| Detailed Application Categorization |
| Detailed Function Times |
| Function Based Profile |
| Libraries |
Detailed Application Categorization
| ID | Time(s) | Binary(%) | MPI(%) | OMP(%) | TBB(%) | Math(%) | System(%) | Pthread(%) | IO(%) | String(%) | Memory(%) | libggml-base.so (%) | libggml-blas.so (%) | libggml-cpu.so (%) | libggml.so (%) | libllama.so (%) | Others(%) |
| ▼1x6– | 17.26 | 0.00 | 0.00 | 10.34 | 0.00 | 1.10 | 0.01 | 0.00 | 0.02 | 0.00 | 0.21 | 0.02 | 0.00 | 88.11 | 0.00 | 0.15 | 0.04 |
| ▼Node isix06.benchmarkcenter.megware.com– | 17.26 | 0.00 | 0.00 | 10.34 | 0.00 | 1.10 | 0.01 | 0.00 | 0.02 | 0.00 | 0.21 | 0.02 | 0.00 | 88.11 | 0.00 | 0.15 | 0.04 |
| ▼Process 7624– | 17.26 | 0.00 | 0.00 | 10.34 | 0.00 | 1.10 | 0.01 | 0.00 | 0.02 | 0.00 | 0.21 | 0.02 | 0.00 | 88.11 | 0.00 | 0.15 | 0.04 |
| ○Thread 7624 | 17.26 | 0.00 | 0.00 | 2.52 | 0.00 | 0.78 | 0.03 | 0.00 | 0.12 | 0.03 | 0.81 | 0.12 | 0.00 | 94.44 | 0.00 | 0.90 | 0.26 |
| ○Thread 7726 | 17.22 | 0.00 | 0.00 | 12.25 | 0.00 | 1.05 | 0.00 | 0.00 | 0.00 | 0.00 | 0.06 | 0.00 | 0.00 | 86.64 | 0.00 | 0.00 | 0.00 |
| ○Thread 7727 | 17.14 | 0.00 | 0.00 | 10.85 | 0.00 | 0.96 | 0.00 | 0.00 | 0.00 | 0.00 | 0.20 | 0.00 | 0.00 | 87.98 | 0.00 | 0.00 | 0.00 |
| ○Thread 7728 | 17.23 | 0.00 | 0.00 | 12.86 | 0.00 | 1.39 | 0.00 | 0.00 | 0.00 | 0.00 | 0.12 | 0.00 | 0.00 | 85.63 | 0.00 | 0.00 | 0.00 |
| ○Thread 7729 | 17.22 | 0.00 | 0.00 | 11.82 | 0.00 | 1.22 | 0.00 | 0.00 | 0.00 | 0.00 | 0.03 | 0.00 | 0.00 | 86.93 | 0.00 | 0.00 | 0.00 |
| ○Thread 7730 | 17.14 | 0.00 | 0.00 | 11.76 | 0.00 | 1.20 | 0.03 | 0.00 | 0.00 | 0.00 | 0.03 | 0.00 | 0.00 | 86.99 | 0.00 | 0.00 | 0.00 |
Detailed Function Times
ggml_backend_amx_mul...
__kmp_hyper_barrier_...
ggml_compute_forward...
__kmp_hardware_times...
quantize_row_q8_0
f64xsubf128
void parallel_for<...
ggml_vec_dot_f16
ggml_vec_swiglu_f32
ggml_compute_forward...
Other Functions
Libraries
- green cell: the library has been found during the run profiling
- red cell: the library does not appear in the run profiling
| Library | 1x6 |
|---|
| /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/176-400-1862/llama.cpp/build/aocc_10/bin/libggml-base.so | |
| /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/176-400-1862/llama.cpp/build/aocc_10/bin/libggml-blas.so | |
| /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/176-400-1862/llama.cpp/build/aocc_10/bin/libggml-cpu.so | |
| /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/176-400-1862/llama.cpp/build/aocc_10/bin/libggml.so | |
| /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/176-400-1862/llama.cpp/build/aocc_10/bin/libllama.so | |
| /cluster/intel/oneapi/2024.0.0/mkl/2024.0/lib/libmkl_core.so.2 | |
| /cluster/intel/oneapi/2024.0.0/mkl/2024.0/lib/libmkl_intel_lp64.so.2 | |
| /cluster/intel/oneapi/2024.0.0/mkl/2024.0/lib/libmkl_intel_thread.so.2 | |
| /home/eoseret/aocc-compiler-5.0.0/lib/libarcher.so | |
| /home/eoseret/aocc-compiler-5.0.0/lib/libomp.so | |
| /usr/lib64/ld-linux-x86-64.so.2 | |
| /usr/lib64/libc.so.6 | |
| /usr/lib64/libdl.so.2 | |
| /usr/lib64/libgcc_s-11-20240719.so.1 | |
| /usr/lib64/libm.so.6 | |
| /usr/lib64/libpthread.so.0 | |
| /usr/lib64/librt.so.1 | |
| /usr/lib64/libstdc++.so.6.0.29 | |