| | | | | | | requested parallelism | walltime sum (s) | nb instances | any sync average per thread time (s) | any wait average per thread time (s) | parallelism overhead (%) | local speedup if perfectly balanced | global speedup if perfectly balanced |
|---|
| start addr | function name | source location | level | ancestor thread num | invoker | parallel or teams | run_0 | run_0 | run_0 | run_0 | run_0 | run_0 | run_0 | run_0 |
|---|
| picongpu:0x4cdc58 | _ZNK8picongpu13currentSolver7DepositINS0_8strategy23StridedC... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 113.486 | 40.5 E3 | 30.754 | 30.749 | 27.1 | 1.372 | 1.070 |
| picongpu:0x4d2958 | _ZNK8picongpu13currentSolver7DepositINS0_8strategy23StridedC... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 108.084 | 40.5 E3 | 29.483 | 29.478 | 27.3 | 1.375 | 1.067 |
| picongpu:0x45d3b9 | void picongpu::Particles<pmacc::meta::String<(char)101>, boo... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 92.952 | 1.50 E3 | 2.437 | 2.437 | 2.62 | 1.027 | 1.005 |
| picongpu:0x47bfd9 | void picongpu::Particles<pmacc::meta::String<(char)105>, boo... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 91.202 | 1.50 E3 | 1.643 | 1.642 | 1.80 | 1.018 | 1.003 |
| picongpu:0x461a78 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 6.888 | 40.5 E3 | 2.215 | 2.210 | 32.2 | 1.474 | 1.005 |
| picongpu:0x47f858 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 2.926 | 40.5 E3 | 0.940 | 0.935 | 32.1 | 1.474 | 1.002 |
| picongpu:0x41e7ee | void cupla::cupla_omp2_seq_sync::KernelExecutor<pmacc::Kerne... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 1.110 | 156 E3 | 0.419 | 0.394 | 37.7 | 1.606 | 1.001 |
| picongpu:0x4fa0f0 | pmacc::TaskSetValue<pmacc::math::Vector<float, 3u, pmacc::ma... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.755 | 1.71 E3 | 54.6 E-3 | 54.4 E-3 | 7.23 | 1.078 | 1.000 |
| picongpu:0x507239 | void pmacc::fields::operations::AddExchangeToBorder::operato... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.534 | 39.0 E3 | 0.252 | 0.248 | 47.2 | 1.895 | 1.001 |
| picongpu:0x509dd9 | void pmacc::fields::operations::CopyGuardToExchange::operato... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.464 | 39.0 E3 | 0.209 | 0.205 | 45.1 | 1.820 | 1.000 |
| picongpu:0x4a0819 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.462 | 1.50 E3 | 94.6 E-3 | 94.5 E-3 | 20.5 | 1.257 | 1.000 |
| picongpu:0x4b0319 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.435 | 1.50 E3 | 89.7 E-3 | 89.5 E-3 | 20.6 | 1.260 | 1.000 |
| picongpu:0x4bd000 | void picongpu::fields::maxwellSolver::fdtd::FDTDBase<picongp... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.404 | 1.50 E3 | 0.117 | 0.117 | 28.9 | 1.407 | 1.000 |
| picongpu:0x4a502c | pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::meta:... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.393 | 39.0 E3 | 0.181 | 0.176 | 46.0 | 1.852 | 1.000 |
| picongpu:0x4bf8a0 | void picongpu::fields::maxwellSolver::fdtd::FDTDBase<picongp... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.391 | 1.50 E3 | 0.175 | 0.175 | 44.9 | 1.814 | 1.000 |
| picongpu:0x4ea9e0 | void picongpu::fields::maxwellSolver::fdtd::FDTDBase<picongp... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.381 | 1.50 E3 | 0.208 | 0.208 | 54.7 | 2.207 | 1.000 |
| picongpu:0x4c20c0 | void picongpu::fields::maxwellSolver::fdtd::FDTDBase<picongp... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.371 | 1.50 E3 | 85.7 E-3 | 85.5 E-3 | 23.1 | 1.301 | 1.000 |
| picongpu:0x4b484c | pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::meta:... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.360 | 39.0 E3 | 0.134 | 0.127 | 37.2 | 1.593 | 1.000 |
| picongpu:0x4dc8b3 | void picongpu::fields::maxwellSolver::fdtd::FDTDBase<picongp... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.315 | 1.50 E3 | 0.194 | 0.193 | 61.4 | 2.589 | 1.000 |
| picongpu:0x49eab3 | pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::meta:... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.246 | 9.00 E3 | 0.168 | 0.167 | 68.2 | 3.147 | 1.000 |
| picongpu:0x4e6500 | void picongpu::fields::maxwellSolver::fdtd::FDTDBase<picongp... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.220 | 1.50 E3 | 36.4 E-3 | 36.2 E-3 | 16.5 | 1.198 | 1.000 |
| picongpu:0x4d8693 | void picongpu::fields::maxwellSolver::fdtd::FDTDBase<picongp... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.177 | 1.50 E3 | 33.5 E-3 | 33.3 E-3 | 18.9 | 1.233 | 1.000 |
| picongpu:0x55fe59 | void picongpu::Particles<pmacc::meta::String<(char)105>, boo... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.153 | 1.00 | 5.28 E-3 | 5.28 E-3 | 3.45 | 1.036 | 1.000 |
| picongpu:0x55b039 | void picongpu::Particles<pmacc::meta::String<(char)101>, boo... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.151 | 1.00 | 3.76 E-3 | 3.76 E-3 | 2.50 | 1.026 | 1.000 |
| picongpu:0x4ae5b3 | pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::meta:... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 0.109 | 1.75 E3 | 82.5 E-3 | 82.3 E-3 | 75.6 | 4.100 | 1.000 |
| picongpu:0x567ac9 | _ZNK6alpaka23TaskKernelCpuOmp2BlocksISt17integral_constantIm... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 43.8 E-3 | 1.00 | 1.35 E-3 | 1.35 E-3 | 3.08 | 1.032 | 1.000 |
| picongpu:0x5c7f09 | alpaka::TaskKernelCpuOmp2Blocks<std::integral_constant<unsig... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 39.4 E-3 | 152 | 8.77 E-3 | 8.75 E-3 | 22.3 | 1.286 | 1.000 |
| picongpu:0x5dd090 | pmacc::TaskSetValue<char, 1u, true>::init() | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 9.74 E-3 | 1.00 | 1.70 E-3 | 1.70 E-3 | 17.4 | 1.211 | 1.000 |
| picongpu:0x511890 | pmacc::TaskSetValue<pmacc::math::Vector<float, 1u, pmacc::ma... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 5.86 E-3 | 157 | 1.24 E-3 | 1.22 E-3 | 21.1 | 1.268 | 1.000 |
| picongpu:0x43ab5d | picongpu::Simulation::fillSimulation() | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 4.89 E-3 | 1.00 | 95.0 E-6 | 94.8 E-6 | 1.94 | 1.020 | 1.000 |
| picongpu:0x566509 | _ZNK6alpaka23TaskKernelCpuOmp2BlocksISt17integral_constantIm... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 4.44 E-3 | 1.00 | 1.61 E-3 | 1.61 E-3 | 36.4 | 1.572 | 1.000 |
| picongpu:0x565a29 | _ZNK6alpaka23TaskKernelCpuOmp2BlocksISt17integral_constantIm... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 4.43 E-3 | 1.00 | 2.28 E-3 | 2.28 E-3 | 51.4 | 2.058 | 1.000 |
| picongpu:0x564469 | _ZNK6alpaka23TaskKernelCpuOmp2BlocksISt17integral_constantIm... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 4.43 E-3 | 1.00 | 1.62 E-3 | 1.62 E-3 | 36.6 | 1.576 | 1.000 |
| picongpu:0x563989 | _ZNK6alpaka23TaskKernelCpuOmp2BlocksISt17integral_constantIm... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 4.41 E-3 | 1.00 | 2.32 E-3 | 2.32 E-3 | 52.5 | 2.104 | 1.000 |
| picongpu:0x566fe9 | _ZNK6alpaka23TaskKernelCpuOmp2BlocksISt17integral_constantIm... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 4.37 E-3 | 1.00 | 2.43 E-3 | 2.42 E-3 | 55.5 | 2.246 | 1.000 |
| picongpu:0x564f49 | _ZNK6alpaka23TaskKernelCpuOmp2BlocksISt17integral_constantIm... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 4.36 E-3 | 1.00 | 2.43 E-3 | 2.43 E-3 | 55.7 | 2.255 | 1.000 |
| picongpu:0x531830 | pmacc::TaskSetValue<pmacc::ExchangeMemoryIndex<unsigned int,... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 3.43 E-3 | 104 | 1.03 E-3 | 1.02 E-3 | 30.0 | 1.429 | 1.000 |
| picongpu:0x53dc90 | pmacc::TaskSetValue<pmacc::Frame<pmacc::detail::OperatorCrea... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 2.94 E-3 | 52.0 | 759 E-6 | 752 E-6 | 25.8 | 1.348 | 1.000 |
| picongpu:0x5502f0 | pmacc::TaskSetValue<pmacc::Frame<pmacc::detail::OperatorCrea... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 2.67 E-3 | 52.0 | 741 E-6 | 735 E-6 | 27.7 | 1.383 | 1.000 |
| picongpu:0x56d9b9 | void picongpu::particles::manipulate<picongpu::particles::ma... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 1.78 E-3 | 1.00 | 42.1 E-6 | 41.9 E-6 | 2.37 | 1.024 | 1.000 |
| picongpu:0x526ed0 | pmacc::TaskSetValue<alpaka::rand::engine::cpu::TinyMersenneT... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 1.73 E-3 | 1.00 | 324 E-6 | 324 E-6 | 18.8 | 1.231 | 1.000 |
| picongpu:0x56b1b9 | void picongpu::particles::manipulate<picongpu::particles::ma... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 1.73 E-3 | 1.00 | 69.0 E-6 | 68.8 E-6 | 3.99 | 1.042 | 1.000 |
| picongpu:0x55d1d9 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 1.41 E-3 | 2.00 | 440 E-6 | 440 E-6 | 31.2 | 1.454 | 1.000 |
| picongpu:0x561a59 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 1.40 E-3 | 2.00 | 424 E-6 | 424 E-6 | 30.4 | 1.436 | 1.000 |
| picongpu:0x5d6c49 | alpaka::TaskKernelCpuOmp2Blocks<std::integral_constant<unsig... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 1.22 E-3 | 152 | 493 E-6 | 475 E-6 | 40.3 | 1.676 | 1.000 |
| picongpu:0x4eeed9 | pmacc::random::RNGProvider<3u, pmacc::random::methods::Alpak... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 643 E-6 | 1.00 | 12.2 E-6 | 12.1 E-6 | 1.90 | 1.019 | 1.000 |
| picongpu:0x538e50 | pmacc::TaskSetValue<pmacc::SuperCell<pmacc::Frame<pmacc::det... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 98.3 E-6 | 3.00 | 29.6 E-6 | 29.2 E-6 | 30.1 | 1.430 | 1.000 |
| picongpu:0x54c230 | _ZN5pmacc12TaskSetValueINS_9SuperCellINS_5FrameINS_6detail29... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 97.1 E-6 | 3.00 | 29.3 E-6 | 29.0 E-6 | 30.2 | 1.433 | 1.000 |
| picongpu:0x536cf4 | pmacc::HostBuffer<pmacc::SuperCell<pmacc::Frame<pmacc::detai... | HostBuffer.hpp:161 | 0 | 0 | runtime | parallel | 52 | 23.5 E-6 | 2.00 | 6.58 E-6 | 6.30 E-6 | 28.0 | 1.389 | 1.000 |
| picongpu:0x54a0d4 | _ZN5pmacc10HostBufferINS_9SuperCellINS_5FrameINS_6detail29Op... | HostBuffer.hpp:161 | 0 | 0 | runtime | parallel | 52 | 17.3 E-6 | 2.00 | 5.28 E-6 | 4.91 E-6 | 30.5 | 1.439 | 1.000 |
| picongpu:0x53fa99 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 15.9 E-6 | 1.00 | 4.90 E-6 | 4.64 E-6 | 30.8 | 1.446 | 1.000 |
| picongpu:0x5541d9 | pmacc::IdProvider<3u>::setNextId(unsigned long) | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 15.1 E-6 | 2.00 | 4.67 E-6 | 4.19 E-6 | 30.9 | 1.447 | 1.000 |
| picongpu:0x551db9 | void pmacc::ParticlesBase<pmacc::ParticleDescription<pmacc::... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 10.3 E-6 | 1.00 | 2.87 E-6 | 2.70 E-6 | 27.9 | 1.386 | 1.000 |
| picongpu:0x558970 | pmacc::TaskSetValue<unsigned long long, 1u, true>::init() | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 7.67 E-6 | 1.00 | 2.83 E-6 | 2.45 E-6 | 36.9 | 1.585 | 1.000 |
| picongpu:0x5553f9 | pmacc::IdProvider<3u>::getNewIdHost() | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 7.62 E-6 | 1.00 | 2.90 E-6 | 2.38 E-6 | 38.0 | 1.614 | 1.000 |
| picongpu:0x5714b0 | pmacc::TaskSetValue<picongpu::particles::debyeLength::Estima... | TaskKernelCpuOmp2Blocks.hpp:855 | 0 | 0 | runtime | parallel | 52 | 7.33 E-6 | 1.00 | 2.72 E-6 | 2.58 E-6 | 37.2 | 1.591 | 1.000 |
