Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
| Total Time (s) | 18.03 | |
| Profiled Time (s) | 14.51 | |
| GFLOPS | 39.435 | |
| Time in analyzed loops (%) | 80.0 | |
| Time in analyzed innermost loops (%) | 55.0 | |
| Time in user code (%) | 80.1 | |
| Compilation Options Score (%) | 100 | |
| Array Access Efficiency (%) | 64.8 | |
|
| Potential Speedups |
| Perfect Flow Complexity | 1.02 | |
| Perfect OpenMP + MPI + Pthread | 1.16 | |
| Perfect OpenMP + MPI + Pthread + Perfect Load Distribution | 1.60 | |
| No Scalar Integer | Potential Speedup | 1.12 | |
| Nb Loops to get 80% | 7 | |
| FP Vectorised | Potential Speedup | 1.46 | |
| Nb Loops to get 80% | 4 | |
| Fully Vectorised | Potential Speedup | 3.04 | |
| Nb Loops to get 80% | 26 | |
| FP Arithmetic Only | Potential Speedup | 1.22 | |
| Nb Loops to get 80% | 17 | |
| Source Object | Issue |
|---|
| ▼exec– | |
| ○IJVector_parcsr.c | |
| ○par_multi_interp.c | |
| ○par_csr_matvec.c | |
| ○par_strength.c | |
| ○random.c | |
| ○par_lr_interp.c | |
| ○vector.c | |
| ○amg.c | |
| ○csr_matvec.c | |
| ○IJMatrix_parcsr.c | |
| ○par_coarsen.c | |
| ○csr_matop.c | |
| ○par_csr_matop.c | |
| ○ams.c | |
| ○par_interp.c | |
| ○binsearch.c | |
| Application | /beegfs/hackathon/users/eoseret/qaas_runs/170-859-5251/intel/AMG/run/binaries/gcc_4/exec |
| Comments | Execution on the Megware (https://www.megware.com/en/) benchmarking cluster |
| Timestamp | 2024-02-22 11:44:14 |
Universal Timestamp | 1708598654 |
| Number of processes observed | 2 |
Number of threads observed | 192 |
| Experiment Type | MPI; OpenMP; |
| Machine | gmz17.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 5.14.0-362.13.1.el9_3.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Dec 21 07:12:43 EST 2023 |
| 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 C89 13.2.0 -march=haswell -g -O3 -O3 -std=gnu90 -fno-tree-vectorize -fno-openmp-simd -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fopenmp -funroll-loops | | |
| Dataset | |
| Run Command | <executable> -n 320 320 320 |
| MPI Command | mpirun -np 2 |
| Number Processes | 1 |
| Number Nodes | 1 |
| Filter | Not Used |
| Profile Start | Not Used |
