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) | 75.48 | 40.07 | 21.26 | 11.99 | 7.49 | 6.06 | 5.46 | 5.18 | 5.20 | 5.25 | 5.22 | 5.49 | 5.31 | 5.54 | 5.78 | |
| Max (Thread Active Time) (s) | 74.50 | 39.13 | 20.33 | 11.09 | 6.44 | 4.96 | 4.25 | 4.03 | 4.00 | 3.93 | 3.74 | 3.96 | 3.68 | 4.18 | 3.94 | |
| Average Active Time (s) | 74.50 | 38.98 | 20.11 | 10.78 | 6.16 | 4.67 | 3.98 | 3.64 | 3.62 | 3.54 | 3.38 | 3.60 | 3.32 | 3.55 | 3.59 | |
| Activity Ratio (%) | 98.7 | 98.4 | 97.7 | 96.2 | 92.5 | 89.6 | 86.8 | 84.6 | 83.5 | 81.0 | 78.0 | 78.3 | 75.2 | 76.4 | 73.6 | |
| Average number of active threads | 0.987 | 1.946 | 3.783 | 7.195 | 13.147 | 18.469 | 23.353 | 28.165 | 33.356 | 37.709 | 41.393 | 47.204 | 50.043 | 56.377 | 59.667 | |
| Affinity Stability (%) | 99.9 | 99.5 | 98.8 | 97.4 | 95.4 | 94.1 | 93.1 | 92.6 | 92.5 | 92.4 | 92.1 | 92.9 | 92.4 | 92.9 | 93.1 | |
| Time in analyzed loops (%) | 99.3 | 99.0 | 98.2 | 95.8 | 91.5 | 86.7 | 84.6 | 81.6 | 78.0 | 76.2 | 76.1 | 71.9 | 68.6 | 66.7 | 65.2 | |
| Time in analyzed innermost loops (%) | 98.3 | 98.0 | 97.2 | 94.7 | 90.6 | 85.9 | 83.8 | 80.8 | 77.3 | 75.5 | 75.3 | 71.2 | 68.0 | 66.1 | 64.6 | |
| Time in user code (%) | 99.6 | 99.3 | 98.6 | 96.1 | 91.9 | 87.3 | 85.0 | 81.9 | 78.3 | 76.8 | 76.6 | 73.5 | 69.3 | 68.0 | 66.6 | |
| Compilation Options Score (%) | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | |
| Array Access Efficiency (%) | 78.4 | 78.4 | 78.5 | 78.4 | 78.4 | 77.5 | 78.4 | 78.4 | 78.4 | 77.7 | 78.4 | 70.0 | 77.7 | 70.6 | 70.5 | |
| 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 | 1.03 | 1.06 | 1.10 | 1.10 | 1.21 | 1.22 | 1.23 | 1.24 | 1.27 | 1.31 | 1.47 | 1.47 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.01 | 1.02 | 1.06 | 1.13 | 1.21 | 1.25 | 1.34 | 1.40 | 1.44 | 1.44 | 1.49 | 1.59 | 1.72 | 1.64 | |
| Scalability - Gap | 1.00 | 1.06 | 1.13 | 1.27 | 1.59 | 1.93 | 2.31 | 2.74 | 3.31 | 3.90 | 4.43 | 5.24 | 5.63 | 6.45 | 7.35 | |
| No Scalar Integer | Potential Speedup | 1.17 | 1.17 | 1.17 | 1.17 | 1.16 | 1.15 | 1.14 | 1.14 | 1.13 | 1.13 | 1.13 | 1.13 | 1.11 | 1.12 | 1.12 |
| 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 | 3 | 3 | 4 | 3 | 2 | 3 | 3 | 3 | 2 | 3 | 1 | 3 | 1 | 1 | |
| Fully Vectorised | Potential Speedup | 1.70 | 1.70 | 1.69 | 1.66 | 1.61 | 1.55 | 1.54 | 1.51 | 1.48 | 1.45 | 1.46 | 1.33 | 1.39 | 1.31 | 1.30 |
| 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 | 3.33 | 3.34 | 3.27 | 3.10 | 2.83 | 2.44 | 2.48 | 2.36 | 2.22 | 2.09 | 2.16 | 1.50 | 1.88 | 1.47 | 1.45 |
| 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 | |
| ○ | |
| ▼llama-vocab.cpp | |
| ○ | |
| ▼basic_string.tcc | |
| ○ | |
| ▼hashtable_policy.h | |
| ○ | |
| ▼libggml-cpu.so | |
| ▼binary-ops.cpp | |
| ○ | |
| ▼traits.cpp | |
| ○ | |
| ▼kernels.cpp | |
| ○ | |
| ▼kleidiai.cpp | |
| ○ | |
| ▼ggml-cpu.cpp | |
| ○ | |
| ▼quants.c | |
| ○ | |
| ▼vec.cpp | |
| ○ | |
| ▼ggml-cpu.c | |
| ○ | |
| ▼ops.cpp | |
| ○ | |
| ▼libggml-base.so | |
| ▼ggml.c | |
| ○ |
| 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/176-409-3181/llama.cpp/run/binaries/gcc_1/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 15:29:38 | 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) -mcpu=neoverse-v2 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -std=gnu11 -funroll-loops -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fno-finite-math-only -fPIC libggml-cpu.so: GNU C11 11.5.0 20240719 (Red Hat 11.5.0-5) -mcpu=neoverse-v2 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -std=gnu11 -funroll-loops -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fno-finite-math-only -fPIC -fopenmp libllama.so: GNU C++17 11.5.0 20240719 (Red Hat 11.5.0-5) -mcpu=neoverse-v2 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -funroll-loops -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fno-finite-math-only -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_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 |