| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime gcc_4 (%) | Exclusive Coverage gcc_4 (%) | Inclusive Coverage gcc_4 (%) | Max Exclusive Time Over Threads gcc_4 (s) | Max Inclusive Time Over Threads gcc_4 (s) | Exclusive Time w.r.t. Wall Time gcc_4 (s) | Inclusive Time w.r.t. Wall Time gcc_4 (s) | Nb Threads gcc_4 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing gcc_4 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|
| 2241 | 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 | 33.53 | 55.85 | 55.85 | 3.34 | 3.34 | 3.84 | 3.84 | 64 | 28.14 | 27.69 | 1 | 1.18 | 4.53 | 1.05 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 2114 | libggml-cpu.so - quants.c:2506-2575 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 7.82 | 12.37 | 12.37 | 0.78 | 0.78 | 0.85 | 0.85 | 64 | 49.44 | 34.59 | 1.06 | 1 | 2.22 | 1.11 | 3 | 4 | 2 | 0 | 0 | 94.44 |
| 2115 | libggml-cpu.so - quants.c:2492-2654 [...] | ggml_vec_dot_q6_K_q8_K | InBetween | 2.46 | 3.28 | 15.64 | 0.25 | 0.94 | 0.23 | 1.07 | 64 | 24.64 | 24.55 | 1.04 | 1.16 | 2.54 | 1.32 | 1 | 3 | 0 | 5 | 0 | 72.22 |
| 820 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.90 | 0.76 | 0.76 | 0.09 | 0.09 | 0.05 | 0.05 | 64 | 2.22 | 10.59 | 1.66 | 1.48 | 10.02 | 2.09 | NA | NA | NA | NA | NA | 0.00 |
| 1614 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.70 | 0.74 | 1.34 | 0.07 | 0.11 | 0.05 | 0.09 | 64 | 16.42 | 27.7 | 2.15 | 1.88 | 4.74 | 1.67 | NA | NA | NA | NA | NA | 0.00 |
| 788 | libggml-cpu.so - vec.cpp:311-311 [...] | ggml_vec_dot_f16 | Single | 0.55 | 0.48 | 0.48 | 0.06 | 0.06 | 0.03 | 0.03 | 64 | 44.44 | 50 | 1 | 1.2 | 2 | 2.03 | 0 | 0 | 4 | 6 | 0 | 60.00 |
| 1623 | libggml-cpu.so - vec.h:491-491 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.45 | 0.43 | 0.43 | 0.05 | 0.05 | 0.03 | 0.03 | 64 | 27.59 | 50 | 1 | 1.01 | 2 | 1.83 | 1 | 0 | 4 | 4 | 0 | 66.67 |
| 794 | libggml-cpu.so - vec.cpp:390-390 [...] | ggml_vec_swiglu_f32 | Innermost | 1.15 | 0.38 | 0.38 | 0.12 | 0.12 | 0.03 | 0.03 | 16 | 84.85 | 48.48 | 1.07 | 1.38 | 1.72 | 1.32 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 2242 | 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 | 0.40 | 0.28 | 56.14 | 0.04 | 3.36 | 0.02 | 3.86 | 64 | 27.59 | 27.86 | 1 | 1 | 4 | 2.49 | NA | NA | NA | NA | NA | 0.00 |
| 2211 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-262 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 2.05 | 0.18 | 0.18 | 0.20 | 0.20 | 0.01 | 0.01 | 4 | 76.21 | 48.38 | 1 | 1.12 | 2.08 | 1.25 | 0 | 0 | 6 | 0 | 0 | 75.00 |
| 2113 | libggml-cpu.so - quants.c:2486-2923 [...] | ggml_vec_dot_q6_K_q8_K | Outermost | 0.25 | 0.11 | 15.75 | 0.03 | 0.95 | 0.01 | 1.08 | 45 | 5.26 | 21.98 | 1.67 | 1 | 4.16 | 2.85 | NA | NA | NA | NA | NA | 0.00 |
| 75 | libggml-cpu.so - ggml-cpu.c:1664-2898 [...] | ggml_graph_compute_thread | Outermost | 0.20 | 0.10 | 0.12 | 0.02 | 0.02 | 0.01 | 0.01 | 48 | 0 | 17.19 | 1 | 1 | 9.23 | 2.56 | NA | NA | NA | NA | NA | 0.00 |
| 431 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.50 | 0.10 | 0.10 | 0.05 | 0.05 | 0.01 | 0.01 | 15 | 25 | 50 | 1 | 1 | 2 | 2 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 2224 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 3.76 | 0.10 | 0.10 | 0.38 | 0.38 | 0.01 | 0.01 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
| 1 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.25 | 0.09 | 0.09 | 0.03 | 0.03 | 0.01 | 0.01 | 40 | 86.21 | 47.41 | 1 | 1.04 | 2.07 | 3.08 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 2220 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 2.91 | 0.08 | 0.08 | 0.29 | 0.29 | 0.01 | 0.01 | 1 | 0 | 21.79 | 1 | 1 | 2.38 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 785 | libggml-cpu.so - vec.cpp:311-337 [...] | ggml_vec_dot_f16 | Outermost | 0.20 | 0.08 | 0.08 | 0.02 | 0.02 | 0.01 | 0.01 | 38 | 13.85 | 19.54 | 2.1 | 1.48 | 3.07 | 2.71 | NA | NA | NA | NA | NA | 0.00 |
| 830 | libggml-cpu.so - ops.cpp:6446-6457 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.20 | 0.07 | 0.07 | 0.02 | 0.02 | 0.00 | 0.00 | 31 | 42.86 | 33.93 | 1 | 1 | 1.68 | 2.53 | 1 | 0 | 0 | 15 | 0 | 53.13 |
| 1613 | libggml-cpu.so - ops.cpp:8818-8826 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.15 | 0.06 | 0.06 | 0.02 | 0.02 | 0.00 | 0.00 | 36 | 0 | 20.54 | 10.67 | 1 | 10.67 | 2.35 | NA | NA | NA | NA | NA | 0.00 |
| 515 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.20 | 0.05 | 0.05 | 0.02 | 0.02 | 0.00 | 0.00 | 16 | 25 | 50 | 1 | 1 | 2 | 1.68 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 64 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.15 | 0.05 | 0.07 | 0.02 | 0.02 | 0.00 | 0.00 | 25 | 0 | 24.62 | 1 | 1 | 2 | 2.27 | NA | NA | NA | NA | NA | 0.00 |
| 815 | libggml-cpu.so - ops.cpp:6210-6475 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.10 | 0.05 | 0.85 | 0.01 | 0.08 | 0.00 | 0.06 | 26 | 0 | 13.23 | 2.04 | 1.62 | 8.83 | 1.58 | NA | NA | NA | NA | NA | 0.00 |
| 1616 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.10 | 0.04 | 0.10 | 0.01 | 0.02 | 0.00 | 0.01 | 24 | 0 | 22.34 | 2.48 | 1.18 | 2.17 | 1.6 | NA | NA | NA | NA | NA | 0.00 |
| 2221 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 1.25 | 0.03 | 0.22 | 0.13 | 0.79 | 0.00 | 0.01 | 1 | 0 | 20.82 | 1 | 1 | 5.37 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 816 | libggml-cpu.so - ops.cpp:6210-6407 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.15 | 0.03 | 0.79 | 0.01 | 0.07 | 0.00 | 0.05 | 19 | 0 | 14.51 | 2.56 | 1.28 | 6.67 | 2.28 | NA | NA | NA | NA | NA | 0.00 |
| 1194 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.20 | 0.03 | 0.03 | 0.02 | 0.02 | 0.00 | 0.00 | 12 | 17.78 | 27.78 | 1 | 1.25 | 4 | 2 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1615 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.10 | 0.03 | 0.06 | 0.01 | 0.01 | 0.00 | 0.00 | 16 | 18.66 | 29.67 | 4.46 | 1.8 | 1.08 | 1.52 | NA | NA | NA | NA | NA | 0.00 |
| 66 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.10 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 18 | 0 | 23.96 | 1 | 1 | 2 | 1.89 | NA | NA | NA | NA | NA | 0.00 |
| 1618 | libggml-cpu.so - vec.h:677-677 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.10 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 17 | 44.44 | 50 | 1 | 1 | 2 | 1.89 | 0 | 0 | 1 | 3 | 0 | 56.25 |
| 1612 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | Outermost | 0.10 | 0.02 | 1.37 | 0.01 | 0.11 | 0.00 | 0.09 | 16 | 0 | 14.42 | 3.22 | 1.34 | 7.48 | 1.78 | NA | NA | NA | NA | NA | 0.00 |
| 63 | libggml-cpu.so - ggml-cpu.c:1193-1194 | ggml_compute_forward_mul_mat | Innermost | 0.10 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 15 | 0 | 21.53 | 1 | 1 | 5.82 | 1.87 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 817 | libggml-cpu.so - ops.cpp:6210-6439 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.10 | 0.02 | 0.81 | 0.01 | 0.07 | 0.00 | 0.06 | 10 | 0 | 26.86 | 1 | 1 | 3.01 | 1.82 | NA | NA | NA | NA | NA | 0.00 |
| 1198 | libggml-cpu.so - vec.h:677-677 [...] | ggml_compute_forward_rms_norm | Innermost | 0.10 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 9 | 44.44 | 50 | 1 | 1 | 2 | 1.8 | 0 | 0 | 1 | 3 | 0 | 56.25 |
| 74 | libggml-cpu.so - ggml-cpu.c:2879-2898 [...] | ggml_graph_compute_thread | Innermost | 0.05 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 9 | 0 | 15.63 | 1 | 1 | 7.33 | 1 | NA | NA | NA | NA | NA | 0.00 |