options

vlasiator - 2026-08-27 13:58:29 - MAQAO 2026.1.0

Help is available by moving the cursor above any symbol or by checking MAQAO website.

Global Metrics

Total Time (s)180.81
Max (Thread Active Time) (s)178.57
Average Active Time (s)96.07
Activity Ratio (%)53.6
Average number of active threads119.018
Affinity Stability (%)99.7
Time in analyzed loops (%)43.2
Time in analyzed innermost loops (%)34.2
Time in user code (%)65.1
Compilation Options Score (%)100
Array Access Efficiency (%)76.7
Potential Speedups
Perfect Flow Complexity1.16
Perfect OpenMP/MPI/Pthread/TBB1.13
Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution2.40
No Scalar IntegerPotential Speedup1.08
Nb Loops to get 80%5
FP VectorisedPotential Speedup1.12
Nb Loops to get 80%5
Fully VectorisedPotential Speedup1.34
Nb Loops to get 80%17
FP Arithmetic OnlyPotential Speedup1.25
Nb Loops to get 80%11

CQA Potential Speedups Summary

Average Active Threads Count⏎

Enable log scale

Loop Based Profile⏎

Innermost Loop Based Profile⏎

Application Categorization⏎

Compilation Options⏎

Source ObjectIssue
▼vlasiator–
○cpu_acc_sort_blocks.cpp
○quadr.cpp
○constantfield.cpp
○spatial_cell_cpu.cpp
○dipole.cpp
○velocity_mesh_cpu.h
○gridGlue.cpp
○arch_moments.cpp
○datareductionoperator.cpp
○sysboundary.cpp
○fsgrid.hpp
○integratefunction.cpp
○open_bucket_hashtable.h
○spatial_cell_cpu.hpp
○Magnetosphere.cpp
○velocity_mesh_parameters.cpp
○ldz_magnetic_field.cpp
○ldz_gradpe.cpp
○ldz_hall.cpp
○velocity_block_container.h
○arch_device_host.h
○gridGlue.hpp
○sysboundarycondition.cpp
○hashtable.h
○stl_algo.h
○cpu_trans_map_amr.cpp
○backgroundfield.cpp
○std_function.h
○ldz_electric_field.cpp
○ldz_volume.cpp
○arch_dt.cpp
○dccrg.hpp
○derivatives.cpp
○cpu_acc_map.cpp
○fs_common.cpp
○vectordipole.cpp
○cpu_acc_load_blocks.cpp
○projectTriAxisSearch.cpp
○backgroundfield.h

Loop Path Count Profile⏎

Cumulated Speedup If No Scalar Integer⏎

Cumulated Speedup If FP Vectorized⏎

Cumulated Speedup If Fully Vectorized⏎

Cumulated Speedup If FP Arithmetic Only⏎

Experiment Summary

Application/gpfs/projects/ehpc535/tools-scaling/vlasiator-installation/vlasiator
Timestamp2026-08-27 13:58:29 Universal Timestamp1787831909
Number of processes observed28 Number of threads observed224
Experiment TypeMPI; OpenMP;
Machinegs17r1b54,gs17r1b65
Model NameIntel(R) Xeon(R) Platinum 8480+
Architecturex86_64 Micro ArchitectureSAPPHIRE_RAPIDS
Cache Size107520 KB Number of Cores56
OS VersionLinux 5.14.0-687.25.1.el9_8.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Jul 9 14:15:14 EDT 2026
Architecture used during static analysisx86_64 Micro Architecture used during static analysisSAPPHIRE_RAPIDS
Frequency Driverintel_cpufreq Frequency Governorperformance
Huge Pagesalways Hyperthreadingon
Number of sockets2 Number of cores per socket56
Compilation Optionsvlasiator: clang version 20.1.8 /gpfs/apps/MN5/GPP/LLVM/20.1.8/GCC/bin/clang-20 --driver-mode=g++ -O3 -g -grecord-command-line -fopenmp -funroll-loops -std=c++20 -march=sapphirerapids -D USE_JEMALLOC -D JEMALLOC_NO_DEMANGLE -D MPICH_IGNORE_CXX_SEEK -MMD -D OMPI_SKIP_MPICXX -D PROFILE -D ACC_SEMILAG_PQM -D TRANS_SEMILAG_PPM -D CATCH_SIGTERM -I /gpfs/projects/ehpc535/tools-scaling/vlasiator-installation/deps/sources/phiprof/include -I /gpfs/projects/ehpc535/tools-scaling/vlasiator-installation/deps/include -D DP -D SPF -D VEC16F_AGNER -ffast-math -fno-finite-math-only -c vlasovsolver/cpu_trans_map_amr.cpp -I /gpfs/projects/ehpc535/tools-scaling/vlasiator-installation/vlasiator-vseitz -isystem ./submodules/eigen/ -I ./submodules/dccrg -I ./submodules/fsgrid -I /gpfs/projects/ehpc535/tools-scaling/vlasiator-installation/deps/include -I /gpfs/projects/ehpc535/tools-scaling/vlasiator-installation/deps/sources/phiprof/include -isystem ./submodules/vectorclass/ -isystem ./submodules/vectorclass-addon/vector3d/ -isystem ./submodules/eigen/ -I /gpfs/projects/ehpc535/tools-scaling/vlasiator-installation/deps/sources/vlsv/ -I /apps/GPP/OPENMPI/4.1.5/GCC/include

Configuration Summary

Dataset
Run Command<executable> --run_config Magnetosphere3D_small.cfg
MPI Commandsrun
Number Processes28
Number Nodes2
Number Processes per Node14
FilterNot Used
Profile StartNot Used
Profile StopNot Used

×