Closed
Conversation
DavidSpickett
pushed a commit
that referenced
this pull request
Feb 22, 2024
…lvm#80904)" This reverts commit b1ac052. This commit breaks coroutine splitting for non-swift calling convention functions. In this example: ```ll ; ModuleID = 'repro.ll' source_filename = "stdlib/test/runtime/test_llcl.mojo" target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" @0 = internal constant { i32, i32 } { i32 trunc (i64 sub (i64 ptrtoint (ptr @craSH to i64), i64 ptrtoint (ptr getelementptr inbounds ({ i32, i32 }, ptr @0, i32 0, i32 1) to i64)) to i32), i32 64 } define dso_local void @af_suspend_fn(ptr %0, i64 %1, ptr %2) #0 { ret void } define dso_local void @craSH(ptr %0) #0 { %2 = call token @llvm.coro.id.async(i32 64, i32 8, i32 0, ptr @0) %3 = call ptr @llvm.coro.begin(token %2, ptr null) %4 = getelementptr inbounds { ptr, { ptr, ptr }, i64, { ptr, i1 }, i64, i64 }, ptr poison, i32 0, i32 0 %5 = call ptr @llvm.coro.async.resume() store ptr %5, ptr %4, align 8 %6 = call { ptr, ptr, ptr } (i32, ptr, ptr, ...) @llvm.coro.suspend.async.sl_p0p0p0s(i32 0, ptr %5, ptr @ctxt_proj_fn, ptr @af_suspend_fn, ptr poison, i64 -1, ptr poison) ret void } define dso_local ptr @ctxt_proj_fn(ptr %0) #0 { ret ptr %0 } ; Function Attrs: nomerge nounwind declare { ptr, ptr, ptr } @llvm.coro.suspend.async.sl_p0p0p0s(i32, ptr, ptr, ...) #1 ; Function Attrs: nounwind declare token @llvm.coro.id.async(i32, i32, i32, ptr) #2 ; Function Attrs: nounwind declare ptr @llvm.coro.begin(token, ptr writeonly) #2 ; Function Attrs: nomerge nounwind declare ptr @llvm.coro.async.resume() #1 attributes #0 = { "target-features"="+adx,+aes,+avx,+avx2,+bmi,+bmi2,+clflushopt,+clwb,+clzero,+crc32,+cx16,+cx8,+f16c,+fma,+fsgsbase,+fxsr,+invpcid,+lzcnt,+mmx,+movbe,+mwaitx,+pclmul,+pku,+popcnt,+prfchw,+rdpid,+rdpru,+rdrnd,+rdseed,+sahf,+sha,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+sse4a,+ssse3,+vaes,+vpclmulqdq,+wbnoinvd,+x87,+xsave,+xsavec,+xsaveopt,+xsaves" } attributes #1 = { nomerge nounwind } attributes #2 = { nounwind } ``` This verifier crashes after the `coro-split` pass with ``` cannot guarantee tail call due to mismatched parameter counts musttail call void @af_suspend_fn(ptr poison, i64 -1, ptr poison) LLVM ERROR: Broken function PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace. Stack dump: 0. Program arguments: opt ../../../reduced.ll -O0 #0 0x00007f1d89645c0e __interceptor_backtrace.part.0 /build/gcc-11-XeT9lY/gcc-11-11.4.0/build/x86_64-linux-gnu/libsanitizer/asan/../../../../src/libsanitizer/sanitizer_common/sanitizer_common_interceptors.inc:4193:28 #1 0x0000556d94d254f7 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Support/Unix/Signals.inc:723:22 #2 0x0000556d94d19a2f llvm::sys::RunSignalHandlers() /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Support/Signals.cpp:105:20 #3 0x0000556d94d1aa42 SignalHandler(int) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Support/Unix/Signals.inc:371:36 #4 0x00007f1d88e42520 (/lib/x86_64-linux-gnu/libc.so.6+0x42520) #5 0x00007f1d88e969fc __pthread_kill_implementation ./nptl/pthread_kill.c:44:76 #6 0x00007f1d88e969fc __pthread_kill_internal ./nptl/pthread_kill.c:78:10 #7 0x00007f1d88e969fc pthread_kill ./nptl/pthread_kill.c:89:10 #8 0x00007f1d88e42476 gsignal ./signal/../sysdeps/posix/raise.c:27:6 #9 0x00007f1d88e287f3 abort ./stdlib/abort.c:81:7 #10 0x0000556d8944be01 std::vector<llvm::json::Value, std::allocator<llvm::json::Value>>::size() const /usr/include/c++/11/bits/stl_vector.h:919:40 #11 0x0000556d8944be01 bool std::operator==<llvm::json::Value, std::allocator<llvm::json::Value>>(std::vector<llvm::json::Value, std::allocator<llvm::json::Value>> const&, std::vector<llvm::json::Value, std::allocator<llvm::json::Value>> const&) /usr/include/c++/11/bits/stl_vector.h:1893:23 #12 0x0000556d8944be01 llvm::json::operator==(llvm::json::Array const&, llvm::json::Array const&) /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/Support/JSON.h:572:69 #13 0x0000556d8944be01 llvm::json::operator==(llvm::json::Value const&, llvm::json::Value const&) (.cold) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Support/JSON.cpp:204:28 #14 0x0000556d949ed2bd llvm::report_fatal_error(char const*, bool) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Support/ErrorHandling.cpp:82:70 #15 0x0000556d8e37e876 llvm::SmallVectorBase<unsigned int>::size() const /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/ADT/SmallVector.h:91:32 #16 0x0000556d8e37e876 llvm::SmallVectorTemplateCommon<llvm::DiagnosticInfoOptimizationBase::Argument, void>::end() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/ADT/SmallVector.h:282:41 #17 0x0000556d8e37e876 llvm::SmallVector<llvm::DiagnosticInfoOptimizationBase::Argument, 4u>::~SmallVector() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/ADT/SmallVector.h:1215:24 #18 0x0000556d8e37e876 llvm::DiagnosticInfoOptimizationBase::~DiagnosticInfoOptimizationBase() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/DiagnosticInfo.h:413:7 #19 0x0000556d8e37e876 llvm::DiagnosticInfoIROptimization::~DiagnosticInfoIROptimization() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/DiagnosticInfo.h:622:7 #20 0x0000556d8e37e876 llvm::OptimizationRemark::~OptimizationRemark() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/DiagnosticInfo.h:689:7 #21 0x0000556d8e37e876 operator() /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Transforms/Coroutines/CoroSplit.cpp:2213:14 #22 0x0000556d8e37e876 emit<llvm::CoroSplitPass::run(llvm::LazyCallGraph::SCC&, llvm::CGSCCAnalysisManager&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&)::<lambda()> > /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/Analysis/OptimizationRemarkEmitter.h:83:12 #23 0x0000556d8e37e876 llvm::CoroSplitPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Transforms/Coroutines/CoroSplit.cpp:2212:13 #24 0x0000556d8c36ecb1 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CoroSplitPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/PassManagerInternal.h:91:3 #25 0x0000556d91c1a84f llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Analysis/CGSCCPassManager.cpp:90:12 #26 0x0000556d8c3690d1 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/PassManagerInternal.h:91:3 #27 0x0000556d91c2162d llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Analysis/CGSCCPassManager.cpp:278:18 #28 0x0000556d8c369035 llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/PassManagerInternal.h:91:3 #29 0x0000556d9457abc5 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/PassManager.h:247:20 #30 0x0000556d8e30979e llvm::CoroConditionalWrapper::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/ubuntu/modular/third-party/llvm-project/llvm/lib/Transforms/Coroutines/CoroConditionalWrapper.cpp:19:74 #31 0x0000556d8c365755 llvm::detail::PassModel<llvm::Module, llvm::CoroConditionalWrapper, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/PassManagerInternal.h:91:3 #32 0x0000556d9457abc5 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/PassManager.h:247:20 #33 0x0000556d89818556 llvm::SmallPtrSetImplBase::isSmall() const /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:196:33 #34 0x0000556d89818556 llvm::SmallPtrSetImplBase::~SmallPtrSetImplBase() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:84:17 #35 0x0000556d89818556 llvm::SmallPtrSetImpl<llvm::AnalysisKey*>::~SmallPtrSetImpl() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:321:7 #36 0x0000556d89818556 llvm::SmallPtrSet<llvm::AnalysisKey*, 2u>::~SmallPtrSet() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/ADT/SmallPtrSet.h:427:7 #37 0x0000556d89818556 llvm::PreservedAnalyses::~PreservedAnalyses() /home/ubuntu/modular/third-party/llvm-project/llvm/include/llvm/IR/Analysis.h:109:7 #38 0x0000556d89818556 llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool) /home/ubuntu/modular/third-party/llvm-project/llvm/tools/opt/NewPMDriver.cpp:532:10 #39 0x0000556d897e3939 optMain /home/ubuntu/modular/third-party/llvm-project/llvm/tools/opt/optdriver.cpp:737:27 #40 0x0000556d89455461 main /home/ubuntu/modular/third-party/llvm-project/llvm/tools/opt/opt.cpp:25:33 #41 0x00007f1d88e29d90 __libc_start_call_main ./csu/../sysdeps/nptl/libc_start_call_main.h:58:16 #42 0x00007f1d88e29e40 call_init ./csu/../csu/libc-start.c:128:20 #43 0x00007f1d88e29e40 __libc_start_main ./csu/../csu/libc-start.c:379:5 #44 0x0000556d897b6335 _start (/home/ubuntu/modular/.derived/third-party/llvm-project/build-relwithdebinfo-asan/bin/opt+0x150c335) Aborted (core dumped)
DavidSpickett
pushed a commit
that referenced
this pull request
Jul 5, 2024
…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 #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 #2 0x55e2952a614b in mlir::fuseIndependentSiblingForLoops(mlir::scf::ForOp, mlir::scf::ForOp, mlir::RewriterBase&) mlir/lib/Dialect/SCF/Utils/Utils.cpp:1398:43 #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 #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 #5 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14 #6 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48 #7 0x55e294646a8d in applySequenceBlock(mlir::Block&, mlir::transform::FailurePropagationMode, mlir::transform::TransformState&, mlir::transform::TransformResults&) mlir/lib/Dialect/Transform/IR/TransformOps.cpp:1788:15 #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 #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 #10 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14 #11 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48 #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 #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 #14 0x55e294582446 in (anonymous namespace)::InterpreterPass::runOnOperation() mlir/lib/Dialect/Transform/Transforms/InterpreterPass.cpp:147:16 #15 0x55e2978e93c6 in operator() mlir/lib/Pass/Pass.cpp:527:17 #16 0x55e2978e93c6 in void llvm::function_ref<void ()>::callback_fn<mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int)::$_1>(long) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12 #17 0x55e2978e207a in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12 #18 0x55e2978e207a in executeAction<mlir::PassExecutionAction, mlir::Pass &> mlir/include/mlir/IR/MLIRContext.h:275:7 #19 0x55e2978e207a in mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int) mlir/lib/Pass/Pass.cpp:521:21 #20 0x55e2978e5fbf in runPipeline mlir/lib/Pass/Pass.cpp:593:16 #21 0x55e2978e5fbf in mlir::PassManager::runPasses(mlir::Operation*, mlir::AnalysisManager) mlir/lib/Pass/Pass.cpp:904:10 #22 0x55e2978e5b65 in mlir::PassManager::run(mlir::Operation*) mlir/lib/Pass/Pass.cpp:884:60 #23 0x55e291ebb460 in performActions(llvm::raw_ostream&, std::__u::shared_ptr<llvm::SourceMgr> const&, mlir::MLIRContext*, mlir::MlirOptMainConfig const&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:408:17 #24 0x55e291ebabd9 in processBuffer mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:481:9 #25 0x55e291ebabd9 in operator() mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:548:12 #26 0x55e291ebabd9 in llvm::LogicalResult llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>::callback_fn<mlir::MlirOptMain(llvm::raw_ostream&, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&)::$_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 #27 0x55e297b1cffe in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12 #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 #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 #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 #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 #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 #33 0x55e291eb115c in mlir::MlirOptMain(int, char**, llvm::StringRef, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:589:14 #34 0x55e291eb15f8 in mlir::MlirOptMain(int, char**, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:605:10 #35 0x55e29130d1be in main mlir/tools/mlir-opt/mlir-opt.cpp:311:33 #36 0x7fbcf3fff3d3 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x613d3) (BuildId: 9a996398ce14a94560b0c642eb4f6e94) #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 #1 0x55e2979eb657 in __libcpp_operator_delete<void *, unsigned long> #2 0x55e2979eb657 in __do_deallocate_handle_size<> #3 0x55e2979eb657 in __libcpp_deallocate #4 0x55e2979eb657 in deallocate #5 0x55e2979eb657 in deallocate #6 0x55e2979eb657 in operator() #7 0x55e2979eb657 in ~vector #8 0x55e2979eb657 in mlir::Block::~Block() mlir/lib/IR/Block.cpp:24:1 #9 0x55e2979ebc17 in deleteNode llvm/include/llvm/ADT/ilist.h:42:39 #10 0x55e2979ebc17 in erase llvm/include/llvm/ADT/ilist.h:205:5 #11 0x55e2979ebc17 in erase llvm/include/llvm/ADT/ilist.h:209:39 #12 0x55e2979ebc17 in mlir::Block::erase() mlir/lib/IR/Block.cpp:67:28 #13 0x55e297aef978 in mlir::RewriterBase::eraseBlock(mlir::Block*) mlir/lib/IR/PatternMatch.cpp:245:10 #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 #15 0x55e297af06d8 in mlir::RewriterBase::mergeBlocks(mlir::Block*, mlir::Block*, mlir::ValueRange) mlir/lib/IR/PatternMatch.cpp:341:3 #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 #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 #18 0x55e2978d5feb in replaceWithAdditionalYields blaze-out/k8-opt-asan/bin/mlir/include/mlir/Interfaces/LoopLikeInterface.cpp.inc:105:14 #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 #20 0x55e2952a614b in mlir::fuseIndependentSiblingForLoops(mlir::scf::ForOp, mlir::scf::ForOp, mlir::RewriterBase&) mlir/lib/Dialect/SCF/Utils/Utils.cpp:1398:43 #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 #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 #23 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14 #24 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48 #25 0x55e294646a8d in applySequenceBlock(mlir::Block&, mlir::transform::FailurePropagationMode, mlir::transform::TransformState&, mlir::transform::TransformResults&) mlir/lib/Dialect/Transform/IR/TransformOps.cpp:1788:15 #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 #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 #28 0x55e297494a60 in apply blaze-out/k8-opt-asan/bin/mlir/include/mlir/Dialect/Transform/Interfaces/TransformInterfaces.cpp.inc:61:14 #29 0x55e297494a60 in mlir::transform::TransformState::applyTransform(mlir::transform::TransformOpInterface) mlir/lib/Dialect/Transform/Interfaces/TransformInterfaces.cpp:953:48 #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 #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 #32 0x55e294582446 in (anonymous namespace)::InterpreterPass::runOnOperation() mlir/lib/Dialect/Transform/Transforms/InterpreterPass.cpp:147:16 #33 0x55e2978e93c6 in operator() mlir/lib/Pass/Pass.cpp:527:17 #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 #35 0x55e2978e207a in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12 #36 0x55e2978e207a in executeAction<mlir::PassExecutionAction, mlir::Pass &> mlir/include/mlir/IR/MLIRContext.h:275:7 #37 0x55e2978e207a in mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int) mlir/lib/Pass/Pass.cpp:521:21 #38 0x55e2978e5fbf in runPipeline mlir/lib/Pass/Pass.cpp:593:16 #39 0x55e2978e5fbf in mlir::PassManager::runPasses(mlir::Operation*, mlir::AnalysisManager) mlir/lib/Pass/Pass.cpp:904:10 #40 0x55e2978e5b65 in mlir::PassManager::run(mlir::Operation*) mlir/lib/Pass/Pass.cpp:884:60 #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 #42 0x55e291ebabd9 in processBuffer mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:481:9 #43 0x55e291ebabd9 in operator() mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:548:12 #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&)::$_0>(long, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12 #45 0x55e297b1cffe in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12 #46 0x55e297b1cffe in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef)::$_0::operator()(llvm::StringRef) const mlir/lib/Support/ToolUtilities.cpp:86:16 #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 #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 #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 #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 #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 #1 0x55e2979ed5d4 in __libcpp_operator_new<unsigned long> #2 0x55e2979ed5d4 in __libcpp_allocate #3 0x55e2979ed5d4 in allocate #4 0x55e2979ed5d4 in __allocate_at_least<std::__u::allocator<mlir::BlockArgument> > #5 0x55e2979ed5d4 in __split_buffer #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&) #7 0x55e2979ec0f2 in push_back #8 0x55e2979ec0f2 in mlir::Block::addArgument(mlir::Type, mlir::Location) mlir/lib/IR/Block.cpp:154:13 #9 0x55e29796e457 in parseRegionBody mlir/lib/AsmParser/Parser.cpp:2172:34 #10 0x55e29796e457 in (anonymous namespace)::OperationParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:2121:7 #11 0x55e29796b25e in (anonymous namespace)::CustomOpAsmParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:1785:16 #12 0x55e297035742 in mlir::scf::ForOp::parse(mlir::OpAsmParser&, mlir::OperationState&) mlir/lib/Dialect/SCF/IR/SCF.cpp:521:14 #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 #14 0x55e29795bea3 in operator() llvm/include/llvm/ADT/FunctionExtras.h:384:12 #15 0x55e29795bea3 in callback_fn<llvm::unique_function<llvm::ParseResult (mlir::OpAsmParser &, mlir::OperationState &)> > llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12 #16 0x55e29795bea3 in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12 #17 0x55e29795bea3 in parseOperation mlir/lib/AsmParser/Parser.cpp:1521:9 #18 0x55e29795bea3 in parseCustomOperation mlir/lib/AsmParser/Parser.cpp:2017:19 #19 0x55e29795bea3 in (anonymous namespace)::OperationParser::parseOperation() mlir/lib/AsmParser/Parser.cpp:1174:10 #20 0x55e297971d20 in parseBlockBody mlir/lib/AsmParser/Parser.cpp:2296:9 #21 0x55e297971d20 in (anonymous namespace)::OperationParser::parseBlock(mlir::Block*&) mlir/lib/AsmParser/Parser.cpp:2226:12 #22 0x55e29796e4f5 in parseRegionBody mlir/lib/AsmParser/Parser.cpp:2184:7 #23 0x55e29796e4f5 in (anonymous namespace)::OperationParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:2121:7 #24 0x55e29796b25e in (anonymous namespace)::CustomOpAsmParser::parseRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:1785:16 #25 0x55e29796b2cf in (anonymous namespace)::CustomOpAsmParser::parseOptionalRegion(mlir::Region&, llvm::ArrayRef<mlir::OpAsmParser::Argument>, bool) mlir/lib/AsmParser/Parser.cpp:1796:12 #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 #27 0x55e2969ba41d in mlir::func::FuncOp::parse(mlir::OpAsmParser&, mlir::OperationState&) mlir/lib/Dialect/Func/IR/FuncOps.cpp:203:10 #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 #29 0x55e29795bea3 in operator() llvm/include/llvm/ADT/FunctionExtras.h:384:12 #30 0x55e29795bea3 in callback_fn<llvm::unique_function<llvm::ParseResult (mlir::OpAsmParser &, mlir::OperationState &)> > llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12 #31 0x55e29795bea3 in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12 #32 0x55e29795bea3 in parseOperation mlir/lib/AsmParser/Parser.cpp:1521:9 #33 0x55e29795bea3 in parseCustomOperation mlir/lib/AsmParser/Parser.cpp:2017:19 #34 0x55e29795bea3 in (anonymous namespace)::OperationParser::parseOperation() mlir/lib/AsmParser/Parser.cpp:1174:10 #35 0x55e297959b78 in parse mlir/lib/AsmParser/Parser.cpp:2725:20 #36 0x55e297959b78 in mlir::parseAsmSourceFile(llvm::SourceMgr const&, mlir::Block*, mlir::ParserConfig const&, mlir::AsmParserState*, mlir::AsmParserCodeCompleteContext*) mlir/lib/AsmParser/Parser.cpp:2785:41 #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 #38 0x55e291ebbfe2 in parseSourceFile<mlir::ModuleOp, const std::__u::shared_ptr<llvm::SourceMgr> &> mlir/include/mlir/Parser/Parser.h:159:14 #39 0x55e291ebbfe2 in parseSourceFile<mlir::ModuleOp> mlir/include/mlir/Parser/Parser.h:189:10 #40 0x55e291ebbfe2 in mlir::parseSourceFileForTool(std::__u::shared_ptr<llvm::SourceMgr> const&, mlir::ParserConfig const&, bool) mlir/include/mlir/Tools/ParseUtilities.h:31:12 #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 #42 0x55e291ebabd9 in processBuffer mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:481:9 #43 0x55e291ebabd9 in operator() mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:548:12 #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&)::$_0>(long, std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&) llvm/include/llvm/ADT/STLFunctionalExtras.h:45:12 #45 0x55e297b1cffe in operator() llvm/include/llvm/ADT/STLFunctionalExtras.h:68:12 #46 0x55e297b1cffe in mlir::splitAndProcessBuffer(std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::__u::unique_ptr<llvm::MemoryBuffer, std::__u::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef)::$_0::operator()(llvm::StringRef) const mlir/lib/Support/ToolUtilities.cpp:86:16 #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 #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 #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 #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 #51 0x55e291eb115c in mlir::MlirOptMain(int, char**, llvm::StringRef, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:589:14 #52 0x55e291eb15f8 in mlir::MlirOptMain(int, char**, llvm::StringRef, mlir::DialectRegistry&) mlir/lib/Tools/mlir-opt/MlirOptMain.cpp:605:10 #53 0x55e29130d1be in main mlir/tools/mlir-opt/mlir-opt.cpp:311:33 #54 0x7fbcf3fff3d3 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x613d3) (BuildId: 9a996398ce14a94560b0c642eb4f6e94) #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
DavidSpickett
pushed a commit
that referenced
this pull request
Jul 5, 2024
While lowering (#pragma omp target update from), clang's generated .omp_task_entry. is setting up 9 arguments while calling __tgt_target_data_update_nowait_mapper. At the same time, in __tgt_target_data_update_nowait_mapper, call to targetData<TaskAsyncInfoWrapperTy>() is converted to a sibcall assuming it has the argument count listed in the signature. AARCH64 asm sequence for this is as follows (removed unrelated insns): ` .omp_task_entry..108: sub sp, sp, #32 stp x29, x30, sp, #16 // 16-byte Folded Spill add x29, sp, #16 str x8, sp, #8. // stack canary str xzr, [sp] bl __tgt_target_data_update_nowait_mapper __tgt_target_data_update_nowait_mapper: sub sp, sp, #32 stp x29, x30, sp, #16 // 16-byte Folded Spill add x29, sp, #16 str x8, sp, #8 // stack canary // Sibcall argument setup adrp x8, :got:_Z16targetDataUpdateP7ident_tR8DeviceTyiPPvS4_PlS5_S4_S4_R11AsyncInfoTyb ldr x8, [x8, :got_lo12:_Z16targetDataUpdateP7ident_tR8DeviceTyiPPvS4_PlS5_S4_S4_R11AsyncInfoTyb] stp x9, x8, x29, #16 adrp x8, .L.str.8 add x8, x8, :lo12:.L.str.8 str x8, x29, #32. <==. This is the insn that erases $fp ldp x29, x30, sp, #16 // 16-byte Folded Reload add sp, sp, #32 // Sibcall b ZL10targetDataI22TaskAsyncInfoWrapperTyEvP7ident_tliPPvS4_PlS5_S4_S4_PFiS2_R8DeviceTyiS4_S4_S5_S5_S4_S4_R11AsyncInfoTybEPKcSD ` On AArch64, call to __tgt_target_data_update_nowait_mapper in .omp_task_entry. sets up only single space on stack and this results in ovewriting $fp and subsequent stack corruption. This issue can be credited to discrepancy of __tgt_target_data_update_nowait_mapper signature in openmp/libomptarget/include/omptarget.h taking 13 arguments while clang/lib/CodeGen/CGOpenMPRuntime.cpp and llvm/include/llvm/Frontend/OpenMP/OMPKinds.def taking only 9 arguments. This patch modifies __tgt_target_data_update_nowait_mapper signature to match .omp_task_entry usage(and other 2 files mentioned above). Co-authored-by: Kugan Vivekanandarajah <kvivekananda@nvidia.com>
DavidSpickett
pushed a commit
that referenced
this pull request
Sep 2, 2024
The worst possible case for a double literal goes like: ``` mov ... movk ..., lsl #16 movk ..., lsl #32 movk ..., lsl #48 fmov ... ``` The limit of 5 in the code gives the impression that `Insn` includes all instructions including the `fmov`, but that's not true. It only counts the integer moves. This led me astray on some other work in this area.
DavidSpickett
pushed a commit
that referenced
this pull request
Apr 7, 2025
…d A520 (llvm#132246) Inefficient SVE codegen occurs on at least two in-order cores, those being Cortex-A510 and Cortex-A520. For example a simple vector add ``` void foo(float a, float b, float dst, unsigned n) { for (unsigned i = 0; i < n; ++i) dst[i] = a[i] + b[i]; } ``` Vectorizes the inner loop into the following interleaved sequence of instructions. ``` add x12, x1, x10 ld1b { z0.b }, p0/z, [x1, x10] add x13, x2, x10 ld1b { z1.b }, p0/z, [x2, x10] ldr z2, [x12, #1, mul vl] ldr z3, [x13, #1, mul vl] dech x11 add x12, x0, x10 fadd z0.s, z1.s, z0.s fadd z1.s, z3.s, z2.s st1b { z0.b }, p0, [x0, x10] addvl x10, x10, #2 str z1, [x12, #1, mul vl] ``` By adjusting the target features to prefer fixed over scalable if the cost is equal we get the following vectorized loop. ``` ldp q0, q3, [x11, #-16] subs x13, x13, #8 ldp q1, q2, [x10, #-16] add x10, x10, #32 add x11, x11, #32 fadd v0.4s, v1.4s, v0.4s fadd v1.4s, v2.4s, v3.4s stp q0, q1, [x12, #-16] add x12, x12, #32 ``` Which is more efficient.
DavidSpickett
pushed a commit
that referenced
this pull request
Jul 2, 2025
Combine sequences such as:
```llvm
%pn1 = phi [init1, %BB1], [%op1, %BB2]
%pn2 = phi [init2, %BB1], [%op2, %BB2]
%op1 = binop %pn1, constant1
%op2 = binop %pn2, constant2
%rdx = binop %op1, %op2
```
Into:
```llvm
%phi_combined = phi [init_combined, %BB1], [%op_combined, %BB2]
%rdx_combined = binop %phi_combined, constant_combined
```
This allows us to simplify interleaved reductions, for example as
introduced by the loop vectorizer.
The anecdotal example for this is the loop below:
```c
float foo() {
float q = 1.f;
for (int i = 0; i < 1000; ++i)
q *= .99f;
return q;
}
```
Which currently gets lowered explicitly such as (on AArch64,
interleaved by four):
```gas
.LBB0_1:
fmul v0.4s, v0.4s, v1.4s
fmul v2.4s, v2.4s, v1.4s
fmul v3.4s, v3.4s, v1.4s
fmul v4.4s, v4.4s, v1.4s
subs w8, w8, #32
b.ne .LBB0_1
```
But with this patch lowers trivially:
```gas
foo:
mov w8, llvm#5028
movk w8, llvm#14389, lsl #16
fmov s0, w8
ret
```
DavidSpickett
pushed a commit
that referenced
this pull request
Aug 8, 2025
…lvm#152156) With this new A320 in-order core, we follow adding the FeatureUseFixedOverScalableIfEqualCost feature to A510 and A520 (llvm#132246), which reaps the same code generation benefits of preferring fixed over scalable when the cost is equal. So when we have: ``` void foo(float* a, float* b, float* dst, unsigned n) { for (unsigned i = 0; i < n; ++i) dst[i] = a[i] + b[i]; } ``` When compiling without the feature enabled, we get: ``` ... ld1b { z0.b }, p0/z, [x0, x10] ld1b { z2.b }, p0/z, [x1, x10] add x12, x0, x10 ldr z1, [x12, #1, mul vl] add x12, x1, x10 ldr z3, [x12, #1, mul vl] fadd z0.s, z2.s, z0.s add x12, x2, x10 fadd z1.s, z3.s, z1.s dech x11 st1b { z0.b }, p0, [x2, x10] incb x10, all, mul #2 str z1, [x12, #1, mul vl] ... ``` When compiling with, we get: ``` ... ldp q0, q1, [x12, #-16] ldp q2, q3, [x11, #-16] subs x13, x13, #8 fadd v0.4s, v2.4s, v0.4s fadd v1.4s, v3.4s, v1.4s add x11, x11, #32 add x12, x12, #32 stp q0, q1, [x10, #-16] add x10, x10, #32 ... ```
DavidSpickett
pushed a commit
that referenced
this pull request
Dec 9, 2025
Follow-on from llvm#170324 to also refactor the NEON tests to reuse the input assembly across all Neoverse cores. The approach is as follows: - Inputs for Neoverse N1/N2/N3 NEON tests are already identical, so first combine those. - Inputs for V2/V3/V3AE NEON tests are also already identical, but differ from N-cores, so combine those separately. - Most significantly, input for V1 differs from all other cores primarily because of 24f0901 (llvm#128892). - Split out features that are not supported across all cores. - Split out FEAT_I8MM, FEAT_FHM, FEAT_FCMA. N1 doesn't have this feature but all other Neoverse cores do. Also adds coverage for N2/N3 since they were missing tests. - Split out FEAT_BF16. V1 doesn't have this feature but all other Neoverse cores do. Also adds coverage for N1/N2/N3 since they were missing tests. - Split out FEAT_FRINTTS. V1/N1 don't have this feature but all other Neoverse cores do. Also adds coverage for N2/N3 since they were missing tests. - Bring Neoverse V2/V3/V3AE and N1/N2/N3 neon tests inline. Comparing N[1-3] against V[2-3] the only change the N cores have that V[2-3] dont is: ``` < st4 { v0.d, v1.d, v2.d, v3.d }[1], [x0], x5 --- > st4 { v0.b, v1.b, v2.b, v3.b }[9], [x0], x5 ``` So we take it for all cores. The rest of the diff is instructions in V[2-3] that arent in N cores, so we also take them. All Neoverse cores can optionally support the Cryptographic Extension. The related features (AES, ...) are enabled by default for V1/N1 but not the other cores, so need to be explicitly enabled via -mattr. - Finally bring Neoverse V1 inline with V2/V3/V3AE/N1/N2/N3 - loads/stores are blended - duplicates with different spaces like `shll v0.2d, v0.2s, #32` are removed - the rest of the diff is instructions in V1 that are not tested in the other cores, so we add them for the other cores
DavidSpickett
pushed a commit
that referenced
this pull request
Jan 5, 2026
…ng destructor (llvm#174082)" This reverts commit 7976ac9. This is causing msan failures. msan-track-origins stack trace: ==9441==WARNING: MemorySanitizer: use-of-uninitialized-value #0 0x55c20df74ad3 in clang::interp::Pointer::operator=(clang::interp::Pointer&&) llvm-project/clang/lib/AST/ByteCode/Pointer.cpp:137:7 #1 0x55c20db81010 in bool clang::interp::InitGlobal<(clang::interp::PrimType)13, clang::interp::Pointer>(clang::interp::InterpState&, clang::interp::CodePtr, unsigned int) llvm-project/clang/lib/AST/ByteCode/Interp.h:1478:16 #2 0x55c20db7ec56 in emitInitGlobalPtr blaze-out/k8-fastbuild-msan/bin/llvm-project/clang/_virtual_includes/ast_bytecode_opcodes_gen/Opcodes.inc:26162:10 #3 0x55c20db7ec56 in clang::interp::EvalEmitter::emitInitGlobal(clang::interp::PrimType, unsigned int, clang::interp::SourceInfo) blaze-out/k8-fastbuild-msan/bin/llvm-project/clang/_virtual_includes/ast_bytecode_opcodes_gen/Opcodes.inc:26042:12 #4 0x55c20da58b87 in clang::interp::Compiler<clang::interp::EvalEmitter>::visitVarDecl(clang::VarDecl const*, clang::Expr const*, bool, bool) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:4924:20 #5 0x55c20da64a61 in clang::interp::Compiler<clang::interp::EvalEmitter>::visitDeclAndReturn(clang::VarDecl const*, clang::Expr const*, bool) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:4831:14 #6 0x55c20da7f290 in clang::interp::EvalEmitter::interpretDecl(clang::VarDecl const*, clang::Expr const*, bool) llvm-project/clang/lib/AST/ByteCode/EvalEmitter.cpp:66:14 #7 0x55c20d970d23 in clang::interp::Context::evaluateAsInitializer(clang::interp::State&, clang::VarDecl const*, clang::Expr const*, clang::APValue&) llvm-project/clang/lib/AST/ByteCode/Context.cpp:141:16 #8 0x55c20e25b8de in clang::Expr::EvaluateAsInitializer(clang::APValue&, clang::ASTContext const&, clang::VarDecl const*, llvm::SmallVectorImpl<std::__msan::pair<clang::SourceLocation, clang::PartialDiagnostic>>&, bool) const llvm-project/clang/lib/AST/ExprConstant.cpp:20754:20 #9 0x55c20da368d5 in clang::interp::Compiler<clang::interp::EvalEmitter>::visitDeclRef(clang::ValueDecl const*, clang::Expr const*) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:7162:19 #10 0x55c20da34986 in clang::interp::Compiler<clang::interp::EvalEmitter>::VisitDeclRefExpr(clang::DeclRefExpr const*) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:7192:16 #11 0x55c20da66666 in clang::StmtVisitorBase<llvm::make_const_ptr, clang::interp::Compiler<clang::interp::EvalEmitter>, bool>::Visit(clang::Stmt const*) blaze-out/k8-fastbuild-msan/bin/llvm-project/clang/include/clang/AST/StmtNodes.inc:474:1 #12 0x55c20da65d3f in clang::interp::Compiler<clang::interp::EvalEmitter>::visit(clang::Expr const*) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:4293:16 #13 0x55c20da57348 in clang::interp::Compiler<clang::interp::EvalEmitter>::VisitCXXTypeidExpr(clang::CXXTypeidExpr const*) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:3893:14 #14 0x55c20da66760 in clang::StmtVisitorBase<llvm::make_const_ptr, clang::interp::Compiler<clang::interp::EvalEmitter>, bool>::Visit(clang::Stmt const*) blaze-out/k8-fastbuild-msan/bin/llvm-project/clang/include/clang/AST/StmtNodes.inc:658:1 #15 0x55c20da65d3f in clang::interp::Compiler<clang::interp::EvalEmitter>::visit(clang::Expr const*) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:4293:16 #16 0x55c20da58afc in clang::interp::Compiler<clang::interp::EvalEmitter>::visitVarDecl(clang::VarDecl const*, clang::Expr const*, bool, bool) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:4921:18 #17 0x55c20da64a61 in clang::interp::Compiler<clang::interp::EvalEmitter>::visitDeclAndReturn(clang::VarDecl const*, clang::Expr const*, bool) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:4831:14 #18 0x55c20da7f290 in clang::interp::EvalEmitter::interpretDecl(clang::VarDecl const*, clang::Expr const*, bool) llvm-project/clang/lib/AST/ByteCode/EvalEmitter.cpp:66:14 #19 0x55c20d970d23 in clang::interp::Context::evaluateAsInitializer(clang::interp::State&, clang::VarDecl const*, clang::Expr const*, clang::APValue&) llvm-project/clang/lib/AST/ByteCode/Context.cpp:141:16 #20 0x55c20e25b8de in clang::Expr::EvaluateAsInitializer(clang::APValue&, clang::ASTContext const&, clang::VarDecl const*, llvm::SmallVectorImpl<std::__msan::pair<clang::SourceLocation, clang::PartialDiagnostic>>&, bool) const llvm-project/clang/lib/AST/ExprConstant.cpp:20754:20 #21 0x55c20dfdcc38 in clang::VarDecl::evaluateValueImpl(llvm::SmallVectorImpl<std::__msan::pair<clang::SourceLocation, clang::PartialDiagnostic>>&, bool) const llvm-project/clang/lib/AST/Decl.cpp:2608:23 #22 0x55c20dfdd1a2 in clang::VarDecl::checkForConstantInitialization(llvm::SmallVectorImpl<std::__msan::pair<clang::SourceLocation, clang::PartialDiagnostic>>&) const llvm-project/clang/lib/AST/Decl.cpp:2687:7 #23 0x55c20b9154da in clang::Sema::CheckCompleteVariableDeclaration(clang::VarDecl*) llvm-project/clang/lib/Sema/SemaDecl.cpp:14941:27 #24 0x55c20b910f36 in clang::Sema::AddInitializerToDecl(clang::Decl*, clang::Expr*, bool) llvm-project/clang/lib/Sema/SemaDecl.cpp:14280:3 #25 0x55c20ad044ee in clang::Parser::ParseDeclarationAfterDeclaratorAndAttributes(clang::Declarator&, clang::Parser::ParsedTemplateInfo const&, clang::Parser::ForRangeInit*) llvm-project/clang/lib/Parse/ParseDecl.cpp:2639:17 #26 0x55c20acfe9f8 in clang::Parser::ParseDeclGroup(clang::ParsingDeclSpec&, clang::DeclaratorContext, clang::ParsedAttributes&, clang::Parser::ParsedTemplateInfo&, clang::SourceLocation*, clang::Parser::ForRangeInit*) llvm-project/clang/lib/Parse/ParseDecl.cpp:2356:7 #27 0x55c20abd8a43 in clang::Parser::ParseDeclOrFunctionDefInternal(clang::ParsedAttributes&, clang::ParsedAttributes&, clang::ParsingDeclSpec&, clang::AccessSpecifier) llvm-project/clang/lib/Parse/Parser.cpp:1181:10 #28 0x55c20abd7654 in clang::Parser::ParseDeclarationOrFunctionDefinition(clang::ParsedAttributes&, clang::ParsedAttributes&, clang::ParsingDeclSpec*, clang::AccessSpecifier) llvm-project/clang/lib/Parse/Parser.cpp:1203:12 #29 0x55c20abd4d9c in clang::Parser::ParseExternalDeclaration(clang::ParsedAttributes&, clang::ParsedAttributes&, clang::ParsingDeclSpec*) llvm-project/clang/lib/Parse/Parser.cpp:1031:14 #30 0x55c20ac96f31 in clang::Parser::ParseInnerNamespace(llvm::SmallVector<clang::Parser::InnerNamespaceInfo, 4u> const&, unsigned int, clang::SourceLocation&, clang::ParsedAttributes&, clang::BalancedDelimiterTracker&) llvm-project/clang/lib/Parse/ParseDeclCXX.cpp:240:7 #31 0x55c20ac950c7 in clang::Parser::ParseNamespace(clang::DeclaratorContext, clang::SourceLocation&, clang::SourceLocation) llvm-project/clang/lib/Parse/ParseDeclCXX.cpp:218:3 #32 0x55c20acfb09b in clang::Parser::ParseDeclaration(clang::DeclaratorContext, clang::SourceLocation&, clang::ParsedAttributes&, clang::ParsedAttributes&, clang::SourceLocation*) llvm-project/clang/lib/Parse/ParseDecl.cpp:1909:12 #33 0x55c20abd3f88 in clang::Parser::ParseExternalDeclaration(clang::ParsedAttributes&, clang::ParsedAttributes&, clang::ParsingDeclSpec*) llvm-project/clang/lib/Parse/Parser.cpp #34 0x55c20abcfe33 in clang::Parser::ParseTopLevelDecl(clang::OpaquePtr<clang::DeclGroupRef>&, clang::Sema::ModuleImportState&) llvm-project/clang/lib/Parse/Parser.cpp:744:12 #35 0x55c20abb214e in clang::ParseAST(clang::Sema&, bool, bool) llvm-project/clang/lib/Parse/ParseAST.cpp:170:20 #36 0x55c20a90adaa in clang::ASTFrontendAction::ExecuteAction() llvm-project/clang/lib/Frontend/FrontendAction.cpp:1432:3 #37 0x55c20a9095bf in clang::FrontendAction::Execute() llvm-project/clang/lib/Frontend/FrontendAction.cpp:1312:3 #38 0x55c20a76cdc7 in clang::CompilerInstance::ExecuteAction(clang::FrontendAction&) llvm-project/clang/lib/Frontend/CompilerInstance.cpp:1004:33 #39 0x55c20805aab0 in clang::ExecuteCompilerInvocation(clang::CompilerInstance*) llvm-project/clang/lib/FrontendTool/ExecuteCompilerInvocation.cpp:310:25 #40 0x55c20802e823 in cc1_main(llvm::ArrayRef<char const*>, char const*, void*) llvm-project/clang/tools/driver/cc1_main.cpp:304:15 #41 0x55c2080218ec in ExecuteCC1Tool(llvm::SmallVectorImpl<char const*>&, llvm::ToolContext const&, llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>) llvm-project/clang/tools/driver/driver.cpp:225:12 #42 0x55c20801ea91 in clang_main(int, char**, llvm::ToolContext const&) llvm-project/clang/tools/driver/driver.cpp:268:12 #43 0x55c20801a6af in main blaze-out/k8-fastbuild-msan/bin/llvm-project/clang/clang-driver.cpp:17:10 #44 0x7f79c4214351 in __libc_start_main (/usr/libc/lib64/libc.so.6+0x61351) (BuildId: ca23ec6d935352118622ce674a8bb52d) #45 0x55c207f8c2e9 in _start /usr/libc/debug-src/src/csu/../sysdeps/x86_64/start.S:120 Member fields were destroyed #0 0x55c207f9f5fd in __sanitizer_dtor_callback_fields llvm-project/compiler-rt/lib/msan/msan_interceptors.cpp:1074:5 #1 0x55c20df74380 in ~Pointer llvm-project/clang/lib/AST/ByteCode/Pointer.h:826:12 #2 0x55c20df74380 in clang::interp::Pointer::~Pointer() llvm-project/clang/lib/AST/ByteCode/Pointer.cpp:93:1 #3 0x55c20da7c5ab in void dtorTy<clang::interp::Pointer>(clang::interp::Block*, std::byte*, clang::interp::Descriptor const*) llvm-project/clang/lib/AST/ByteCode/Descriptor.cpp:49:32 #4 0x55c20d976b91 in clang::interp::Block::invokeDtor() llvm-project/clang/lib/AST/ByteCode/InterpBlock.h:149:7 #5 0x55c20da651a1 in clang::interp::Compiler<clang::interp::EvalEmitter>::visitDeclAndReturn(clang::VarDecl const*, clang::Expr const*, bool) llvm-project/clang/lib/AST/ByteCode/Compiler.cpp:4869:22 #6 0x55c20da7f290 in clang::interp::EvalEmitter::interpretDecl(clang::VarDecl const*, clang::Expr const*, bool) llvm-project/clang/lib/AST/ByteCode/EvalEmitter.cpp:66:14 #7 0x55c20d970d23 in clang::interp::Context::evaluateAsInitializer(clang::interp::State&, clang::VarDecl const*, clang::Expr const*, clang::APValue&) llvm-project/clang/lib/AST/ByteCode/Context.cpp:141:16 #8 0x55c20e25b8de in clang::Expr::EvaluateAsInitializer(clang::APValue&, clang::ASTContext const&, clang::VarDecl const*, llvm::SmallVectorImpl<std::__msan::pair<clang::SourceLocation, clang::PartialDiagnostic>>&, bool) const llvm-project/clang/lib/AST/ExprConstant.cpp:20754:20 #9 0x55c20dfdcc38 in clang::VarDecl::evaluateValueImpl(llvm::SmallVectorImpl<std::__msan::pair<clang::SourceLocation, clang::PartialDiagnostic>>&, bool) const llvm-project/clang/lib/AST/Decl.cpp:2608:23 #10 0x55c20dfdd1a2 in clang::VarDecl::checkForConstantInitialization(llvm::SmallVectorImpl<std::__msan::pair<clang::SourceLocation, clang::PartialDiagnostic>>&) const llvm-project/clang/lib/AST/Decl.cpp:2687:7 #11 0x55c20b9154da in clang::Sema::CheckCompleteVariableDeclaration(clang::VarDecl*) llvm-project/clang/lib/Sema/SemaDecl.cpp:14941:27 #12 0x55c20b910f36 in clang::Sema::AddInitializerToDecl(clang::Decl*, clang::Expr*, bool) llvm-project/clang/lib/Sema/SemaDecl.cpp:14280:3 #13 0x55c20ad044ee in clang::Parser::ParseDeclarationAfterDeclaratorAndAttributes(clang::Declarator&, clang::Parser::ParsedTemplateInfo const&, clang::Parser::ForRangeInit*) llvm-project/clang/lib/Parse/ParseDecl.cpp:2639:17 #14 0x55c20acfe9f8 in clang::Parser::ParseDeclGroup(clang::ParsingDeclSpec&, clang::DeclaratorContext, clang::ParsedAttributes&, clang::Parser::ParsedTemplateInfo&, clang::SourceLocation*, clang::Parser::ForRangeInit*) llvm-project/clang/lib/Parse/ParseDecl.cpp:2356:7 #15 0x55c20abd8a43 in clang::Parser::ParseDeclOrFunctionDefInternal(clang::ParsedAttributes&, clang::ParsedAttributes&, clang::ParsingDeclSpec&, clang::AccessSpecifier) llvm-project/clang/lib/Parse/Parser.cpp:1181:10 #16 0x55c20abd7654 in clang::Parser::ParseDeclarationOrFunctionDefinition(clang::ParsedAttributes&, clang::ParsedAttributes&, clang::ParsingDeclSpec*, clang::AccessSpecifier) llvm-project/clang/lib/Parse/Parser.cpp:1203:12 #17 0x55c20abd4d9c in clang::Parser::ParseExternalDeclaration(clang::ParsedAttributes&, clang::ParsedAttributes&, clang::ParsingDeclSpec*) llvm-project/clang/lib/Parse/Parser.cpp:1031:14 #18 0x55c20ac96f31 in clang::Parser::ParseInnerNamespace(llvm::SmallVector<clang::Parser::InnerNamespaceInfo, 4u> const&, unsigned int, clang::SourceLocation&, clang::ParsedAttributes&, clang::BalancedDelimiterTracker&) llvm-project/clang/lib/Parse/ParseDeclCXX.cpp:240:7 #19 0x55c20ac950c7 in clang::Parser::ParseNamespace(clang::DeclaratorContext, clang::SourceLocation&, clang::SourceLocation) llvm-project/clang/lib/Parse/ParseDeclCXX.cpp:218:3 #20 0x55c20acfb09b in clang::Parser::ParseDeclaration(clang::DeclaratorContext, clang::SourceLocation&, clang::ParsedAttributes&, clang::ParsedAttributes&, clang::SourceLocation*) llvm-project/clang/lib/Parse/ParseDecl.cpp:1909:12
DavidSpickett
pushed a commit
that referenced
this pull request
Feb 12, 2026
Rotations that implement reverse operations, for example:
```c
uint64x2_t foo(uint64x2_t r) {
return (r >> 32) | (r << 32);
}
```
Are currently lowered as XAR (when available):
```gas
foo:
movi v1.2d, #0000000000000000
xar v0.2d, v0.2d, v1.2d, #32
ret
```
This is suboptimal as REV* instructions typically have higher throughput
than XAR and do not require the zero operand.
This patch combines half-rotations to Neon or SVE REVs so that they're
no longer selected as XAR.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.