Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
| Metric | r0 | r1 | r2 | r3 | r4 | r5 | r6 | r7 | r8 | r9 | r10 | r11 | r12 | r13 | r14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Total Time (s) | 135.78 | 67.94 | 35.24 | 18.89 | 10.98 | 8.81 | 7.56 | 6.91 | 6.59 | 6.37 | 6.29 | 6.67 | 6.23 | 6.63 | 6.69 | |
| Max (Thread Active Time) (s) | 134.86 | 67.01 | 34.33 | 17.91 | 9.97 | 7.70 | 6.45 | 5.66 | 5.25 | 4.94 | 4.63 | 4.97 | 4.52 | 4.76 | 4.80 | |
| Average Active Time (s) | 134.86 | 66.86 | 34.10 | 17.69 | 9.65 | 7.37 | 6.04 | 5.36 | 4.87 | 4.60 | 4.40 | 4.78 | 4.19 | 4.52 | 4.44 | |
| Activity Ratio (%) | 99.3 | 99.1 | 98.6 | 97.7 | 95.1 | 92.6 | 90.2 | 88.6 | 85.2 | 83.5 | 81.3 | 82.5 | 78.4 | 78.7 | 76.4 | |
| Average number of active threads | 0.993 | 1.968 | 3.870 | 7.489 | 14.062 | 20.079 | 25.584 | 30.994 | 35.467 | 40.410 | 44.757 | 51.571 | 53.824 | 60.014 | 63.734 | |
| Affinity Stability (%) | 100.0 | 99.7 | 99.3 | 98.4 | 97.0 | 96.1 | 95.3 | 94.8 | 94.4 | 93.9 | 93.7 | 94.3 | 93.7 | 94.0 | 94.1 | |
| Time in analyzed loops (%) | 99.3 | 99.1 | 98.8 | 97.2 | 93.2 | 90.2 | 87.5 | 83.5 | 80.7 | 78.4 | 76.9 | 75.8 | 71.8 | 71.1 | 69.5 | |
| Time in analyzed innermost loops (%) | 98.4 | 98.1 | 97.8 | 96.2 | 92.1 | 89.3 | 86.7 | 82.8 | 80.1 | 77.7 | 76.3 | 75.2 | 71.2 | 70.5 | 68.9 | |
| Time in user code (%) | 99.6 | 99.3 | 99.0 | 97.5 | 93.5 | 90.6 | 87.8 | 84.0 | 81.1 | 78.8 | 77.4 | 76.4 | 72.3 | 71.8 | 70.2 | |
| Compilation Options Score (%) | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | |
| Array Access Efficiency (%) | 78.5 | 78.5 | 78.5 | 78.5 | 78.5 | 78.3 | 78.5 | 78.5 | 78.4 | 78.3 | 78.4 | 76.7 | 78.3 | 76.8 | 76.7 | |
| Potential Speedups | | |||||||||||||||
| Perfect Flow Complexity | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB | 1.00 | 1.00 | 1.01 | 1.01 | 1.06 | 1.08 | 1.11 | 1.12 | 1.16 | 1.18 | 1.19 | 1.23 | 1.27 | 1.28 | 1.32 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.00 | 1.01 | 1.03 | 1.10 | 1.15 | 1.21 | 1.25 | 1.32 | 1.35 | 1.35 | 1.35 | 1.48 | 1.46 | 1.53 | |
| Scalability - Gap | 1.00 | 1.00 | 1.04 | 1.11 | 1.29 | 1.56 | 1.78 | 2.04 | 2.33 | 2.63 | 2.97 | 3.54 | 3.67 | 4.29 | 4.73 | |
| No Scalar Integer | Potential Speedup | 1.18 | 1.17 | 1.17 | 1.17 | 1.16 | 1.15 | 1.15 | 1.14 | 1.14 | 1.13 | 1.13 | 1.11 | 1.12 | 1.10 | 1.10 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 1 | 2 | 2 | |
| FP Vectorised | Potential Speedup | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.03 | 1.00 | 1.03 | 1.03 |
| Nb Loops to get 80% | 3 | 4 | 4 | 3 | 4 | 3 | 3 | 3 | 3 | 2 | 3 | 1 | 2 | 1 | 1 | |
| Fully Vectorised | Potential Speedup | 1.70 | 1.70 | 1.70 | 1.68 | 1.63 | 1.58 | 1.57 | 1.53 | 1.50 | 1.47 | 1.47 | 1.36 | 1.42 | 1.33 | 1.32 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 1 | 2 | 2 | |
| Only FP Arithmetic | Potential Speedup | 3.31 | 3.29 | 3.27 | 3.15 | 2.89 | 2.68 | 2.59 | 2.41 | 2.30 | 2.19 | 2.17 | 1.91 | 1.99 | 1.82 | 1.78 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 1 | 2 | 2 | |
| Source Object | Issue |
|---|---|
| ▼libllama.so | |
| ▼hashtable.h | |
| ○ | -funroll-loops is missing. |
| ▼llama-vocab.cpp | |
| ○ | -funroll-loops is missing. |
| ▼libggml-cpu.so | |
| ▼binary-ops.cpp | |
| ○ | -funroll-loops is missing. |
| ▼traits.cpp | |
| ○ | -funroll-loops is missing. |
| ▼kernels.cpp | |
| ○ | -funroll-loops is missing. |
| ▼kleidiai.cpp | |
| ○ | -funroll-loops is missing. |
| ▼ggml-cpu.cpp | |
| ○ | -funroll-loops is missing. |
| ▼quants.c | |
| ○ | -funroll-loops is missing. |
| ▼vec.cpp | |
| ○ | -funroll-loops is missing. |
| ▼ggml-cpu.c | |
| ○ | -funroll-loops is missing. |
| ▼ops.cpp | |
| ○ | -funroll-loops is missing. |
| ▼libggml-base.so | |
| ▼ggml.c | |
| ○ | -funroll-loops is missing. |
| r0 | r1 | r2 | r3 | r4 | r5 | r6 | r7 | r8 | r9 | r10 | r11 | r12 | r13 | r14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Application | /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-5681/llama.cpp/run/base_runs/defaults/gcc/exec | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Timestamp | 2025-11-26 15:36:37 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Experiment Type | MPI; | MPI; OpenMP; | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 | same as r1 |
| Machine | ip-172-31-35-140.ec2.internal | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Architecture | aarch64 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Micro Architecture | ARM_NEOVERSE_V2 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Model Name | |||||||||||||||
| Cache Size | |||||||||||||||
| Number of Cores | |||||||||||||||
| Maximal Frequency | 0 GHz | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| OS Version | Linux 6.1.158-178.288.amzn2023.aarch64 #1 SMP Mon Nov 3 18:38:05 UTC 2025 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Architecture used during static analysis | aarch64 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Micro Architecture used during static analysis | ARM_NEOVERSE_V2 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Compilation Options | libggml-base.so: GNU C11 11.5.0 20240719 (Red Hat 11.5.0-5) -march=armv8.2-a+crypto -mtune=neoverse-n1 -mlittle-endian -mabi=lp64 -g -O3 -O3 -std=gnu11 -fno-omit-frame-pointer -fcf-protection=none -fPIC libggml-cpu.so: GNU C11 11.5.0 20240719 (Red Hat 11.5.0-5) -mcpu=neoverse-v2+crypto+sve2-aes+sve2-sha3+nomemtag+nossbs+nopredres+dotprod+i8mm+sve -mlittle-endian -mabi=lp64 -g -O3 -O3 -std=gnu11 -fno-omit-frame-pointer -fcf-protection=none -fPIC -fopenmp libllama.so: GNU C++17 11.5.0 20240719 (Red Hat 11.5.0-5) -march=armv8.2-a+crypto -mtune=neoverse-n1 -mlittle-endian -mabi=lp64 -g -O3 -O3 -fno-omit-frame-pointer -fcf-protection=none -fPIC | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of processes observed | 1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of threads observed | 1 | 2 | 4 | 8 | 16 | 24 | 32 | 40 | 48 | 56 | 64 | 72 | 80 | 88 | 96 |
| Frequency Driver | NA | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Frequency Governor | NA | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Huge Pages | madvise | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | 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 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of sockets | 1 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Number of cores per socket | 96 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| MAQAO version | 2025.1.3 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| MAQAO build | b489783858807c9a72e0923fd7b399a22c81991c::20251024-122946 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |
| Comments | OV scalability run using gcc | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 |