Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
| Metric | r0 | r1 | |
|---|---|---|---|
| Total Time (s) | 8.66 | 8.18 | |
| Max (Thread Active Time) (s) | 8.66 | 8.18 | |
| Average Active Time (s) | 8.66 | 8.18 | |
| Activity Ratio (%) | 100.0 | 100.0 | |
| Average number of active threads | 1.000 | 1.000 | |
| Affinity Stability (%) | 99.9 | 99.9 | |
| GFLOPS | 7.246 | 7.825 | |
| Time in analyzed loops (%) | 92.0 | 95.8 | |
| Time in analyzed innermost loops (%) | 89.1 | 87.8 | |
| Time in user code (%) | 92.3 | 96.0 | |
| Compilation Options Score (%) | 75.0 | 100 | |
| Array Access Efficiency (%) | 50.4 | 49.8 | |
| Potential Speedups | | ||
| Perfect Flow Complexity | 1.00 | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB | 1.00 | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.00 | |
| No Scalar Integer | Potential Speedup | 1.01 | 1.04 |
| Nb Loops to get 80% | 4 | 5 | |
| FP Vectorised | Potential Speedup | 1.37 | 1.26 |
| Nb Loops to get 80% | 4 | 4 | |
| Fully Vectorised | Potential Speedup | 2.97 | 2.77 |
| Nb Loops to get 80% | 5 | 5 | |
| Only FP Arithmetic | Potential Speedup | 1.01 | 1.06 |
| Nb Loops to get 80% | 5 | 7 | |
| Source Object | Issue |
|---|---|
| ▼attention-gcc-native | |
| ▼random.tcc | |
| ○ | -funroll-loops is missing. |
| ▼attention_v2.cpp | |
| ○ | -funroll-loops is missing. |
| r0 | r1 | |
|---|---|---|
| Experiment Name | ||
| Application | ./attention-gcc-native | ./attention-armclang-native |
| Timestamp | 2026-06-22 15:59:17 | 2026-06-22 15:58:37 |
| Experiment Type | Sequential | same as r0 |
| Machine | ip-172-31-9-132.ec2.internal | same as r0 |
| Architecture | aarch64 | same as r0 |
| Micro Architecture | ARM_NEOVERSE_V2 | same as r0 |
| Model Name | ||
| Cache Size | ||
| Number of Cores | ||
| Maximal Frequency | 0.00 GHz | same as r0 |
| OS Version | Linux 6.1.170-213.321.amzn2023.aarch64 #1 SMP Thu May 14 12:18:13 UTC 2026 | same as r0 |
| Architecture used during static analysis | aarch64 | same as r0 |
| Micro Architecture used during static analysis | ARM_NEOVERSE_V2 | same as r0 |
| Compilation Options | attention-gcc-native: GNU C++17 14.2.1 20250110 (Red Hat 14.2.1-7) -mlittle-endian -mabi=lp64 -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+nossbs -g -O3 -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros | attention-armclang-native: Arm Toolchain for Linux 22.1.0 clang version 22.1.0 (https://github.com/arm/arm-toolchain.git c95792353373404441df364b5a762338e5642230) /opt/arm/arm-toolchain-for-linux/bin/clang-22 -frtlib-add-rpath -fveclib=ArmPL -mllvm -gvn-add-phi-translation=1 -mllvm -store-to-load-forwarding-conflict-detection=0 --driver-mode=g++ -O3 -g -grecord-command-line -mcpu=native -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-armclang-native -dumpdir attention-armclang-native- |
| Number of processes observed | 1 | same as r0 |
| Number of threads observed | 1 | same as r0 |
| Frequency Driver | NA | same as r0 |
| Frequency Governor | NA | same as r0 |
| Huge Pages | madvise | same as r0 |
| Hyperthreading | off | same as r0 |
| Number of sockets | 1 | same as r0 |
| Number of cores per socket | 96 | same as r0 |
| MAQAO version | 2026.0.1 | same as r0 |
| MAQAO build | Build information not available | same as r0 |
| Comments | same as r0 |