| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime armclang_3 (%) | Exclusive Coverage armclang_3 (%) | Inclusive Coverage armclang_3 (%) | Max Exclusive Time Over Threads armclang_3 (s) | Max Inclusive Time Over Threads armclang_3 (s) | Exclusive Time w.r.t. Wall Time armclang_3 (s) | Inclusive Time w.r.t. Wall Time armclang_3 (s) | Nb Threads armclang_3 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing armclang_3 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|
| 2528 | 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 | 30.54 | 47.35 | 47.35 | 2.25 | 2.25 | 2.38 | 2.38 | 95 | 28.14 | 55.37 | 1 | 1 | 1.85 | 1.13 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 2425 | libggml-cpu.so - quants.c:2506-2590 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 7.52 | 12.09 | 12.09 | 0.55 | 0.55 | 0.61 | 0.61 | 96 | 50.56 | 65.8 | 1 | 1 | 1.47 | 1.1 | 2 | 0 | 1 | 19 | 0 | 55.68 |
| 2426 | libggml-cpu.so - quants.c:2492-2660 [...] | ggml_vec_dot_q6_K_q8_K | Outermost | 1.42 | 1.58 | 13.67 | 0.11 | 0.61 | 0.08 | 0.69 | 96 | 19.23 | 39.9 | 1 | 1 | 2.32 | 1.59 | 0 | 0 | 0 | 22 | 0 | 50.00 |
| 1596 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.88 | 0.68 | 0.68 | 0.06 | 0.06 | 0.03 | 0.03 | 95 | 0 | 26.14 | 1 | 2 | 4.2 | 2.27 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 1896 | libggml-cpu.so - ops.cpp:8793-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.74 | 0.60 | 0.92 | 0.06 | 0.08 | 0.03 | 0.05 | 86 | 0 | 34.34 | 2.26 | 2.85 | 1.19 | 1.97 | NA | NA | NA | NA | NA | 0.00 |
| 908 | libggml-cpu.so - vec.cpp:311-316 | ggml_vec_dot_f16 | Single | 0.81 | 0.57 | 0.57 | 0.06 | 0.06 | 0.03 | 0.03 | 86 | 50 | 100 | 1 | 1 | 1 | 2.24 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 1908 | libggml-cpu.so - vec.h:491-497 | ggml_compute_forward_flash_attn_ext | Innermost | 0.54 | 0.32 | 0.32 | 0.04 | 0.04 | 0.02 | 0.02 | 79 | 40 | 100 | 1 | 1 | 1 | 2.49 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 916 | libggml-cpu.so - vec.h:1045-1072 [...] | ggml_vec_swiglu_f32 | Innermost | 1.35 | 0.25 | 0.25 | 0.10 | 0.10 | 0.01 | 0.01 | 16 | 73.33 | 91.67 | 1.04 | 1 | 1 | 1.57 | NA | NA | NA | NA | NA | 0.00 |
| 73 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 0.54 | 0.22 | 0.22 | 0.04 | 0.04 | 0.01 | 0.01 | 59 | 0 | 38.84 | 1 | 1 | 5.33 | 2.68 | NA | NA | NA | NA | NA | 0.00 |
| 2496 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-258 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 2.84 | 0.18 | 0.18 | 0.21 | 0.21 | 0.01 | 0.01 | 4 | 77.23 | 96.44 | 1 | 1 | 1.03 | 1.15 | 1 | 0 | 1 | 3 | 0 | 65.00 |
| 2529 | 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 | 0.27 | 0.13 | 47.48 | 0.02 | 2.26 | 0.01 | 2.39 | 62 | 27.59 | 55.71 | 1 | 1 | 1.62 | 2.38 | NA | NA | NA | NA | NA | 0.00 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.41 | 0.10 | 0.10 | 0.03 | 0.03 | 0.00 | 0.00 | 46 | 91.67 | 98.61 | 1 | 1 | 1 | 3.49 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 541 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.61 | 0.09 | 0.09 | 0.04 | 0.04 | 0.00 | 0.00 | 16 | 0 | 23.68 | 1 | 1 | 5.33 | 1.92 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 437 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.68 | 0.08 | 0.08 | 0.05 | 0.05 | 0.00 | 0.00 | 15 | 0 | 25 | 1 | 1 | 5.33 | 2.21 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1591 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.27 | 0.07 | 0.07 | 0.02 | 0.02 | 0.00 | 0.00 | 39 | 55.56 | 43.75 | 1.07 | 1.58 | 2.35 | 2.74 | 0 | 0 | 1 | 2 | 0 | 58.33 |
| 2511 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 3.66 | 0.07 | 0.07 | 0.27 | 0.27 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 1 | 0 | 0 | 0 | 1 | 50.00 |
| 1914 | libggml-cpu.so - vec.h:677-682 | ggml_compute_forward_flash_attn_ext | Innermost | 0.14 | 0.04 | 0.04 | 0.01 | 0.01 | 0.00 | 0.00 | 29 | 50 | 100 | 1 | 1 | 1 | 1.71 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1587 | libggml-cpu.so - ops.cpp:6210-6462 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.20 | 0.03 | 0.71 | 0.01 | 0.06 | 0.00 | 0.04 | 24 | 0 | 39.72 | 5.92 | 1.4 | 3.04 | 2.67 | NA | NA | NA | NA | NA | 0.00 |
| 2512 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:115-118 | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 1.76 | 0.03 | 0.03 | 0.13 | 0.13 | 0.00 | 0.00 | 1 | 0 | 31.25 | 1 | 1 | 5.33 | 1 | 0 | 0 | 0 | 1 | 1 | 25.00 |
| 1353 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.27 | 0.02 | 0.02 | 0.02 | 0.02 | 0.00 | 0.00 | 11 | 16.67 | 54.17 | 1 | 1.25 | 2 | 2.32 | 0 | 0 | 1 | 0 | 0 | 75.00 |
| 1588 | libggml-cpu.so - ops.cpp:6210-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.07 | 0.02 | 0.81 | 0.01 | 0.08 | 0.00 | 0.04 | 19 | 0 | 41.88 | 1 | 1 | 3.01 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 53 | libggml-cpu.so - ggml-cpu.c:1183-1194 [...] | ggml_compute_forward_mul_mat | Innermost | 0.14 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 17 | 0 | 50 | 1 | 1 | 2 | 1.89 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1893 | libggml-cpu.so - vec.h:375-751 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.14 | 0.02 | 0.98 | 0.01 | 0.09 | 0.00 | 0.05 | 15 | 0 | 44.59 | 2.01 | 1.34 | 1.34 | 1.87 | NA | NA | NA | NA | NA | 0.00 |
| 1354 | libggml-cpu.so - vec.h:677-682 | ggml_compute_forward_rms_norm | Innermost | 0.14 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 11 | 50 | 100 | 1 | 1 | 1 | 1.57 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 54 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.14 | 0.02 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 12 | 0 | 46.88 | 1 | 1 | 2 | 1.85 | NA | NA | NA | NA | NA | 0.00 |
| 2510 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Outermost | 0.74 | 0.01 | 0.11 | 0.05 | 0.45 | 0.00 | 0.01 | 1 | 0 | 46.25 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |