********************************************************************************
MAQAO 2.21.4 - 07eb2902ade069371c0df3e2f8cceca5d41c0371::20250519-154801 || 2025/05/19
./maqao_custom OV -R1 --with-scalability -c=maqao_config.json -xp=scalability_limited
CPY: [true] ./multithreading_assembly_perf_test --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/Assembly/libassembly.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libassembly.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/BoundaryConditions/libboundary_conditions.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libboundary_conditions.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/Dofs/libdofs.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libdofs.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/ExternalParameters/libexternal_parameters.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libexternal_parameters.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/FESpace/libfe_space.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libfe_space.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/FiniteElements/libfinite_elements.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libfinite_elements.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/LinearSolvers/liblinear_solvers.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/liblinear_solvers.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/Mesh/libmesh.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libmesh.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/NonLinearSolvers/libnon_linear_solvers.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libnon_linear_solvers.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/Output/liboutput.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/liboutput.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/Problem/libproblem.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libproblem.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/src/Tools/libtools.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libtools.so
CPY: [true] /data/coe/users/d644583/a-set-gcc/build/a-solve/tests/test_helpers/libasolve_test_helpers.so --> /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/libs/libasolve_test_helpers.so
CMD: OMP_NUM_THREADS=1 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_0" --mpi-command="mpirun -n 1 --map-by slot:PE=1 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 1 --ncut 200 --method ColMutexes --storage SparseCOO
CMD: OMP_NUM_THREADS=2 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_1" --mpi-command="mpirun -n 1 --map-by slot:PE=2 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 2 --ncut 200 --method ColMutexes --storage SparseCOO
CMD: OMP_NUM_THREADS=4 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_2" --mpi-command="mpirun -n 1 --map-by slot:PE=4 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 4 --ncut 200 --method ColMutexes --storage SparseCOO
CMD: OMP_NUM_THREADS=8 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_3" --mpi-command="mpirun -n 1 --map-by slot:PE=8 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 8 --ncut 200 --method ColMutexes --storage SparseCOO
CMD: OMP_NUM_THREADS=16 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_4" --mpi-command="mpirun -n 1 --map-by slot:PE=16 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 16 --ncut 200 --method ColMutexes --storage SparseCOO
CMD: OMP_NUM_THREADS=32 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_5" --mpi-command="mpirun -n 1 --map-by slot:PE=32 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 32 --ncut 200 --method ColMutexes --storage SparseCOO
CMD: OMP_NUM_THREADS=64 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_6" --mpi-command="mpirun -n 1 --map-by slot:PE=64 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 64 --ncut 200 --method ColMutexes --storage SparseCOO
CMD: OMP_NUM_THREADS=128 /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/./maqao_custom lprof _caller=oneview -start-after-seconds=-1 --xp="/data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/tools/lprof_npsu_run_7" --mpi-command="mpirun -n 1 --map-by slot:PE=128 --bind-to core" --collect-CPU-time-intervals --collect-topology -ldi=libassembly.so,libboundary_conditions.so,libdofs.so,libexternal_parameters.so,libfe_space.so,libfinite_elements.so,liblinear_solvers.so,libmesh.so,libnon_linear_solvers.so,liboutput.so,libproblem.so,libtools.so,libasolve_test_helpers.so -stdout-start-keywords="Starting compute_internal_reac" -stdout-stop-keywords="compute_internal_reac done" -- /data/coe/users/d644583/a-set-gcc/build/a-solve/perf_tests/assembly_perf_tests/scalability_limited/binaries/multithreading_assembly_perf_test --max_threads 128 --ncut 200 --method ColMutexes --storage SparseCOO
In run tbb_1, 3 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.018583702621981% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
12 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.07061806996353% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run tbb_2, 1 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.0036174415145069% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
7 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.028939532116055% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run tbb_4, 1 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.0035590787883848% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
1 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.0035590787883848% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run tbb_8, 2 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.010311695281416% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run tbb_16, 2 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.014767178334296% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
3 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.0088603072799742% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run tbb_32, 2 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.012213966809213% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
3 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.0081426445394755% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run tbb_64, 4 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.017501674126834% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
3 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.0032815639860927% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run tbb_128, 7 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.01381925525493% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
9 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.01%).
That represents 0.011516046070028% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis