| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime gcc_0 (%) | Exclusive Coverage gcc_0 (%) | Inclusive Coverage gcc_0 (%) | Max Exclusive Time Over Threads gcc_0 (s) | Max Inclusive Time Over Threads gcc_0 (s) | Exclusive Time w.r.t. Wall Time gcc_0 (s) | Inclusive Time w.r.t. Wall Time gcc_0 (s) | Nb Threads gcc_0 | GFLOPS gcc_0 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing gcc_0 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1989 | libggml-cpu.so - quants.c:108-1035 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 78.51 | 58.45 | 58.45 | 52.07 | 52.07 | 33.64 | 33.64 | 192 | 60.31 | NA | NA | NA | NA | NA | 1.55 | NA | NA | NA | NA | NA | 0.00 |
| 1618 | libggml-cpu.so - sgemm.cpp:818-1038 [...] | void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long) | Innermost | 0.17 | 0.10 | 0.10 | 0.11 | 0.11 | 0.05 | 0.05 | 189 | 263.21 | NA | NA | NA | NA | NA | 1.98 | NA | NA | NA | NA | NA | 0.00 |
| 1626 | libggml-cpu.so - sgemm.cpp:818-1038 [...] | void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<2>(long, long, long, long) | Innermost | 0.17 | 0.09 | 0.09 | 0.11 | 0.11 | 0.05 | 0.05 | 189 | 129.76 | NA | NA | NA | NA | NA | 2.03 | NA | NA | NA | NA | NA | 0.00 |
| 63 | libggml-cpu.so - ggml-cpu.c:1164-1397 [...] | ggml_compute_forward_mul_mat | InBetween | 0.21 | 0.08 | 0.09 | 0.14 | 0.14 | 0.05 | 0.05 | 192 | 75.80 | 0 | 11.84 | 1 | 1 | 8 | 2.98 | NA | NA | NA | NA | NA | 0.00 |
| 71 | libggml-cpu.so - ggml-cpu.c:1664-2891 [...] | ggml_graph_compute_thread | Single | 0.24 | 0.08 | 0.08 | 0.16 | 0.16 | 0.04 | 0.04 | 180 | 3.79 | 0 | 9.38 | 1 | 1 | 13.68 | 3.46 | NA | NA | NA | NA | NA | 0.00 |
| 722 | libggml-cpu.so - vec.cpp:311-311 [...] | ggml_vec_dot_f16 | Single | 0.30 | 0.04 | 0.04 | 0.20 | 0.20 | 0.02 | 0.02 | 33 | 990.43 | 100 | 66.67 | 1 | 1 | 1.69 | 1.55 | 0 | 0 | 4 | 0 | 0 | 75.00 |
| 1433 | libggml-cpu.so - vec.h:491-491 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.33 | 0.04 | 0.04 | 0.22 | 0.22 | 0.02 | 0.02 | 33 | 1583.82 | 100 | 70 | 1 | 1 | 1.39 | 1.71 | 1 | 1 | 3 | 0 | 0 | 85.00 |
| 1982 | libggml-cpu.so - quants.c:298-321 [...] | quantize_row_q8_0 | Single | 0.11 | 0.03 | 0.03 | 0.07 | 0.07 | 0.02 | 0.02 | 139 | 0.46 | 66.67 | 31.25 | 1 | 1.2 | 2.72 | 3.1 | NA | NA | NA | NA | NA | 0.00 |
| 759 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.11 | 0.03 | 0.03 | 0.07 | 0.07 | 0.02 | 0.02 | 192 | 163.90 | 19.23 | 9.74 | 1.18 | 1.35 | 14.49 | 4.32 | NA | NA | NA | NA | NA | 0.00 |
| 726 | libggml-cpu.so - vec.cpp:372-372 [...] | ggml_vec_swiglu_f32 | Single | 0.26 | 0.00 | 0.00 | 0.17 | 0.17 | 0.00 | 0.00 | 7 | 5257.86 | 100 | 100 | 1 | 1 | 1 | 6.61 | 0 | 3 | 0 | 0 | 0 | 100.00 |