| 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 |
|---|
| 2405 | 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 | 34.62 | 53.40 | 53.40 | 3.36 | 3.36 | 3.80 | 3.80 | 64 | 28.14 | 27.69 | 1 | 1.18 | 4.53 | 1.06 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 2288 | libggml-cpu.so - quants.c:2506-2590 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 10.24 | 15.32 | 15.32 | 1.00 | 1.00 | 1.09 | 1.09 | 64 | 50.56 | 33.98 | 1 | 1 | 2.57 | 1.1 | 2 | 0 | 1 | 19 | 0 | 55.68 |
| 2289 | libggml-cpu.so - quants.c:2492-2660 [...] | ggml_vec_dot_q6_K_q8_K | Outermost | 1.85 | 2.12 | 17.43 | 0.18 | 1.12 | 0.15 | 1.24 | 64 | 61.82 | 61.76 | 1.19 | 1.85 | 1 | 1.44 | 0 | 0 | 0 | 22 | 0 | 50.00 |
| 1750 | libggml-cpu.so - ops.cpp:8793-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.77 | 0.73 | 1.06 | 0.08 | 0.10 | 0.05 | 0.08 | 63 | 15.14 | 37.61 | 4.04 | 1 | 1.86 | 1.7 | NA | NA | NA | NA | NA | 0.00 |
| 1442 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.67 | 0.66 | 0.66 | 0.07 | 0.07 | 0.05 | 0.05 | 64 | 0 | 12.26 | 1 | 1.64 | 8.73 | 1.67 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 910 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 2.06 | 0.54 | 0.54 | 0.20 | 0.20 | 0.04 | 0.04 | 16 | 70.45 | 81.46 | 1 | 1 | 1.24 | 1.57 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 903 | libggml-cpu.so - vec.cpp:231-262 | ggml_vec_dot_f16 | Single | 0.57 | 0.44 | 0.44 | 0.05 | 0.05 | 0.03 | 0.03 | 64 | 96 | 97 | 1 | 1 | 1 | 2.12 | 0 | 0 | 0 | 16 | 0 | 50.00 |
| 1757 | libggml-cpu.so - vec.h:411-458 | ggml_compute_forward_flash_attn_ext | Innermost | 0.41 | 0.32 | 0.32 | 0.04 | 0.04 | 0.02 | 0.02 | 61 | 100 | 100 | 1 | 1 | 1 | 2.03 | 0 | 0 | 0 | 4 | 0 | 50.00 |
| 2406 | 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 | 0.41 | 0.26 | 53.67 | 0.04 | 3.37 | 0.02 | 3.82 | 61 | 27.59 | 27.86 | 1 | 1 | 4 | 2.44 | NA | NA | NA | NA | NA | 0.00 |
| 2368 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-258 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 2.47 | 0.23 | 0.23 | 0.24 | 0.24 | 0.02 | 0.02 | 4 | 77.23 | 48.22 | 1 | 1.12 | 2.08 | 1.11 | 1 | 0 | 1 | 3 | 0 | 65.00 |
| 86 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 0.36 | 0.18 | 0.18 | 0.03 | 0.03 | 0.01 | 0.01 | 52 | 0 | 19.42 | 1 | 1 | 10.67 | 2.72 | NA | NA | NA | NA | NA | 0.00 |
| 1282 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.57 | 0.12 | 0.12 | 0.05 | 0.05 | 0.01 | 0.01 | 16 | 94.12 | 95.59 | 1 | 1 | 1.04 | 1.91 | 0 | 0 | 0 | 1 | 0 | 50.00 |
| 2388 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 4.17 | 0.11 | 0.11 | 0.41 | 0.41 | 0.01 | 0.01 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 1 | 0 | 0 | 0 | 1 | 50.00 |
| 431 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.51 | 0.11 | 0.11 | 0.05 | 0.05 | 0.01 | 0.01 | 16 | 0 | 12.5 | 1 | 1 | 10.67 | 1.98 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.26 | 0.09 | 0.09 | 0.02 | 0.02 | 0.01 | 0.01 | 38 | 90.48 | 95.41 | 1 | 1 | 1.05 | 2.92 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1437 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.21 | 0.08 | 0.08 | 0.02 | 0.02 | 0.01 | 0.01 | 38 | 35.29 | 19.85 | 1.2 | 1.5 | 4.99 | 2.58 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 65 | libggml-cpu.so - ggml-cpu.c:1183-1194 [...] | ggml_compute_forward_mul_mat | Innermost | 0.15 | 0.08 | 0.08 | 0.02 | 0.02 | 0.01 | 0.01 | 41 | 0 | 25 | 1 | 1 | 4 | 2.16 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 541 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.36 | 0.07 | 0.07 | 0.04 | 0.04 | 0.01 | 0.01 | 15 | 0 | 11.84 | 1 | 1 | 10.67 | 1.88 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1433 | libggml-cpu.so - ops.cpp:6210-6409 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.15 | 0.06 | 0.72 | 0.02 | 0.07 | 0.00 | 0.05 | 35 | 0 | 20.94 | 5.47 | 1.45 | 5.76 | 2.19 | NA | NA | NA | NA | NA | 0.00 |
| 2389 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:115-118 | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 1.80 | 0.05 | 0.05 | 0.17 | 0.17 | 0.00 | 0.00 | 1 | 0 | 15.63 | 1 | 1 | 10.35 | 1 | 0 | 0 | 0 | 1 | 1 | 25.00 |
| 1744 | libggml-cpu.so - vec.h:282-725 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.21 | 0.04 | 1.12 | 0.02 | 0.10 | 0.00 | 0.08 | 21 | 4.26 | 30.35 | 40.28 | 1.01 | 1.61 | 2.9 | NA | NA | NA | NA | NA | 0.00 |
| 64 | 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 | 24 | 0 | 23.86 | 1 | 1 | 2 | 1.85 | NA | NA | NA | NA | NA | 0.00 |
| 2387 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Outermost | 1.03 | 0.03 | 0.18 | 0.10 | 0.68 | 0.00 | 0.01 | 1 | 0 | 22.92 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1434 | libggml-cpu.so - ops.cpp:6210-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.10 | 0.02 | 0.82 | 0.01 | 0.08 | 0.00 | 0.06 | 16 | 7.69 | 21.07 | 5.05 | 1.7 | 6.85 | 1.88 | NA | NA | NA | NA | NA | 0.00 |
| 69 | libggml-cpu.so - ggml-cpu.c:1163-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.15 | 0.02 | 0.10 | 0.01 | 0.02 | 0.00 | 0.01 | 12 | 0 | 24.36 | 1 | 1 | 2 | 2.57 | NA | NA | NA | NA | NA | 0.00 |
| 1760 | 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 | 11 | 100 | 100 | 1 | 1 | 1 | 1.83 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1285 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_rms_norm | Innermost | 0.15 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 7 | 100 | 100 | 1 | 1 | 1 | 2.1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1758 | libggml-cpu.so - vec.h:710-717 | ggml_compute_forward_flash_attn_ext | Innermost | 0.10 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 7 | 96 | 97 | 1 | 1 | 1 | 1.75 | 0 | 0 | 0 | 8 | 0 | 50.00 |
