Help is available by moving the cursor above any
symbol or by checking MAQAO website.
| Metric | r0 | r1 | r2 | r3 | r4 | r5 | |
|---|---|---|---|---|---|---|---|
| Total Time (s) | 27.51 | 27.70 | 28.44 | 28.78 | 20.58 | 13.81 | |
| Max (Thread Active Time) (s) | 27.49 | 27.68 | 28.43 | 28.76 | 20.57 | 13.80 | |
| Average Active Time (s) | 27.49 | 27.68 | 28.43 | 28.76 | 20.57 | 13.80 | |
| Activity Ratio (%) | 99.9 | 99.9 | 100.0 | 99.9 | 99.9 | 99.9 | |
| Average number of active threads | 0.999 | 0.999 | 1.000 | 0.999 | 0.999 | 0.999 | |
| Affinity Stability (%) | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 | 60.3 | |
| GFLOPS | 1.121 | 1.114 | 1.150 | 1.136 | 1.653 | 2.507 | |
| Time in analyzed loops (%) | 94.5 | 94.1 | 92.7 | 91.8 | 94.4 | 98.9 | |
| Time in analyzed innermost loops (%) | 88.8 | 89.2 | 81.8 | 81.5 | 86.3 | 72.6 | |
| Time in user code (%) | 94.6 | 94.2 | 92.8 | 91.9 | 97.9 | 98.8 | |
| Compilation Options Score (%) | 75.0 | 75.0 | 100 | 100 | 99.9 | 99.8 | |
| Array Access Efficiency (%) | 53.3 | 53.3 | 63.7 | 64.0 | 34.3 | 31.3 | |
| Potential Speedups | |||||||
| Perfect Flow Complexity | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
| No Scalar Integer | Potential Speedup | 1.03 | 1.03 | 1.08 | 1.08 | 1.13 | 1.07 |
| Nb Loops to get 80% | 7 | 6 | 4 | 4 | 6 | 7 | |
| FP Vectorised | Potential Speedup | 2.23 | 2.23 | 1.58 | 1.46 | 1.17 | 1.03 |
| Nb Loops to get 80% | 5 | 5 | 5 | 4 | 6 | 6 | |
| Fully Vectorised | Potential Speedup | 7.69 | 7.35 | 5.93 | 4.33 | 3.73 | 1.70 |
| Nb Loops to get 80% | 10 | 9 | 8 | 6 | 7 | 9 | |
| Only FP Arithmetic | Potential Speedup | 1.05 | 1.05 | 1.10 | 1.10 | 1.70 | 2.01 |
| Nb Loops to get 80% | 7 | 7 | 5 | 5 | 6 | 9 | |
| Source Object | Issue |
|---|---|
| ▼attention-gcc-skl256 | |
| ▼random.tcc | |
| ○ | -funroll-loops is missing. |
| ▼attention_v2.cpp | |
| ○ | -funroll-loops is missing. |
| r0 | r1 | r2 | r3 | r4 | r5 | |
|---|---|---|---|---|---|---|
| Experiment Name | ||||||
| Application | ./attention-gcc-skl256 | ./attention-gcc-skl512 | ./attention-clang-skl256 | ./attention-clang-skl512 | ./attention-icx-skl256 | ./attention-icx-skl512 |
| Timestamp | 2026-06-22 17:48:57 | 2026-06-22 17:49:49 | 2026-06-22 17:46:26 | 2026-06-22 17:45:23 | 2026-06-24 16:32:27 | 2026-06-24 16:29:58 |
| Experiment Type | Sequential | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Machine | skylake | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Architecture | x86_64 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Micro Architecture | SKYLAKE | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Model Name | Intel(R) Xeon(R) Platinum 8170 CPU @ 2.10GHz | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Cache Size | 36608 KB | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of Cores | 26 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Maximal Frequency | 2.10 GHz | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| OS Version | Linux 6.19.8-arch1-1 #1 SMP PREEMPT_DYNAMIC Sat, 14 Mar 2026 01:07:43 +0000 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Architecture used during static analysis | x86_64 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Micro Architecture used during static analysis | SKYLAKE | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Compilation Options | attention-gcc-skl256: GNU C++20 16.1.1 20260430 -march=skylake-avx512 -mprefer-vector-width=256 -g -O3 -fno-omit-frame-pointer -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros | attention-gcc-skl512: GNU C++20 16.1.1 20260430 -march=skylake-avx512 -mprefer-vector-width=512 -g -O3 -fno-omit-frame-pointer -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros | attention-clang-skl256: clang version 22.1.6 /usr/bin/clang++ --driver-mode=g++ -O3 -g -fno-omit-frame-pointer -grecord-command-line -march=skylake-avx512 -mprefer-vector-width=256 -fveclib=libmvec -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-clang-skl256 -dumpdir attention-clang-skl256- | attention-clang-skl512: clang version 22.1.6 /usr/bin/clang++ --driver-mode=g++ -O3 -g -fno-omit-frame-pointer -grecord-command-line -march=skylake-avx512 -mprefer-vector-width=512 -fveclib=libmvec -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-clang-skl512 -dumpdir attention-clang-skl512- | attention-icx-skl256: --driver-mode=g++ --intel -O3 -g -grecord-command-line -fno-omit-frame-pointer -march=native -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-icx-skl256 -fveclib=SVML -faltmathlib=SVML -fheinous-gnu-extensions -dumpdir attention-icx-skl256- libc.so.6: N/A + libstdc++.so.6.0.35: N/A | attention-icx-skl512: --driver-mode=g++ --intel -O3 -g -grecord-command-line -fno-omit-frame-pointer -march=native -mprefer-vector-width=512 -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-icx-skl512 -fveclib=SVML -faltmathlib=SVML -fheinous-gnu-extensions -dumpdir attention-icx-skl512- libc.so.6: N/A + libstdc++.so.6.0.35: N/A |
| Number of processes observed | 1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of threads observed | 1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Frequency Driver | intel_cpufreq | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Frequency Governor | schedutil | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Huge Pages | always | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Hyperthreading | off | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of sockets | 2 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of cores per socket | 26 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| MAQAO version | 2026.0.1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| MAQAO build | 5913ca57b6edfb4b485a73198a6fcad282267733::20260622-042016 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Comments | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |