options

Help is available by moving the cursor above any symbol or by checking MAQAO website.

Global Metrics

Metricr0r1r2r3r4r5r6r7r8r9r10r11r12r13r14
Total Time (s)28.2715.489.156.505.795.936.366.917.498.178.829.5110.1910.9011.66
Max (Thread Active Time) (s)27.3213.276.623.622.201.621.281.100.970.900.880.860.700.680.67
Average Active Time (s)27.3213.206.593.582.171.611.271.090.950.870.790.740.680.650.64
Activity Ratio (%)96.687.777.762.543.731.823.118.014.412.09.988.627.326.505.90
Average number of active threads0.9661.7052.8804.4035.9906.5256.3796.2926.1175.9835.7455.6345.3525.2535.239
Affinity Stability (%)99.998.896.994.793.593.593.894.394.795.195.495.895.996.396.5
Time in analyzed loops (%)16.915.115.612.410.710.811.010.210.99.9310.410.49.6311.512.1
Time in analyzed innermost loops (%)16.114.414.511.810.110.310.59.6410.59.499.889.939.2511.111.7
Time in user code (%)17.215.415.812.710.911.011.310.411.210.210.610.69.8611.712.4
Compilation Options Score (%)75.075.075.075.075.075.075.075.075.075.074.975.075.074.975.0
Array Access Efficiency (%)76.877.677.277.577.477.377.677.777.377.576.976.077.276.076.6
Potential Speedups
Perfect Flow Complexity1.001.001.001.001.001.001.001.001.001.001.001.001.001.001.00
Perfect OpenMP/MPI/Pthread/TBB1.001.001.011.011.021.021.021.051.031.051.041.021.071.071.06
Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution1.001.011.011.021.041.041.051.081.071.101.191.261.151.151.16
Scalability - Gap1.001.101.291.843.285.037.209.7812.7216.1819.9724.2228.8433.9439.60
No Scalar IntegerPotential Speedup1.031.021.031.021.021.021.021.021.021.021.021.021.021.021.02
Nb Loops to get 80%333222333333333
FP VectorisedPotential Speedup1.001.001.001.001.001.001.001.001.001.001.001.011.001.011.01
Nb Loops to get 80%444434333432322
Fully VectorisedPotential Speedup1.071.061.071.051.051.041.051.041.051.041.041.041.041.041.05
Nb Loops to get 80%222111111212222
Only FP ArithmeticPotential Speedup1.131.121.121.091.081.081.081.071.081.071.071.071.071.081.08
Nb Loops to get 80%222111111112222

Scalability Speedup

Cumulated Speedup If No Scalar Integer

Cumulated Speedup If FP Vectorized

Cumulated Speedup If Fully Vectorized

Cumulated Speedup If Only FP Arithmetic

Loop Based Profiles

Innermost / Single Loops

Inbetween Loops

Outermost Loops

Cumulated Coverage With All Loops

Innermost Loop Based Profiles

Coverage

Count

Application Categorization

Time

Coverage

Compilation Options

Source ObjectIssue
▼libllama.so–
▼llama-vocab.cpp–
○-funroll-loops is missing.
▼basic_string.tcc–
○-funroll-loops is missing.
▼hashtable_policy.h–
○-funroll-loops is missing.
▼llama-impl.cpp–
○-funroll-loops is missing.
▼unicode.cpp–
○-funroll-loops is missing.
▼basic_string.h–
○-funroll-loops is missing.
▼hashtable.h–
○-funroll-loops is missing.
▼libggml-cpu.so–
▼binary-ops.cpp–
○-funroll-loops is missing.
▼traits.cpp–
○-funroll-loops is missing.
▼kleidiai.cpp–
○-funroll-loops is missing.
▼vec.cpp–
○-funroll-loops is missing.
▼quants.c–
○-funroll-loops is missing.
▼ggml-cpu.c–
○-funroll-loops is missing.
▼ops.cpp–
○-funroll-loops is missing.
▼libggml-base.so–
▼ggml-quants.c–
○-funroll-loops is missing.
▼ggml.c–
○-funroll-loops is missing.
▼basic_string.tcc–
○-funroll-loops is missing.
▼stl_vector.h–
○-funroll-loops is missing.
▼gguf.cpp–
○-funroll-loops is missing.
▼ggml-backend.cpp–
○-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.

Path Count Profiles

Coverage

Count

Low Iteration Count Profiles

Coverage

Count

Average Number of Active Threads

Run 1 - 1x1

Run 2 - 1x2

Run 3 - 1x4

Run 4 - 1x8

Run 5 - 1x16

Run 6 - 1x24

Run 7 - 1x32

Run 8 - 1x40

Run 9 - 1x48

Run 10 - 1x56

Run 11 - 1x64

Run 12 - 1x72

Run 13 - 1x80

Run 14 - 1x88

Run 15 - 1x96

Experiment Summaries

r0r1r2r3r4r5r6r7r8r9r10r11r12r13r14
Application/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-2112/llama.cpp/run/base_runs/defaults/gcc/execsame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Timestamp2025-11-26 12:51:42same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Experiment TypeMPI; MPI; OpenMP; same as r1same as r1same as r1same as r1same as r1same as r1same as r1same as r1same as r1same as r1same as r1same as r1same as r1
Machineip-172-31-35-140.ec2.internalsame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Architectureaarch64same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Micro ArchitectureARM_NEOVERSE_V2same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Model Name
Cache Size
Number of Cores
Maximal Frequency0 GHzsame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
OS VersionLinux 6.1.158-178.288.amzn2023.aarch64 #1 SMP Mon Nov 3 18:38:05 UTC 2025same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Architecture used during static analysisaarch64same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Micro Architecture used during static analysisARM_NEOVERSE_V2same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same 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-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 r0same as r0same as r0libggml-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 r0same as r0same as r0same as r0libggml-base.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 -std=gnu++17 -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 		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 		same as r9same as r0same as r10same as r0
Number of processes observed1same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Number of threads observed12481624324048566472808896
Frequency DriverNAsame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Frequency GovernorNAsame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Huge Pagesmadvisesame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Hyperthreadingoffsame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Number of sockets1same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
Number of cores per socket96same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
MAQAO version2025.1.3same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
MAQAO buildb489783858807c9a72e0923fd7b399a22c81991c::20251024-122946same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
CommentsOV scalability run using gccsame as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0same as r0
×