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) | 176.10 | 90.47 | 47.82 | 29.04 | 21.10 | 18.41 | 17.72 | 17.72 | 18.36 | 18.60 | 19.46 | 20.35 | 21.22 | 22.25 | 24.35 | |
| Max (Thread Active Time) (s) | 175.08 | 86.80 | 43.89 | 24.44 | 15.10 | 10.93 | 8.68 | 7.32 | 6.41 | 5.44 | 4.86 | 4.44 | 4.06 | 3.76 | 3.57 | |
| Average Active Time (s) | 175.08 | 86.77 | 43.73 | 24.19 | 14.93 | 10.77 | 8.54 | 7.15 | 6.20 | 5.32 | 4.75 | 4.30 | 3.97 | 3.69 | 3.47 | |
| Activity Ratio (%) | 99.4 | 96.4 | 92.7 | 85.6 | 73.7 | 61.3 | 50.6 | 42.4 | 35.4 | 30.0 | 25.6 | 22.1 | 19.5 | 17.2 | 14.8 | |
| Average number of active threads | 0.994 | 1.918 | 3.657 | 6.665 | 11.324 | 14.037 | 15.422 | 16.134 | 16.205 | 16.027 | 15.632 | 15.232 | 14.973 | 14.575 | 13.669 | |
| Affinity Stability (%) | 100.0 | 99.8 | 99.5 | 98.9 | 98.4 | 98.1 | 98.0 | 98.0 | 98.0 | 98.0 | 98.0 | 98.1 | 98.2 | 98.3 | 98.4 | |
| Time in analyzed loops (%) | 4.79 | 4.28 | 3.97 | 3.40 | 3.25 | 3.16 | 3.01 | 2.76 | 3.03 | 3.06 | 3.20 | 3.44 | 3.28 | 3.60 | 3.36 | |
| Time in analyzed innermost loops (%) | 3.94 | 3.48 | 3.09 | 2.66 | 2.57 | 2.54 | 2.49 | 2.29 | 2.52 | 2.56 | 2.68 | 2.96 | 2.80 | 3.12 | 2.86 | |
| Time in user code (%) | 4.89 | 4.39 | 4.09 | 3.50 | 3.35 | 3.24 | 3.10 | 2.85 | 3.12 | 3.14 | 3.29 | 3.54 | 3.42 | 3.69 | 3.47 | |
| Compilation Options Score (%) | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 74.9 | 75.0 | 75.0 | 75.0 | 75.0 | 75.0 | 74.9 | |
| Array Access Efficiency (%) | 73.5 | 74.0 | 73.4 | 73.3 | 73.3 | 73.2 | 73.7 | 73.7 | 74.0 | 72.9 | 74.0 | 73.4 | 73.6 | 72.6 | 71.9 | |
| 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 | 1.00 | 1.00 | 1.00 | 1.01 | 1.01 | 1.01 | 1.02 | 1.01 | 1.03 | 1.02 | 1.03 | 1.03 | 1.05 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.00 | 1.00 | 1.01 | 1.01 | 1.02 | 1.02 | 1.03 | 1.04 | 1.06 | 1.05 | 1.05 | 1.07 | 1.06 | 1.07 | 1.08 | |
| Scalability - Gap | 1.00 | 1.03 | 1.09 | 1.32 | 1.92 | 2.51 | 3.22 | 4.02 | 5.00 | 5.91 | 7.07 | 8.32 | 9.64 | 11.12 | 13.27 | |
| No Scalar Integer | Potential Speedup | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 |
| Nb Loops to get 80% | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 5 | 4 | 5 | 4 | |
| FP Vectorised | Potential Speedup | 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 |
| Nb Loops to get 80% | 3 | 3 | 3 | 4 | 3 | 3 | 3 | 3 | 3 | 3 | 3 | 3 | 3 | 3 | 3 | |
| Fully Vectorised | Potential Speedup | 1.02 | 1.02 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 | 1.01 |
| Nb Loops to get 80% | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 4 | 3 | 3 | 3 | 4 | 3 | 4 | 5 | |
| Only FP Arithmetic | Potential Speedup | 1.03 | 1.03 | 1.03 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 | 1.02 |
| Nb Loops to get 80% | 4 | 4 | 4 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | 4 | 5 | 4 | 5 | 5 | |
| Source Object | Issue |
|---|---|
| ▼libllama.so | |
| ▼hashtable.h | |
| ○ | -funroll-loops is missing. |
| ▼hashtable_policy.h | |
| ○ | -funroll-loops is missing. |
| ▼libggml-cpu.so | |
| ▼binary-ops.cpp | |
| ○ | -funroll-loops is missing. |
| ▼ops.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-quants.c | |
| ○ | -funroll-loops is missing. |
| ▼libggml-blas.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. |
| 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/176-410-1312/llama.cpp/run/base_runs/defaults/gcc/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 13:25:23 | 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 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-blas.so: N/A libggml-cpu.so: GNU C11 11.5.0 20240719 (Red Hat 11.5.0-5) -mcpu=neoverse-v2+crypto+sve2-aes+sve2-sha3+nomemtag+nossbs+nopredres+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 | 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=neoverse-v2+crypto+sve2-aes+sve2-sha3+nomemtag+nossbs+nopredres+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 | same as r1 | same as r1 | same as r0 | same as r0 | same as r1 | libggml-cpu.so: GNU C11 11.5.0 20240719 (Red Hat 11.5.0-5) -mcpu=neoverse-v2+crypto+sve2-aes+sve2-sha3+nomemtag+nossbs+nopredres+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 | same as r0 | same as r1 | same as r1 | same as r1 | same as r1 | 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 | 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 | 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 |