Name | Module | Coverage run_0 (%) | Coverage Excluding Loops run_0 (%) | Max Inclusive Time Over Threads run_0 (s) | Max Exclusive Time Over Threads run_0 (s) | Inclusive Time w.r.t. Wall Time run_0 (s) | Exclusive Time w.r.t. Wall Time run_0 (s) | Nb Threads run_0 | Deviation (coverage) run_0 | Deviation (walltime) run_0 | Categories run_0 | Compilation Options |
---|---|---|---|---|---|---|---|---|---|---|---|---|
○DGEMV | libmkl_intel_lp64.so.1 | 42.27 | 42.27 | 5.83 | 5.83 | 27.47 | 27.47 | 128 | 10.56 | 1.04 | Math (%): 100.00 | |
○DGEMM | libmkl_intel_lp64.so.1 | 21.88 | 21.88 | 3.44 | 3.44 | 14.22 | 14.22 | 128 | 8.20 | 0.86 | Math (%): 100.00 | |
○void tbb::detail::d1::dynamic_grainsize_mode<tbb::detail::d1::adaptive_mode<tbb::detail::d1::auto_partition_type> >::work_balance<tbb::detail::d1::start_for<tbb::detail::d1::blocked_range<unsigned long>, tbb::detail::d2::parallel_fo... | libassembly.so | 4.70 | 4.70 | 0.69 | 0.69 | 3.05 | 3.05 | 128 | 0.75 | 0.07 | Others (%): 99.99 Math (%): 0.01 | |
○rml::internal::internalPoolMalloc(rml::internal::MemoryPool*, unsigned long) | libtbbmalloc.so.2.13 | 3.62 | 3.62 | 0.63 | 0.63 | 2.35 | 2.35 | 128 | 0.75 | 0.08 | Others (%): 100.00 | |
○rml::internal::Backend::genericGetBlock(int, unsigned long, bool) [clone .constprop.1] | libtbbmalloc.so.2.13 | 3.45 | 3.45 | 0.48 | 0.48 | 2.25 | 2.25 | 128 | 0.53 | 0.05 | Others (%): 100.00 | |
○mkl_blas_def_xdgemv | libmkl_def.so.1 | 2.24 | 2.24 | 0.37 | 0.37 | 1.45 | 1.45 | 128 | 0.48 | 0.05 | Math (%): 100.00 | |
○rml::internal::Backend::askMemFromOS(unsigned long, long, int*, int, bool*, bool) | libtbbmalloc.so.2.13 | 1.98 | 1.98 | 0.30 | 0.30 | 1.28 | 1.28 | 128 | 0.35 | 0.03 | Others (%): 100.00 | |
○rml::internal::Backend::IndexedBins::getFromBin(int, rml::internal::BackendSync*, unsigned long, bool, bool, bool, int*) [clone .constprop.0] | libtbbmalloc.so.2.13 | 1.95 | 1.95 | 0.31 | 0.31 | 1.27 | 1.27 | 128 | 0.35 | 0.03 | Others (%): 100.00 | |
○mkl_blas_def_dgemm_kernel_zen | libmkl_def.so.1 | 1.36 | 1.36 | 0.28 | 0.28 | 0.89 | 0.89 | 128 | 0.44 | 0.05 | Math (%): 100.00 | |
○void tbb::detail::d1::dynamic_grainsize_mode<tbb::detail::d1::adaptive_mode<tbb::detail::d1::auto_partition_type> >::work_balance<tbb::detail::d1::start_for<tbb::detail::d1::blocked_range<unsigned long>, tbb::detail::d2::parallel_fo... | libassembly.so | 1.32 | 1.32 | 0.19 | 0.19 | 0.86 | 0.86 | 128 | 0.22 | 0.02 | Others (%): 100.00 | |
○void tbb::detail::d1::dynamic_grainsize_mode<tbb::detail::d1::adaptive_mode<tbb::detail::d1::auto_partition_type> >::work_balance<tbb::detail::d1::start_for<tbb::detail::d1::blocked_range<unsigned long>, tbb::detail::d2::parallel_fo... | libassembly.so | 0.99 | 0.99 | 0.15 | 0.15 | 0.64 | 0.64 | 128 | 0.23 | 0.02 | Others (%): 100.00 | |
○void aset::asolve::set_from_csc<double>(Eigen::SparseMatrix<double, 0, int>&, aset::asolve::StorageCSC<int, double>&&) | libassembly.so | 0.80 | 0.80 | 11.24 | 11.24 | 0.52 | 0.52 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○tbb::detail::d1::start_for<tbb::detail::d1::blocked_range<unsigned long>, tbb::detail::d2::parallel_for_body_wrapper<__gnu_cxx::__normal_iterator<aset::asolve::FiniteElement* const*, std::vector<aset::asolve::FiniteElement*, std::allocato... | libassembly.so | 0.78 | 0.78 | 0.18 | 0.18 | 0.51 | 0.51 | 128 | 0.26 | 0.03 | Others (%): 100.00 | |
○__GI___sched_yield | libc-2.28.so | 0.77 | 0.77 | 0.14 | 0.14 | 0.50 | 0.50 | 128 | 0.21 | 0.02 | System (%): 99.30 Math (%): 0.42 Pthread (%): 0.28 | |
○void std::__introsort_loop<__gnu_cxx::__normal_iterator<int*, std::vector<int, tbb::detail::d1::scalable_allocator<int> > >, long, __gnu_cxx::__ops::_Iter_less_iter>(__gnu_cxx::__normal_iterator<int*, std::vector<int, tbb::det... | libassembly.so | 0.70 | 0.70 | 0.12 | 0.12 | 0.45 | 0.45 | 128 | 0.17 | 0.02 | Others (%): 100.00 | |
○rml::internal::OrphanedBlocks::put(long, rml::internal::Block*) | libtbbmalloc.so.2.13 | 0.65 | 0.03 | 0.13 | 0.03 | 0.42 | 0.02 | 127 | 0.33 | 0.03 | Pthread (%): 99.23 Others (%): 0.77 | |
○mm_account_ptr_by_tid | libmkl_core.so.1 | 0.57 | 0.57 | 0.17 | 0.17 | 0.37 | 0.37 | 125 | 0.44 | 0.05 | Math (%): 100.00 | |
○mkl_blas_def_dgemm_copybn_bdz | libmkl_def.so.1 | 0.42 | 0.42 | 0.10 | 0.10 | 0.27 | 0.27 | 128 | 0.18 | 0.02 | Math (%): 100.00 | |
○aset::asolve::Element_U<aset::asolve::ReferenceElement<aset::asolve::quadrature::HexaGauss8, aset::asolve::Hexa8Interpolation1, 3, (aset::asolve::FormulationFlag)0>, TypeList<aset::asolve::ElementRule<aset::asolve::ReferenceElement<aset::... | libfinite_elements.so | 0.42 | 0.42 | 0.09 | 0.09 | 0.27 | 0.27 | 128 | 0.17 | 0.02 | Others (%): 100.00 | |
○__memset_avx512_erms | libc-2.28.so | 0.39 | 0.39 | 2.57 | 2.57 | 0.25 | 0.25 | 127 | 0.35 | 0.23 | Memory (%): 100.00 | |
○__memcpy_avx512_unaligned_erms | libc-2.28.so | 0.37 | 0.37 | 4.00 | 4.00 | 0.24 | 0.24 | 103 | 0.60 | 0.39 | Memory (%): 100.00 | |
○Eigen::internal::general_matrix_vector_product<long, double, Eigen::internal::TensorContractionInputMapper<double, long, 1, Eigen::TensorEvaluator<Eigen::TensorFixedSize<double, Eigen::Sizes<3l, 3l, 3l, 3l>, 0, long> const, Eigen::Defa... | libamat.so | 0.36 | 0.36 | 0.09 | 0.09 | 0.23 | 0.23 | 128 | 0.17 | 0.02 | Others (%): 100.00 | |
○mkl_blas_def_dgemm_copyat_bdz | libmkl_def.so.1 | 0.35 | 0.35 | 0.10 | 0.10 | 0.23 | 0.23 | 128 | 0.15 | 0.02 | Math (%): 100.00 | |
○aset::asolve::Node::add_dof(aset::asolve::DofType const&, aset::asolve::DofCollection&) | libdofs.so | 0.34 | 0.34 | 4.76 | 4.76 | 0.22 | 0.22 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○void Eigen::internal::call_dense_assignment_loop<Eigen::Matrix<double, 24, 24, 0, 24, 24>, Eigen::CwiseBinaryOp<Eigen::internal::scalar_product_op<double, double>, Eigen::Product<Eigen::Product<Eigen::Transpose<Eigen::Matrix<d... | libfinite_elements.so | 0.30 | 0.30 | 0.08 | 0.08 | 0.20 | 0.20 | 125 | 0.16 | 0.02 | Others (%): 100.00 | |
○aset::asolve::MutDof::operator aset::asolve::Dof() const | libdofs.so | 0.30 | 0.30 | 1.14 | 1.14 | 0.20 | 0.20 | 127 | 0.17 | 0.10 | Others (%): 100.00 | |
○mkl_blas_def_dgemm_copyan_bdz | libmkl_def.so.1 | 0.30 | 0.30 | 0.07 | 0.07 | 0.19 | 0.19 | 126 | 0.13 | 0.01 | Math (%): 100.00 | |
○void std::__introsort_loop<__gnu_cxx::__normal_iterator<int*, std::vector<int, std::allocator<int> > >, long, __gnu_cxx::__ops::_Iter_less_iter>(__gnu_cxx::__normal_iterator<int*, std::vector<int, std::allocator<int> >... | libassembly.so | 0.24 | 0.24 | 0.09 | 0.09 | 0.15 | 0.15 | 125 | 0.17 | 0.02 | Others (%): 100.00 | |
○aset::asolve::DofList::operator[](unsigned long) const | libdofs.so | 0.22 | 0.02 | 0.91 | 0.01 | 0.15 | 0.01 | 124 | 0.14 | 0.08 | Others (%): 100.00 | |
►aset::asolve::StorageCSC<int, double> aset::asolve::extract_modify_storage_constraint<int, double>(aset::asolve::StorageCSC<int, double>&, std::vector<bool, std::allocator<bool> > const&, double) | multithreading_assembly_perf_test | 0.20 | 0.00 | 2.84 | 0.00 | 0.13 | 0.00 | 1 | 0.00 | 0.00 | Exe (%): 100.00 | GNU C++20 13.2.0 -march=znver4 -g3 -O3 -std=c++20 -fno-omit-frame-pointer -fopenmp |
►Loop 312 - vector.tcc:114-523 - multithreading_assembly_perf_test [...] | 0.20 | 0.00 | 2.84 | 0.04 | 0.13 | 0.00 | 1 | 0.00 | 0.00 | |||
►Loop 324 - new_allocator.h:147-168 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 325 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 326 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0.00 | 0.00 | |||
○Loop 311 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 327 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
►Loop 321 - new_allocator.h:147-168 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 1 | 0.00 | 0.00 | |||
○Loop 323 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0.00 | 0.00 | |||
○Loop 322 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
►Loop 314 - sparse_matrix.hpp:708-714 - multithreading_assembly_perf_test [...] | 0.20 | 0.20 | 2.78 | 2.78 | 0.13 | 0.13 | 1 | 0.00 | 0.00 | |||
○Loop 315 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 313 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 317 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 316 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 320 - stl_algo.h:2030-2041 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 319 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 318 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0.00 | 0.00 | |||
►aset::asolve::FiniteElement::dofs_rank() const | multithreading_assembly_perf_test | 0.20 | 0.17 | 0.80 | 0.58 | 0.13 | 0.11 | 125 | 0.13 | 0.07 | Exe (%): 100.00 | GNU C++20 13.2.0 -march=znver4 -g3 -O3 -std=c++20 -fno-omit-frame-pointer -fopenmp |
○Loop 188 - allocator.h:184-184 - multithreading_assembly_perf_test | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 189 - finite_elements.hpp:288-289 - multithreading_assembly_perf_test [...] | 0.03 | 0.03 | 0.23 | 0.23 | 0.02 | 0.02 | 31 | 0.05 | 0.04 | |||
○rml::internal::Backend::coalescAndPutList(rml::internal::FreeBlock*, bool, bool) | libtbbmalloc.so.2.13 | 0.19 | 0.00 | 0.05 | 0.00 | 0.12 | 0.00 | 127 | 0.09 | 0.01 | Others (%): 100.00 | |
○aset::asolve::MutDofIterator::operator*() const | libdofs.so | 0.18 | 0.06 | 2.48 | 0.63 | 0.12 | 0.04 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○aset::asolve::Dof::rank() const | libdofs.so | 0.18 | 0.18 | 0.81 | 0.81 | 0.11 | 0.11 | 114 | 0.12 | 0.07 | Others (%): 100.00 | |
○aset::asolve::Assembler<aset::asolve::FESpace, Eigen::SparseMatrix<double, 0, int> >::element_to_element_() | libassembly.so | 0.17 | 0.17 | 2.39 | 2.39 | 0.11 | 0.11 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○mkl_serv_cbwr_get@plt | libmkl_core.so.1 | 0.17 | 0.17 | 0.05 | 0.05 | 0.11 | 0.11 | 125 | 0.10 | 0.01 | Math (%): 100.00 | |
○aset::amat::BehaviorBase::update_val_for_input_variables() | libamat.so | 0.16 | 0.16 | 0.05 | 0.05 | 0.11 | 0.11 | 122 | 0.10 | 0.01 | Others (%): 100.00 | |
○__memset_avx512_unaligned_erms | libc-2.28.so | 0.16 | 0.16 | 0.07 | 0.07 | 0.10 | 0.10 | 119 | 0.10 | 0.01 | Memory (%): 100.00 | |
○mkl_blas_def_xdgemm_bdz | libmkl_def.so.1 | 0.15 | 0.15 | 0.05 | 0.05 | 0.10 | 0.10 | 122 | 0.10 | 0.01 | Math (%): 100.00 | |
○rml::internal::freeSmallObject(void*) [clone .lto_priv.0] | libtbbmalloc.so.2.13 | 0.14 | 0.14 | 0.23 | 0.23 | 0.09 | 0.09 | 115 | 0.08 | 0.02 | Others (%): 100.00 | |
○_int_free | libc-2.28.so | 0.14 | 0.14 | 1.84 | 1.84 | 0.09 | 0.09 | 24 | 0.57 | 0.37 | Memory (%): 100.00 | |
○aset::amat::IsotropicElasticBehavior::integrate() const | libamat.so | 0.13 | 0.13 | 0.04 | 0.04 | 0.09 | 0.09 | 120 | 0.09 | 0.01 | Others (%): 100.00 | |
○rml::internal::MemoryPool::getEmptyBlock(unsigned long) | libtbbmalloc.so.2.13 | 0.13 | 0.13 | 0.04 | 0.04 | 0.08 | 0.08 | 119 | 0.08 | 0.01 | Others (%): 100.00 | |
○__GI___libc_malloc | libc-2.28.so | 0.12 | 0.12 | 1.41 | 1.41 | 0.08 | 0.08 | 41 | 0.33 | 0.22 | Memory (%): 100.00 | |
○std::array<std::pair<aset::asolve::DofType, int>, (total_nb_dofs<TypeList<aset::asolve::ElementRule<aset::asolve::ReferenceElement<aset::asolve::quadrature::HexaGauss8, aset::asolve::Hexa8Interpolation1, 3, (aset::asolve::FormulationFl... | libfinite_elements.so | 0.11 | 0.11 | 1.53 | 1.53 | 0.07 | 0.07 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○aset::asolve::Dof::increment_value() const | libdofs.so | 0.11 | 0.11 | 0.03 | 0.03 | 0.07 | 0.07 | 113 | 0.07 | 0.01 | Others (%): 100.00 | |
►aset::asolve::StorageCSC<int, double>::StorageCSC<tbb::detail::d1::scalable_allocator<int> >(int, int, std::vector<std::vector<int, tbb::detail::d1::scalable_allocator<int> >, std::allocator<std::vector<int, tbb::deta... | multithreading_assembly_perf_test | 0.10 | 0.00 | 1.45 | 0.00 | 0.07 | 0.00 | 1 | 0.00 | 0.00 | Exe (%): 100.00 | GNU C++20 13.2.0 -march=znver4 -g3 -O3 -std=c++20 -fno-omit-frame-pointer -fopenmp |
►Loop 369 - vector.tcc:114-836 - multithreading_assembly_perf_test [...] | 0.10 | 0.01 | 1.44 | 0.09 | 0.07 | 0.00 | 1 | 0.00 | 0.00 | |||
○Loop 368 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 373 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 372 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 371 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 375 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.10 | 0.10 | 1.35 | 1.35 | 0.06 | 0.06 | 1 | 0.00 | 0.00 | |||
○Loop 370 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 376 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 374 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 367 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 378 - stl_iterator.h:1197-1197 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0.00 | 0.00 | |||
○Loop 366 - allocator.h:184-184 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○Loop 377 - stl_uninitialized.h:351-351 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | |||
○aset::asolve::Dof::begin_total_value() const | libdofs.so | 0.09 | 0.09 | 0.03 | 0.03 | 0.06 | 0.06 | 109 | 0.06 | 0.01 | Others (%): 100.00 | |
○aset::asolve::Part::create_elements(aset::asolve::FESpace&) | libfe_space.so | 0.09 | 0.09 | 1.31 | 1.31 | 0.06 | 0.06 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○mkl_serv_cbwr_get | libmkl_core.so.1 | 0.09 | 0.09 | 0.04 | 0.04 | 0.06 | 0.06 | 111 | 0.06 | 0.01 | Math (%): 100.00 | |
○_int_malloc | libc-2.28.so | 0.09 | 0.09 | 1.20 | 1.20 | 0.06 | 0.06 | 11 | 0.54 | 0.36 | Memory (%): 100.00 | |
○aset::amat::IPDataView::attach_storage_for_ip(unsigned long) | libamat.so | 0.09 | 0.09 | 0.03 | 0.03 | 0.06 | 0.06 | 113 | 0.05 | 0.01 | Others (%): 100.00 | |
○mkl_serv_allocate | libmkl_core.so.1 | 0.09 | 0.09 | 0.04 | 0.04 | 0.06 | 0.06 | 106 | 0.07 | 0.01 | Math (%): 100.00 | |
○aset::asolve::FESpace::elements(std::basic_string_view<char, std::char_traits<char> >) const | libfe_space.so | 0.08 | 0.08 | 1.14 | 1.14 | 0.05 | 0.05 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○Eigen::internal::compute_inverse<Eigen::Matrix<double, 3, 3, 0, 3, 3>, Eigen::Matrix<double, 3, 3, 0, 3, 3>, 3>::run(Eigen::Matrix<double, 3, 3, 0, 3, 3> const&, Eigen::Matrix<double, 3, 3, 0, 3, 3>&) | libfinite_elements.so | 0.08 | 0.08 | 0.04 | 0.04 | 0.05 | 0.05 | 106 | 0.06 | 0.01 | Others (%): 100.00 | |
○aset::amat::IPDataView::compute_rate_from_incr(double const&) | libamat.so | 0.08 | 0.08 | 0.04 | 0.04 | 0.05 | 0.05 | 103 | 0.06 | 0.01 | Others (%): 100.00 | |
○__memcmp_avx2_movbe | libc-2.28.so | 0.07 | 0.07 | 0.94 | 0.94 | 0.05 | 0.05 | 16 | 0.35 | 0.23 | Memory (%): 100.00 | |
○_dl_update_slotinfo | ld-2.28.so | 0.07 | 0.07 | 0.02 | 0.02 | 0.05 | 0.05 | 95 | 0.05 | 0.01 | System (%): 100.00 | |
○mkl_blas_errchk_dgemm | libmkl_intel_lp64.so.1 | 0.07 | 0.07 | 0.02 | 0.02 | 0.05 | 0.05 | 99 | 0.05 | 0.00 | Math (%): 100.00 | |
○mkl_serv_lsame | libmkl_core.so.1 | 0.07 | 0.07 | 0.04 | 0.04 | 0.04 | 0.04 | 103 | 0.05 | 0.01 | Math (%): 100.00 | |
○void Eigen::internal::call_dense_assignment_loop<Eigen::Matrix<double, 9, 1, 0, 9, 1>, Eigen::Map<Eigen::Matrix<double, 9, 1, 0, 9, 1>, 0, Eigen::Stride<0, 0> >, Eigen::internal::assign_op<double, double> >(Eigen::Matrix... | libfinite_elements.so | 0.06 | 0.06 | 0.03 | 0.03 | 0.04 | 0.04 | 82 | 0.06 | 0.01 | Others (%): 100.00 | |
○scalable_free | libtbbmalloc.so.2.13 | 0.06 | 0.06 | 0.63 | 0.63 | 0.04 | 0.04 | 30 | 0.17 | 0.11 | Others (%): 100.00 | |
○auto aset::asolve::GenericFiniteElement<aset::asolve::ReferenceElement<aset::asolve::quadrature::HexaGauss8, aset::asolve::Hexa8Interpolation1, 3, (aset::asolve::FormulationFlag)0>, TypeList<aset::asolve::ElementRule<aset::asolve::ReferenceE... | libfinite_elements.so | 0.06 | 0.06 | 0.02 | 0.02 | 0.04 | 0.04 | 91 | 0.05 | 0.00 | Others (%): 100.00 | |
○Eigen::internal::TensorExecutor<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::TensorFixedSize<double, Eigen::Sizes<3l, 3l>, 0, long>, 0, Eigen::MakePointer>, Eigen::TensorFixedSize<double, Eigen::Sizes<3l, 3l>, 0, long> ... | libfinite_elements.so | 0.05 | 0.05 | 0.02 | 0.02 | 0.04 | 0.04 | 86 | 0.05 | 0.01 | Others (%): 100.00 | |
○mkl_serv_deallocate | libmkl_core.so.1 | 0.05 | 0.05 | 0.03 | 0.03 | 0.03 | 0.03 | 87 | 0.04 | 0.00 | Math (%): 100.00 | |
○mkl_blas_errchk_dgemv | libmkl_intel_lp64.so.1 | 0.05 | 0.05 | 0.02 | 0.02 | 0.03 | 0.03 | 86 | 0.04 | 0.00 | Math (%): 100.00 | |
○void Eigen::internal::call_dense_assignment_loop<Eigen::Matrix<double, 9, 9, 0, 9, 9>, Eigen::Map<Eigen::Matrix<double, -1, -1, 0, -1, -1>, 0, Eigen::Stride<0, 0> >, Eigen::internal::assign_op<double, double> >(Eigen::Ma... | libfinite_elements.so | 0.05 | 0.05 | 0.02 | 0.02 | 0.03 | 0.03 | 83 | 0.04 | 0.00 | Others (%): 100.00 | |
○void Eigen::TensorEvaluator<Eigen::TensorContractionOp<std::array<Eigen::IndexPair<int>, 2ul> const, Eigen::TensorFixedSize<double, Eigen::Sizes<3l, 3l, 3l, 3l>, 0, long> const, Eigen::TensorFixedSize<double, Eigen::Sizes&l... | libamat.so | 0.05 | 0.05 | 0.02 | 0.02 | 0.03 | 0.03 | 79 | 0.04 | 0.00 | Others (%): 100.00 | |
○Eigen::internal::TensorExecutor<Eigen::TensorAssignOp<Eigen::TensorFixedSize<double, Eigen::Sizes<3l, 3l>, 0, long>, Eigen::TensorMap<Eigen::TensorFixedSize<double, Eigen::Sizes<3l, 3l>, 0, long>, 0, Eigen::MakePointer> ... | libfinite_elements.so | 0.04 | 0.04 | 0.02 | 0.02 | 0.03 | 0.03 | 75 | 0.04 | 0.00 | Others (%): 100.00 | |
○aset::asolve::Dof::get_dof_type() const | libdofs.so | 0.04 | 0.04 | 0.61 | 0.61 | 0.03 | 0.03 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○rml::internal::LargeObjectCache::doCleanup(unsigned long, bool) | libtbbmalloc.so.2.13 | 0.04 | 0.04 | 0.02 | 0.02 | 0.03 | 0.03 | 79 | 0.03 | 0.00 | Others (%): 100.00 | |
○__GI___pthread_getspecific | libpthread-2.28.so | 0.04 | 0.04 | 0.05 | 0.05 | 0.03 | 0.03 | 76 | 0.06 | 0.01 | Math (%): 81.67 Pthread (%): 18.33 | |
○rml::internal::internalMalloc(unsigned long) | libtbbmalloc.so.2.13 | 0.04 | 0.04 | 0.02 | 0.02 | 0.03 | 0.03 | 81 | 0.03 | 0.00 | Others (%): 100.00 | |
○mkl_blas_def_xdgemm | libmkl_def.so.1 | 0.04 | 0.04 | 0.02 | 0.02 | 0.03 | 0.03 | 78 | 0.04 | 0.00 | Math (%): 100.00 | |
○aset::asolve::Node::position() const | libdofs.so | 0.04 | 0.04 | 0.03 | 0.03 | 0.03 | 0.03 | 81 | 0.04 | 0.00 | Others (%): 100.00 | |
○aset::amat::MaterialContext::get_tangent_operator(unsigned long) const | libamat.so | 0.04 | 0.04 | 0.02 | 0.02 | 0.02 | 0.02 | 69 | 0.04 | 0.00 | Others (%): 100.00 | |
○aset::asolve::Node::dofs() | libdofs.so | 0.04 | 0.04 | 0.51 | 0.51 | 0.02 | 0.02 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○aset::asolve::GenericFiniteElement<aset::asolve::ReferenceElement<aset::asolve::quadrature::HexaGauss8, aset::asolve::Hexa8Interpolation1, 3, (aset::asolve::FormulationFlag)0>, TypeList<aset::asolve::ElementRule<aset::asolve::ReferenceElemen... | libfinite_elements.so | 0.04 | 0.04 | 0.51 | 0.51 | 0.02 | 0.02 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○__GI___libc_free | libc-2.28.so | 0.03 | 0.03 | 0.46 | 0.46 | 0.02 | 0.02 | 7 | 0.25 | 0.17 | Memory (%): 100.00 | |
○__tls_get_addr | ld-2.28.so | 0.03 | 0.03 | 0.03 | 0.03 | 0.02 | 0.02 | 72 | 0.04 | 0.00 | System (%): 100.00 | |
○aset::amat::Behavior<aset::amat::IsotropicElasticBehavior>::integration() const | libamat.so | 0.03 | 0.03 | 0.02 | 0.02 | 0.02 | 0.02 | 68 | 0.03 | 0.00 | Others (%): 100.00 | |
○mkl_serv_cpu_detect | libmkl_core.so.1 | 0.03 | 0.03 | 0.01 | 0.01 | 0.02 | 0.02 | 61 | 0.03 | 0.00 | Math (%): 100.00 | |
○aset::asolve::MutDofList::end() | libdofs.so | 0.03 | 0.03 | 0.44 | 0.44 | 0.02 | 0.02 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○std::_Rb_tree<std::pair<int, int>, std::pair<std::pair<int, int> const, aset::asolve::FiniteElement*>, std::_Select1st<std::pair<std::pair<int, int> const, aset::asolve::FiniteElement*> >, std::less<std::pair<in... | libfe_space.so | 0.03 | 0.03 | 0.44 | 0.44 | 0.02 | 0.02 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○aset::amat::BehaviorDirectIntegrator<aset::amat::BehaviorBase>::integrate() | libamat.so | 0.03 | 0.03 | 0.01 | 0.01 | 0.02 | 0.02 | 69 | 0.03 | 0.00 | Others (%): 100.00 | |
○update_get_addr | ld-2.28.so | 0.03 | 0.03 | 0.02 | 0.02 | 0.02 | 0.02 | 60 | 0.03 | 0.00 | System (%): 100.00 | |
○tbb::detail::d1::task* tbb::detail::r1::task_dispatcher::receive_or_steal_task<false, tbb::detail::r1::outermost_worker_waiter>(tbb::detail::r1::thread_data&, tbb::detail::r1::execution_data_ext&, tbb::detail::r1::outermost_worker_waiter&... | libtbb.so.12.13 | 0.03 | 0.03 | 0.01 | 0.01 | 0.02 | 0.02 | 69 | 0.02 | 0.00 | Others (%): 100.00 | |
○aset::amat::IntegrationPointDataBlock::operator[](unsigned long) | libamat.so | 0.03 | 0.03 | 0.41 | 0.41 | 0.02 | 0.02 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○malloc_consolidate | libc-2.28.so | 0.03 | 0.03 | 0.41 | 0.41 | 0.02 | 0.02 | 1 | 0.00 | 0.00 | Memory (%): 76.83 Math (%): 23.17 | |
○void std::vector<int, tbb::detail::d1::scalable_allocator<int> >::_M_range_insert<__gnu_cxx::__normal_iterator<int const*, std::vector<int, std::allocator<int> > > >(__gnu_cxx::__normal_iterator<int*, std::vector<i... | libassembly.so | 0.03 | 0.03 | 0.02 | 0.02 | 0.02 | 0.02 | 59 | 0.03 | 0.00 | Others (%): 100.00 | |
○mkl_blas_dgemm | libmkl_sequential.so.1 | 0.03 | 0.03 | 0.01 | 0.01 | 0.02 | 0.02 | 56 | 0.03 | 0.00 | Math (%): 100.00 | |
○aset::asolve::DofList::push_back(unsigned long) | libdofs.so | 0.03 | 0.03 | 0.37 | 0.37 | 0.02 | 0.02 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○mkl_blas_def_dgemm_getbufs_bdz | libmkl_def.so.1 | 0.03 | 0.03 | 0.02 | 0.02 | 0.02 | 0.02 | 51 | 0.03 | 0.00 | Math (%): 100.00 | |
○Eigen::internal::TensorExecutor<Eigen::TensorAssignOp<Eigen::TensorFixedSize<double, Eigen::Sizes<3l, 3l>, 0, long>, Eigen::TensorContractionOp<std::array<Eigen::IndexPair<int>, 2ul> const, Eigen::TensorFixedSize<double,... | libamat.so | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 50 | 0.02 | 0.00 | Others (%): 100.00 | |
○tbb::detail::r1::outermost_worker_waiter::continue_execution(tbb::detail::r1::arena_slot&, tbb::detail::d1::task*&) const | libtbb.so.12.13 | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 53 | 0.02 | 0.00 | Others (%): 100.00 | |
○std::_Sp_counted_base<(__gnu_cxx::_Lock_policy)2>::_M_release() | multithreading_assembly_perf_test | 0.02 | 0.00 | 0.30 | 0.00 | 0.01 | 0.00 | 1 | 0.00 | 0.00 | Exe (%): 100.00 | GNU C++20 13.2.0 -march=znver4 -g3 -O3 -std=c++20 -fno-omit-frame-pointer -fopenmp |
○aset::amat::Behavior<aset::amat::IsotropicElasticBehavior>::compute_tangent_operator_direct() const | libamat.so | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 48 | 0.03 | 0.00 | Others (%): 100.00 | |
○aset::asolve::DofIterator::operator*() const | libdofs.so | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 53 | 0.02 | 0.00 | Others (%): 100.00 | |
○mkl_serv_set_xerbla_interface | libmkl_sequential.so.1 | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 47 | 0.02 | 0.00 | Math (%): 100.00 | |
○aset::asolve::Mesh::setup_id_to_rank_index() | libmesh.so | 0.02 | 0.02 | 0.29 | 0.29 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○unknown_function | [vdso] | 0.02 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 46 | 0.02 | 0.00 | Others (%): 100.00 | |
○aset::asolve::DofCollection::push_back_dof(aset::asolve::DofType const&) | libdofs.so | 0.02 | 0.02 | 0.27 | 0.27 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○Eigen::PlainObjectBase<Eigen::Matrix<double, 24, 24, 0, 24, 24> >::PlainObjectBase<Eigen::CwiseNullaryOp<Eigen::internal::scalar_constant_op<double>, Eigen::Matrix<double, 24, 24, 0, 24, 24> > >(Eigen::DenseBase<Eigen... | libfinite_elements.so | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 40 | 0.03 | 0.00 | Others (%): 100.00 | |
○std::_Hash_bytes(void const*, unsigned long, unsigned long) | libstdc++.so.6.0.32 | 0.02 | 0.02 | 0.25 | 0.25 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○aset::amat::MaterialContext::integrate() const | libamat.so | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 39 | 0.02 | 0.00 | Others (%): 100.00 | |
○aset::asolve::DofTypeRecorder::operator[](long) const | libdofs.so | 0.02 | 0.02 | 0.23 | 0.23 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○aset::asolve::GenericFiniteElement<aset::asolve::ReferenceElement<aset::asolve::quadrature::HexaGauss8, aset::asolve::Hexa8Interpolation1, 3, (aset::asolve::FormulationFlag)0>, TypeList<aset::asolve::ElementRule<aset::asolve::ReferenceElemen... | libfinite_elements.so | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 36 | 0.02 | 0.00 | Others (%): 100.00 | |
○rml::internal::BackRefIdx::newBackRef(bool) | libtbbmalloc.so.2.13 | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 38 | 0.02 | 0.00 | Others (%): 100.00 | |
○mkl_blas_xdgemv | libmkl_core.so.1 | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 41 | 0.01 | 0.00 | Math (%): 100.00 | |
○__tls_get_addr_slow | ld-2.28.so | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 40 | 0.01 | 0.00 | System (%): 100.00 | |
○mkl_blas_def_dgemm_blk_info_bdz | libmkl_def.so.1 | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 39 | 0.01 | 0.00 | Math (%): 100.00 | |
○operator new(unsigned long) | libstdc++.so.6.0.32 | 0.01 | 0.01 | 0.21 | 0.21 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
►aset::asolve::Graph<int>::colorize() | multithreading_assembly_perf_test | 0.01 | 0.00 | 0.20 | 0.00 | 0.01 | 0.00 | 1 | 0.00 | 0.00 | Exe (%): 100.00 | GNU C++20 13.2.0 -march=znver4 -g3 -O3 -std=c++20 -fno-omit-frame-pointer -fopenmp |
►Loop 443 - graph_tools.hpp:104-205 - multithreading_assembly_perf_test [...] | 0.01 | 0.00 | 0.20 | 0.01 | 0.01 | 0.00 | 1 | 0.00 | 0.00 | |||
○Loop 444 - graph_tools.hpp:202-203 - multithreading_assembly_perf_test [...] | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0.00 | 0.00 | |||
○Loop 445 - graph_tools.hpp:199-200 - multithreading_assembly_perf_test [...] | 0.01 | 0.01 | 0.16 | 0.16 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | |||
○unknown_function | multithreading_assembly_perf_test | 0.01 | 0.00 | 0.11 | 0.00 | 0.01 | 0.00 | 17 | 0.03 | 0.02 | Exe (%): 100.00 | |
○mkl_serv_cpuiszen | libmkl_core.so.1 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 32 | 0.02 | 0.00 | Math (%): 100.00 | |
○unlink_chunk.isra.2 | libc-2.28.so | 0.01 | 0.01 | 0.19 | 0.19 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | Memory (%): 86.49 Math (%): 13.51 | |
○void Eigen::internal::gemv_dense_selector<2, 1, true>::run<Eigen::Transpose<Eigen::Matrix<double, 9, 24, 0, 9, 24> >, Eigen::Matrix<double, 9, 1, 0, 9, 1>, Eigen::Matrix<double, 24, 1, 0, 24, 1> >(Eigen::Transpose<Eig... | libfinite_elements.so | 0.01 | 0.01 | 0.02 | 0.02 | 0.01 | 0.01 | 30 | 0.03 | 0.00 | Others (%): 100.00 | |
○mkl_serv_lsame@plt | libmkl_intel_lp64.so.1 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 29 | 0.02 | 0.00 | Math (%): 100.00 | |
○std::__detail::_Node_const_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, aset::acore::FunParamWrapper<aset::asolve::FiniteElement> >, false, true> std::_Hashtab... | libfe_space.so | 0.01 | 0.01 | 0.16 | 0.16 | 0.01 | 0.01 | 1 | 0.00 | 0.00 | Others (%): 100.00 | |
○rml::internal::FreeBlockPool::returnBlock(rml::internal::Block*) | libtbbmalloc.so.2.13 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 26 | 0.03 | 0.00 | Others (%): 100.00 | |
○aset::amat::BehaviorDirectIntegrator<aset::amat::BehaviorBase>::compute_tangent_operator() | libamat.so | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | 25 | 0.02 | 0.00 | Others (%): 100.00 | |
○rml::internal::MemoryPool::onThreadShutdown(rml::internal::TLSData*) [clone .part.0] | libtbbmalloc.so.2.13 | 0.01 | 0.01 | 0.00 | 0.00 | 0.01 | 0.01 | 29 | 0.00 | 0.00 | Pthread (%): 100.00 |