| Name | Module | Coverage gcc_0 (%) | Coverage Excluding Loops gcc_0 (%) | Max Inclusive Time Over Threads gcc_0 (s) | Max Exclusive Time Over Threads gcc_0 (s) | Inclusive Time w.r.t. Wall Time gcc_0 (s) | Exclusive Time w.r.t. Wall Time gcc_0 (s) | Nb Threads gcc_0 | Deviation (coverage) gcc_0 | Deviation (walltime) gcc_0 | Categories gcc_0 | GFLOPS gcc_0 | Compilation Options |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ►(anonymous namespace)::tinygemm_kernel_vnni<block_q8_0, block_q8_0, float, 1, 64, 32>::apply(int, void const*, void const*, float*, int) | libggml-cpu.so | 86.35 | 0.00 | 24.65 | 0.01 | 24.14 | 0.00 | 192 | 1.87 | 0.48 | /scratch/users/amazouz/QAAS/service/Llama.cpp/sdp772511/175-793-6543/llama.cpp/build/llama.cpp/../gcc/bin/libggml-blas.so (%): 100.00 | 89.25 | GNU C++17 13.3.0 -march=graniterapids -mmmx -mpopcnt -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mavx -mavx2 -mno-sse4a -mno-fma4 -mno-xop -mfma -mavx512f -mbmi -mbmi2 -maes -mpclmul -mavx512vl -mavx512bw -mavx512dq -mavx512cd -mno-avx512er -mno-avx512p... |
| ○Loop 405 - mmq.cpp:1597-1597 - libggml-cpu.so [...] | 86.35 | 86.35 | 24.65 | 24.65 | 24.14 | 24.14 | 192 | 1.87 | 0.48 | 89.25 | |||
| ○omp_get_num_procs | libgomp.so.1.0.0 | 11.29 | 0.00 | 4.34 | 0.01 | 3.16 | 0.00 | 192 | 2.10 | 0.59 | OMP (%): 100.00 | 0.66 | |
| ►quantize_row_q8_0 | libggml-cpu.so | 0.03 | 0.00 | 0.36 | 0.01 | 0.01 | 0.00 | 6 | 0.24 | 0.07 | /scratch/users/amazouz/QAAS/service/Llama.cpp/sdp772511/175-793-6543/llama.cpp/build/llama.cpp/../gcc/bin/libggml-blas.so (%): 100.00 | 1067.28 | GNU C11 13.3.0 -march=graniterapids -mmmx -mpopcnt -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mavx -mavx2 -mno-sse4a -mno-fma4 -mno-xop -mfma -mavx512f -mbmi -mbmi2 -maes -mpclmul -mavx512vl -mavx512bw -mavx512dq -mavx512cd -mno-avx512er -mno-avx512pf ... |
| ○Loop 2122 - quants.c:298-321 - libggml-cpu.so [...] | 0.03 | 0.03 | 0.36 | 0.36 | 0.01 | 0.01 | 6 | 0.25 | 0.07 | 1070.90 |