Help is available by moving the cursor above any symbol or by checking MAQAO website.
Total Time (s) | 22.22 | ||
Profiled Time (s) | 12.13 | ||
GFLOPS | 32.231 | ||
Time in analyzed loops (%) | 84.4 | ||
Time in analyzed innermost loops (%) | 19.4 | ||
Time in user code (%) | 84.6 | ||
Compilation Options Score (%) | 100 | ||
Array Access Efficiency (%) | 75.9 | ||
Potential Speedups | |||
Perfect Flow Complexity | 1.05 | ||
Perfect OpenMP + MPI + Pthread | 1.10 | ||
Perfect OpenMP + MPI + Pthread + Perfect Load Distribution | 1.66 | ||
No Scalar Integer | Potential Speedup | 1.11 | |
Nb Loops to get 80% | 8 | ||
FP Vectorised | Potential Speedup | 1.04 | |
Nb Loops to get 80% | 4 | ||
Fully Vectorised | Potential Speedup | 1.46 | |
Nb Loops to get 80% | 24 | ||
FP Arithmetic Only | Potential Speedup | 1.96 | |
Nb Loops to get 80% | 14 |
Source Object | Issue |
---|---|
▼libparcsr_ls.so | |
○ams.c | |
○par_multi_interp.c | |
○par_coarsen.c | |
○par_strength.c | |
○par_coarse_parms.c | |
○par_lr_interp.c | |
○par_interp.c | |
○par_indepset.c | |
▼libHYPRE_utilities.so | |
○hypre_qsort.c | |
○random.c | |
○binsearch.c | |
▼exec | |
○amg.c | |
▼libseq_mv.so | |
○csr_matvec.c | |
○csr_matrix.c | |
○vector.c | |
○csr_matop.c | |
▼libIJ_mv.so | |
○IJVector_parcsr.c | |
○IJMatrix_parcsr.c | |
▼libparcsr_mv.so | |
○par_csr_matvec.c | |
○par_csr_matop.c |
Application | /scratch_na/users/xoserete/qaas_runs/171-418-3331/intel/AMG/run/binaries/gcc_10/exec | ||||
Timestamp | 2024-04-27 04:55:31 | Universal Timestamp | 1714186531 | ||
Number of processes observed | 2 | Number of threads observed | 112 | ||
Experiment Type | MPI; OpenMP; | ||||
Machine | o401 | ||||
Model Name | Intel (R) Xeon (R) CPU Max 9480 | ||||
Architecture | x86_64 | Micro Architecture | SAPPHIRE_RAPIDS | ||
Cache Size | 115200 KB | Number of Cores | 56 | ||
OS Version | Linux 4.18.0-477.27.1.el8_8.x86_64 #1 SMP Thu Aug 31 10:29:22 EDT 2023 | ||||
Architecture used during static analysis | x86_64 | Micro Architecture used during static analysis | SAPPHIRE_RAPIDS | ||
Frequency Driver | acpi-cpufreq | Frequency Governor | performance | ||
Huge Pages | never | Hyperthreading | on | ||
Number of sockets | 2 | Number of cores per socket | 56 | ||
Compilation Options | exec: GNU GIMPLE 13.1.0 -mprefer-vector-width=512 -march=sapphirerapids -mprefer-vector-width=512 -g -g -O3 -O3 -O3 -O3 -fno-openacc -fno-pie -fcf-protection=none -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops -fltrans libHYPRE_utilities.so: GNU GIMPLE 13.1.0 -mprefer-vector-width=512 -march=sapphirerapids -mprefer-vector-width=512 -g -g -O3 -O3 -O3 -O3 -fno-openacc -fcf-protection=none -fPIC -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops -fltrans libIJ_mv.so: GNU GIMPLE 13.1.0 -mprefer-vector-width=512 -march=sapphirerapids -mprefer-vector-width=512 -g -g -O3 -O3 -O3 -O3 -fno-openacc -fcf-protection=none -fPIC -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops -fltrans libparcsr_ls.so: GNU GIMPLE 13.1.0 -mprefer-vector-width=512 -march=sapphirerapids -mprefer-vector-width=512 -g -g -O3 -O3 -O3 -O3 -fno-openacc -fcf-protection=none -fPIC -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops -fltrans libparcsr_mv.so: GNU GIMPLE 13.1.0 -mprefer-vector-width=512 -march=sapphirerapids -mprefer-vector-width=512 -g -g -O3 -O3 -O3 -O3 -fno-openacc -fcf-protection=none -fPIC -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops -fltrans libseq_mv.so: GNU GIMPLE 13.1.0 -mprefer-vector-width=512 -march=sapphirerapids -mprefer-vector-width=512 -g -g -O3 -O3 -O3 -O3 -fno-openacc -fcf-protection=none -fPIC -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops -fltrans |
Dataset | |
Run Command | <executable> -n 320 320 320 |
MPI Command | mpirun -np 2 numactl -m 8-15 |
Number Processes | 1 |
Number Nodes | 1 |
Filter | Not Used |
Profile Start | Not Used |