| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime orig_0 (%) | Exclusive Coverage orig_0 (%) | Inclusive Coverage orig_0 (%) | Max Exclusive Time Over Threads orig_0 (s) | Max Inclusive Time Over Threads orig_0 (s) | Exclusive Time w.r.t. Wall Time orig_0 (s) | Inclusive Time w.r.t. Wall Time orig_0 (s) | Nb Threads orig_0 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing orig_0 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|
| 2354 | 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 | 30.44 | 46.25 | 46.25 | 2.26 | 2.26 | 2.45 | 2.45 | 95 | 28.14 | 55.37 | 1 | 1 | 1.85 | 1.12 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 2236 | libggml-cpu.so - quants.c:2506-2590 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 7.68 | 12.10 | 12.10 | 0.57 | 0.57 | 0.64 | 0.64 | 96 | 50.56 | 65.8 | 1 | 1 | 1.47 | 1.09 | 2 | 0 | 1 | 19 | 0 | 55.68 |
| 2237 | libggml-cpu.so - quants.c:2492-2660 [...] | ggml_vec_dot_q6_K_q8_K | Outermost | 1.35 | 1.30 | 13.40 | 0.10 | 0.62 | 0.07 | 0.71 | 96 | 64.15 | 74.65 | 1.08 | 1 | 1.08 | 1.77 | 0 | 0 | 0 | 22 | 0 | 50.00 |
| 886 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 3.50 | 0.84 | 0.84 | 0.26 | 0.26 | 0.04 | 0.04 | 16 | 70.45 | 83.38 | 1 | 1 | 1.21 | 1.19 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 1408 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 1.08 | 0.70 | 0.70 | 0.08 | 0.08 | 0.04 | 0.04 | 96 | 0 | 24.52 | 1 | 1.64 | 4.36 | 2.63 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 879 | libggml-cpu.so - vec.cpp:231-262 | ggml_vec_dot_f16 | Single | 0.54 | 0.38 | 0.38 | 0.04 | 0.04 | 0.02 | 0.02 | 82 | 100 | 100 | 1 | 1 | 1 | 2.05 | 0 | 0 | 0 | 14 | 0 | 50.00 |
| 73 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 0.81 | 0.34 | 0.34 | 0.06 | 0.06 | 0.02 | 0.02 | 73 | 0 | 38.84 | 1 | 1 | 5.33 | 3.07 | NA | NA | NA | NA | NA | 0.00 |
| 1718 | libggml-cpu.so - vec.h:411-458 | ggml_compute_forward_flash_attn_ext | Innermost | 0.54 | 0.32 | 0.32 | 0.04 | 0.04 | 0.02 | 0.02 | 77 | 100 | 100 | 1 | 1 | 1 | 2.29 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1710 | libggml-cpu.so - vec.h:282-662 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.47 | 0.31 | 0.45 | 0.04 | 0.05 | 0.02 | 0.02 | 83 | 16.83 | 53.17 | 3.04 | 1.03 | 1.39 | 2.27 | NA | NA | NA | NA | NA | 0.00 |
| 2317 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-258 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 3.10 | 0.18 | 0.18 | 0.23 | 0.23 | 0.01 | 0.01 | 4 | 77.23 | 96.44 | 1 | 1 | 1.03 | 1.21 | 1 | 0 | 1 | 3 | 0 | 65.00 |
| 2355 | 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 | 0.34 | 0.17 | 46.42 | 0.03 | 2.26 | 0.01 | 2.46 | 73 | 27.59 | 55.71 | 1 | 1 | 1.62 | 2.57 | NA | NA | NA | NA | NA | 0.00 |
| 1713 | libggml-cpu.so - vec.h:282-725 [...] | ggml_compute_forward_flash_attn_ext | Outermost | 0.34 | 0.16 | 0.94 | 0.03 | 0.08 | 0.01 | 0.05 | 68 | 16.49 | 49.06 | 5.71 | 1 | 1.45 | 2.56 | NA | NA | NA | NA | NA | 0.00 |
| 520 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.74 | 0.09 | 0.09 | 0.05 | 0.05 | 0.01 | 0.01 | 16 | 0 | 23.68 | 1 | 1 | 5.33 | 2.23 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1721 | libggml-cpu.so - ops.cpp:8778-8920 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.20 | 0.09 | 0.15 | 0.02 | 0.03 | 0.00 | 0.01 | 51 | 0 | 47.79 | 80 | 1.14 | 1.6 | 2.1 | NA | NA | NA | NA | NA | 0.00 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.34 | 0.09 | 0.09 | 0.02 | 0.02 | 0.00 | 0.00 | 41 | 92.5 | 98.75 | 1 | 1 | 1 | 2.85 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 1249 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.61 | 0.09 | 0.09 | 0.05 | 0.05 | 0.00 | 0.00 | 16 | 94.12 | 97.06 | 1 | 1 | 1.03 | 2.03 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 2337 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 4.24 | 0.08 | 0.08 | 0.31 | 0.31 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 1 | 0 | 0 | 0 | 1 | 50.00 |
| 413 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.54 | 0.07 | 0.07 | 0.04 | 0.04 | 0.00 | 0.00 | 16 | 0 | 25 | 1 | 1 | 5.33 | 2.06 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1399 | libggml-cpu.so - ops.cpp:6210-6409 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.20 | 0.07 | 0.77 | 0.02 | 0.06 | 0.00 | 0.04 | 41 | 0 | 41.88 | 5.47 | 1.38 | 2.88 | 2.2 | NA | NA | NA | NA | NA | 0.00 |
| 1403 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.40 | 0.06 | 0.06 | 0.03 | 0.03 | 0.00 | 0.00 | 28 | 35.29 | 39.71 | 1.2 | 1.33 | 2.49 | 3.65 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 53 | libggml-cpu.so - ggml-cpu.c:1183-1194 [...] | ggml_compute_forward_mul_mat | Innermost | 0.13 | 0.05 | 0.05 | 0.01 | 0.01 | 0.00 | 0.00 | 35 | 0 | 50 | 1 | 1 | 2 | 1.67 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1722 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_flash_attn_ext | Innermost | 0.20 | 0.05 | 0.05 | 0.02 | 0.02 | 0.00 | 0.00 | 30 | 100 | 100 | 1 | 1 | 1 | 2.31 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2338 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:115-118 | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 2.09 | 0.04 | 0.04 | 0.16 | 0.16 | 0.00 | 0.00 | 1 | 0 | 31.25 | 1 | 1 | 5.33 | 1 | 0 | 0 | 0 | 1 | 1 | 25.00 |
| 54 | 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 | 19 | 0 | 46.88 | 1 | 1 | 2 | 1.9 | NA | NA | NA | NA | NA | 0.00 |
| 1400 | libggml-cpu.so - ops.cpp:6210-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.13 | 0.02 | 0.84 | 0.01 | 0.07 | 0.00 | 0.04 | 16 | 7.69 | 42.15 | 5.05 | 1.52 | 3.73 | 1.88 | NA | NA | NA | NA | NA | 0.00 |
| 2336 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Outermost | 0.81 | 0.01 | 0.13 | 0.06 | 0.53 | 0.00 | 0.01 | 1 | 0 | 45.83 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1252 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_rms_norm | Innermost | 0.13 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 8 | 100 | 100 | 1 | 1 | 1 | 1.45 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 56 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | InBetween | 0.07 | 0.01 | 0.09 | 0.01 | 0.01 | 0.00 | 0.00 | 9 | 0 | 48.2 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1709 | libggml-cpu.so - vec.h:474-662 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.07 | 0.01 | 0.06 | 0.01 | 0.02 | 0.00 | 0.00 | 9 | 12.24 | 50.78 | 16.23 | 1.01 | 1.35 | 1 | NA | NA | NA | NA | NA | 0.00 |