| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime aocc_0 (%) | Exclusive Coverage aocc_0 (%) | Inclusive Coverage aocc_0 (%) | Max Exclusive Time Over Threads aocc_0 (s) | Max Inclusive Time Over Threads aocc_0 (s) | Exclusive Time w.r.t. Wall Time aocc_0 (s) | Inclusive Time w.r.t. Wall Time aocc_0 (s) | Nb Threads aocc_0 | GFLOPS aocc_0 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing aocc_0 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 97 | libggml-cpu.so - ggml-cpu.c:1291-1297 | ggml_compute_forward_mul_mat | Innermost | 1.30 | 1.42 | 1.42 | 0.41 | 0.41 | 0.21 | 0.21 | 186 | 3.22 | 0 | 11.38 | 1 | 1 | 2.46 | 1.93 | NA | NA | NA | NA | NA | 0.00 |
| 3047 | libggml-cpu.so - sgemm.cpp:144-464 [...] | void (anonymous namespace)::tinyBLAS<16, float __vector(16), float __vector(16), unsigned short, unsigned short, float>::gemm<4, 6, 2>(long, long, long) | Innermost | 0.41 | 0.50 | 0.50 | 0.13 | 0.13 | 0.07 | 0.07 | 192 | 2974.14 | NA | NA | NA | NA | NA | 1.8 | NA | NA | NA | NA | NA | 0.00 |
| 4 | libggml-cpu.so - ggml-impl.h:346-404 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.29 | 0.19 | 0.19 | 0.09 | 0.09 | 0.03 | 0.03 | 161 | 2.29 | 7.69 | 8.17 | 1.37 | 4.39 | 15.48 | 2.78 | 0 | 2 | 0 | 0 | 0 | 100.00 |
| 2015 | libggml-cpu.so - vec.h:89-89 | ggml_compute_forward_soft_max | Innermost | 0.19 | 0.18 | 0.18 | 0.06 | 0.06 | 0.03 | 0.03 | 191 | 16.80 | 100 | 50 | 1 | 1 | 2 | 2.31 | 0 | 2 | 0 | 0 | 0 | 100.00 |
| 2113 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.16 | 0.14 | 0.14 | 0.05 | 0.05 | 0.02 | 0.02 | 192 | 678.54 | 1.96 | 6.62 | 1.01 | 1.14 | 4.06 | 2.52 | 1 | 2 | 0 | 0 | 0 | 100.00 |
| 384 | libggml-cpu.so - mmq.cpp:303-1392 [...] | 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 | 0.14 | 0.12 | 0.12 | 0.05 | 0.05 | 0.02 | 0.02 | 176 | 0.00 | 90.91 | 38.76 | 1.47 | 1 | 1.41 | 2.46 | 23 | 0 | 0 | 9 | 0 | 85.94 |
| 1236 | libggml-cpu.so - vec.h:1084-1116 [...] | ggml_vec_swiglu_f32 | Single | 0.16 | 0.11 | 0.11 | 0.05 | 0.05 | 0.02 | 0.02 | 171 | 1184.97 | 98 | 98.13 | 1.02 | 1 | 1 | 2.69 | 0.5 | 0 | 0 | 3 | 0 | 56.25 |
| 1758 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.13 | 0.11 | 0.11 | 0.04 | 0.04 | 0.02 | 0.02 | 192 | 63.08 | 0 | 7.81 | 1 | 1.98 | 13.02 | 2.56 | 0 | 1 | 0 | 0 | 0 | 100.00 |