| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime armclang_1 (%) | Exclusive Coverage armclang_1 (%) | Inclusive Coverage armclang_1 (%) | Max Exclusive Time Over Threads armclang_1 (s) | Max Inclusive Time Over Threads armclang_1 (s) | Exclusive Time w.r.t. Wall Time armclang_1 (s) | Inclusive Time w.r.t. Wall Time armclang_1 (s) | Nb Threads armclang_1 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing armclang_1 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2396 | 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 | 43.55 | 85.60 | 85.60 | 2.94 | 2.94 | 3.57 | 3.57 | 64 | 28.14 | 27.69 | 1 | 1.18 | 4.53 | 1.02 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 1744 | libggml-cpu.so - ops.cpp:8793-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 1.11 | 1.25 | 1.41 | 0.08 | 0.08 | 0.05 | 0.06 | 64 | 15.14 | 37.61 | 4.04 | 1 | 1.86 | 1.78 | NA | NA | NA | NA | NA | 0.00 |
| 1441 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 1.48 | 1.18 | 1.18 | 0.10 | 0.10 | 0.05 | 0.05 | 64 | 0 | 13.07 | 1 | 2 | 8.39 | 2.52 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 910 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 0.74 | 0.84 | 0.84 | 0.05 | 0.05 | 0.04 | 0.04 | 64 | 70.45 | 81.46 | 1 | 1 | 1.24 | 1.77 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 2397 | 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 | 0.44 | 0.41 | 86.01 | 0.03 | 2.96 | 0.02 | 3.58 | 61 | 27.59 | 27.86 | 1 | 1 | 4 | 2.06 | NA | NA | NA | NA | NA | 0.00 |
| 2360 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-258 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 0.52 | 0.36 | 0.36 | 0.04 | 0.04 | 0.01 | 0.01 | 61 | 77.23 | 48.22 | 1 | 1.12 | 2.08 | 2.75 | 1 | 0 | 1 | 3 | 0 | 65.00 |
| 544 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.37 | 0.30 | 0.30 | 0.03 | 0.03 | 0.01 | 0.01 | 60 | 0 | 11.84 | 1 | 1 | 10.67 | 2.29 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1281 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.37 | 0.27 | 0.27 | 0.03 | 0.03 | 0.01 | 0.01 | 56 | 88.89 | 91.67 | 1 | 1 | 1 | 2.43 | 0 | 0 | 0 | 1 | 0 | 50.00 |
| 433 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.30 | 0.26 | 0.26 | 0.02 | 0.02 | 0.01 | 0.01 | 54 | 0 | 12.5 | 1 | 1 | 10.67 | 1.91 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 2282 | libggml-cpu.so - quants.c:2506-2590 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 0.15 | 0.25 | 0.25 | 0.01 | 0.01 | 0.01 | 0.01 | 63 | 50.56 | 33.98 | 1 | 1 | 2.57 | 1.19 | 2 | 0 | 1 | 19 | 0 | 55.68 |
| 1751 | libggml-cpu.so - vec.h:411-458 | ggml_compute_forward_flash_attn_ext | Innermost | 0.30 | 0.16 | 0.16 | 0.02 | 0.02 | 0.01 | 0.01 | 41 | 100 | 100 | 1 | 1 | 1 | 2.38 | 0 | 0 | 0 | 4 | 0 | 50.00 |
| 2379 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 4.44 | 0.14 | 0.14 | 0.30 | 0.30 | 0.01 | 0.01 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 1 | 0 | 0 | 0 | 1 | 50.00 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.22 | 0.13 | 0.13 | 0.02 | 0.02 | 0.01 | 0.01 | 37 | 89.47 | 94.92 | 1 | 1 | 1.06 | 2.02 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 903 | libggml-cpu.so - vec.cpp:231-262 | ggml_vec_dot_f16 | Single | 0.30 | 0.12 | 0.12 | 0.02 | 0.02 | 0.01 | 0.01 | 38 | 96 | 97 | 1 | 1 | 1 | 2.92 | 0 | 0 | 0 | 16 | 0 | 50.00 |
| 2380 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:115-118 | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 3.40 | 0.11 | 0.11 | 0.23 | 0.23 | 0.00 | 0.00 | 1 | 0 | 15.63 | 1 | 1 | 10.35 | 1 | 0 | 0 | 0 | 1 | 1 | 25.00 |
| 1436 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.22 | 0.09 | 0.09 | 0.02 | 0.02 | 0.00 | 0.00 | 35 | 45.45 | 22.44 | 1.07 | 1.61 | 4.71 | 2.63 | 0 | 0 | 1 | 2 | 0 | 58.33 |
| 1433 | libggml-cpu.so - ops.cpp:6210-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.22 | 0.05 | 1.36 | 0.02 | 0.12 | 0.00 | 0.06 | 17 | 0 | 20.94 | 1 | 1 | 5.05 | 2.43 | NA | NA | NA | NA | NA | 0.00 |
| 1432 | libggml-cpu.so - ops.cpp:6210-6462 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.07 | 0.04 | 1.22 | 0.01 | 0.10 | 0.00 | 0.05 | 17 | 0 | 19.86 | 5.92 | 1.47 | 6.07 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2378 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Outermost | 1.26 | 0.04 | 0.29 | 0.09 | 0.62 | 0.00 | 0.01 | 1 | 0 | 22.92 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1284 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_rms_norm | Innermost | 0.15 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 11 | 100 | 100 | 1 | 1 | 1 | 1.83 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2283 | libggml-cpu.so - quants.c:2492-2660 [...] | ggml_vec_dot_q6_K_q8_K | Outermost | 0.07 | 0.03 | 0.27 | 0.01 | 0.01 | 0.00 | 0.01 | 12 | 61.82 | 61.76 | 1.19 | 1.85 | 1 | 1 | 0 | 0 | 0 | 22 | 0 | 50.00 |
| 86 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 0.15 | 0.03 | 0.03 | 0.01 | 0.01 | 0.00 | 0.00 | 10 | 0 | 19.42 | 1 | 1 | 10.67 | 1.82 | NA | NA | NA | NA | NA | 0.00 |
| 1754 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_flash_attn_ext | Innermost | 0.07 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 9 | 100 | 100 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1738 | libggml-cpu.so - vec.h:282-725 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.07 | 0.02 | 1.46 | 0.01 | 0.06 | 0.00 | 0.06 | 8 | 4.26 | 30.35 | 40.28 | 1.01 | 1.61 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 390 | libggml-cpu.so - traits.cpp:13-17 [...] | ggml_cpu_extra_compute_forward | Single | 0.07 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 6 | 0 | 25 | 1 | 1 | 4 | 1 | 0 | 0 | 1 | 2 | 0 | 62.19 |