options

gmx - 2024-08-01 18:14:42 - MAQAO 2.20.7

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

Global Metrics

Total Time (s)82.84
Profiled Time (s)81.16
Time in analyzed loops (%)26.6
Time in analyzed innermost loops (%)24.5
Time in user code (%)26.8
Compilation Options Score (%)100
Array Access Efficiency (%)59.5
Potential Speedups
Perfect Flow Complexity1.04
Perfect OpenMP + MPI + Pthread1.16
Perfect OpenMP + MPI + Pthread + Perfect Load Distribution3.68
No Scalar IntegerPotential Speedup1.01
Nb Loops to get 80%10
FP VectorisedPotential Speedup1.01
Nb Loops to get 80%8
Fully VectorisedPotential Speedup1.12
Nb Loops to get 80%13
FP Arithmetic OnlyPotential Speedup1.10
Nb Loops to get 80%11

CQA Potential Speedups Summary

Loop Based Profile⏎

Innermost Loop Based Profile⏎

Application Categorization⏎

Compilation Options⏎

Source ObjectIssue
▼libgromacs.so.9.0.0–
○lincs.cpp
○pbc.cpp
○pme_redistribute.cpp
○fft5d.cpp
○threaded_force_buffer.cpp
○event.cpp
○pme_grid.cpp
○pme_gather.cpp
○kerneldispatch.cpp
○simd_prune_kernel.cpp
○pme_spread.cpp
○calc_verletbuf.cpp
○simd_kernel.h
○settle.cpp
○pairs.cpp
○pairlist.cpp
○sim_util.cpp
○update.cpp
○md_support.cpp
○domdec_specatomcomm.cpp
○kernel_common.cpp
○pme_solve.cpp
○atomdata.cpp
○bonded.cpp

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../../install/bin/gmx
Timestamp2024-08-01 18:14:42 Universal Timestamp1722528882
Number of processes observed1 Number of threads observed192
Experiment TypeOpenMP;
Machineins01.benchmarkcenter.megware.com
Model NameAMD EPYC 9654 96-Core Processor
Architecturex86_64 Micro ArchitectureZEN_V4
Cache Size1024 KB Number of Cores96
OS VersionLinux 5.14.0-427.18.1.el9_4.x86_64 #1 SMP PREEMPT_DYNAMIC Tue May 28 06:27:02 EDT 2024
Architecture used during static analysisx86_64 Micro Architecture used during static analysisZEN_V4
Frequency Driveracpi-cpufreq Frequency Governorperformance
Huge Pagesalways Hyperthreadingon
Number of sockets2 Number of cores per socket96
Compilation Optionslibgromacs.so.9.0.0: AMD clang version 16.0.3 (CLANG: AOCC_4.1.0-Build#270 2023_07_10) /cluster/comp/aocc/4.1.0/bin/clang-16 --driver-mode=g++ -D GMX_DOUBLE=0 -D HAVE_CONFIG_H -D TMPI_EXPORTS -D TMPI_USE_VISIBILITY -D USE_STD_INTTYPES_H -D libgromacs_EXPORTS -I /home/eoseret/gromacs-2024.2/src/include -I /home/eoseret/gromacs-2024.2/build/src/include -I /home/eoseret/gromacs-2024.2/src -I /home/eoseret/gromacs-2024.2/api/legacy/include -I /home/eoseret/gromacs-2024.2/build/api/legacy/include -I /home/eoseret/gromacs-2024.2/src/gromacs/analysisdata/include -I /home/eoseret/gromacs-2024.2/src/gromacs/applied_forces/include -I /home/eoseret/gromacs-2024.2/src/gromacs/commandline/include -I /home/eoseret/gromacs-2024.2/src/gromacs/compat/include -I /home/eoseret/gromacs-2024.2/src/gromacs/coordinateio/include -I /home/eoseret/gromacs-2024.2/src/gromacs/correlationfunctions/include -I /home/eoseret/gromacs-2024.2/src/gromacs/fft/include -I /home/eoseret/gromacs-2024.2/src/gromacs/gpu_utils/include -I /home/eoseret/gromacs-2024.2/src/gromacs/math/include -I /home/eoseret/gromacs-2024.2/src/gromacs/timing/include -I /home/eoseret/gromacs-2024.2/src/gromacs/utility/include -I /home/eoseret/gromacs-2024.2/src/gromacs/domdec/include -I /home/eoseret/gromacs-2024.2/src/gromacs/mdlib/include -I /home/eoseret/gromacs-2024.2/src/gromacs/pbcutil/include -I /home/eoseret/gromacs-2024.2/src/gromacs/pulling/include -I /home/eoseret/gromacs-2024.2/src/gromacs/topology/include -I /home/eoseret/gromacs-2024.2/src/gromacs/energyanalysis/include -I /home/eoseret/gromacs-2024.2/src/gromacs/fileio/include -I /home/eoseret/gromacs-2024.2/src/gromacs/essentialdynamics/include -I /home/eoseret/gromacs-2024.2/src/gromacs/ewald/include -I /home/eoseret/gromacs-2024.2/src/gromacs/gmxana/include -I /home/eoseret/gromacs-2024.2/src/gromacs/gmxlib/include -I /home/eoseret/gromacs-2024.2/src/gromacs/gmxpreprocess/include -I /home/eoseret/gromacs-2024.2/src/gromacs/mdtypes/include -I /home/eoseret/gromacs-2024.2/src/gromacs/hardware/include -I /home/eoseret/gromacs-2024.2/src/gromacs/imd/include -I /home/eoseret/gromacs-2024.2/src/gromacs/linearalgebra/include -I /home/eoseret/gromacs-2024.2/src/gromacs/listed_forces/include -I /home/eoseret/gromacs-2024.2/src/gromacs/mdrun/include -I /home/eoseret/gromacs-2024.2/src/gromacs/mdrunutility/include -I /home/eoseret/gromacs-2024.2/src/gromacs/mdspan/include -I /home/eoseret/gromacs-2024.2/src/gromacs/mimic/include -I /home/eoseret/gromacs-2024.2/src/gromacs/modularsimulator/include -I /home/eoseret/gromacs-2024.2/src/gromacs/nbnxm/include -I /home/eoseret/gromacs-2024.2/src/gromacs/onlinehelp/include -I /home/eoseret/gromacs-2024.2/src/gromacs/options/include -I /home/eoseret/gromacs-2024.2/src/gromacs/random/include -I /home/eoseret/gromacs-2024.2/src/gromacs/restraint/include -I /home/eoseret/gromacs-2024.2/src/gromacs/selection/include -I /home/eoseret/gromacs-2024.2/src/gromacs/simd/include -I /home/eoseret/gromacs-2024.2/src/gromacs/statistics/include -I /home/eoseret/gromacs-2024.2/src/gromacs/swap/include -I /home/eoseret/gromacs-2024.2/src/gromacs/tables/include -I /home/eoseret/gromacs-2024.2/src/gromacs/taskassignment/include -I /home/eoseret/gromacs-2024.2/src/gromacs/tools/include -I /home/eoseret/gromacs-2024.2/src/gromacs/trajectory/include -I /home/eoseret/gromacs-2024.2/src/gromacs/trajectoryanalysis/include -isystem /home/eoseret/gromacs-2024.2/src/external/thread_mpi/include -isystem /home/eoseret/gromacs-2024.2/src/external -isystem /home/eoseret/gromacs-2024.2/src/external/tng_io/include -isystem /home/eoseret/gromacs-2024.2/build/tng/include -isystem /cluster/intel/oneapi/2024.0.0/mkl/2024.0/include -isystem /home/eoseret/gromacs-2024.2/src/external/muparser/include -isystem /home/eoseret/gromacs-2024.2/src/external/lmfit -isystem /home/eoseret/gromacs-2024.2/src/external/colvars -g -fno-omit-frame-pointer -grecord-command-line -O3 -D NDEBUG -std=c++17 -fPIC -march=skylake-avx512 -Wno-reserved-identifier -Wno-missing-field-initializers -Weverything -Wno-c++98-compat -Wno-c++98-compat-pedantic -Wno-source-uses-openmp -Wno-c++17-extensions -Wno-documentation-unknown-command -Wno-covered-switch-default -Wno-switch-enum -Wno-switch-default -Wno-extra-semi-stmt -Wno-weak-vtables -Wno-shadow -Wno-padded -Wno-reserved-id-macro -Wno-double-promotion -Wno-exit-time-destructors -Wno-global-constructors -Wno-documentation -Wno-format-nonliteral -Wno-used-but-marked-unused -Wno-float-equal -Wno-conditional-uninitialized -Wno-conversion -Wno-disabled-macro-expansion -Wno-unused-macros -Wno-unsafe-buffer-usage -Wno-cast-function-type-strict -fopenmp=libomp -MD -MT src/gromacs/CMakeFiles/libgromacs.dir/nbnxm/kernel_common.cpp.o -MF CMakeFiles/libgromacs.dir/nbnxm/kernel_common.cpp.o.d -o CMakeFiles/libgromacs.dir/nbnxm/kernel_common.cpp.o -c /home/eoseret/gromacs-2024.2/src/gromacs/nbnxm/kernel_common.cpp
CommentsGROMACS 2024.2 compiled with AOCC 4.1 running on two 96 cores AMD Zen 4 processors, using 2 MPI threads and 92 OMP threads per MPI thread/rank. Pinning is controlled by GROMACS.

Configuration Summary

Dataset
Run Command<executable> mdrun -s ion_channel.tpr -ntmpi 2 -nsteps 10000 -pin on -deffnm aocc
Number Processes1
Number Nodes1
FilterNot Used
Profile StartNot Used
×