Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
| Total Time (s) | 40.13 | ||
| Max (Thread Active Time) (s) | 25.63 | ||
| Average Active Time (s) | 10.56 | ||
| Activity Ratio (%) | 26.6 | ||
| Average number of active threads | 18.945 | ||
| Affinity Stability (%) | 0 | ||
| Time in analyzed loops (%) | 10.9 | ||
| Time in analyzed innermost loops (%) | 10.8 | ||
| Time in user code (%) | 11.0 | ||
| Compilation Options Score (%) | 74.6 | ||
| Array Access Efficiency (%) | 71.6 | ||
| Potential Speedups | | ||
| Perfect Flow Complexity | 1.00 | ||
| Perfect OpenMP + MPI + Pthread | 3.27 | ||
| Perfect OpenMP + MPI + Pthread + Perfect Load Distribution | 13.8 | ||
| No Scalar Integer | Potential Speedup | 1.00 | |
| Nb Loops to get 80% | 1 | ||
| FP Vectorised | Potential Speedup | 1.00 | |
| Nb Loops to get 80% | 1 | ||
| Fully Vectorised | Potential Speedup | 1.00 | |
| Nb Loops to get 80% | 1 | ||
| FP Arithmetic Only | Potential Speedup | 1.00 | |
| Nb Loops to get 80% | 2 | ||
| Source Object | Issue |
|---|---|
| ▼libllama.so | |
| ▼llama-sampling.cpp | |
| ○ | -O3 or -Ofast is missing. |
| ○ | -mcpu=native is missing. |
| ○ | -funroll-loops is missing. |
| ▼exec | |
| ▼sampling.cpp | |
| ○ | -O3 or -Ofast is missing. |
| ○ | -mcpu=native is missing. |
| ○ | -funroll-loops is missing. |
| ▼libggml-base.so | |
| ▼ | |
| ○ | -g is missing for some functions (possibly ones added by the compiler), it is needed to have more accurate reports. Other recommended flags are: -O2/-O3, -march=(target) |
| ○ | -O2, -O3 or -Ofast is missing. |
| ○ | -mcpu=native is missing. |
| ▼libggml-cpu.so | |
| ○vec.cpp | -funroll-loops is missing. |
| ○quants.c | -funroll-loops is missing. |
| Application | /scratch/users/amazouz/QAAS/service/Llama.cpp/ortce-gh/175-931-3387/llama.cpp/run/base_runs/defaults/gcc/exec | ||||
| Timestamp | 2025-10-01 03:16:54 | Universal Timestamp | 1759313814 | ||
| Number of processes observed | 1 | Number of threads observed | 72 | ||
| Experiment Type | MPI; OpenMP; | ||||
| Machine | ortce-gh | ||||
| Architecture | aarch64 | Micro Architecture | ARM_NEOVERSE_V2 | ||
| OS Version | Linux 6.8.0-84-generic-64k #84-Ubuntu SMP PREEMPT_DYNAMIC Fri Sep 5 15:19:10 UTC 2025 | ||||
| Architecture used during static analysis | aarch64 | Micro Architecture used during static analysis | ARM_NEOVERSE_V2 | ||
| Frequency Driver | cppc_cpufreq | Frequency Governor | ondemand | ||
| Huge Pages | always | Hyperthreading | off | ||
| Number of sockets | 1 | Number of cores per socket | 72 | ||
| Compilation Options | exec: GNU C++17 14.2.0 -mlittle-endian -mabi=lp64 -g -O3 -O3 -fno-omit-frame-pointer -fcf-protection=none -fPIC GNU C17 14.2.0 -mlittle-endian -mabi=lp64 -g -g -g -O2 -O2 -O2 -fbuilding-libgcc -fno-stack-protector -fPIC libggml-base.so: N/A libggml-cpu.so: GNU C11 14.2.0 -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+sve2-sm4+norng+dotprod+i8mm+sve+nosme -mlittle-endian -mabi=lp64 -g -O3 -O3 -std=gnu11 -fno-omit-frame-pointer -fcf-protection=none -fPIC -fopenmp libllama.so: GNU C++17 14.2.0 -mlittle-endian -mabi=lp64 -g -O3 -O3 -fno-omit-frame-pointer -fcf-protection=none -fPIC GNU C17 14.2.0 -mlittle-endian -mabi=lp64 -g -g -g -O2 -O2 -O2 -fbuilding-libgcc -fno-stack-protector -fPIC | ||||
| Dataset | |
| Run Command | <executable> -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 72 -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 |