Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
| Total Time (s) | 18.78 | ||
| Max (Thread Active Time) (s) | 17.76 | ||
| Average Active Time (s) | 17.38 | ||
| Activity Ratio (%) | 96.8 | ||
| Average number of active threads | 59.224 | ||
| Affinity Stability (%) | 98.4 | ||
| Time in analyzed loops (%) | 80.6 | ||
| Time in analyzed innermost loops (%) | 79.9 | ||
| Time in user code (%) | 84.6 | ||
| Compilation Options Score (%) | 100 | ||
| Array Access Efficiency (%) | 70.9 | ||
| Potential Speedups | | ||
| Perfect Flow Complexity | 1.00 | ||
| Perfect OpenMP/MPI/Pthread/TBB | 1.11 | ||
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.21 | ||
| No Scalar Integer | Potential Speedup | 1.10 | |
| Nb Loops to get 80% | 1 | ||
| FP Vectorised | Potential Speedup | 1.10 | |
| Nb Loops to get 80% | 1 | ||
| Fully Vectorised | Potential Speedup | 2.06 | |
| Nb Loops to get 80% | 1 | ||
| FP Arithmetic Only | Potential Speedup | 1.82 | |
| Nb Loops to get 80% | 1 | ||
| Source Object | Issue |
|---|---|
| ▼libllama.so | |
| ○llama-vocab.cpp | |
| ○llama-sampling.cpp | |
| ○hashtable.h | |
| ○llama-impl.cpp | |
| ○stl_heap.h | |
| ○vector.tcc | |
| ○hashtable_policy.h | |
| ○llama-kv-cache.cpp | |
| ▼exec | |
| ○sampling.cpp | |
| ○vector.tcc | |
| ○basic_string.h | |
| ○regex_executor.tcc | |
| ▼libggml-base.so | |
| ○ggml-backend.cpp | |
| ○ggml.c | |
| ▼libggml-cpu.so | |
| ○binary-ops.cpp | |
| ○repack.cpp | |
| ○traits.cpp | |
| ○ggml-cpu.cpp | |
| ○ops.cpp | |
| ○vec.cpp | |
| ○ggml-cpu.c | |
| ○quants.c |
| Application | /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/binaries/gcc_4/exec | ||||
| Timestamp | 2025-09-12 14:45:35 | Universal Timestamp | 1757688335 | ||
| Number of processes observed | 1 | Number of threads observed | 64 | ||
| Experiment Type | MPI; OpenMP; | ||||
| Machine | ip-172-31-18-66 | ||||
| Architecture | aarch64 | Micro Architecture | ARM_NEOVERSE_V1 | ||
| OS Version | Linux 6.14.0-1012-aws #12~24.04.1-Ubuntu SMP Fri Aug 15 00:07:14 UTC 2025 | ||||
| Architecture used during static analysis | aarch64 | Micro Architecture used during static analysis | ARM_NEOVERSE_V1 | ||
| Frequency Driver | NA | Frequency Governor | NA | ||
| Huge Pages | madvise | Hyperthreading | off | ||
| Number of sockets | 1 | Number of cores per socket | 64 | ||
| Compilation Options | exec: GNU C++17 14.2.0 -mcpu=neoverse-v1+nosve+nosve2 -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 14.2.0 -mcpu=neoverse-v1+nosve+nosve2 -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 14.2.0 -mcpu=neoverse-v1+nosve+nosve2 -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 14.2.0 -mcpu=neoverse-v1+nosve+nosve2 -mlittle-endian -mabi=lp64 -g -O3 -O3 -O3 -funroll-loops -ffast-math -fno-omit-frame-pointer -fcf-protection=none -fno-finite-math-only -fPIC | ||||
| Dataset | |
| Run Command | <executable> -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 64 -n 512 -p "what is a LLM?" --seed 0 |
| MPI Command | mpirun -n <number_processes> --bind-to none --report-bindings |
| Number Processes | 1 |
| Number Nodes | 1 |
| Filter | Not Used |
| Profile Start | Not Used |