Help is available by moving the cursor above any symbol or by checking MAQAO website.
Total Time (s) | 78.53 | ||
Profiled Time (s) | 74.31 | ||
GFLOPS | 144.377 | ||
Time in analyzed loops (%) | 96.6 | ||
Time in analyzed innermost loops (%) | 16.3 | ||
Time in user code (%) | 96.6 | ||
Compilation Options Score (%) | 100 | ||
Array Access Efficiency (%) | 83.5 | ||
Potential Speedups | |||
Perfect Flow Complexity | 1.02 | ||
Perfect OpenMP + MPI + Pthread | 1.01 | ||
Perfect OpenMP + MPI + Pthread + Perfect Load Distribution | 1.13 | ||
No Scalar Integer | Potential Speedup | 1.18 | |
Nb Loops to get 80% | 6 | ||
FP Vectorised | Potential Speedup | 1.77 | |
Nb Loops to get 80% | 3 | ||
Fully Vectorised | Potential Speedup | 3.52 | |
Nb Loops to get 80% | 24 | ||
FP Arithmetic Only | Potential Speedup | 3.63 | |
Nb Loops to get 80% | 13 |
Source Object | Issue |
---|---|
▼libparcsr_ls.so | |
○par_coarsen.c | |
○par_strength.c | |
○par_lr_interp.c | |
○ams.c | |
○par_multi_interp.c | |
▼libHYPRE_utilities.so | |
○random.c | |
▼libparcsr_mv.so | |
○par_csr_matop.c | |
▼libseq_mv.so | |
○csr_matvec.c | |
○vector.c | |
○csr_matrix.c | |
○csr_matop.c | |
▼libIJ_mv.so | |
○IJVector_parcsr.c | |
○IJMatrix_parcsr.c | |
▼exec | |
○amg.c |
Application | /home/eoseret/qaas_runs_CPU_9468/172-019-1763/intel/AMG/run/binaries/gcc_11/exec | ||||
Timestamp | 2024-07-05 20:17:25 | Universal Timestamp | 1720203445 | ||
Number of processes observed | 8 | Number of threads observed | 192 | ||
Experiment Type | MPI; OpenMP; | ||||
Machine | gpu04sas.benchmarkcenter.megware.com | ||||
Model Name | AMD EPYC 9654 96-Core Processor | ||||
Architecture | x86_64 | Micro Architecture | ZEN_V4 | ||
Cache Size | 1024 KB | Number of Cores | 96 | ||
OS Version | Linux 5.14.0-427.20.1.el9_4.x86_64 #1 SMP PREEMPT_DYNAMIC Mon Jun 10 08:04:28 EDT 2024 | ||||
Architecture used during static analysis | x86_64 | Micro Architecture used during static analysis | ZEN_V4 | ||
Frequency Driver | acpi-cpufreq | Frequency Governor | performance | ||
Huge Pages | always | Hyperthreading | on | ||
Number of sockets | 2 | Number of cores per socket | 96 | ||
Compilation Options | exec: GNU GIMPLE 13.2.0 -march=haswell -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 13.2.0 -march=haswell -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 13.2.0 -march=haswell -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 13.2.0 -march=haswell -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 13.2.0 -march=haswell -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 13.2.0 -march=haswell -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 400 400 400 |
MPI Command | mpirun -n <number_processes> |
Number Processes | 8 |
Number Nodes | 1 |
Filter | Not Used |
Profile Start | Not Used |