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) | 11.27 | 11.18 | 11.23 | 11.21 | 11.27 | 11.22 | 11.22 | 11.21 | 11.16 | 11.23 | 11.23 | 11.24 | 11.29 | 11.16 | 11.19 | |
| Max (Thread Active Time) (s) | 10.61 | 10.51 | 10.58 | 10.55 | 10.55 | 10.60 | 10.42 | 10.59 | 10.50 | 10.54 | 10.60 | 10.57 | 10.64 | 10.51 | 10.54 | |
| Average Active Time (s) | 10.36 | 10.27 | 10.33 | 10.31 | 10.35 | 10.27 | 10.28 | 10.28 | 10.23 | 10.33 | 10.31 | 10.30 | 10.38 | 10.25 | 10.26 | |
| Activity Ratio (%) | 96.8 | 96.8 | 96.9 | 96.9 | 96.7 | 96.6 | 96.5 | 96.7 | 96.7 | 96.9 | 96.7 | 96.6 | 96.9 | 96.9 | 96.7 | |
| Average number of active threads | 88.236 | 88.221 | 88.334 | 88.274 | 88.117 | 87.916 | 87.940 | 88.054 | 88.030 | 88.297 | 88.136 | 87.964 | 88.287 | 88.152 | 88.024 | |
| Affinity Stability (%) | 99.4 | 99.4 | 99.4 | 99.4 | 99.4 | 99.4 | 99.4 | 99.4 | 99.3 | 99.4 | 99.4 | 99.4 | 99.4 | 99.4 | 99.4 | |
| Time in analyzed loops (%) | 72.9 | 72.8 | 73.0 | 72.7 | 71.9 | 71.4 | 70.7 | 72.1 | 71.9 | 72.9 | 72.6 | 71.1 | 72.8 | 72.9 | 71.9 | |
| Time in analyzed innermost loops (%) | 72.1 | 72.0 | 72.2 | 71.9 | 71.2 | 70.5 | 70.0 | 71.4 | 71.2 | 72.1 | 71.9 | 70.4 | 72.0 | 72.1 | 71.2 | |
| Time in user code (%) | 73.7 | 73.4 | 73.8 | 73.5 | 72.7 | 72.1 | 71.5 | 72.8 | 72.7 | 73.6 | 73.2 | 71.9 | 73.6 | 73.5 | 72.5 | |
| Compilation Options Score (%) | 99.3 | 99.3 | 99.3 | 99.3 | 99.3 | 99.2 | 99.3 | 99.3 | 99.3 | 99.3 | 99.3 | 99.3 | 99.3 | 99.3 | 99.3 | |
| Array Access Efficiency (%) | 93.1 | 92.1 | 91.4 | 92.9 | 92.2 | 93.7 | 94.2 | 95.5 | 92.1 | 93.5 | 95.3 | 94.7 | 89.8 | 94.9 | 93.0 | |
| 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 | 1.21 | 1.23 | 1.21 | 1.24 | 1.27 | 1.23 | 1.29 | 1.22 | 1.20 | 1.22 | 1.21 | 1.22 | 1.21 | 1.22 | 1.24 | |
| Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution | 1.39 | 1.39 | 1.39 | 1.39 | 1.40 | 1.43 | 1.42 | 1.41 | 1.41 | 1.38 | 1.40 | 1.43 | 1.39 | 1.39 | 1.41 | |
| Scalability - Gap | 1.00 | 0.99 | 1.00 | 0.99 | 1.00 | 1.00 | 1.00 | 0.99 | 0.99 | 1.00 | 1.00 | 1.00 | 1.00 | 0.99 | 0.99 | |
| No Scalar Integer | Potential Speedup | 1.14 | 1.13 | 1.14 | 1.13 | 1.13 | 1.13 | 1.13 | 1.13 | 1.13 | 1.14 | 1.13 | 1.13 | 1.13 | 1.14 | 1.13 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| FP Vectorised | Potential Speedup | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 | 1.06 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Fully Vectorised | Potential Speedup | 1.27 | 1.27 | 1.27 | 1.27 | 1.27 | 1.27 | 1.26 | 1.27 | 1.27 | 1.27 | 1.27 | 1.27 | 1.27 | 1.27 | 1.27 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Only FP Arithmetic | Potential Speedup | 1.58 | 1.58 | 1.58 | 1.58 | 1.57 | 1.56 | 1.55 | 1.57 | 1.57 | 1.58 | 1.58 | 1.56 | 1.58 | 1.58 | 1.57 |
| Nb Loops to get 80% | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
| Source Object | Issue |
|---|---|
| ▼libllama.so | |
| ▼stl_tree.h | |
| ○ | |
| ▼llama-sampling.cpp | |
| ○ | |
| ▼hashtable_policy.h | |
| ○ | |
| ▼vector.tcc | |
| ○ | |
| ▼shared_ptr_base.h | |
| ○ | |
| ▼hashtable.h | |
| ○ | |
| ▼llama-context.cpp | |
| ○ | |
| ▼llama-graph.cpp | |
| ○ | |
| ▼llama-kv-cache.cpp | |
| ○ | |
| ▼llama-vocab.cpp | |
| ○ | |
| ▼llama-kv-cells.h | |
| ○ | |
| ▼stl_vector.h | |
| ○ | |
| ▼llama-impl.cpp | |
| ○ | |
| ▼unicode.cpp | |
| ○ | |
| ▼stl_pair.h | |
| ○ | |
| ▼llama-batch.cpp | |
| ○ | |
| ▼llama-model-loader.cpp | |
| ○ | |
| ▼libggml-cpu.so | |
| ▼binary-ops.cpp | |
| ○ | |
| ▼repack.cpp | |
| ○ | |
| ▼ops.cpp | |
| ○ | |
| ▼ggml-cpu.cpp | |
| ○ | |
| ▼traits.cpp | |
| ○ | |
| ▼vec.cpp | |
| ○ | |
| ▼ggml-cpu.c | |
| ○ | |
| ▼quants.c | |
| ○ | |
| ▼libggml-blas.so | |
| ▼ggml-blas.cpp | |
| ○ | |
| ▼libggml-base.so | |
| ▼ggml-quants.c | |
| ○ | |
| ▼ggml-threading.cpp | |
| ○ | |
| ▼stl_construct.h | |
| ○ | |
| ▼vector.tcc | |
| ○ | |
| ▼gguf.cpp | |
| ○ | |
| ▼ggml-backend.cpp | |
| ○ | |
| ▼ggml.c | |
| ○ | |
| ▼[vdso] | |
| ▼ | |
| ○ | -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. |
| ▼exec | |
| ▼stl_uninitialized.h | |
| ○ | |
| ▼sampling.cpp | |
| ○ | |
| ▼regex_executor.tcc | |
| ○ | |
| ▼main.cpp | |
| ○ | |
| ▼common.cpp | |
| ○ | |
| ▼arg.cpp | |
| ○ | |
| ▼vector.tcc | |
| ○ | |
| ▼basic_string.h | |
| ○ | |
| ▼invoke.h | |
| ○ |
| r0 | r1 | r2 | r3 | r4 | r5 | r6 | r7 | r8 | r9 | r10 | r11 | r12 | r13 | r14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Application | /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/run/binaries/armclang_3/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 | 2025-09-16 14:08:51 | 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; OpenMP; | 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 |
| Machine | ip-172-31-47-249.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 6.1.109-118.189.amzn2023.aarch64 #1 SMP Tue Sep 10 08:58:40 UTC 2024 | 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 | + [vdso]: N/A exec: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 --driver-mode=g++ -D GGML_BACKEND_SHARED -D GGML_SHARED -D GGML_USE_BLAS -D GGML_USE_CPU -D LLAMA_SHARED -D LLAMA_USE_CURL -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/../vendor -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/../include -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -MD -MT common/CMakeFiles/common.dir/regex-partial.cpp.o -MF common/CMakeFiles/common.dir/regex-partial.cpp.o.d -o common/CMakeFiles/common.dir/regex-partial.cpp.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/regex-partial.cpp libggml-base.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 -D GGML_BUILD -D GGML_COMMIT=\"unknown\" -D GGML_SCHED_MAX_COPIES=4 -D GGML_SHARED -D GGML_VERSION=\"0.0.0\" -D _GNU_SOURCE -D _XOPEN_SOURCE=600 -D ggml_base_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wdouble-promotion -std=gnu11 -MD -MT ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o -MF ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o.d -o ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c libggml-cpu.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 -D GGML_BACKEND_BUILD -D GGML_BACKEND_SHARED -D GGML_SCHED_MAX_COPIES=4 -D GGML_SHARED -D GGML_USE_CPU_REPACK -D GGML_USE_LLAMAFILE -D GGML_USE_OPENMP -D _GNU_SOURCE -D _XOPEN_SOURCE=600 -D ggml_cpu_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/.. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wdouble-promotion -fopenmp=libomp -std=gnu11 -MD -MT ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o -MF ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o.d -o ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c libllama.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 --driver-mode=g++ -D GGML_BACKEND_SHARED -D GGML_SHARED -D GGML_USE_BLAS -D GGML_USE_CPU -D LLAMA_BUILD -D LLAMA_SHARED -D llama_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/../include -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -MD -MT src/CMakeFiles/llama.dir/llama-vocab.cpp.o -MF src/CMakeFiles/llama.dir/llama-vocab.cpp.o.d -o src/CMakeFiles/llama.dir/llama-vocab.cpp.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp | + [vdso]: N/A exec: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 --driver-mode=g++ -D GGML_BACKEND_SHARED -D GGML_SHARED -D GGML_USE_BLAS -D GGML_USE_CPU -D LLAMA_SHARED -D LLAMA_USE_CURL -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/../vendor -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/../include -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -MD -MT common/CMakeFiles/common.dir/regex-partial.cpp.o -MF common/CMakeFiles/common.dir/regex-partial.cpp.o.d -o common/CMakeFiles/common.dir/regex-partial.cpp.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/regex-partial.cpp libggml-base.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 -D GGML_BUILD -D GGML_COMMIT=\"unknown\" -D GGML_SCHED_MAX_COPIES=4 -D GGML_SHARED -D GGML_VERSION=\"0.0.0\" -D _GNU_SOURCE -D _XOPEN_SOURCE=600 -D ggml_base_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wdouble-promotion -std=gnu11 -MD -MT ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o -MF ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o.d -o ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c libggml-blas.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 --driver-mode=g++ -D GGML_BACKEND_BUILD -D GGML_BACKEND_SHARED -D GGML_SCHED_MAX_COPIES=4 -D GGML_SHARED -D _GNU_SOURCE -D _XOPEN_SOURCE=600 -D ggml_blas_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-blas/.. -I /opt/arm/armpl-24.10.1_AmazonLinux-2023_arm-linux-compiler/include -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -std=gnu++17 -MD -MT ggml/src/ggml-blas/CMakeFiles/ggml-blas.dir/ggml-blas.cpp.o -MF ggml/src/ggml-blas/CMakeFiles/ggml-blas.dir/ggml-blas.cpp.o.d -o ggml/src/ggml-blas/CMakeFiles/ggml-blas.dir/ggml-blas.cpp.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-blas/ggml-blas.cpp libggml-cpu.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 -D GGML_BACKEND_BUILD -D GGML_BACKEND_SHARED -D GGML_SCHED_MAX_COPIES=4 -D GGML_SHARED -D GGML_USE_CPU_REPACK -D GGML_USE_LLAMAFILE -D GGML_USE_OPENMP -D _GNU_SOURCE -D _XOPEN_SOURCE=600 -D ggml_cpu_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/.. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wdouble-promotion -fopenmp=libomp -std=gnu11 -MD -MT ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o -MF ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o.d -o ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c libllama.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 --driver-mode=g++ -D GGML_BACKEND_SHARED -D GGML_SHARED -D GGML_USE_BLAS -D GGML_USE_CPU -D LLAMA_BUILD -D LLAMA_SHARED -D llama_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/../include -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -MD -MT src/CMakeFiles/llama.dir/llama-vocab.cpp.o -MF src/CMakeFiles/llama.dir/llama-vocab.cpp.o.d -o src/CMakeFiles/llama.dir/llama-vocab.cpp.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp | + [vdso]: N/A exec: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 --driver-mode=g++ -D GGML_BACKEND_SHARED -D GGML_SHARED -D GGML_USE_BLAS -D GGML_USE_CPU -D LLAMA_SHARED -D LLAMA_USE_CURL -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/../vendor -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/../include -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -MD -MT common/CMakeFiles/common.dir/sampling.cpp.o -MF common/CMakeFiles/common.dir/sampling.cpp.o.d -o common/CMakeFiles/common.dir/sampling.cpp.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/sampling.cpp libggml-base.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 -D GGML_BUILD -D GGML_COMMIT=\"unknown\" -D GGML_SCHED_MAX_COPIES=4 -D GGML_SHARED -D GGML_VERSION=\"0.0.0\" -D _GNU_SOURCE -D _XOPEN_SOURCE=600 -D ggml_base_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wdouble-promotion -std=gnu11 -MD -MT ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o -MF ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o.d -o ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c libggml-cpu.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 -D GGML_BACKEND_BUILD -D GGML_BACKEND_SHARED -D GGML_SCHED_MAX_COPIES=4 -D GGML_SHARED -D GGML_USE_CPU_REPACK -D GGML_USE_LLAMAFILE -D GGML_USE_OPENMP -D _GNU_SOURCE -D _XOPEN_SOURCE=600 -D ggml_cpu_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/.. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wdouble-promotion -fopenmp=libomp -std=gnu11 -MD -MT ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o -MF ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o.d -o ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/arm/quants.c.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c libllama.so: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_AmazonLinux-2023/llvm-bin/clang-19 --driver-mode=g++ -D GGML_BACKEND_SHARED -D GGML_SHARED -D GGML_USE_BLAS -D GGML_USE_CPU -D LLAMA_BUILD -D LLAMA_SHARED -D llama_EXPORTS -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/. -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/../include -I /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/../include -O3 -O3 -mcpu=neoverse-v2+nosve+nosve2 -armpl -ffast-math -g -fno-omit-frame-pointer -fcf-protection=none -no-pie -grecord-command-line -fno-finite-math-only -O3 -D NDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -MD -MT src/CMakeFiles/llama.dir/llama-vocab.cpp.o -MF src/CMakeFiles/llama.dir/llama-vocab.cpp.o.d -o src/CMakeFiles/llama.dir/llama-vocab.cpp.o -c /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp | same as r0 | same as r2 | same as r2 | same as r2 | same as r0 | same as r0 | same as r2 | same as r0 | same as r0 | same as r0 | same as r2 | same as r2 |
| 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 | 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 |
| 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 | 2025.1.2 | 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 | Build information not available | 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 armclang_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 |