| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1843 | libggml-cpu.so - sgemm.cpp:399-399 [...] | void (anonymous namespace)::tinyBLAS<16, float __vector(16), float __vector(16), unsigned short, unsigned short, float>::gemm_bloc<4, 6>(long, long) | Single | 0.12 | 1.58 | 1.58 | 0.18 | 0.18 | 0.12 | 0.12 | 192 | 1943.42 | 100 | 85.29 | 1 | 1 | 1.29 | 1.57 | 0 | 10 | 0 | 0 | 0 | 100.00 |
| 1387 | libggml-cpu.so - ops.cpp:5552-5563 | ggml_compute_forward_set_rows | Innermost | 0.07 | 0.70 | 0.70 | 0.10 | 0.10 | 0.05 | 0.05 | 192 | 3.31 | 0 | 12.5 | 1 | 1 | 8 | 1.98 | 1 | 0 | 0 | 3 | 1 | 50.00 |
| 1407 | libggml-cpu.so - vec.h:89-89 | ggml_compute_forward_soft_max | Innermost | 0.06 | 0.59 | 0.59 | 0.09 | 0.09 | 0.04 | 0.04 | 192 | 14.24 | 100 | 50 | 1 | 1 | 2 | 2.09 | 0 | 2 | 0 | 0 | 0 | 100.00 |
| 996 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.04 | 0.38 | 0.38 | 0.06 | 0.06 | 0.03 | 0.03 | 192 | 773.26 | 19.61 | 9.8 | 1.14 | 1.71 | 5.33 | 2.19 | NA | NA | NA | NA | NA | 0.00 |
| 66 | libggml-cpu.so - ggml-cpu.c:1291-1297 | ggml_compute_forward_mul_mat | Innermost | 0.04 | 0.28 | 0.28 | 0.06 | 0.06 | 0.02 | 0.02 | 191 | 28.71 | 0 | 11.34 | 1 | 1 | 2 | 2.9 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 1322 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.03 | 0.25 | 0.25 | 0.04 | 0.04 | 0.02 | 0.02 | 192 | 57.80 | 0 | 7.81 | 1 | 2.95 | 14 | 2.23 | 0 | 1 | 0 | 0 | 0 | 100.00 |
| 963 | libggml-cpu.so - vec.cpp:372-372 [...] | ggml_vec_swiglu_f32 | Single | 0.03 | 0.16 | 0.16 | 0.05 | 0.05 | 0.01 | 0.01 | 171 | 1581.66 | 100 | 100 | 1.02 | 1 | 1 | 3.77 | 0 | 3 | 0 | 0 | 0 | 100.00 |
| 716 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.03 | 0.15 | 0.15 | 0.04 | 0.04 | 0.01 | 0.01 | 160 | 48.96 | 100 | 50 | 1 | 1.41 | 2 | 3.1 | 0 | 3 | 0 | 0 | 0 | 100.00 |
| 455 | libggml-cpu.so - mmq.cpp:822-1392 [...] | void parallel_for<(anonymous namespace)::convert_B_packed_format<block_q8_0, 32>(void*, block_q8_0 const*, int, int)::{lambda(int, int)#1}>(int, (anonymous namespace)::convert_B_packed_format<block_q8_0, 32>(void*, block_q8_0 const*, int,... | Innermost | 0.03 | 0.14 | 0.14 | 0.04 | 0.04 | 0.01 | 0.01 | 145 | 0.00 | 78.57 | 69.64 | 3.5 | 1 | 1.03 | 3.04 | 2 | 0 | 0 | 20 | 0 | 54.55 |
| 1406 | libggml-cpu.so - vec.h:677-677 [...] | ggml_compute_forward_soft_max | Innermost | 0.03 | 0.14 | 0.14 | 0.04 | 0.04 | 0.01 | 0.01 | 165 | 46.04 | 100 | 100 | 1 | 1 | 1 | 3.46 | 1 | 1 | 1 | 0 | 0 | 91.67 |
| 1396 | libggml-cpu.so - vec.h:1444-1445 | ggml_compute_forward_soft_max | Innermost | 0.02 | 0.11 | 0.11 | 0.03 | 0.03 | 0.01 | 0.01 | 192 | 234.94 | 33.33 | 12.5 | 1 | 1 | 16 | 3.07 | 1 | 1 | 0 | 0 | 0 | 100.00 |
| 1842 | libggml-cpu.so - sgemm.cpp:425-427 [...] | void (anonymous namespace)::tinyBLAS<16, float __vector(16), float __vector(16), unsigned short, unsigned short, float>::gemm_bloc<4, 6>(long, long) | Single | 0.02 | 0.11 | 0.11 | 0.03 | 0.03 | 0.01 | 0.01 | 192 | 4816.60 | 90.91 | 33.81 | 1 | 1.24 | 3.33 | 3.87 | 0 | 0 | 2 | 1 | 0 | 66.67 |
| 2214 | libggml-cpu.so - quants.c:298-321 [...] | quantize_row_q8_0 | Single | 0.96 | 0.10 | 0.10 | 1.43 | 1.43 | 0.01 | 0.01 | 1 | 707.09 | 60 | 28.75 | 1 | 1.4 | 2.84 | 1 | NA | NA | NA | NA | NA | 0.00 |