options

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

Global Metrics

Metricr0r1r2r3
Total Time (s)1.49 E3821.58806.64476.71
Profiled Time (s)1.49 E3818.03803.54473.06
Time in analyzed loops (%)6.986.506.655.97
Time in analyzed innermost loops (%)5.555.215.344.84
Time in user code (%)93.886.387.274.9
Compilation Options Score (%)100100100100
Array Access Efficiency (%)58.458.358.058.1
Scalability - Gap1.001.101.081.28
Potential Speedups
Perfect Flow Complexity1.021.021.021.02
Perfect OpenMP + MPI + Pthread1.031.071.061.11
Perfect OpenMP + MPI + Pthread + Perfect Load Distribution1.071.161.151.34
No Scalar IntegerPotential Speedup1.011.011.011.01
Nb Loops to get 80%8888
FP VectorisedPotential Speedup1.001.011.011.01
Nb Loops to get 80%3333
Fully VectorisedPotential Speedup1.071.061.071.06
Nb Loops to get 80%22222122
Only FP ArithmeticPotential Speedup1.041.031.031.03
Nb Loops to get 80%18191819
OpenMP perfectly balancedPotential Speedup1.031.091.081.18
Nb Loops to get 80%3323

Scalability Speedup

Cumulated Speedup If No Scalar Integer

Cumulated Speedup If FP Vectorized

Cumulated Speedup If Fully Vectorized

Cumulated Speedup If Only FP Arithmetic

Cumulated Speedup if OpenMP Perfectly Balanced

Loop Based Profiles

Innermost / Single Loops

Inbetween Loops

Outermost Loops

Cumulated Coverage With All Loops

Innermost Loop Based Profiles

Coverage

Count

Application Categorization

Time

Coverage

Compilation Options

Source ObjectIssue
▼picongpu–
▼TaskKernel.hpp–
○
▼EventStream.cpp–
○
▼TaskCopyDeviceToHost.hpp–
○
▼mutex–
○
▼TaskParticlesReceive.hpp–
○
▼eventSystem.cpp–
○
▼EventNotify.cpp–
○
▼Mask.hpp–
○
▼CommunicatorMPI.cpp–
○
▼TaskReceiveParticlesExchange.hpp–
○
▼ITask.hpp–
○
▼TaskFieldReceiveAndInsertExchange.hpp–
○
▼Apply.hpp–
○
▼TaskCopyDeviceToDevice.hpp–
○
▼Simulation.hpp–
○
▼ParticlesBase.tpp–
○
▼EventPool.hpp–
○
▼StrideMapping.hpp–
○
▼CopyGuardToExchange.hpp–
○
▼kernel.hpp–
○
▼EventTask.cpp–
○
▼CurrentDeposition.hpp–
○
▼EventGenericThreads.hpp–
○
▼Deposit.hpp–
○
▼shared_ptr_base.h–
○
▼Manager.cpp–
○
▼TaskParticlesSend.hpp–
○
▼TaskSend.hpp–
○
▼TaskReceive.hpp–
○
▼TaskGetCurrentSizeFromDevice.hpp–
○
▼Transaction.cpp–
○
▼Stream.hpp–
○
▼TaskSendMPI.hpp–
○
▼FieldJ.kernel–
○
▼stl_tree.h–
○
▼Particles.kernel–
○
▼Event.hpp–
○
▼event.cpp–
○
▼Device.hpp–
○
▼StreamTask.cpp–
○
▼TaskLogicalAnd.hpp–
○
▼TaskReceiveMPI.hpp–
○
▼parsing.hpp–
○
▼std_function.h–
○
▼AddExchangeToBorder.hpp–
○
▼Buffer.hpp–
○
▼ParticlePush.hpp–
○
▼TaskKernelCpuOmp2Blocks.hpp–
○
▼FDTDBase.hpp–
○
▼ParticlesBase.hpp–
○
▼vector.tcc–
○
▼CudaEvent.cpp–
○
▼stl_map.h–
○
▼TaskFieldSendExchange.hpp–
○
▼CudaEventHandle.cpp–
○
▼Factory.tpp–
○
▼TaskCopyHostToDevice.hpp–
○
▼Traits.hpp–
○
▼DeviceBuffer.hpp–
○
▼TransactionManager.cpp–
○
▼GridBuffer.hpp–
○
▼TaskSendParticlesExchange.hpp–
○
▼TaskFieldReceiveAndInsert.hpp–
○
▼invoke.h–
○
▼DataConnector.cpp–
○
▼memory.cpp–
○
▼HostBuffer.hpp–
○
▼EventDataReceive.hpp–
○
▼future–
○

Path Count Profiles

Coverage

Count

Low Iteration Count Profiles

Coverage

Count

Experiment Summaries

r0r1r2r3
Experiment Namepicongpu, khi_test, 128x128x32, scalability OMP 1x13,2x13,1x26,2x26picongpu, khi_test, 128x128x32, scalability OMP 1x13,2x13,1x26,2x26picongpu, khi_test, 128x128x32, scalability OMP 1x13,2x13,1x26,2x26picongpu, khi_test, 128x128x32, scalability OMP 1x13,2x13,1x26,2x26
Application./bin/picongpusame as r0same as r0same as r0
Timestamp
Experiment TypeOpenMP; same as r0same as r0same as r0
Machineskylakesame as r0same as r0same as r0
Architecturex86_64same as r0same as r0same as r0
Micro ArchitectureSKYLAKEsame as r0same as r0same as r0
Model NameIntel(R) Xeon(R) Platinum 8170 CPU @ 2.10GHzsame as r0same as r0same as r0
Cache Size36608 KBsame as r0same as r0same as r0
Number of Cores26same as r0same as r0same as r0
Maximal Frequency2.1 GHzsame as r0same as r0same as r0
OS VersionLinux 6.5.7-arch1-1 #1 SMP PREEMPT_DYNAMIC Tue, 10 Oct 2023 21:10:21 +0000same as r0same as r0same as r0
Architecture used during static analysisx86_64same as r0same as r0same as r0
Micro Architecture used during static analysisSKYLAKEsame as r0same as r0same as r0
Compilation Options picongpu: clang based Intel(R) oneAPI DPC++/C++ Compiler 2023.0.0 (2023.0.0.20221201) --driver-mode=g++ --intel -I /home/eoseret/apps/buildPIC/khi_test_omp2b_icpx/include -I /home/eoseret/apps/picongpu/include/picongpu/.. -I /home/eoseret/apps/picongpu/thirdParty/cupla/include -I /home/eoseret/apps/picongpu/include/pmacc/.. -D ALPAKA_ACC_CPU_B_OMP2_T_SEQ_ENABLED -D ALPAKA_BLOCK_SHARED_DYN_MEMBER_ALLOC_KIB=47 -D ALPAKA_DEBUG=0 -D ALPAKA_OFFLOAD_MAX_BLOCK_SIZE= -D BOOST_ATOMIC_DYN_LINK -D BOOST_ATOMIC_NO_LIB -D BOOST_NO_AUTO_PTR -D BOOST_PROGRAM_OPTIONS_DYN_LINK -D BOOST_PROGRAM_OPTIONS_NO_LIB -D CMAKE_BUILD_TYPE=Release -D CMAKE_CXX_COMPILER_ID=IntelLLVM -D CMAKE_CXX_COMPILER_VERSION=2023.0.0 -D CMAKE_SYSTEM=Linux-6.5.7-arch1-1 -D CMAKE_SYSTEM_PROCESSOR=x86_64 -D CMAKE_VERSION=3.27.7 -D CUPLA_STREAM_ASYNC_ENABLED=0 -D PIC_VERBOSE_LVL=1 -D PMACC_VERBOSE_LVL=0 -isystem /opt/intel/oneapi/mpi/2021.8.0/include -isystem /home/eoseret/apps/picongpu/thirdParty/cupla/alpaka/include -g -fno-omit-frame-pointer -x Host -fiopenmp -O3 -D NDEBUG -std=c++17 -fiopenmp -MD -MT CMakeFiles/picongpu.dir/main.cpp.o -MF CMakeFiles/picongpu.dir/main.cpp.o.d -o CMakeFiles/picongpu.dir/main.cpp.o -c /home/eoseret/apps/picongpu/include/picongpu/main.cpp -fveclib=SVML -fheinous-gnu-extensions same as r0same as r0same as r0
Number of processes observed1same as r0same as r0same as r0
Number of threads observed1326same as r152
Frequency Driverintel_cpufreqsame as r0same as r0same as r0
Frequency Governorperformancesame as r0same as r0same as r0
Huge Pagesalwayssame as r0same as r0same as r0
Hyperthreadingoffsame as r0same as r0same as r0
Number of sockets2same as r0same as r0same as r0
Number of cores per socket26same as r0same as r0same as r0
MAQAO version2.18.0same as r0same as r0same as r0
MAQAO buildb42f6f97013f6f62087f6ca443544250f50b2841::20231130-145227same as r0same as r0same as r0
Commentssame as r0same as r0same as r0
×