| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime aocc_7 (%) | Exclusive Coverage aocc_7 (%) | Inclusive Coverage aocc_7 (%) | Max Exclusive Time Over Threads aocc_7 (s) | Max Inclusive Time Over Threads aocc_7 (s) | Exclusive Time w.r.t. Wall Time aocc_7 (s) | Inclusive Time w.r.t. Wall Time aocc_7 (s) | Nb Threads aocc_7 | GFLOPS aocc_7 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing aocc_7 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2159 | libggml-cpu.so - quants.c:108-1042 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 82.64 | 61.85 | 61.85 | 57.26 | 57.26 | 37.70 | 37.70 | 192 | 53.82 | NA | NA | NA | NA | NA | 1.53 | NA | NA | NA | NA | NA | 0.00 |
| 2021 | libggml-cpu.so - sgemm.cpp:138-1044 [...] | void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<2>(long, long, long, long) | Innermost | 0.19 | 0.11 | 0.11 | 0.13 | 0.13 | 0.07 | 0.07 | 189 | 108.06 | NA | NA | NA | NA | NA | 1.98 | NA | NA | NA | NA | NA | 0.00 |
| 61 | libggml-cpu.so - ggml-cpu.c:1164-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.22 | 0.09 | 0.10 | 0.15 | 0.20 | 0.06 | 0.06 | 192 | 55.91 | 0 | 11.88 | 1 | 1 | 8 | 2.67 | NA | NA | NA | NA | NA | 0.00 |
| 2013 | libggml-cpu.so - sgemm.cpp:138-1044 [...] | void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long) | InBetween | 0.17 | 0.08 | 0.11 | 0.12 | 0.13 | 0.05 | 0.07 | 189 | 171.59 | 64.29 | 31.47 | 2.2 | 1 | 5.18 | 2.55 | 0 | 0 | 0 | 2 | 1 | 33.33 |
| 78 | libggml-cpu.so - ggml-cpu.c:533-2891 [...] | ggml_graph_compute_thread | Single | 0.16 | 0.05 | 0.05 | 0.11 | 0.11 | 0.03 | 0.03 | 181 | 17.69 | 0 | 9.56 | 1 | 1 | 14.61 | 3.79 | NA | NA | NA | NA | NA | 0.00 |
| 1459 | libggml-cpu.so - vec.h:491-497 | ggml_compute_forward_flash_attn_ext | Innermost | 0.36 | 0.04 | 0.04 | 0.25 | 0.25 | 0.03 | 0.03 | 35 | 1606.01 | 100 | 75 | 1 | 1 | 1.45 | 1.82 | 0 | 2 | 0 | 0 | 0 | 100.00 |
| 2012 | libggml-cpu.so - sgemm.cpp:138-1044 [...] | void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long) | Innermost | 0.10 | 0.04 | 0.04 | 0.07 | 0.07 | 0.02 | 0.02 | 189 | 290.25 | NA | NA | NA | NA | NA | 3.14 | NA | NA | NA | NA | NA | 0.00 |
| 758 | libggml-cpu.so - vec.cpp:311-316 | ggml_vec_dot_f16 | Single | 0.27 | 0.03 | 0.03 | 0.19 | 0.19 | 0.02 | 0.02 | 32 | 878.66 | 100 | 66.67 | 1 | 1 | 1.57 | 1.62 | 0 | 2 | 0 | 0 | 0 | 100.00 |
| 1446 | libggml-cpu.so - ops.cpp:8759-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.12 | 0.01 | 0.05 | 0.08 | 0.27 | 0.01 | 0.03 | 34 | 2299.56 | 22.73 | 14.74 | 2.4 | 1.47 | 2.08 | 2.67 | NA | NA | NA | NA | NA | 0.00 |
| 63 | libggml-cpu.so - ggml-cpu.c:1193-1194 | ggml_compute_forward_mul_mat | Innermost | 0.13 | 0.01 | 0.01 | 0.09 | 0.09 | 0.01 | 0.01 | 140 | 131.51 | 0 | 12.5 | 1 | 1 | 8 | 13.12 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 353 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.30 | 0.00 | 0.00 | 0.21 | 0.21 | 0.00 | 0.00 | 1 | 120.08 | 0 | 6.25 | 1 | 1.33 | 16 | 1 | 0 | 3 | 0 | 0 | 0 | 100.00 |
| 766 | libggml-cpu.so - vec.h:1084-1115 [...] | ggml_vec_swiglu_f32 | Single | 0.25 | 0.00 | 0.00 | 0.17 | 0.17 | 0.00 | 0.00 | 7 | 5283.19 | 98 | 98.13 | 1 | 1 | 1 | 6.61 | 0.5 | 0 | 0 | 3 | 0 | 56.25 |
| 433 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.17 | 0.00 | 0.00 | 0.12 | 0.12 | 0.00 | 0.00 | 1 | 194.29 | 0 | 6.25 | 1 | 1.33 | 16 | 1 | 0 | 3 | 0 | 0 | 0 | 100.00 |