| 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 | 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 |
|---|
| 2205 | libggml-cpu.so - kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c:131-131 | kai_run_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm | Innermost | 34.17 | 54.94 | 54.94 | 3.40 | 3.40 | 3.82 | 3.82 | 64 | 28.14 | 27.69 | 1 | 1.18 | 4.53 | 1.08 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 2072 | libggml-cpu.so - quants.c:2506-2575 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 9.13 | 14.16 | 14.16 | 0.91 | 0.91 | 0.98 | 0.98 | 64 | 49.72 | 34.67 | 1.06 | 1 | 2.22 | 1.12 | 3 | 4 | 2 | 0 | 0 | 94.44 |
| 2073 | libggml-cpu.so - quants.c:2492-2654 [...] | ggml_vec_dot_q6_K_q8_K | InBetween | 2.16 | 2.74 | 16.90 | 0.22 | 1.04 | 0.19 | 1.17 | 64 | 58.33 | 55.86 | 1.04 | 1.44 | 1.11 | 1.36 | 1 | 4 | 2 | 2 | 0 | 83.33 |
| 780 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.80 | 0.82 | 0.82 | 0.08 | 0.08 | 0.06 | 0.06 | 64 | 1.79 | 10.16 | 1.8 | 1.42 | 10.03 | 1.7 | 1 | 0 | 0 | 0 | 1 | 50.00 |
| 1530 | libggml-cpu.so - vec.h:282-725 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.65 | 0.54 | 1.17 | 0.06 | 0.11 | 0.04 | 0.08 | 63 | 15.2 | 31.87 | 3.13 | 1 | 1.59 | 2.04 | NA | NA | NA | NA | NA | 0.00 |
| 1540 | libggml-cpu.so - vec.h:411-458 | ggml_compute_forward_flash_attn_ext | Innermost | 0.55 | 0.45 | 0.45 | 0.05 | 0.05 | 0.03 | 0.03 | 64 | 96.97 | 96.98 | 1 | 1 | 1 | 2.1 | 1 | 0 | 0 | 16 | 0 | 52.94 |
| 759 | libggml-cpu.so - vec.cpp:231-262 | ggml_vec_dot_f16 | Single | 0.50 | 0.40 | 0.40 | 0.05 | 0.05 | 0.03 | 0.03 | 64 | 100 | 100 | 1 | 1 | 1 | 2.17 | 0 | 0 | 0 | 16 | 0 | 50.00 |
| 761 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 1.10 | 0.32 | 0.32 | 0.11 | 0.11 | 0.02 | 0.02 | 16 | 80 | 97.59 | 1 | 1 | 1.03 | 1.51 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 2206 | libggml-cpu.so - kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c:131-131 | kai_run_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm | InBetween | 0.35 | 0.23 | 55.16 | 0.04 | 3.41 | 0.02 | 3.83 | 61 | 27.59 | 27.86 | 1 | 1 | 4 | 2.57 | NA | NA | NA | NA | NA | 0.00 |
| 2174 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-262 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 2.06 | 0.18 | 0.18 | 0.21 | 0.21 | 0.01 | 0.01 | 4 | 76.21 | 48.38 | 1 | 1.12 | 2.08 | 1.25 | 0 | 0 | 6 | 0 | 0 | 75.00 |
| 1151 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.45 | 0.12 | 0.12 | 0.05 | 0.05 | 0.01 | 0.01 | 16 | 0 | 13.28 | 1 | 2.37 | 8.35 | 1.69 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 71 | libggml-cpu.so - ggml-cpu.c:1664-2898 [...] | ggml_graph_compute_thread | Outermost | 0.25 | 0.11 | 0.12 | 0.03 | 0.03 | 0.01 | 0.01 | 48 | 0 | 17.19 | 1 | 1 | 10.67 | 2.96 | NA | NA | NA | NA | NA | 0.00 |
| 3 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.25 | 0.11 | 0.11 | 0.02 | 0.02 | 0.01 | 0.01 | 41 | 95.35 | 93.9 | 1 | 1 | 1 | 2.56 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1531 | libggml-cpu.so - ops.cpp:8817-8819 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.25 | 0.10 | 0.10 | 0.03 | 0.03 | 0.01 | 0.01 | 44 | 0 | 13.54 | 1.22 | 1.63 | 10.4 | 3.06 | 1 | 1 | 0 | 0 | 0 | 100.00 |
| 424 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.40 | 0.10 | 0.10 | 0.04 | 0.04 | 0.01 | 0.01 | 16 | 25 | 50 | 1 | 1 | 2 | 1.8 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 2188 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 3.51 | 0.09 | 0.09 | 0.35 | 0.35 | 0.01 | 0.01 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
| 2071 | libggml-cpu.so - quants.c:2486-2923 [...] | ggml_vec_dot_q6_K_q8_K | Outermost | 0.25 | 0.08 | 16.97 | 0.03 | 1.04 | 0.01 | 1.18 | 37 | 2.7 | 20.21 | 1.42 | 1 | 4.38 | 3.3 | NA | NA | NA | NA | NA | 0.00 |
| 2186 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:115-118 | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 2.51 | 0.07 | 0.07 | 0.25 | 0.25 | 0.00 | 0.00 | 1 | 0 | 15.63 | 1 | 1 | 10.67 | 1 | 0 | 0 | 0 | 0 | 1 | 0.00 |
| 498 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.25 | 0.06 | 0.06 | 0.03 | 0.03 | 0.00 | 0.00 | 16 | 25 | 50 | 1 | 1 | 2 | 1.74 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 790 | libggml-cpu.so - ops.cpp:6446-6457 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.15 | 0.06 | 0.06 | 0.01 | 0.01 | 0.00 | 0.00 | 31 | 42.86 | 33.93 | 1 | 1 | 1.6 | 2.27 | 2 | 0 | 0 | 7 | 0 | 61.11 |
| 60 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.10 | 0.04 | 0.07 | 0.01 | 0.02 | 0.00 | 0.00 | 25 | 0 | 24.51 | 1 | 1 | 2 | 1.56 | NA | NA | NA | NA | NA | 0.00 |
| 757 | libggml-cpu.so - vec.cpp:224-337 [...] | ggml_vec_dot_f16 | Outermost | 0.10 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 21 | 41.67 | 58.64 | 1 | 1 | 1.23 | 1.75 | NA | NA | NA | NA | NA | 0.00 |
| 387 | libggml-cpu.so - traits.cpp:13-17 | ggml_cpu_extra_compute_forward | Single | 0.15 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 19 | 0 | 23.7 | 1 | 1 | 5.39 | 2.59 | 0 | 0 | 1 | 2 | 0 | 62.19 |
| 777 | libggml-cpu.so - ops.cpp:6210-6481 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.15 | 0.03 | 0.87 | 0.01 | 0.08 | 0.00 | 0.06 | 18 | 0 | 27.03 | 1 | 1 | 2.94 | 2.57 | NA | NA | NA | NA | NA | 0.00 |
| 1538 | libggml-cpu.so - ops.cpp:8825-8826 | ggml_compute_forward_flash_attn_ext | Innermost | 0.10 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 17 | NA | NA | NA | NA | NA | 1.7 | NA | NA | NA | NA | NA | 0.00 |
| 59 | libggml-cpu.so - ggml-cpu.c:1193-1194 | ggml_compute_forward_mul_mat | Innermost | 0.10 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 17 | 0 | 21.53 | 1 | 1 | 5.82 | 1.79 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 2185 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 0.90 | 0.02 | 0.21 | 0.09 | 0.76 | 0.00 | 0.01 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1535 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_flash_attn_ext | Innermost | 0.10 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 14 | 100 | 100 | 1 | 1 | 1 | 1.75 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2184 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 0.75 | 0.02 | 0.09 | 0.07 | 0.32 | 0.00 | 0.01 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1532 | libggml-cpu.so - ops.cpp:8778-8920 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.10 | 0.02 | 0.04 | 0.01 | 0.02 | 0.00 | 0.00 | 12 | 15.6 | 31.32 | 8.06 | 1.01 | 1.46 | 1.71 | NA | NA | NA | NA | NA | 0.00 |
| 62 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.10 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 13 | 0 | 24.02 | 1 | 1 | 2 | 1.86 | NA | NA | NA | NA | NA | 0.00 |
| 776 | libggml-cpu.so - ops.cpp:6210-6481 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.05 | 0.02 | 0.84 | 0.01 | 0.08 | 0.00 | 0.06 | 13 | 0 | 20.85 | 6.77 | 1.33 | 5.9 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2144 | libggml-cpu.so - kleidiai.cpp:535-547 [...] | ggml::cpu::kleidiai::extra_buffer_type::get_tensor_traits(ggml_tensor const*) | Single | 0.15 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 9 | 0 | 25 | 1 | 1 | 4 | 2.45 | NA | NA | NA | NA | NA | 0.00 |
| 775 | libggml-cpu.so - ops.cpp:6210-6481 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.05 | 0.01 | 0.88 | 0.00 | 0.09 | 0.00 | 0.06 | 9 | 0 | 22.24 | 1 | 1 | 5.26 | 1 | NA | NA | NA | NA | NA | 0.00 |