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) | 51.69 | 28.22 | 15.14 | 8.97 | 5.91 | 5.07 | 5.04 | 4.95 | 4.99 | 4.92 | 4.89 | 4.95 | 5.09 | 5.17 | 5.30 | |
| Max (Thread Active Time) (s) | 50.77 | 27.33 | 14.23 | 8.02 | 4.89 | 3.99 | 3.88 | 3.73 | 3.67 | 3.49 | 3.44 | 3.55 | 3.65 | 3.51 | 3.77 | |
| Average Active Time (s) | 50.77 | 27.16 | 14.00 | 7.74 | 4.61 | 3.69 | 3.56 | 3.42 | 3.35 | 3.23 | 3.14 | 3.11 | 3.11 | 3.16 | 3.29 | |
| Activity Ratio (%) | 98.2 | 97.8 | 96.7 | 94.6 | 90.9 | 87.7 | 85.4 | 83.6 | 81.6 | 80.3 | 78.3 | 76.9 | 74.2 | 74.0 | 74.7 | |
| Average number of active threads | 0.982 | 1.925 | 3.698 | 6.903 | 12.474 | 17.462 | 22.581 | 27.586 | 32.241 | 36.857 | 41.002 | 45.287 | 48.912 | 53.790 | 59.557 | |
| Affinity Stability (%) | 99.9 | 99.3 | 98.2 | 96.4 | 94.0 | 92.5 | 92.3 | 92.0 | 91.9 | 91.6 | 91.4 | 91.4 | 91.8 | 91.9 | 92.1 | |
| Time in analyzed loops (%) | 95.8 | 93.8 | 93.1 | 90.1 | 84.7 | 79.6 | 77.7 | 73.7 | 73.2 | 72.3 | 69.7 | 67.5 | 65.7 | 64.3 | 61.4 | |
| Time in analyzed innermost loops (%) | 95.0 | 93.1 | 92.3 | 89.3 | 84.0 | 79.0 | 77.0 | 73.2 | 72.6 | 71.7 | 69.2 | 67.0 | 65.3 | 63.8 | 61.0 | |
| Time in user code (%) | 99.3 | 98.5 | 97.7 | 94.6 | 89.3 | 83.5 | 81.6 | 77.5 | 76.8 | 75.8 | 73.1 | 70.5 | 68.8 | 67.4 | 64.4 | |
| Compilation Options Score (%) | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | |
| Array Access Efficiency (%) | 61.6 | 61.5 | 61.5 | 61.5 | 61.3 | 61.1 | 61.2 | 61.1 | 61.0 | 61.0 | 61.0 | 60.7 | 60.9 | 60.7 | 61.0 | |
| 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 | 1.04 | 1.07 | 1.11 | 1.17 | 1.22 | 1.26 | 1.23 | 1.23 | 1.30 | 1.39 | 1.38 | 1.44 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.02 | 1.04 | 1.09 | 1.18 | 1.29 | 1.33 | 1.40 | 1.42 | 1.41 | 1.49 | 1.61 | 1.70 | 1.64 | 1.77 | |
| Scalability - Gap | 1.00 | 1.09 | 1.17 | 1.39 | 1.83 | 2.35 | 3.12 | 3.83 | 4.64 | 5.32 | 6.06 | 6.89 | 7.88 | 8.80 | 9.85 | |
| No Scalar Integer | Potential Speedup | 1.20 | 1.20 | 1.20 | 1.19 | 1.18 | 1.16 | 1.16 | 1.15 | 1.15 | 1.15 | 1.14 | 1.14 | 1.13 | 1.13 | 1.12 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| FP Vectorised | Potential Speedup | 1.08 | 1.08 | 1.08 | 1.08 | 1.07 | 1.07 | 1.07 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.05 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Fully Vectorised | Potential Speedup | 1.36 | 1.35 | 1.34 | 1.33 | 1.30 | 1.27 | 1.27 | 1.25 | 1.25 | 1.24 | 1.23 | 1.22 | 1.22 | 1.21 | 1.20 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Only FP Arithmetic | Potential Speedup | 1.27 | 1.26 | 1.26 | 1.25 | 1.22 | 1.20 | 1.19 | 1.18 | 1.18 | 1.17 | 1.16 | 1.15 | 1.15 | 1.14 | 1.14 |
| Nb Loops to get 80% | 2 | 2 | 2 | 2 | 2 | 2 | 2 | 2 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Source Object | Issue |
|---|---|
| ▼libllama.so | |
| ▼hashtable.h | |
| ○ | |
| ▼hashtable_policy.h | |
| ○ | |
| ▼llama-vocab.cpp | |
| ○ | |
| ▼unicode.cpp | |
| ○ | |
| ▼basic_string.h | |
| ○ | |
| ▼llama-impl.cpp | |
| ○ | |
| ▼libggml-cpu.so | |
| ▼binary-ops.cpp | |
| ○ | |
| ▼traits.cpp | |
| ○ | |
| ▼kernels.cpp | |
| ○ | |
| ▼kleidiai.cpp | |
| ○ | |
| ▼ggml-cpu.cpp | |
| ○ | |
| ▼vec.cpp | |
| ○ | |
| ▼ops.cpp | |
| ○ | |
| ▼ggml-cpu.c | |
| ○ | |
| ▼quants.c | |
| ○ | |
| ▼libggml-base.so | |
| ▼gguf.cpp | |
| ○ | |
| ▼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/176-409-1188/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 15:23:30 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | same as r0 | 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 C++17 11.5.0 20240719 (Red Hat 11.5.0-5) -mcpu=neoverse-v2 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -std=gnu++17 -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 | 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 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 |
| 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 |