Help is available by moving the cursor above any
symbol or by checking MAQAO website.
| Metric | r0 | r1 |
|---|
| Total Time (s) | 25.45 | 10.91 |
| Profiled Time (s) | 25.04 | 10.53 |
| Time in analyzed loops (%) | 91.1 | 85.4 |
| Time in analyzed innermost loops (%) | 81.8 | 78.7 |
| Time in user code (%) | 91.2 | 85.6 |
| Compilation Options Score (%) | 75.0 | 75.0 |
| Array Access Efficiency (%) | Not Available | Not Available |
|
| Potential Speedups |
| Perfect Flow Complexity | 1.00 | 1.00 |
| Perfect OpenMP + MPI + Pthread | 1.08 | 1.15 |
| Perfect OpenMP + MPI + Pthread + Perfect Load Distribution | 1.21 | 1.35 |
| No Scalar Integer | Potential Speedup | 1.06 | 1.04 |
| Nb Loops to get 80% | 1 | 1 |
| FP Vectorised | Potential Speedup | 1.00 | 1.00 |
| Nb Loops to get 80% | 1 | 1 |
| Fully Vectorised | Potential Speedup | 1.04 | 1.17 |
| Nb Loops to get 80% | 1 | 2 |
| Only FP Arithmetic | Potential Speedup | 1.07 | 1.35 |
| Nb Loops to get 80% | 1 | 2 |
| Source Object | Issue |
| ▼spmxv.exe– | |
| ▼ooo_cmdline.h– | |
| ○ | -funroll-loops is missing. |
| ▼ooo_cmdline.cpp– | |
| ○ | -funroll-loops is missing. |
| ▼main.cpp– | |
| ○ | -funroll-loops is missing. |
| Source Object | Issue |
| ▼spmxv.exe– | |
| ▼ooo_cmdline.h– | |
| ○ | -funroll-loops is missing. |
| ▼ooo_cmdline.cpp– | |
| ○ | -funroll-loops is missing. |
| ▼main.cpp– | |
| ○ | -funroll-loops is missing. |
| r0 | r1 |
| Experiment Name | | |
| Application | ./spmxv.exe | same as r0 |
| Timestamp | 2024-07-04 14:55:05 | 2024-07-04 17:21:44 |
| Experiment Type | OpenMP; | same as r0 |
| Machine | ip-172-31-42-13 | p11-grace01.cs.it4i.cz |
| Architecture | aarch64 | |
| Micro Architecture | ARM_NEOVERSE_V1 | |
| Model Name | | |
| Cache Size | | |
| Number of Cores | | |
| Maximal Frequency | 0 GHz | 3.42 GHz |
| OS Version | Linux 6.5.0-1021-aws #21~22.04.1-Ubuntu SMP Fri May 10 21:19:37 UTC 2024 | Linux 5.14.0-362.18.1.el9_3.aarch64 #1 SMP PREEMPT_DYNAMIC Thu Jan 25 07:56:00 UTC 2024 |
| Architecture used during static analysis | aarch64 | same as r0 |
| Micro Architecture used during static analysis | ARM_NEOVERSE_V1 | same as r0 |
| Compilation Options |
spmxv.exe: GNU C++17 12.2.0 -mlittle-endian -mabi=lp64 -mcpu=zeus+crypto+sha3+sm4+nodotprod+noprofile -g -Ofast -fopenmp | spmxv.exe: GNU C++17 12.2.0 -mlittle-endian -mabi=lp64 -mcpu=demeter+crypto+rcpc+sve2-sm4+sve2-aes+sve2-sha3+nodotprod+noprofile+norng+nomemtag+nopredres+nopauth -g -Ofast -fopenmp |
| Number of processes observed | 1 | same as r0 |
| Number of threads observed | 64 | same as r0 |
| Frequency Driver | NA | cppc_cpufreq |
| Frequency Governor | NA | performance |
| Huge Pages | madvise | always |
| Hyperthreading | off | same as r0 |
| Number of sockets | 1 | 2 |
| Number of cores per socket | 64 | 72 |
| MAQAO version | 2.20.4 | same as r0 |
| MAQAO build | fe14d3adfb3256b508e58d35c4c7bad8c581967c::20240703-182948 | same as r0 |
| Comments | | same as r0 |