.is_broadcastable/shape.cstr_broadcastable nary.

Add message and tests for op verification failures

Feb 15 2021, 1:12 AM · Restricted Project

Feb 11 2021

tpopp added inline comments to D96401: Make shape.is_broadcastable/shape.cstr_broadcastable nary.
Feb 11 2021, 8:39 AM · Restricted Project
tpopp updated the diff for D96401: Make shape.is_broadcastable/shape.cstr_broadcastable nary.

Address code cleanup comments.

Feb 11 2021, 8:39 AM · Restricted Project

Feb 10 2021

tpopp requested review of D96401: Make shape.is_broadcastable/shape.cstr_broadcastable nary.
Feb 10 2021, 1:44 AM · Restricted Project

Feb 9 2021

tpopp added inline comments to D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.
Feb 9 2021, 7:03 AM · Restricted Project
tpopp updated the diff for D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.

Replace naryBroadcast helper with only a single dim calculation.

Feb 9 2021, 6:30 AM · Restricted Project
tpopp added inline comments to D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.
Feb 9 2021, 3:35 AM · Restricted Project

Feb 8 2021

tpopp updated the diff for D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.

Removed binary broadcast case and updated tests accordingly.

Feb 8 2021, 5:56 AM · Restricted Project

Feb 5 2021

tpopp updated the diff for D96111: Reorder MLIRContext location in BuiltinAttributes.h.

Update flang usages

Feb 5 2021, 4:15 AM · Restricted Project
tpopp requested review of D96111: Reorder MLIRContext location in BuiltinAttributes.h.
Feb 5 2021, 2:00 AM · Restricted Project

Feb 4 2021

tpopp added a comment to D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.

I'm going to wait on fixing the test until I hear your thoughts on the two options for lowering broadcast.

Feb 4 2021, 7:48 AM · Restricted Project
tpopp updated the diff for D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.

Fix variable names and adress other comments.

Feb 4 2021, 7:48 AM · Restricted Project

Feb 1 2021

tpopp updated the diff for D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.

Follow naming convention in new functions.

Feb 1 2021, 4:51 AM · Restricted Project
tpopp requested review of D95777: [mlir][shape] Generalize broadcast to a variadic number of shapes.
Feb 1 2021, 2:45 AM · Restricted Project

Jan 28 2021

tpopp updated the diff for D95535: [mlir] Prevent segfault in Tensor canonicalization.

Correct test case.

Jan 28 2021, 3:14 AM · Restricted Project
tpopp updated the diff for D95535: [mlir] Prevent segfault in Tensor canonicalization.

Correct constant name

Jan 28 2021, 2:20 AM · Restricted Project
tpopp added inline comments to D95535: [mlir] Prevent segfault in Tensor canonicalization.
Jan 28 2021, 2:19 AM · Restricted Project
tpopp updated the diff for D95535: [mlir] Prevent segfault in Tensor canonicalization.

Correct tests and fix comparison order.

Jan 28 2021, 2:16 AM · Restricted Project

Jan 27 2021

tpopp requested review of D95535: [mlir] Prevent segfault in Tensor canonicalization.
Jan 27 2021, 8:30 AM · Restricted Project

Jan 26 2021

tpopp added a comment to D95430: [mlir] Fold shape.eq %a, %a to true.

I don't know if this works with whatever Shape Error types exist these days, so please let me know what you think.

Jan 26 2021, 2:20 AM · Restricted Project
tpopp requested review of D95430: [mlir] Fold shape.eq %a, %a to true.
Jan 26 2021, 2:20 AM · Restricted Project

Jan 25 2021

tpopp abandoned D95337: [mlir] Fix constructor resolution of ImplicitLocOpBuilder.

Abandoning for another change.

Jan 25 2021, 2:59 AM · Restricted Project
tpopp requested review of D95337: [mlir] Fix constructor resolution of ImplicitLocOpBuilder.
Jan 25 2021, 2:32 AM · Restricted Project

Jan 19 2021

tpopp added a comment to D94934: [llvm] Prevent infinite loop in InstCombine of select statements.

I apologize, but I was not having any luck at creating a test case that wasn't constant folded away.

Jan 19 2021, 1:31 AM · Restricted Project

Jan 18 2021

tpopp added a comment to D94862: [InstCombine] Replace one-use select operand based on condition.

I've been unable to create a reproducer because of other optimizations getting in the way, but I'm seeing a case of infinite loops in inst combine due to both CmpLHS and CmpRHS being constants.

Jan 18 2021, 2:45 PM · Restricted Project
tpopp added reviewers for D94934: [llvm] Prevent infinite loop in InstCombine of select statements: nikic, aqjune.
Jan 18 2021, 2:42 PM · Restricted Project
tpopp requested review of D94934: [llvm] Prevent infinite loop in InstCombine of select statements.
Jan 18 2021, 2:41 PM · Restricted Project
tpopp added a comment to D92071: [PowerPC] support register pressure reduction in machine combiner..

Thanks for addressing the issues shchenz! I'm glad you figured out the use-of-uninitialized-value because that one confused me. I'm finishing my workday for the day, so I can rerun the patch tomorrow. Alternatively, all I know is that I had errors in my environment and that's what sanitizers showed, so you reproducing and fixing the issues is plenty I think.

Jan 18 2021, 11:19 AM · Restricted Project
tpopp added a comment to D92071: [PowerPC] support register pressure reduction in machine combiner..

I'm going to roll this back as it's causing build bot failures (in progress example here: http://45.33.8.238/win/31506/). Sanitizers show the following issues:

==9097==WARNING: MemorySanitizer: use-of-uninitialized-value
    #0 0x5628a1bd3d10 in llvm::PPCInstrInfo::getFMAPatterns(llvm::MachineInstr&, llvm::SmallVectorImpl<llvm::MachineCombinerPattern>&, bool) const third_party/llvm/llvm-project/llvm/lib/Target/PowerPC/PPCInstrIn
fo.cpp:474:27                                                                                            
    #1 0x5628a1bd7e6c in llvm::PPCInstrInfo::getMachineCombinerPatterns(llvm::MachineInstr&, llvm::SmallVectorImpl<llvm::MachineCombinerPattern>&, bool) const third_party/llvm/llvm-project/llvm/lib/Target/PowerP
C/PPCInstrInfo.cpp:751:7                            
    #2 0x5628a3291840 in combineInstructions third_party/llvm/llvm-project/llvm/lib/CodeGen/MachineCombiner.cpp:593:15
    #3 0x5628a3291840 in (anonymous namespace)::MachineCombiner::runOnMachineFunction(llvm::MachineFunction&) third_party/llvm/llvm-project/llvm/lib/CodeGen/MachineCombiner.cpp:736:16                            
    #4 0x5628a32f91a2 in llvm::MachineFunctionPass::runOnFunction(llvm::Function&) third_party/llvm/llvm-project/llvm/lib/CodeGen/MachineFunctionPass.cpp:72:13                                                    
    #5 0x5628a5e0dce7 in llvm::FPPassManager::runOnFunction(llvm::Function&) third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:1439:27                                                               
    #6 0x5628a5e22f60 in llvm::FPPassManager::runOnModule(llvm::Module&) third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:1485:16                                                                   
    #7 0x5628a5e0f1d5 in runOnModule third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:1554:27
    #8 0x5628a5e0f1d5 in llvm::legacy::PassManagerImpl::run(llvm::Module&) third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:541:44                                                                  
    #9 0x56289f8dcb66 in compileModule(char**, llvm::LLVMContext&) third_party/llvm/llvm-project/llvm/tools/llc/llc.cpp:658:8

and

==1709==ERROR: AddressSanitizer: stack-use-after-scope on address 0x7f155364a060 at pc 0x555a067755c4 bp 0x7fff9b909050 sp 0x7fff9b909048
READ of size 8 at 0x7f155364a060 thread T0
    #0 0x555a067755c3 in operator[] third_party/crosstool/v18/stable/toolchain/bin/../include/c++/v1/vector:1550:18
    #1 0x555a067755c3 in llvm::PPCInstrInfo::shouldReduceRegisterPressure(llvm::MachineBasicBlock*, llvm::RegisterClassInfo*) const third_party/llvm/llvm-project/llvm/lib/Target/PowerPC/PPCInstrInfo.cpp:655:10
    #2 0x555a07df5618 in combineInstructions third_party/llvm/llvm-project/llvm/lib/CodeGen/MachineCombiner.cpp:561:12
    #3 0x555a07df5618 in (anonymous namespace)::MachineCombiner::runOnMachineFunction(llvm::MachineFunction&) third_party/llvm/llvm-project/llvm/lib/CodeGen/MachineCombiner.cpp:736:16
    #4 0x555a07e54479 in llvm::MachineFunctionPass::runOnFunction(llvm::Function&) third_party/llvm/llvm-project/llvm/lib/CodeGen/MachineFunctionPass.cpp:72:13
    #5 0x555a0b360710 in llvm::FPPassManager::runOnFunction(llvm::Function&) third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:1439:27
    #6 0x555a0b374470 in llvm::FPPassManager::runOnModule(llvm::Module&) third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:1485:16
    #7 0x555a0b3616e0 in runOnModule third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:1554:27
    #8 0x555a0b3616e0 in llvm::legacy::PassManagerImpl::run(llvm::Module&) third_party/llvm/llvm-project/llvm/lib/IR/LegacyPassManager.cpp:541:44
    #9 0x555a0461db8b in compileModule(char**, llvm::LLVMContext&) third_party/llvm/llvm-project/llvm/tools/llc/llc.cpp:658:8
    #10 0x555a046183bf in main third_party/llvm/llvm-project/llvm/tools/llc/llc.cpp:363:22
Jan 18 2021, 3:00 AM · Restricted Project

Jan 15 2021

tpopp updated the diff for D94784: [llvm][nvptx] add atomicity to counter in ISelLowering.

Another naming convention correction.

Jan 15 2021, 1:09 PM · Restricted Project