Skip to content

Commit

Permalink
Revert "[mlir][loops] Reland Refactor LoopFuseSiblingOp and support p…
Browse files Browse the repository at this point in the history 
…arallel fusion llvm#94391 (llvm#97607)"

This reverts commit edbc0e3.

Reason for rollback. ASAN complains about this PR:

==4320==ERROR: AddressSanitizer: heap-use-after-free on address 0x502000006cd8 at pc 0x55e2978d63cf bp 0x7ffe6431c2b0 sp 0x7ffe6431c2a8
READ of size 8 at 0x502000006cd8 thread T0
    #0 0x55e2978d63ce in map<llvm::MutableArrayRef<mlir::BlockArgument> &, llvm::MutableArrayRef<mlir::BlockArgument>, nullptr> mlir/include/mlir/IR/IRMapping.h:40:11
    llvm#1 0x55e2978d63ce in mlir::createFused(mlir::LoopLikeOpInterface, mlir::LoopLikeOpInterface, mlir::RewriterBase&, std::__u::function<llvm::SmallVector<mlir::Value, 6u> (mlir::OpBuilder&, mlir::Location, llvm::ArrayRef<mlir::BlockArgument>)>, llvm::function_ref<void (mlir::RewriterBase&, mlir::LoopLikeOpInterface, mlir::LoopLikeOpInterface&, mlir::IRMapping)>) mlir/lib/Interfaces/LoopLikeInterface.cpp:156:11
    llvm#2 0x55e2952a614b in mlir::fuseIndependentSiblingForLoops(mlir::scf::ForOp, mlir::scf::ForOp, mlir::RewriterBase&) mlir/lib/Dialect/SCF/Utils/Utils.cpp:1398:43
    llvm#3 0x55e291480c6f in mlir::transform::LoopFuseSiblingOp::apply(mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) mlir/lib/Dialect/SCF/TransformOps/SCFTransformOps.cpp:482:17
    llvm#4 0x55e29149ed5e in mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Model<mlir::transform::LoopFuseSiblingOp>::apply(mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Concept const*, mlir::Operation*, mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.h.inc:477:56
    llvm#5 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14
    llvm#6 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48
    llvm#7 0x55e294646a8d in applySequenceBlock(mlir::Block&, mlir::transform::FailurePropagationMode, mlir::transform::TransformState&, mlir::transform::TransformResults&) mlir/lib/Dialect/Transform/IR/TransformOps.cpp:1788:15
    llvm#8 0x55e29464f927 in mlir::transform::NamedSequenceOp::apply(mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) mlir/lib/Dialect/Transform/IR/TransformOps.cpp:2155:10
    llvm#9 0x55e2945d28ee in mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Model<mlir::transform::NamedSequenceOp>::apply(mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Concept const*, mlir::Operation*, mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.h.inc:477:56
    llvm#10 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14
    llvm#11 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48
    llvm#12 0x55e2974a5fe2 in mlir::transform::applyTransforms(mlir::Operation*, mlir::transform::TransformOpInterface, mlir::RaggedArray<llvm::PointerUnion<mlir::Operation*, mlir::Attribute, mlir::Value>> const&, mlir::transform::TransformOptions const&, bool) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:2016:16
    llvm#13 0x55e2945888d7 in mlir::transform::applyTransformNamedSequence(mlir::RaggedArray<llvm::PointerUnion<mlir::Operation*, mlir::Attribute, mlir::Value>>, mlir::transform::TransformOpInterface, mlir::ModuleOp, mlir::transform::TransformOptions const&) mlir/lib/Dialect/Transform/Transforms/TransformInterpreterUtils.cpp:234:10
    llvm#14 0x55e294582446 in (anonymous namespace)::InterpreterPass::runOnOperation() mlir/lib/Dialect/Transform/Transforms/InterpreterPass.cpp:147:16
    llvm#15 0x55e2978e93c6 in operator() mlir/lib/Pass/Pass.cpp:527:17
    llvm#16 0x55e2978e93c6 in void llvm::function_ref<void ()>::callback_fn<mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int)::$_1>(long) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12
    llvm#17 0x55e2978e207a in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12
    llvm#18 0x55e2978e207a in executeAction<mlir::PassExecutionAction, mlir::Pass &> mlir/include/mlir/IR/MLIRContext.h:275:7
    llvm#19 0x55e2978e207a in mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int) mlir/lib/Pass/Pass.cpp:521:21
    llvm#20 0x55e2978e5fbf in runPipeline mlir/lib/Pass/Pass.cpp:593:16
    llvm#21 0x55e2978e5fbf in mlir::PassManager::runPasses(mlir::Operation*, mlir::AnalysisManager) mlir/lib/Pass/Pass.cpp:904:10
    llvm#22 0x55e2978e5b65 in mlir::PassManager::run(mlir::Operation*) mlir/lib/Pass/Pass.cpp:884:60
    llvm#23 0x55e291ebb460 in performActions(llvm::raw_ostream&, std::__u::shared_ptr<llvm::SourceMgr> const&, mlir::MLIRContext*, mlir::MlirOptMainConfig const&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:408:17
    llvm#24 0x55e291ebabd9 in processBuffer mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:481:9
    llvm#25 0x55e291ebabd9 in operator() mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:548:12
    llvm#26 0x55e291ebabd9 in llvm::LogicalResult llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>::callback_fn<mlir::MlirOptMain(llvm::raw_ostream&, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&)::$_0>(long, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12
    llvm#27 0x55e297b1cffe in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12
    llvm#28 0x55e297b1cffe in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef)::$_0::operator()(llvm::StringRef) const mlir/lib/Support/ToolUtilities.cpp:86:16
    llvm#29 0x55e297b1c9c5 in interleave<const llvm::StringRef *, (lambda at mlir/lib/Support/ToolUtilities.cpp:79:23), (lambda at llvm/include/llvm/ADT/STLExtras.h:2147:49), void> llvm/include/llvm/ADT/STLExtras.h:2125:3
    llvm#30 0x55e297b1c9c5 in interleave<llvm::SmallVector<llvm::StringRef, 8U>, (lambda at mlir/lib/Support/ToolUtilities.cpp:79:23), llvm::raw_ostream, llvm::StringRef> llvm/include/llvm/ADT/STLExtras.h:2147:3
    llvm#31 0x55e297b1c9c5 in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef) mlir/lib/Support/ToolUtilities.cpp:89:3
    llvm#32 0x55e291eb0cf0 in mlir::MlirOptMain(llvm::raw_ostream&, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:551:10
    llvm#33 0x55e291eb115c in mlir::MlirOptMain(int, char**, llvm::StringRef, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:589:14
    llvm#34 0x55e291eb15f8 in mlir::MlirOptMain(int, char**, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:605:10
    llvm#35 0x55e29130d1be in main mlir/tools/mlir-opt/mlir-opt.cpp:311:33
    llvm#36 0x7fbcf3fff3d3 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x613d3) (BuildId: 9a996398ce14a94560b0c642eb4f6e94)
    llvm#37 0x55e2912365a9 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120

0x502000006cd8 is located 8 bytes inside of 16-byte region [0x502000006cd0,0x502000006ce0)
freed by thread T0 here:
    #0 0x55e29130b7e2 in operator delete(void*, unsigned long) compiler-rt/lib/asan/asan_new_delete.cpp:155:3
    llvm#1 0x55e2979eb657 in __libcpp_operator_delete<void *, unsigned long>
    llvm#2 0x55e2979eb657 in __do_deallocate_handle_size<>
    llvm#3 0x55e2979eb657 in __libcpp_deallocate
    llvm#4 0x55e2979eb657 in deallocate
    llvm#5 0x55e2979eb657 in deallocate
    llvm#6 0x55e2979eb657 in operator()
    llvm#7 0x55e2979eb657 in ~vector
    llvm#8 0x55e2979eb657 in mlir::Block::~Block() mlir/lib/IR/Block.cpp:24:1
    llvm#9 0x55e2979ebc17 in deleteNode llvm/include/llvm/ADT/ilist.h:42:39
    llvm#10 0x55e2979ebc17 in erase llvm/include/llvm/ADT/ilist.h:205:5
    llvm#11 0x55e2979ebc17 in erase llvm/include/llvm/ADT/ilist.h:209:39
    llvm#12 0x55e2979ebc17 in mlir::Block::erase() mlir/lib/IR/Block.cpp:67:28
    llvm#13 0x55e297aef978 in mlir::RewriterBase::eraseBlock(mlir::Block*) mlir/lib/IR/PatternMatch.cpp:245:10
    llvm#14 0x55e297af0563 in mlir::RewriterBase::inlineBlockBefore(mlir::Block*, mlir::Block*, llvm::ilist_iterator<llvm::ilist_detail::node_options<mlir::Operation, false, false, void, false, void>, false, false>, mlir::ValueRange) mlir/lib/IR/PatternMatch.cpp:331:3
    llvm#15 0x55e297af06d8 in mlir::RewriterBase::mergeBlocks(mlir::Block*, mlir::Block*, mlir::ValueRange) mlir/lib/IR/PatternMatch.cpp:341:3
    llvm#16 0x55e297036608 in mlir::scf::ForOp::replaceWithAdditionalYields(mlir::RewriterBase&, mlir::ValueRange, bool, std::__u::function<llvm::SmallVector<mlir::Value, 6u> (mlir::OpBuilder&, mlir::Location, llvm::ArrayRef<mlir::BlockArgument>)> const&) mlir/lib/Dialect/SCF/IR/SCF.cpp:575:12
    llvm#17 0x55e2970673ca in mlir::detail::LoopLikeOpInterfaceInterfaceTraits::Model<mlir::scf::ForOp>::replaceWithAdditionalYields(mlir::detail::LoopLikeOpInterfaceInterfaceTraits::Concept const*, mlir::Operation*, mlir::RewriterBase&, mlir::ValueRange, bool, std::__u::function<llvm::SmallVector<mlir::Value, 6u> (mlir::OpBuilder&, mlir::Location, llvm::ArrayRef<mlir::BlockArgument>)> const&) blaze-out/k8-opt-asan/bin/mlir/include/mlir/Interfaces/LoopLikeInterface.h.inc:658:56
    llvm#18 0x55e2978d5feb in replaceWithAdditionalYields blaze-out/k8-opt-asan/bin/mlir/include/mlir/Interfaces/LoopLikeInterface.cpp.inc:105:14
    llvm#19 0x55e2978d5feb in mlir::createFused(mlir::LoopLikeOpInterface, mlir::LoopLikeOpInterface, mlir::RewriterBase&, std::__u::function<llvm::SmallVector<mlir::Value, 6u> (mlir::OpBuilder&, mlir::Location, llvm::ArrayRef<mlir::BlockArgument>)>, llvm::function_ref<void (mlir::RewriterBase&, mlir::LoopLikeOpInterface, mlir::LoopLikeOpInterface&, mlir::IRMapping)>) mlir/lib/Interfaces/LoopLikeInterface.cpp:135:14
    llvm#20 0x55e2952a614b in mlir::fuseIndependentSiblingForLoops(mlir::scf::ForOp, mlir::scf::ForOp, mlir::RewriterBase&) mlir/lib/Dialect/SCF/Utils/Utils.cpp:1398:43
    llvm#21 0x55e291480c6f in mlir::transform::LoopFuseSiblingOp::apply(mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) mlir/lib/Dialect/SCF/TransformOps/SCFTransformOps.cpp:482:17
    llvm#22 0x55e29149ed5e in mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Model<mlir::transform::LoopFuseSiblingOp>::apply(mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Concept const*, mlir::Operation*, mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.h.inc:477:56
    llvm#23 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14
    llvm#24 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48
    llvm#25 0x55e294646a8d in applySequenceBlock(mlir::Block&, mlir::transform::FailurePropagationMode, mlir::transform::TransformState&, mlir::transform::TransformResults&) mlir/lib/Dialect/Transform/IR/TransformOps.cpp:1788:15
    llvm#26 0x55e29464f927 in mlir::transform::NamedSequenceOp::apply(mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) mlir/lib/Dialect/Transform/IR/TransformOps.cpp:2155:10
    llvm#27 0x55e2945d28ee in mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Model<mlir::transform::NamedSequenceOp>::apply(mlir::transform::detail::TransformOpInterfaceInterfaceTraits::Concept const*, mlir::Operation*, mlir::transform::TransformRewriter&, mlir::transform::TransformResults&, mlir::transform::TransformState&) blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.h.inc:477:56
    llvm#28 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14
    llvm#29 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48
    llvm#30 0x55e2974a5fe2 in mlir::transform::applyTransforms(mlir::Operation*, mlir::transform::TransformOpInterface, mlir::RaggedArray<llvm::PointerUnion<mlir::Operation*, mlir::Attribute, mlir::Value>> const&, mlir::transform::TransformOptions const&, bool) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:2016:16
    llvm#31 0x55e2945888d7 in mlir::transform::applyTransformNamedSequence(mlir::RaggedArray<llvm::PointerUnion<mlir::Operation*, mlir::Attribute, mlir::Value>>, mlir::transform::TransformOpInterface, mlir::ModuleOp, mlir::transform::TransformOptions const&) mlir/lib/Dialect/Transform/Transforms/TransformInterpreterUtils.cpp:234:10
    llvm#32 0x55e294582446 in (anonymous namespace)::InterpreterPass::runOnOperation() mlir/lib/Dialect/Transform/Transforms/InterpreterPass.cpp:147:16
    llvm#33 0x55e2978e93c6 in operator() mlir/lib/Pass/Pass.cpp:527:17
    llvm#34 0x55e2978e93c6 in void llvm::function_ref<void ()>::callback_fn<mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int)::$_1>(long) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12
    llvm#35 0x55e2978e207a in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12
    llvm#36 0x55e2978e207a in executeAction<mlir::PassExecutionAction, mlir::Pass &> mlir/include/mlir/IR/MLIRContext.h:275:7
    llvm#37 0x55e2978e207a in mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int) mlir/lib/Pass/Pass.cpp:521:21
    llvm#38 0x55e2978e5fbf in runPipeline mlir/lib/Pass/Pass.cpp:593:16
    llvm#39 0x55e2978e5fbf in mlir::PassManager::runPasses(mlir::Operation*, mlir::AnalysisManager) mlir/lib/Pass/Pass.cpp:904:10
    llvm#40 0x55e2978e5b65 in mlir::PassManager::run(mlir::Operation*) mlir/lib/Pass/Pass.cpp:884:60
    llvm#41 0x55e291ebb460 in performActions(llvm::raw_ostream&, std::__u::shared_ptr<llvm::SourceMgr> const&, mlir::MLIRContext*, mlir::MlirOptMainConfig const&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:408:17
    llvm#42 0x55e291ebabd9 in processBuffer mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:481:9
    llvm#43 0x55e291ebabd9 in operator() mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:548:12
    llvm#44 0x55e291ebabd9 in llvm::LogicalResult llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>::callback_fn<mlir::MlirOptMain(llvm::raw_ostream&, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&)::$_0>(long, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12
    llvm#45 0x55e297b1cffe in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12
    llvm#46 0x55e297b1cffe in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef)::$_0::operator()(llvm::StringRef) const mlir/lib/Support/ToolUtilities.cpp:86:16
    llvm#47 0x55e297b1c9c5 in interleave<const llvm::StringRef *, (lambda at mlir/lib/Support/ToolUtilities.cpp:79:23), (lambda at llvm/include/llvm/ADT/STLExtras.h:2147:49), void> llvm/include/llvm/ADT/STLExtras.h:2125:3
    llvm#48 0x55e297b1c9c5 in interleave<llvm::SmallVector<llvm::StringRef, 8U>, (lambda at mlir/lib/Support/ToolUtilities.cpp:79:23), llvm::raw_ostream, llvm::StringRef> llvm/include/llvm/ADT/STLExtras.h:2147:3
    llvm#49 0x55e297b1c9c5 in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef) mlir/lib/Support/ToolUtilities.cpp:89:3
    llvm#50 0x55e291eb0cf0 in mlir::MlirOptMain(llvm::raw_ostream&, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:551:10
    llvm#51 0x55e291eb115c in mlir::MlirOptMain(int, char**, llvm::StringRef, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:589:14

previously allocated by thread T0 here:
    #0 0x55e29130ab5d in operator new(unsigned long) compiler-rt/lib/asan/asan_new_delete.cpp:86:3
    llvm#1 0x55e2979ed5d4 in __libcpp_operator_new<unsigned long>
    llvm#2 0x55e2979ed5d4 in __libcpp_allocate
    llvm#3 0x55e2979ed5d4 in allocate
    llvm#4 0x55e2979ed5d4 in __allocate_at_least<std::__u::allocator<mlir::BlockArgument> >
    llvm#5 0x55e2979ed5d4 in __split_buffer
    llvm#6 0x55e2979ed5d4 in mlir::BlockArgument* std::__u::vector<mlir::BlockArgument, std::__u::allocator<mlir::BlockArgument>>::__push_back_slow_path<mlir::BlockArgument const&>(mlir::BlockArgument const&)
    llvm#7 0x55e2979ec0f2 in push_back
    llvm#8 0x55e2979ec0f2 in mlir::Block::addArgument(mlir::Type, mlir::Location) mlir/lib/IR/Block.cpp:154:13
    llvm#9 0x55e29796e457 in parseRegionBody mlir/lib/AsmParser/Parser.cpp:2172:34
    llvm#10 0x55e29796e457 in (anonymous namespace)::OperationParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:2121:7
    llvm#11 0x55e29796b25e in (anonymous namespace)::CustomOpAsmParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:1785:16
    llvm#12 0x55e297035742 in mlir::scf::ForOp::parse(mlir::OpAsmParser&, mlir::OperationState&) mlir/lib/Dialect/SCF/IR/SCF.cpp:521:14
    llvm#13 0x55e291322c18 in llvm::ParseResult llvm::detail::UniqueFunctionBase<llvm::ParseResult, mlir::OpAsmParser&, mlir::OperationState&>::CallImpl<llvm::ParseResult (*)(mlir::OpAsmParser&, mlir::OperationState&)>(void*, mlir::OpAsmParser&, mlir::OperationState&) llvm/include/llvm/ADT/FunctionExtras.h:220:12
    llvm#14 0x55e29795bea3 in operator() llvm/include/llvm/ADT/FunctionExtras.h:384:12
    llvm#15 0x55e29795bea3 in callback_fn<llvm::unique_function<llvm::ParseResult (mlir::OpAsmParser &, mlir::OperationState &)> > llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12
    llvm#16 0x55e29795bea3 in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12
    llvm#17 0x55e29795bea3 in parseOperation mlir/lib/AsmParser/Parser.cpp:1521:9
    llvm#18 0x55e29795bea3 in parseCustomOperation mlir/lib/AsmParser/Parser.cpp:2017:19
    llvm#19 0x55e29795bea3 in (anonymous namespace)::OperationParser::parseOperation() mlir/lib/AsmParser/Parser.cpp:1174:10
    llvm#20 0x55e297971d20 in parseBlockBody mlir/lib/AsmParser/Parser.cpp:2296:9
    llvm#21 0x55e297971d20 in (anonymous namespace)::OperationParser::parseBlock(mlir::Block*&) mlir/lib/AsmParser/Parser.cpp:2226:12
    llvm#22 0x55e29796e4f5 in parseRegionBody mlir/lib/AsmParser/Parser.cpp:2184:7
    llvm#23 0x55e29796e4f5 in (anonymous namespace)::OperationParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:2121:7
    llvm#24 0x55e29796b25e in (anonymous namespace)::CustomOpAsmParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:1785:16
    llvm#25 0x55e29796b2cf in (anonymous namespace)::CustomOpAsmParser::parseOptionalRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:1796:12
    llvm#26 0x55e2978d89ff in mlir::function_interface_impl::parseFunctionOp(mlir::OpAsmParser&, mlir::OperationState&, bool, mlir::StringAttr, llvm::function_ref<mlir::Type (mlir::Builder&, llvm::ArrayRef<mlir::Type>, llvm::ArrayRef<mlir::Type>, mlir::function_interface_impl::VariadicFlag, std::__u::basic_string<char, std::__u::char_traits<char>, std::__u::allocator<char>>&)>, mlir::StringAttr, mlir::StringAttr) mlir/lib/Interfaces/FunctionImplementation.cpp:232:14
    llvm#27 0x55e2969ba41d in mlir::func::FuncOp::parse(mlir::OpAsmParser&, mlir::OperationState&) mlir/lib/Dialect/Func/IR/FuncOps.cpp:203:10
    llvm#28 0x55e291322c18 in llvm::ParseResult llvm::detail::UniqueFunctionBase<llvm::ParseResult, mlir::OpAsmParser&, mlir::OperationState&>::CallImpl<llvm::ParseResult (*)(mlir::OpAsmParser&, mlir::OperationState&)>(void*, mlir::OpAsmParser&, mlir::OperationState&) llvm/include/llvm/ADT/FunctionExtras.h:220:12
    llvm#29 0x55e29795bea3 in operator() llvm/include/llvm/ADT/FunctionExtras.h:384:12
    llvm#30 0x55e29795bea3 in callback_fn<llvm::unique_function<llvm::ParseResult (mlir::OpAsmParser &, mlir::OperationState &)> > llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12
    llvm#31 0x55e29795bea3 in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12
    llvm#32 0x55e29795bea3 in parseOperation mlir/lib/AsmParser/Parser.cpp:1521:9
    llvm#33 0x55e29795bea3 in parseCustomOperation mlir/lib/AsmParser/Parser.cpp:2017:19
    llvm#34 0x55e29795bea3 in (anonymous namespace)::OperationParser::parseOperation() mlir/lib/AsmParser/Parser.cpp:1174:10
    llvm#35 0x55e297959b78 in parse mlir/lib/AsmParser/Parser.cpp:2725:20
    llvm#36 0x55e297959b78 in mlir::parseAsmSourceFile(llvm::SourceMgr const&, mlir::Block*, mlir::ParserConfig const&, mlir::AsmParserState*, mlir::AsmParserCodeCompleteContext*) mlir/lib/AsmParser/Parser.cpp:2785:41
    llvm#37 0x55e29790d5c2 in mlir::parseSourceFile(std::__u::shared_ptr<llvm::SourceMgr> const&, mlir::Block*, mlir::ParserConfig const&, mlir::LocationAttr*) mlir/lib/Parser/Parser.cpp:46:10
    llvm#38 0x55e291ebbfe2 in parseSourceFile<mlir::ModuleOp, const std::__u::shared_ptr<llvm::SourceMgr> &> mlir/include/mlir/Parser/Parser.h:159:14
    llvm#39 0x55e291ebbfe2 in parseSourceFile<mlir::ModuleOp> mlir/include/mlir/Parser/Parser.h:189:10
    llvm#40 0x55e291ebbfe2 in mlir::parseSourceFileForTool(std::__u::shared_ptr<llvm::SourceMgr> const&, mlir::ParserConfig const&, bool) mlir/include/mlir/Tools/ParseUtilities.h:31:12
    llvm#41 0x55e291ebb263 in performActions(llvm::raw_ostream&, std::__u::shared_ptr<llvm::SourceMgr> const&, mlir::MLIRContext*, mlir::MlirOptMainConfig const&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:383:33
    llvm#42 0x55e291ebabd9 in processBuffer mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:481:9
    llvm#43 0x55e291ebabd9 in operator() mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:548:12
    llvm#44 0x55e291ebabd9 in llvm::LogicalResult llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>::callback_fn<mlir::MlirOptMain(llvm::raw_ostream&, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&)::$_0>(long, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12
    llvm#45 0x55e297b1cffe in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12
    llvm#46 0x55e297b1cffe in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef)::$_0::operator()(llvm::StringRef) const mlir/lib/Support/ToolUtilities.cpp:86:16
    llvm#47 0x55e297b1c9c5 in interleave<const llvm::StringRef *, (lambda at mlir/lib/Support/ToolUtilities.cpp:79:23), (lambda at llvm/include/llvm/ADT/STLExtras.h:2147:49), void> llvm/include/llvm/ADT/STLExtras.h:2125:3
    llvm#48 0x55e297b1c9c5 in interleave<llvm::SmallVector<llvm::StringRef, 8U>, (lambda at mlir/lib/Support/ToolUtilities.cpp:79:23), llvm::raw_ostream, llvm::StringRef> llvm/include/llvm/ADT/STLExtras.h:2147:3
    llvm#49 0x55e297b1c9c5 in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef) mlir/lib/Support/ToolUtilities.cpp:89:3
    llvm#50 0x55e291eb0cf0 in mlir::MlirOptMain(llvm::raw_ostream&, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:551:10
    llvm#51 0x55e291eb115c in mlir::MlirOptMain(int, char**, llvm::StringRef, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:589:14
    llvm#52 0x55e291eb15f8 in mlir::MlirOptMain(int, char**, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:605:10
    llvm#53 0x55e29130d1be in main mlir/tools/mlir-opt/mlir-opt.cpp:311:33
    llvm#54 0x7fbcf3fff3d3 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x613d3) (BuildId: 9a996398ce14a94560b0c642eb4f6e94)
    llvm#55 0x55e2912365a9 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120

SUMMARY: AddressSanitizer: heap-use-after-free mlir/include/mlir/IR/IRMapping.h:40:11 in map<llvm::MutableArrayRef<mlir::BlockArgument> &, llvm::MutableArrayRef<mlir::BlockArgument>, nullptr>
Shadow bytes around the buggy address:
  0x502000006a00: fa fa 00 fa fa fa 00 00 fa fa 00 fa fa fa 00 fa
  0x502000006a80: fa fa 00 fa fa fa 00 00 fa fa 00 00 fa fa 00 00
  0x502000006b00: fa fa 00 00 fa fa 00 00 fa fa 00 fa fa fa 00 fa
  0x502000006b80: fa fa 00 fa fa fa 00 fa fa fa 00 00 fa fa 00 00
  0x502000006c00: fa fa 00 00 fa fa 00 00 fa fa 00 00 fa fa fd fa
=>0x502000006c80: fa fa fd fa fa fa fd fd fa fa fd[fd]fa fa fd fd
  0x502000006d00: fa fa 00 fa fa fa 00 fa fa fa 00 fa fa fa 00 fa
  0x502000006d80: fa fa 00 fa fa fa 00 fa fa fa 00 fa fa fa 00 fa
  0x502000006e00: fa fa 00 fa fa fa 00 fa fa fa 00 00 fa fa 00 fa
  0x502000006e80: fa fa 00 fa fa fa 00 00 fa fa 00 fa fa fa 00 fa
  0x502000006f00: fa fa 00 fa fa fa 00 fa fa fa 00 fa fa fa 00 fa
Shadow byte legend (one shadow byte represents 8 application bytes):
  Addressable:           00
  Partially addressable: 01 02 03 04 05 06 07
  Heap left redzone:       fa
  Freed heap region:       fd
  Stack left redzone:      f1
  Stack mid redzone:       f2
  Stack right redzone:     f3
  Stack after return:      f5
  Stack use after scope:   f8
  Global redzone:          f9
  Global init order:       f6
  Poisoned by user:        f7
  Container overflow:      fc
  Array cookie:            ac
  Intra object redzone:    bb
  ASan internal:           fe
  Left alloca redzone:     ca
  Right alloca redzone:    cb
==4320==ABORTING
  • Loading branch information
@pifon2a @kbluck
pifon2a authored and kbluck committed Jul 6, 2024
1 parent 92afd6c commit f5c2456
Show file tree
Hide file tree
Showing 9 changed files with 283 additions and 646 deletions.
3 changes: 1 addition & 2 deletions mlir/include/mlir/Dialect/SCF/IR/SCFOps.td
View file
Original file line number Diff line number Diff line change
Expand Up @@ -303,8 +303,7 @@ def ForallOp : SCF_Op<"forall", [
DeclareOpInterfaceMethods<LoopLikeOpInterface,
["getInitsMutable", "getRegionIterArgs", "getLoopInductionVars",
"getLoopLowerBounds", "getLoopUpperBounds", "getLoopSteps",
"replaceWithAdditionalYields", "promoteIfSingleIteration",
"yieldTiledValuesAndReplace"]>,
"promoteIfSingleIteration", "yieldTiledValuesAndReplace"]>,
RecursiveMemoryEffects,
SingleBlockImplicitTerminator<"scf::InParallelOp">,
DeclareOpInterfaceMethods<RegionBranchOpInterface>,
Expand Down
20 changes: 0 additions & 20 deletions mlir/include/mlir/Dialect/SCF/Utils/Utils.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -181,16 +181,6 @@ Loops tilePerfectlyNested(scf::ForOp rootForOp, ArrayRef<Value> sizes);
void getPerfectlyNestedLoops(SmallVectorImpl<scf::ForOp> &nestedLoops,
scf::ForOp root);

//===----------------------------------------------------------------------===//
// Fusion related helpers
//===----------------------------------------------------------------------===//

/// Check structural compatibility between two loops such as iteration space
/// and dominance.
bool checkFusionStructuralLegality(LoopLikeOpInterface target,
LoopLikeOpInterface source,
Diagnostic &diag);

/// Given two scf.forall loops, `target` and `source`, fuses `target` into
/// `source`. Assumes that the given loops are siblings and are independent of
/// each other.
Expand All @@ -212,16 +202,6 @@ scf::ForallOp fuseIndependentSiblingForallLoops(scf::ForallOp target,
scf::ForOp fuseIndependentSiblingForLoops(scf::ForOp target, scf::ForOp source,
RewriterBase &rewriter);

/// Given two scf.parallel loops, `target` and `source`, fuses `target` into
/// `source`. Assumes that the given loops are siblings and are independent of
/// each other.
///
/// This function does not perform any legality checks and simply fuses the
/// loops. The caller is responsible for ensuring that the loops are legal to
/// fuse.
scf::ParallelOp fuseIndependentSiblingParallelLoops(scf::ParallelOp target,
scf::ParallelOp source,
RewriterBase &rewriter);
} // namespace mlir

#endif // MLIR_DIALECT_SCF_UTILS_UTILS_H_
20 changes: 0 additions & 20 deletions mlir/include/mlir/Interfaces/LoopLikeInterface.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -90,24 +90,4 @@ struct JamBlockGatherer {
/// Include the generated interface declarations.
#include "mlir/Interfaces/LoopLikeInterface.h.inc"

namespace mlir {
/// A function that rewrites `target`'s terminator as a teminator obtained by
/// fusing `source` into `target`.
using FuseTerminatorFn =
function_ref<void(RewriterBase &rewriter, LoopLikeOpInterface source,
LoopLikeOpInterface &target, IRMapping mapping)>;

/// Returns a fused `LoopLikeOpInterface` created by fusing `source` to
/// `target`. The `NewYieldValuesFn` callback is used to pass to the
/// `replaceWithAdditionalYields` interface method to replace the loop with a
/// new loop with (possibly) additional yields, while the `FuseTerminatorFn`
/// callback is repsonsible for updating the fused loop terminator.
LoopLikeOpInterface createFused(LoopLikeOpInterface target,
LoopLikeOpInterface source,
RewriterBase &rewriter,
NewYieldValuesFn newYieldValuesFn,
FuseTerminatorFn fuseTerminatorFn);

} // namespace mlir

#endif // MLIR_INTERFACES_LOOPLIKEINTERFACE_H_
38 changes: 0 additions & 38 deletions mlir/lib/Dialect/SCF/IR/SCF.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -618,44 +618,6 @@ void ForOp::getSuccessorRegions(RegionBranchPoint point,

SmallVector<Region *> ForallOp::getLoopRegions() { return {&getRegion()}; }

FailureOr<LoopLikeOpInterface> ForallOp::replaceWithAdditionalYields(
RewriterBase &rewriter, ValueRange newInitOperands,
bool replaceInitOperandUsesInLoop,
const NewYieldValuesFn &newYieldValuesFn) {
// Create a new loop before the existing one, with the extra operands.
OpBuilder::InsertionGuard g(rewriter);
rewriter.setInsertionPoint(getOperation());
SmallVector<Value> inits(getOutputs());
llvm::append_range(inits, newInitOperands);
scf::ForallOp newLoop = rewriter.create<scf::ForallOp>(
getLoc(), getMixedLowerBound(), getMixedUpperBound(), getMixedStep(),
inits, getMapping(),
/*bodyBuilderFn =*/[](OpBuilder &, Location, ValueRange) {});

// Move the loop body to the new op.
rewriter.mergeBlocks(getBody(), newLoop.getBody(),
newLoop.getBody()->getArguments().take_front(
getBody()->getNumArguments()));

if (replaceInitOperandUsesInLoop) {
// Replace all uses of `newInitOperands` with the corresponding basic block
// arguments.
for (auto &&[newOperand, oldOperand] :
llvm::zip(newInitOperands, newLoop.getBody()->getArguments().take_back(
newInitOperands.size()))) {
rewriter.replaceUsesWithIf(newOperand, oldOperand, [&](OpOperand &use) {
Operation *user = use.getOwner();
return newLoop->isProperAncestor(user);
});
}
}

// Replace the old loop.
rewriter.replaceOp(getOperation(),
newLoop->getResults().take_front(getNumResults()));
return cast<LoopLikeOpInterface>(newLoop.getOperation());
}

/// Promotes the loop body of a forallOp to its containing block if it can be
/// determined that the loop has a single iteration.
LogicalResult scf::ForallOp::promoteIfSingleIteration(RewriterBase &rewriter) {
Expand Down
140 changes: 119 additions & 21 deletions mlir/lib/Dialect/SCF/TransformOps/SCFTransformOps.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -261,10 +261,8 @@ loopScheduling(scf::ForOp forOp,
return 1;
};

std::optional<int64_t> ubConstant =
getConstantIntValue(forOp.getUpperBound());
std::optional<int64_t> lbConstant =
getConstantIntValue(forOp.getLowerBound());
std::optional<int64_t> ubConstant = getConstantIntValue(forOp.getUpperBound());
std::optional<int64_t> lbConstant = getConstantIntValue(forOp.getLowerBound());
DenseMap<Operation *, unsigned> opCycles;
std::map<unsigned, std::vector<Operation *>> wrappedSchedule;
for (Operation &op : forOp.getBody()->getOperations()) {
Expand Down Expand Up @@ -449,6 +447,113 @@ void transform::TakeAssumedBranchOp::getEffects(
// LoopFuseSiblingOp
//===----------------------------------------------------------------------===//

/// Check if `target` and `source` are siblings, in the context that `target`
/// is being fused into `source`.
///
/// This is a simple check that just checks if both operations are in the same
/// block and some checks to ensure that the fused IR does not violate
/// dominance.
static DiagnosedSilenceableFailure isOpSibling(Operation *target,
Operation *source) {
// Check if both operations are same.
if (target == source)
return emitSilenceableFailure(source)
<< "target and source need to be different loops";

// Check if both operations are in the same block.
if (target->getBlock() != source->getBlock())
return emitSilenceableFailure(source)
<< "target and source are not in the same block";

// Check if fusion will violate dominance.
DominanceInfo domInfo(source);
if (target->isBeforeInBlock(source)) {
// Since `target` is before `source`, all users of results of `target`
// need to be dominated by `source`.
for (Operation *user : target->getUsers()) {
if (!domInfo.properlyDominates(source, user, /*enclosingOpOk=*/false)) {
return emitSilenceableFailure(target)
<< "user of results of target should be properly dominated by "
"source";
}
}
} else {
// Since `target` is after `source`, all values used by `target` need
// to dominate `source`.

// Check if operands of `target` are dominated by `source`.
for (Value operand : target->getOperands()) {
Operation *operandOp = operand.getDefiningOp();
// Operands without defining operations are block arguments. When `target`
// and `source` occur in the same block, these operands dominate `source`.
if (!operandOp)
continue;

// Operand's defining operation should properly dominate `source`.
if (!domInfo.properlyDominates(operandOp, source,
/*enclosingOpOk=*/false))
return emitSilenceableFailure(target)
<< "operands of target should be properly dominated by source";
}

// Check if values used by `target` are dominated by `source`.
bool failed = false;
OpOperand *failedValue = nullptr;
visitUsedValuesDefinedAbove(target->getRegions(), [&](OpOperand *operand) {
Operation *operandOp = operand->get().getDefiningOp();
if (operandOp && !domInfo.properlyDominates(operandOp, source,
/*enclosingOpOk=*/false)) {
// `operand` is not an argument of an enclosing block and the defining
// op of `operand` is outside `target` but does not dominate `source`.
failed = true;
failedValue = operand;
}
});

if (failed)
return emitSilenceableFailure(failedValue->getOwner())
<< "values used inside regions of target should be properly "
"dominated by source";
}

return DiagnosedSilenceableFailure::success();
}

/// Check if `target` scf.forall can be fused into `source` scf.forall.
///
/// This simply checks if both loops have the same bounds, steps and mapping.
/// No attempt is made at checking that the side effects of `target` and
/// `source` are independent of each other.
static bool isForallWithIdenticalConfiguration(Operation *target,
Operation *source) {
auto targetOp = dyn_cast<scf::ForallOp>(target);
auto sourceOp = dyn_cast<scf::ForallOp>(source);
if (!targetOp || !sourceOp)
return false;

return targetOp.getMixedLowerBound() == sourceOp.getMixedLowerBound() &&
targetOp.getMixedUpperBound() == sourceOp.getMixedUpperBound() &&
targetOp.getMixedStep() == sourceOp.getMixedStep() &&
targetOp.getMapping() == sourceOp.getMapping();
}

/// Check if `target` scf.for can be fused into `source` scf.for.
///
/// This simply checks if both loops have the same bounds and steps. No attempt
/// is made at checking that the side effects of `target` and `source` are
/// independent of each other.
static bool isForWithIdenticalConfiguration(Operation *target,
Operation *source) {
auto targetOp = dyn_cast<scf::ForOp>(target);
auto sourceOp = dyn_cast<scf::ForOp>(source);
if (!targetOp || !sourceOp)
return false;

return targetOp.getLowerBound() == sourceOp.getLowerBound() &&
targetOp.getUpperBound() == sourceOp.getUpperBound() &&
targetOp.getStep() == sourceOp.getStep();
}

DiagnosedSilenceableFailure
transform::LoopFuseSiblingOp::apply(transform::TransformRewriter &rewriter,
transform::TransformResults &results,
Expand All @@ -464,32 +569,25 @@ transform::LoopFuseSiblingOp::apply(transform::TransformRewriter &rewriter,
<< "source handle (got " << llvm::range_size(sourceOps) << ")";
}

auto target = dyn_cast<LoopLikeOpInterface>(*targetOps.begin());
auto source = dyn_cast<LoopLikeOpInterface>(*sourceOps.begin());
if (!target || !source)
return emitSilenceableFailure(target->getLoc())
<< "target or source is not a loop op";
Operation *target = *targetOps.begin();
Operation *source = *sourceOps.begin();

// Check if loops can be fused
Diagnostic diag(target.getLoc(), DiagnosticSeverity::Error);
if (!mlir::checkFusionStructuralLegality(target, source, diag))
return DiagnosedSilenceableFailure::silenceableFailure(std::move(diag));
// Check if the target and source are siblings.
DiagnosedSilenceableFailure diag = isOpSibling(target, source);
if (!diag.succeeded())
return diag;

Operation *fusedLoop;
// TODO: Support fusion for loop-like ops besides scf.for, scf.forall
// and scf.parallel.
if (isa<scf::ForOp>(target) && isa<scf::ForOp>(source)) {
/// TODO: Support fusion for loop-like ops besides scf.for and scf.forall.
if (isForWithIdenticalConfiguration(target, source)) {
fusedLoop = fuseIndependentSiblingForLoops(
cast<scf::ForOp>(target), cast<scf::ForOp>(source), rewriter);
} else if (isa<scf::ForallOp>(target) && isa<scf::ForallOp>(source)) {
} else if (isForallWithIdenticalConfiguration(target, source)) {
fusedLoop = fuseIndependentSiblingForallLoops(
cast<scf::ForallOp>(target), cast<scf::ForallOp>(source), rewriter);
} else if (isa<scf::ParallelOp>(target) && isa<scf::ParallelOp>(source)) {
fusedLoop = fuseIndependentSiblingParallelLoops(
cast<scf::ParallelOp>(target), cast<scf::ParallelOp>(source), rewriter);
} else
return emitSilenceableFailure(target->getLoc())
<< "unsupported loop type for fusion";
<< "operations cannot be fused";

assert(fusedLoop && "failed to fuse operations");

Expand Down
80 changes: 74 additions & 6 deletions mlir/lib/Dialect/SCF/Transforms/ParallelLoopFusion.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,6 @@
#include "mlir/Dialect/MemRef/IR/MemRef.h"
#include "mlir/Dialect/SCF/IR/SCF.h"
#include "mlir/Dialect/SCF/Transforms/Transforms.h"
#include "mlir/Dialect/SCF/Utils/Utils.h"
#include "mlir/IR/Builders.h"
#include "mlir/IR/IRMapping.h"
#include "mlir/IR/OpDefinition.h"
Expand All @@ -38,6 +37,24 @@ static bool hasNestedParallelOp(ParallelOp ploop) {
return walkResult.wasInterrupted();
}

/// Verify equal iteration spaces.
static bool equalIterationSpaces(ParallelOp firstPloop,
ParallelOp secondPloop) {
if (firstPloop.getNumLoops() != secondPloop.getNumLoops())
return false;

auto matchOperands = [&](const OperandRange &lhs,
const OperandRange &rhs) -> bool {
// TODO: Extend this to support aliases and equal constants.
return std::equal(lhs.begin(), lhs.end(), rhs.begin());
};
return matchOperands(firstPloop.getLowerBound(),
secondPloop.getLowerBound()) &&
matchOperands(firstPloop.getUpperBound(),
secondPloop.getUpperBound()) &&
matchOperands(firstPloop.getStep(), secondPloop.getStep());
}

/// Checks if the parallel loops have mixed access to the same buffers. Returns
/// `true` if the first parallel loop writes to the same indices that the second
/// loop reads.
Expand Down Expand Up @@ -136,10 +153,9 @@ verifyDependencies(ParallelOp firstPloop, ParallelOp secondPloop,
static bool isFusionLegal(ParallelOp firstPloop, ParallelOp secondPloop,
const IRMapping &firstToSecondPloopIndices,
llvm::function_ref<bool(Value, Value)> mayAlias) {
Diagnostic diag(firstPloop.getLoc(), DiagnosticSeverity::Remark);
return !hasNestedParallelOp(firstPloop) &&
!hasNestedParallelOp(secondPloop) &&
checkFusionStructuralLegality(firstPloop, secondPloop, diag) &&
equalIterationSpaces(firstPloop, secondPloop) &&
succeeded(verifyDependencies(firstPloop, secondPloop,
firstToSecondPloopIndices, mayAlias));
}
Expand All @@ -158,9 +174,61 @@ static void fuseIfLegal(ParallelOp firstPloop, ParallelOp &secondPloop,
mayAlias))
return;

IRRewriter rewriter(builder);
secondPloop = mlir::fuseIndependentSiblingParallelLoops(
firstPloop, secondPloop, rewriter);
DominanceInfo dom;
// We are fusing first loop into second, make sure there are no users of the
// first loop results between loops.
for (Operation *user : firstPloop->getUsers())
if (!dom.properlyDominates(secondPloop, user, /*enclosingOpOk*/ false))
return;

ValueRange inits1 = firstPloop.getInitVals();
ValueRange inits2 = secondPloop.getInitVals();

SmallVector<Value> newInitVars(inits1.begin(), inits1.end());
newInitVars.append(inits2.begin(), inits2.end());

IRRewriter b(builder);
b.setInsertionPoint(secondPloop);
auto newSecondPloop = b.create<ParallelOp>(
secondPloop.getLoc(), secondPloop.getLowerBound(),
secondPloop.getUpperBound(), secondPloop.getStep(), newInitVars);

Block *newBlock = newSecondPloop.getBody();
auto term1 = cast<ReduceOp>(block1->getTerminator());
auto term2 = cast<ReduceOp>(block2->getTerminator());

b.inlineBlockBefore(block2, newBlock, newBlock->begin(),
newBlock->getArguments());
b.inlineBlockBefore(block1, newBlock, newBlock->begin(),
newBlock->getArguments());

ValueRange results = newSecondPloop.getResults();
if (!results.empty()) {
b.setInsertionPointToEnd(newBlock);

ValueRange reduceArgs1 = term1.getOperands();
ValueRange reduceArgs2 = term2.getOperands();
SmallVector<Value> newReduceArgs(reduceArgs1.begin(), reduceArgs1.end());
newReduceArgs.append(reduceArgs2.begin(), reduceArgs2.end());

auto newReduceOp = b.create<scf::ReduceOp>(term2.getLoc(), newReduceArgs);

for (auto &&[i, reg] : llvm::enumerate(llvm::concat<Region>(
term1.getReductions(), term2.getReductions()))) {
Block &oldRedBlock = reg.front();
Block &newRedBlock = newReduceOp.getReductions()[i].front();
b.inlineBlockBefore(&oldRedBlock, &newRedBlock, newRedBlock.begin(),
newRedBlock.getArguments());
}

firstPloop.replaceAllUsesWith(results.take_front(inits1.size()));
secondPloop.replaceAllUsesWith(results.take_back(inits2.size()));
}
term1->erase();
term2->erase();
firstPloop.erase();
secondPloop.erase();
secondPloop = newSecondPloop;
}

void mlir::scf::naivelyFuseParallelOps(
Expand Down
Loading

0 comments on commit f5c2456

Please sign in to comment.