Name | Module | Coverage run_0 (%) | Max Time Over Threads run_0 (s) | Time w.r.t. Wall Time run_0 (s) | Nb Threads run_0 | Deviation (coverage) run_0 | Deviation (walltime) run_0 | Categories run_0 | GFLOPS run_0 | Compilation Options |
---|---|---|---|---|---|---|---|---|---|---|
►ljForce._omp_fn.1 | exec | 57.48 | 7.18 | 8.9 | 112 | 3.96 | 0.54 | Exe (%): 100.00 | 234.48 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 80 - ljForce.c:175-216 - exec [...] | 0.02 | 0.01 | 0 | 112 | 0.03 | 0.00 | 0.00 | |||
►Loop 82 - ljForce.c:178-216 - exec [...] | 0.28 | 0.06 | 0.04 | 112 | 0.12 | 0.01 | 339.15 | |||
►Loop 83 - ljForce.c:187-216 - exec [...] | 4.54 | 0.69 | 0.7 | 112 | 0.59 | 0.07 | 238.32 | |||
○Loop 84 - ljForce.c:191-216 - exec [...] | 52.63 | 6.53 | 8.15 | 112 | 3.76 | 0.51 | 233.82 | |||
○Loop 81 - ljForce.c:172-172 - exec | 0 | 0 | 0 | 0 | 0.00 | 0.00 | 0.00 | |||
○gomp_team_barrier_wait_end | libgomp.so.1.0.0 | 11.51 | 2.73 | 1.78 | 112 | 6.68 | 0.70 | OMP (%): 100.00 | 0.00 | |
►ljForce._omp_fn.0 | exec | 8.24 | 1.09 | 1.28 | 112 | 1.80 | 0.19 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○Loop 79 - ljForce.c:161-161 - exec [...] | 8.24 | 1.09 | 1.28 | 112 | 1.80 | 0.19 | 0.00 | |||
►advanceVelocity._omp_fn.0 | exec | 6.17 | 0.97 | 0.96 | 112 | 2.00 | 0.21 | Exe (%): 100.00 | 4.79 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 93 - timestep.c:74-78 - exec | 2.82 | 0.63 | 0.44 | 112 | 1.42 | 0.15 | 3.47 | |||
○Loop 94 - timestep.c:74-78 - exec | 3.34 | 0.56 | 0.52 | 112 | 0.92 | 0.10 | 5.91 | |||
○gomp_barrier_wait_end | libgomp.so.1.0.0 | 5.33 | 0.64 | 0.82 | 112 | 0.74 | 0.08 | OMP (%): 100.00 | 0.00 | |
►sortAtomsInCell | exec | 4.76 | 0.67 | 0.74 | 112 | 1.29 | 0.14 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○Loop 55 - haloExchange.c:621-630 - exec | 2.62 | 0.4 | 0.41 | 112 | 0.65 | 0.07 | 0.00 | |||
○Loop 54 - haloExchange.c:633-642 - exec | 0.05 | 0.02 | 0.01 | 73 | 0.05 | 0.00 | 0.00 | |||
►advancePosition._omp_fn.0 | exec | 4.3 | 0.65 | 0.67 | 112 | 1.17 | 0.12 | Exe (%): 100.00 | 6.06 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 91 - timestep.c:88-94 - exec | 1.46 | 0.36 | 0.23 | 112 | 0.83 | 0.09 | 4.10 | |||
○Loop 92 - timestep.c:88-94 - exec | 2.83 | 0.46 | 0.44 | 112 | 0.64 | 0.07 | 7.08 | |||
○unknown_function | Unknown module | 0.54 | 0.12 | 0.08 | 112 | 0.18 | 0.02 | Others (%): 100.00 | 0.00 | |
○getBoxFromCoord | exec | 0.47 | 3.31 | 0.07 | 2 | 4.30 | 0.68 | Exe (%): 100.00 | 19.02 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►kineticEnergy._omp_fn.0 | exec | 0.36 | 0.06 | 0.06 | 112 | 0.11 | 0.01 | Exe (%): 100.00 | 7.51 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 96 - timestep.c:110-116 - exec | 0.12 | 0.04 | 0.02 | 108 | 0.08 | 0.01 | 2.75 | |||
○Loop 97 - timestep.c:110-116 - exec | 0.23 | 0.05 | 0.04 | 112 | 0.08 | 0.01 | 9.89 | |||
○Loop 95 - timestep.c:107-107 - exec | 0 | 0 | 0 | 0 | 0.00 | 0.00 | 0.00 | |||
○putAtomInBox | exec | 0.11 | 0.91 | 0.02 | 2 | 2.00 | 0.31 | Exe (%): 100.00 | 9.48 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○sortAtomsById | exec | 0.11 | 0.04 | 0.02 | 106 | 0.07 | 0.01 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►loadAtomsBuffer | exec | 0.09 | 0.58 | 0.01 | 2 | 0.60 | 0.10 | Exe (%): 100.00 | 13.85 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 32 - haloExchange.c:376-390 - exec | 0 | 0.02 | 0 | 2 | 0.00 | 0.00 | 0.00 | |||
○Loop 33 - haloExchange.c:380-390 - exec | 0.08 | 0.56 | 0.01 | 2 | 0.60 | 0.10 | 13.40 | |||
○unknown_kernel_region | kernel | 0.08 | 0.23 | 0.01 | 83 | 0.20 | 0.03 | OMP (%): 7.45 System (%): 69.16 MPI (%): 23.39 | 2.85 | |
○getBoxFromTuple | exec | 0.06 | 0.37 | 0.01 | 2 | 0.19 | 0.03 | Exe (%): 100.00 | 86.25 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○MPL_gpu_cuda_finalize | libmpi.so.12.0.0 | 0.04 | 0.44 | 0.01 | 2 | 1.98 | 0.30 | MPI (%): 100.00 | 0.00 | |
○f64xsubf128 | libm-2.28.so | 0.04 | 0.01 | 0.01 | 111 | 0.03 | 0.00 | Math (%): 100.00 | 21.20 | |
►gasdev | exec | 0.03 | 0.01 | 0.01 | 111 | 0.03 | 0.00 | Exe (%): 100.00 | 28.40 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○Loop 90 - random.c:26-48 - exec [...] | 0.01 | 0.01 | 0 | 66 | 0.03 | 0.00 | 0.00 | |||
►randomDisplacements._omp_fn.0 | exec | 0.03 | 0 | 0 | 70 | 0.02 | 0.00 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 64 - initAtoms.c:197-202 - exec | 0 | 0 | 0 | 1 | 0.00 | 0.00 | 0.00 | |||
○Loop 65 - initAtoms.c:197-202 - exec | 0.02 | 0 | 0 | 70 | 0.02 | 0.00 | 0.00 | |||
○__GI___pthread_mutex_lock | libpthread-2.28.so | 0.02 | 0.2 | 0 | 1 | 0.00 | 0.00 | Pthread (%): 100.00 | 0.00 | |
○mkSeed | exec | 0.02 | 0.01 | 0 | 90 | 0.03 | 0.00 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○MPIR_Progress_hook_exec_on_vci | libmpi.so.12.0.0 | 0.02 | 0.22 | 0 | 2 | 0.94 | 0.14 | MPI (%): 100.00 | 0.00 | |
►updateLinkCells | exec | 0.02 | 0.17 | 0 | 2 | 0.23 | 0.04 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 75 - linkCells.c:291-301 - exec | 0 | 0.02 | 0 | 2 | 0.05 | 0.01 | 0.00 | |||
○Loop 76 - linkCells.c:295-301 - exec | 0.02 | 0.15 | 0 | 2 | 0.18 | 0.03 | 0.00 | |||
○Loop 77 - linkCells.c:384-385 - exec | 0 | 0 | 0 | 0 | 0.00 | 0.00 | 0.00 | |||
►redistributeAtoms._omp_fn.0 | exec | 0.01 | 0.01 | 0 | 12 | 0.02 | 0.00 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○Loop 98 - timestep.c:154-154 - exec | 0.01 | 0.01 | 0 | 12 | 0.02 | 0.00 | 0.00 | |||
○I_MPI_memcpy_xeon_sse | libmpi.so.12.0.0 | 0.01 | 0.04 | 0 | 2 | 0.02 | 0.00 | MPI (%): 100.00 | 0.00 | |
►setVcm._omp_fn.0 | exec | 0.01 | 0 | 0 | 53 | 0.02 | 0.00 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 56 - initAtoms.c:126-133 - exec | 0 | 0 | 0 | 15 | 0.02 | 0.00 | 0.00 | |||
○Loop 57 - initAtoms.c:126-133 - exec | 0.01 | 0 | 0 | 39 | 0.02 | 0.00 | 0.00 | |||
○__pthread_mutex_unlock_usercnt | libpthread-2.28.so | 0.01 | 0.17 | 0 | 2 | 0.74 | 0.11 | Pthread (%): 100.00 | 0.00 | |
○gomp_barrier_wait | libgomp.so.1.0.0 | 0.01 | 0 | 0 | 17 | 0.00 | 0.00 | OMP (%): 100.00 | 0.00 | |
○copyAtom.isra.0 | exec | 0.01 | 0.04 | 0 | 2 | 0.02 | 0.00 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○MPIDI_OFI_progress | libmpi.so.12.0.0 | 0.01 | 0.06 | 0 | 2 | 0.28 | 0.04 | MPI (%): 100.00 | 0.00 | |
○I_MPI_memcpy_multipage_avx512 | libmpi.so.12.0.0 | 0.01 | 0.04 | 0 | 2 | 0.04 | 0.01 | MPI (%): 100.00 | 0.00 | |
►setTemperature._omp_fn.1 | exec | 0.01 | 0 | 0 | 38 | 0.01 | 0.00 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 60 - initAtoms.c:177-181 - exec | 0 | 0 | 0 | 10 | 0.02 | 0.00 | 0.00 | |||
○Loop 61 - initAtoms.c:177-181 - exec | 0.01 | 0 | 0 | 30 | 0.02 | 0.00 | 0.00 | |||
►computeVcm._omp_fn.0 | exec | 0.01 | 0 | 0 | 38 | 0.02 | 0.00 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
►Loop 58 - initAtoms.c:221-228 - exec | 0 | 0 | 0 | 9 | 0.02 | 0.00 | 0.00 | |||
○Loop 59 - initAtoms.c:221-228 - exec | 0.01 | 0 | 0 | 33 | 0.02 | 0.00 | 0.00 | |||
►unloadAtomsBuffer | exec | 0.01 | 0.09 | 0 | 2 | 0.18 | 0.03 | Exe (%): 100.00 | 0.00 | GNU C17 13.1.0 -march=haswell -g -O2 -fsave-optimization-record -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops |
○Loop 40 - haloExchange.c:414-424 - exec [...] | 0.01 | 0.09 | 0 | 2 | 0.18 | 0.03 | 0.00 | |||
○I_MPI_memcpy_stream_nontemporal_avx512 | libmpi.so.12.0.0 | 0.01 | 0.08 | 0 | 2 | 0.09 | 0.01 | MPI (%): 100.00 | 0.00 |