Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
- There is no filter information to display
| Total Time (s) | 6.65 | |
| Max (Thread Active Time) (s) | 4.99 | |
| Average Active Time (s) | 4.61 | |
| Activity Ratio (%) | 82.2 | |
| Average number of active threads | 44.346 | |
| Affinity Stability (%) | 93.5 | |
| Time in analyzed loops (%) | 79.4 | |
| Time in analyzed innermost loops (%) | 78.7 | |
| Time in user code (%) | 80.1 | |
| Compilation Options Score (%) | 75.0 | |
| Array Access Efficiency (%) | 75.1 | |
|
| Potential Speedups | |
| Perfect Flow Complexity | 1.00 | |
| Perfect OpenMP/MPI/Pthread/TBB | 1.17 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.35 | |
| No Scalar Integer | Potential Speedup | 1.08 | |
| Nb Loops to get 80% | 1 | |
| FP Vectorised | Potential Speedup | 1.00 | |
| Nb Loops to get 80% | 2 | |
| Fully Vectorised | Potential Speedup | 1.10 | |
| Nb Loops to get 80% | 2 | |
| FP Arithmetic Only | Potential Speedup | 2.02 | |
| Nb Loops to get 80% | 1 | |
| Source Object | Issue |
|---|
| ▼libllama.so– | |
| ○hashtable.h | -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. |
| ○ops.cpp | -funroll-loops is missing. |
| ○kleidiai.cpp | -funroll-loops is missing. |
| ○vec.cpp | -funroll-loops is missing. |
| ○ggml-cpu.c | -funroll-loops is missing. |
| ○quants.c | -funroll-loops is missing. |
| ▼libggml-base.so– | |
| ○ggml.c | -funroll-loops is missing. |
| Application | /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-1084/llama.cpp/run/base_runs/defaults/gcc/exec |
| Timestamp | 2025-11-25 17:22:24 |
Universal Timestamp | 1764091344 |
| Number of processes observed | 1 |
Number of threads observed | 64 |
| Experiment Type | MPI; OpenMP; |
| Machine | ip-172-31-46-37.ec2.internal |
| Architecture | aarch64 |
Micro Architecture | ARM_NEOVERSE_V1 |
| OS Version | Linux 6.1.158-178.288.amzn2023.aarch64 #1 SMP Mon Nov 3 18:38:05 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 | 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=zeus+crypto+sha3+sm4+noprofile+nossbs+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 | | |
| Dataset | |
| Run Command | <executable> -m meta-llama-3.1-8b-instruct-Q8_0.gguf -t 64 -b 2048 -ub 512 -npp 0 -ntg 128 -npl 1 -c 16384 --seed 0 --output-format jsonl |
| MPI Command | mpirun -n <number_processes> --bind-to none --report-bindings /usr/bin/numactl -C 0-63 |
| Number Processes | 1 |
| Number Nodes | 1 |
| Filter | Not Used |
| Profile Start | Not Used |
| Profile Stop | Not Used |
