Skip to content

Memory profiling causes rocmIsEnabled to segfault #47450

Open
@iarspider

Description

@iarspider

Output of LD_PRELOAD=libPerfToolsAllocMonitorPreload.so:libPerfToolsMaxMemoryPreload.so gdb --args rocmIsEnabled (these libraries are preloaded if --maxmem_profile is passed to cmsDriver):

#0  0x00001555538a8a4c in _int_free () from /lib64/libc.so.6
#1  0x00001555555441ac in operator delete(void*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/nweek-02878/el8_amd64_gcc12/cms/cmssw/CMSSW_15_1_X_2025-02-23-0000/lib/el8_amd64_gcc12/libPerfToolsAllocMonitorPreload.so
#2  0x000015554f8dd24d in llvm::GenericCycleInfoCompute<llvm::GenericSSAContext<llvm::Function> >::updateDepth(llvm::GenericCycle<llvm::GenericSSAContext<llvm::Function> >*) ()
   from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#3  0x000015554f8ddd93 in llvm::GenericCycleInfoCompute<llvm::GenericSSAContext<llvm::Function> >::run(llvm::BasicBlock*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#4  0x000015554f8dfc22 in llvm::CycleInfoWrapperPass::runOnFunction(llvm::Function&) [clone .localalias.5] () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#5  0x0000155550035c69 in llvm::FPPassManager::runOnFunction(llvm::Function&) [clone .localalias.4] () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#6  0x0000155550035db1 in llvm::FPPassManager::runOnModule(llvm::Module&) [clone .localalias.54] () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#7  0x0000155550036a7f in llvm::legacy::PassManagerImpl::run(llvm::Module&) [clone .localalias.36] () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#8  0x000015554c0695ac in clang::EmitBackendOutput(clang::DiagnosticsEngine&, clang::HeaderSearchOptions const&, clang::CodeGenOptions const&, clang::TargetOptions const&, clang::LangOptions const&, llvm::StringRef, llvm::Module*, clang::BackendAction, llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>, std::unique_ptr<llvm::raw_pwrite_stream, std::default_delete<llvm::raw_pwrite_stream> >, clang::BackendConsumer*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#9  0x000015554c0454a1 in clang::CodeGenAction::ExecuteAction() [clone .localalias.40] () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#10 0x000015554db23851 in clang::FrontendAction::Execute() () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#11 0x000015554daaf2fa in clang::CompilerInstance::ExecuteAction(clang::FrontendAction&) [clone .localalias.2] () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#12 0x000015554bb9e673 in clang::ExecuteCompilerInvocation(clang::CompilerInstance*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#13 0x000015554af7fd6b in COMGR::AMDGPUCompiler::executeInProcessDriver(llvm::ArrayRef<char const*>) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#14 0x000015554af81fdc in COMGR::AMDGPUCompiler::processFile(char const*, char const*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#15 0x000015554af82618 in COMGR::AMDGPUCompiler::processFiles(amd_comgr_data_kind_s, char const*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#16 0x000015554af9356d in amd_comgr_do_action () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamd_comgr.so.2
#17 0x0000155553e8c205 in amd::device::Program::compileAndLinkExecutable(amd_comgr_data_set_s, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, amd::option::Options*, char**, unsigned long*, amd::device::Program::file_type_t) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#18 0x0000155553e8ebd4 in amd::device::Program::linkImplLC(amd::option::Options*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#19 0x0000155553e8b141 in amd::device::Program::build(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, char const*, amd::option::Options*, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#20 0x0000155553eb4b26 in amd::Program::build(std::vector<amd::Device*, std::allocator<amd::Device*> > const&, char const*, void (*)(_cl_program*, void*), void*, bool, bool) ()
   from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#21 0x0000155553e85ded in amd::Device::BlitProgram::create(amd::Device*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) ()
   from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#22 0x0000155553ec2edb in amd::roc::Device::createBlitProgram() () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#23 0x0000155553f06aa8 in amd::roc::KernelBlitManager::createProgram(amd::roc::Device&) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#24 0x0000155553edb4cd in amd::roc::VirtualGPU::create() () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#25 0x0000155553ebce08 in amd::roc::Device::createVirtualDevice(amd::CommandQueue*) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#26 0x0000155553ea9f74 in amd::HostQueue::HostQueue(amd::Context&, amd::Device&, unsigned long, unsigned int, amd::CommandQueue::Priority, std::vector<unsigned int, std::allocator<unsigned int> > const&) ()
   from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#27 0x0000155553e05e19 in hip::Stream::Stream(hip::Device*, hip::Stream::Priority, unsigned int, bool, std::vector<unsigned int, std::allocator<unsigned int> > const&, hipStreamCaptureStatus) ()
   from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#28 0x0000155553ca1c94 in hip::Device::NullStream(bool) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#29 0x0000155553d4dba7 in hip::ihipMemset(void*, long, unsigned long, unsigned long, ihipStream_t*, bool) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#30 0x0000155553d7ed2c in hip::hipMemset(void*, int, unsigned long) () from /cvmfs/cms-ib.cern.ch/sw/x86_64/week0/el8_amd64_gcc12/cms/cmssw-patch/CMSSW_15_1_X_2025-02-24-1100/external/el8_amd64_gcc12/lib/libamdhip64.so.6
#31 0x00000000004012fd in isRocmDeviceSupported(int) ()
#32 0x0000000000401190 in main ()

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions