Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
- There is no filter information to display
| Total Time (s) | 9.70 | |
| Max (Thread Active Time) (s) | 9.70 | |
| Average Active Time (s) | 9.70 | |
| Activity Ratio (%) | 100.0 | |
| Average number of active threads | 1.000 | |
| Affinity Stability (%) | 99.9 | |
| GFLOPS | 3.159 | |
| Time in analyzed loops (%) | 93.7 | |
| Time in analyzed innermost loops (%) | 86.2 | |
| Time in user code (%) | 93.7 | |
| Compilation Options Score (%) | 100 | |
| Array Access Efficiency (%) | 75.6 | |
|
| Potential Speedups | |
| Perfect Flow Complexity | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | |
| No Scalar Integer | Potential Speedup | 1.04 | |
| Nb Loops to get 80% | 3 | |
| FP Vectorised | Potential Speedup | 1.69 | |
| Nb Loops to get 80% | 4 | |
| Fully Vectorised | Potential Speedup | 5.33 | |
| Nb Loops to get 80% | 5 | |
| FP Arithmetic Only | Potential Speedup | 1.06 | |
| Nb Loops to get 80% | 4 | |
| Source Object | Issue |
|---|
| ▼attention-avx512– | |
| ○attention.cpp | |
| Application | ./attention-avx512 |
| Timestamp | 2026-05-20 17:41:32 |
Universal Timestamp | 1779291692 |
| Number of processes observed | 1 |
Number of threads observed | 1 |
| Experiment Type | Sequential |
| Machine | gmz17.benchmarkcenter.megware.com |
| Model Name | AMD EPYC 9655 96-Core Processor |
| Architecture | x86_64 |
Micro Architecture | ZEN_V5 |
| Cache Size | 1024 KB |
Number of Cores | 96 |
| OS Version | Linux 5.14.0-611.54.6.el9_7.x86_64 #1 SMP PREEMPT_DYNAMIC Fri May 15 04:23:18 EDT 2026 |
| Architecture used during static analysis | x86_64 |
Micro Architecture used during static analysis | ZEN_V5 |
| Frequency Driver | amd-pstate-epp |
Frequency Governor | performance |
| Huge Pages | always |
Hyperthreading | on |
| Number of sockets | 2 |
Number of cores per socket | 96 |
| Compilation Options | attention-avx512: AMD clang version 17.0.6 (CLANG: AOCC_5.1.0-Build#1994 2025_12_23) /cluster/comp/aocc/5.1.0/bin/clang-17 --driver-mode=g++ -O3 -g -fno-omit-frame-pointer -grecord-command-line -march=native -mprefer-vector-width=512 -Rpass=loop-vectorize -Rpass-analysis=loop-vectorize -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention.cpp -o attention-avx512 -dumpdir attention-avx512- | | |
| Dataset | |
| Run Command | <executable> 128 32 10000 |
| Filter | Not Used |
| Profile Start | Not Used |
| Profile Stop | Not Used |
