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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Total Time (s) | 279.51 | 140.32 | 71.46 | 37.13 | 20.45 | 15.74 | 12.97 | 11.66 | 10.77 | 10.83 | 10.31 | |
| Max (Thread Active Time) (s) | 278.42 | 139.27 | 70.42 | 36.00 | 19.27 | 14.46 | 11.50 | 10.08 | 9.12 | 9.12 | 8.53 | |
| Average Active Time (s) | 278.42 | 139.07 | 70.10 | 35.67 | 18.86 | 14.04 | 11.16 | 9.77 | 8.79 | 8.67 | 8.08 | |
| Activity Ratio (%) | 99.6 | 99.5 | 99.2 | 98.6 | 97.0 | 95.4 | 93.6 | 92.1 | 90.3 | 88.8 | 87.4 | |
| Average number of active threads | 0.996 | 1.982 | 3.924 | 7.687 | 14.756 | 21.416 | 27.551 | 33.514 | 39.166 | 44.853 | 50.155 | |
| Affinity Stability (%) | 100.0 | 99.9 | 99.6 | 99.1 | 98.3 | 97.7 | 97.1 | 96.7 | 96.3 | 96.2 | 95.9 | |
| Time in analyzed loops (%) | 99.3 | 99.2 | 98.7 | 98.0 | 94.9 | 92.0 | 90.1 | 86.7 | 84.8 | 83.1 | 82.9 | |
| Time in analyzed innermost loops (%) | 98.1 | 97.9 | 97.4 | 96.8 | 93.7 | 90.8 | 88.9 | 85.6 | 83.7 | 82.0 | 81.8 | |
| Time in user code (%) | 99.6 | 99.5 | 99.0 | 98.4 | 95.3 | 92.7 | 90.7 | 87.3 | 85.4 | 83.8 | 83.5 | |
| Compilation Options Score (%) | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | |
| Array Access Efficiency (%) | 79.9 | 79.9 | 79.9 | 79.9 | 79.9 | 79.6 | 79.8 | 79.8 | 79.8 | 79.5 | 79.8 | |
| 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 | |
| Perfect OpenMP/MPI/Pthread/TBB | 1.00 | 1.00 | 1.00 | 1.01 | 1.04 | 1.07 | 1.08 | 1.10 | 1.13 | 1.14 | 1.13 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.00 | 1.01 | 1.02 | 1.07 | 1.11 | 1.13 | 1.17 | 1.21 | 1.25 | 1.26 | |
| Scalability - Gap | 1.00 | 1.00 | 1.02 | 1.06 | 1.17 | 1.35 | 1.48 | 1.67 | 1.85 | 2.17 | 2.36 | |
| No Scalar Integer | Potential Speedup | 1.46 | 1.46 | 1.45 | 1.45 | 1.43 | 1.38 | 1.40 | 1.38 | 1.37 | 1.33 | 1.35 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| FP Vectorised | Potential Speedup | 1.19 | 1.19 | 1.19 | 1.19 | 1.18 | 1.16 | 1.17 | 1.16 | 1.16 | 1.15 | 1.16 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Fully Vectorised | Potential Speedup | 5.16 | 5.11 | 5.00 | 4.87 | 4.34 | 3.38 | 3.70 | 3.37 | 3.20 | 2.77 | 3.05 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Only FP Arithmetic | Potential Speedup | 3.10 | 3.10 | 3.06 | 3.02 | 2.83 | 2.54 | 2.59 | 2.44 | 2.36 | 2.21 | 2.29 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Source Object | Issue |
|---|---|
| ▼libllama.so | |
| ▼hashtable.h | |
| ○ | |
| ▼llama-vocab.cpp | |
| ○ | |
| ▼libggml-cpu.so | |
| ▼binary-ops.cpp | |
| ○ | |
| ▼traits.cpp | |
| ○ | |
| ▼kernels.cpp | |
| ○ | |
| ▼vec.cpp | |
| ○ | |
| ▼kleidiai.cpp | |
| ○ | |
| ▼ops.cpp | |
| ○ | |
| ▼ggml-cpu.c | |
| ○ | |
| ▼quants.c | |
| ○ | |
| ▼libggml-base.so | |
| ▼ggml.c | |
| ○ |
| r0 | r1 | r2 | r3 | r4 | r5 | r6 | r7 | r8 | r9 | r10 | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Application | /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/run/binaries/gcc_5/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 |
| Timestamp | 2025-11-26 16:37:12 | 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 |
| Machine | ip-172-31-46-37.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 |
| 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 |
| Micro Architecture | ARM_NEOVERSE_V1 | 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 |
| 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 |
| 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 |
| Micro Architecture used during static analysis | ARM_NEOVERSE_V1 | 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-v1 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -std=gnu11 -fno-tree-vectorize -fno-openmp-simd -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-v1 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -std=gnu11 -fno-tree-vectorize -fno-openmp-simd -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-v1 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -fno-tree-vectorize -fno-openmp-simd -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 |
| 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 |
| Number of threads observed | 1 | 2 | 4 | 8 | 16 | 24 | 32 | 40 | 48 | 56 | 64 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| Number of cores per socket | 64 | 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 |
| 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 |
| Comments | OV scalability run using gcc_5 | 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 |