| 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 |
|---|
| 2189 | 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 | 29.23 | 47.25 | 47.25 | 2.25 | 2.25 | 2.47 | 2.47 | 95 | 28.14 | 55.37 | 1 | 1 | 1.85 | 1.1 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 2056 | libggml-cpu.so - quants.c:2506-2575 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 6.95 | 11.15 | 11.15 | 0.54 | 0.54 | 0.58 | 0.58 | 96 | 49.72 | 67.11 | 1.06 | 1 | 1.26 | 1.12 | 3 | 4 | 2 | 0 | 0 | 94.44 |
| 2057 | libggml-cpu.so - quants.c:2492-2654 [...] | ggml_vec_dot_q6_K_q8_K | InBetween | 1.49 | 1.66 | 12.81 | 0.12 | 0.59 | 0.09 | 0.67 | 96 | 58.33 | 71.72 | 1.05 | 1 | 1.17 | 1.63 | 1 | 4 | 2 | 2 | 0 | 83.33 |
| 775 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.91 | 0.78 | 0.78 | 0.07 | 0.07 | 0.04 | 0.04 | 96 | 1.83 | 20.42 | 1.81 | 1.57 | 5 | 2.1 | 1 | 0 | 0 | 0 | 1 | 50.00 |
| 1515 | libggml-cpu.so - vec.h:282-725 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.78 | 0.49 | 0.99 | 0.06 | 0.10 | 0.03 | 0.05 | 86 | 15.2 | 44.54 | 5.75 | 1.03 | 1.34 | 2.59 | NA | NA | NA | NA | NA | 0.00 |
| 754 | libggml-cpu.so - vec.cpp:231-262 | ggml_vec_dot_f16 | Single | 0.65 | 0.43 | 0.43 | 0.05 | 0.05 | 0.02 | 0.02 | 85 | 100 | 100 | 1 | 1 | 1 | 2.44 | 0 | 0 | 0 | 16 | 0 | 50.00 |
| 1525 | libggml-cpu.so - vec.h:411-458 | ggml_compute_forward_flash_attn_ext | Innermost | 0.58 | 0.32 | 0.32 | 0.04 | 0.04 | 0.02 | 0.02 | 82 | 96.97 | 96.99 | 1.24 | 1 | 1 | 2.83 | 1 | 0 | 0 | 16 | 0 | 52.94 |
| 756 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 1.36 | 0.31 | 0.31 | 0.11 | 0.11 | 0.02 | 0.02 | 16 | 80 | 97.68 | 1 | 1 | 1.03 | 1.34 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 2158 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-262 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 2.34 | 0.16 | 0.16 | 0.18 | 0.18 | 0.01 | 0.01 | 4 | 76.21 | 96.75 | 1 | 1 | 1.03 | 1.13 | 0 | 0 | 6 | 0 | 0 | 75.00 |
| 2190 | 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 | 0.26 | 0.15 | 47.40 | 0.02 | 2.25 | 0.01 | 2.48 | 71 | 27.59 | 55.71 | 1 | 1 | 1.62 | 2.25 | NA | NA | NA | NA | NA | 0.00 |
| 5 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.39 | 0.10 | 0.10 | 0.03 | 0.03 | 0.01 | 0.01 | 47 | 88.37 | 93.9 | 1 | 1 | 1 | 3.32 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1148 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.58 | 0.09 | 0.09 | 0.04 | 0.04 | 0.00 | 0.00 | 16 | 0 | 26.56 | 1 | 1.96 | 4.17 | 1.95 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1516 | libggml-cpu.so - ops.cpp:8817-8819 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.26 | 0.08 | 0.08 | 0.02 | 0.02 | 0.00 | 0.00 | 46 | 0 | 27.08 | 1.22 | 1.63 | 5.2 | 2.67 | 1 | 1 | 0 | 0 | 0 | 100.00 |
| 71 | libggml-cpu.so - ggml-cpu.c:1664-2898 [...] | ggml_graph_compute_thread | Outermost | 0.19 | 0.07 | 0.08 | 0.01 | 0.02 | 0.00 | 0.00 | 45 | 0 | 34.38 | 1 | 1 | 5.33 | 2.25 | NA | NA | NA | NA | NA | 0.00 |
| 2170 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:115-118 | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 3.70 | 0.07 | 0.07 | 0.28 | 0.28 | 0.00 | 0.00 | 1 | 0 | 31.25 | 1 | 1 | 4.33 | 1 | 0 | 0 | 0 | 0 | 1 | 0.00 |
| 2055 | libggml-cpu.so - quants.c:2486-2923 [...] | ggml_vec_dot_q6_K_q8_K | Outermost | 0.13 | 0.06 | 12.86 | 0.01 | 0.59 | 0.00 | 0.67 | 41 | 2.78 | 40.15 | 1.45 | 1 | 1.65 | 1.71 | NA | NA | NA | NA | NA | 0.00 |
| 2172 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 3.12 | 0.06 | 0.06 | 0.24 | 0.24 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
| 419 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.45 | 0.05 | 0.05 | 0.04 | 0.04 | 0.00 | 0.00 | 15 | 25 | 100 | 1 | 1 | 1 | 2.44 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 785 | libggml-cpu.so - ops.cpp:6446-6457 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.26 | 0.05 | 0.05 | 0.02 | 0.02 | 0.00 | 0.00 | 31 | 42.86 | 53.57 | 1 | 1 | 1.94 | 3.02 | 2 | 0 | 0 | 7 | 0 | 61.11 |
| 1523 | libggml-cpu.so - ops.cpp:8825-8826 | ggml_compute_forward_flash_attn_ext | Innermost | 0.19 | 0.04 | 0.04 | 0.02 | 0.02 | 0.00 | 0.00 | 25 | NA | NA | NA | NA | NA | 2.59 | NA | NA | NA | NA | NA | 0.00 |
| 493 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.32 | 0.03 | 0.03 | 0.03 | 0.03 | 0.00 | 0.00 | 13 | 25 | 100 | 1 | 1 | 1 | 2.6 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 1520 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_flash_attn_ext | Innermost | 0.13 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 21 | 100 | 100 | 1 | 1 | 1 | 1.75 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2168 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 1.49 | 0.03 | 0.10 | 0.11 | 0.40 | 0.00 | 0.01 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 62 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.13 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 15 | 0 | 48.05 | 1 | 1 | 2 | 1.58 | NA | NA | NA | NA | NA | 0.00 |
| 752 | libggml-cpu.so - vec.cpp:224-337 [...] | ggml_vec_dot_f16 | Outermost | 0.06 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 19 | 41.67 | 63.12 | 1.55 | 1 | 1.4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1517 | libggml-cpu.so - ops.cpp:8778-8920 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.13 | 0.02 | 0.06 | 0.01 | 0.01 | 0.00 | 0.00 | 16 | 15.6 | 45.89 | 8.06 | 1.01 | 1.46 | 1.78 | NA | NA | NA | NA | NA | 0.00 |
| 2116 | libggml-cpu.so - kleidiai.cpp:56-569 [...] | ggml_backend_cpu_kleidiai_buffer_type | Outermost | 0.13 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 16 | 0 | 50 | 1 | 1 | 2 | 1.88 | NA | NA | NA | NA | NA | 0.00 |
| 382 | libggml-cpu.so - traits.cpp:13-17 | ggml_cpu_extra_compute_forward | Single | 0.13 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 15 | 0 | 47.4 | 1 | 1 | 2.69 | 1.87 | 0 | 0 | 1 | 2 | 0 | 62.19 |
| 60 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.13 | 0.02 | 0.04 | 0.01 | 0.01 | 0.00 | 0.00 | 14 | 0 | 49.01 | 1 | 1 | 2 | 1.75 | NA | NA | NA | NA | NA | 0.00 |
| 59 | libggml-cpu.so - ggml-cpu.c:1193-1194 | ggml_compute_forward_mul_mat | Innermost | 0.13 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 12 | 0 | 43.06 | 1 | 1 | 2.95 | 1.71 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 771 | libggml-cpu.so - ops.cpp:6210-6481 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.13 | 0.02 | 0.80 | 0.01 | 0.06 | 0.00 | 0.04 | 12 | 0 | 41.95 | 6.65 | 1.3 | 3 | 1.85 | NA | NA | NA | NA | NA | 0.00 |
| 772 | libggml-cpu.so - ops.cpp:6210-6481 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.13 | 0.01 | 0.81 | 0.01 | 0.06 | 0.00 | 0.04 | 11 | 0 | 49.44 | 1 | 1 | 1.93 | 1.83 | NA | NA | NA | NA | NA | 0.00 |
| 770 | libggml-cpu.so - ops.cpp:6210-6481 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.06 | 0.01 | 0.83 | 0.01 | 0.07 | 0.00 | 0.04 | 10 | 0 | 44.49 | 1 | 1 | 2.8 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2128 | libggml-cpu.so - kleidiai.cpp:535-547 [...] | ggml::cpu::kleidiai::extra_buffer_type::get_tensor_traits(ggml_tensor const*) | Single | 0.06 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 9 | 0 | 50 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1147 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_rms_norm | Innermost | 0.19 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 6 | 100 | 100 | 1 | 1 | 1 | 2 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2169 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 0.58 | 0.01 | 0.17 | 0.04 | 0.68 | 0.00 | 0.01 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |