| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime gcc_2 (%) | Exclusive Coverage gcc_2 (%) | Inclusive Coverage gcc_2 (%) | Max Exclusive Time Over Threads gcc_2 (s) | Max Inclusive Time Over Threads gcc_2 (s) | Exclusive Time w.r.t. Wall Time gcc_2 (s) | Inclusive Time w.r.t. Wall Time gcc_2 (s) | Nb Threads gcc_2 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing gcc_2 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|
| 2186 | 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 | 42.52 | 88.98 | 88.98 | 2.92 | 2.92 | 4.00 | 4.00 | 64 | 28.14 | 27.69 | 1 | 1.18 | 4.53 | 1.02 | 0 | 0 | 5 | 0 | 0 | 75.00 |
| 1555 | libggml-cpu.so - ops.cpp:8817-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.87 | 1.30 | 1.30 | 0.06 | 0.06 | 0.06 | 0.06 | 64 | 36.89 | 48.19 | 1.45 | 1.03 | 1.44 | 1.43 | NA | NA | NA | NA | NA | 0.00 |
| 783 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 1.38 | 1.17 | 1.17 | 0.10 | 0.10 | 0.05 | 0.05 | 64 | 2.3 | 10.27 | 1.66 | 1.48 | 10.02 | 2.52 | NA | NA | NA | NA | NA | 0.00 |
| 763 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 1.16 | 0.96 | 0.96 | 0.08 | 0.08 | 0.04 | 0.04 | 64 | 92.65 | 98.58 | 1 | 1 | 1.02 | 2.57 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 2187 | 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 | 0.51 | 0.46 | 89.44 | 0.04 | 2.95 | 0.02 | 4.02 | 62 | 27.59 | 27.86 | 1 | 1 | 4 | 2.27 | NA | NA | NA | NA | NA | 0.00 |
| 2155 | libggml-cpu.so - kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c:96-262 [...] | kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | Innermost | 0.44 | 0.40 | 0.40 | 0.03 | 0.03 | 0.02 | 0.02 | 59 | 76.21 | 48.38 | 1 | 1.12 | 2.08 | 2.13 | 0 | 0 | 6 | 0 | 0 | 75.00 |
| 420 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.36 | 0.32 | 0.32 | 0.03 | 0.03 | 0.01 | 0.01 | 55 | 25 | 50 | 1 | 1 | 2 | 2.1 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 494 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.44 | 0.31 | 0.31 | 0.03 | 0.03 | 0.01 | 0.01 | 54 | 25 | 50 | 1 | 1 | 2 | 2.51 | 0 | 0 | 3 | 0 | 0 | 75.00 |
| 1163 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.36 | 0.31 | 0.31 | 0.03 | 0.03 | 0.01 | 0.01 | 57 | 98.46 | 98.47 | 1 | 1 | 1 | 2.26 | 0 | 0 | 1 | 0 | 0 | 75.00 |
| 2169 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:127-139 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | Innermost | 6.18 | 0.21 | 0.21 | 0.43 | 0.43 | 0.01 | 0.01 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.36 | 0.16 | 0.16 | 0.03 | 0.03 | 0.01 | 0.01 | 41 | 89.74 | 93.27 | 1 | 1 | 1 | 3.06 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 2165 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 4.87 | 0.16 | 0.16 | 0.34 | 0.34 | 0.01 | 0.01 | 1 | 0 | 21.76 | 1 | 1 | 2.27 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2052 | libggml-cpu.so - quants.c:2506-2575 [...] | ggml_vec_dot_q6_K_q8_K | Innermost | 0.15 | 0.14 | 0.14 | 0.01 | 0.01 | 0.01 | 0.01 | 43 | 49.44 | 34.59 | 1.06 | 1 | 2.22 | 1.54 | 3 | 4 | 2 | 0 | 0 | 94.44 |
| 793 | libggml-cpu.so - ops.cpp:6446-6457 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.15 | 0.09 | 0.09 | 0.01 | 0.01 | 0.00 | 0.00 | 29 | 42.86 | 33.93 | 1 | 1 | 1.68 | 1.61 | 1 | 0 | 0 | 15 | 0 | 53.13 |
| 2053 | libggml-cpu.so - quants.c:2492-2656 [...] | ggml_vec_dot_q6_K_q8_K | InBetween | 0.15 | 0.08 | 0.22 | 0.01 | 0.01 | 0.00 | 0.01 | 32 | 53.33 | 55.4 | 1.17 | 2.89 | 1.24 | 1.94 | 1 | 3 | 2 | 3 | 0 | 77.78 |
| 778 | libggml-cpu.so - ops.cpp:6210-6475 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.29 | 0.07 | 1.31 | 0.02 | 0.10 | 0.00 | 0.06 | 19 | 0 | 13.09 | 2.04 | 1.65 | 8.99 | 2.81 | NA | NA | NA | NA | NA | 0.00 |
| 779 | libggml-cpu.so - ops.cpp:6210-6407 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.22 | 0.07 | 1.24 | 0.02 | 0.10 | 0.00 | 0.06 | 19 | 0 | 14.77 | 2.59 | 1.27 | 6.55 | 2.11 | NA | NA | NA | NA | NA | 0.00 |
| 759 | libggml-cpu.so - vec.cpp:224-337 [...] | ggml_vec_dot_f16 | Outermost | 0.22 | 0.05 | 0.05 | 0.02 | 0.02 | 0.00 | 0.00 | 18 | 62.96 | 67.9 | 1.18 | 1 | 1.24 | 2.57 | NA | NA | NA | NA | NA | 0.00 |
| 2166 | libggml-cpu.so - kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c:107-154 [...] | kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | InBetween | 1.53 | 0.05 | 0.42 | 0.11 | 0.86 | 0.00 | 0.02 | 1 | 0 | 20.63 | 1 | 1 | 5.46 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1165 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_rms_norm | Innermost | 0.15 | 0.05 | 0.05 | 0.01 | 0.01 | 0.00 | 0.00 | 17 | 100 | 100 | 1 | 1 | 1 | 1.79 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1554 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.07 | 0.04 | 0.05 | 0.01 | 0.01 | 0.00 | 0.00 | 16 | 10.37 | 28.3 | 14.43 | 1.01 | 1.46 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1565 | libggml-cpu.so - simd-mappings.h:51-51 [...] | ggml_compute_forward_flash_attn_ext | Single | 0.07 | 0.02 | 0.02 | 0.00 | 0.00 | 0.00 | 0.00 | 7 | 0 | 16.41 | 1.13 | 1.13 | 6 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1566 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | Outermost | 0.15 | 0.01 | 1.37 | 0.01 | 0.06 | 0.00 | 0.06 | 5 | 0 | 33.19 | 6.67 | 1 | 1.92 | 1.67 | NA | NA | NA | NA | NA | 0.00 |
| 73 | libggml-cpu.so - ggml-cpu.c:1664-2898 [...] | ggml_graph_compute_thread | Outermost | 0.07 | 0.01 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 6 | 0 | 17.9 | 1 | 1 | 8.42 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 780 | libggml-cpu.so - ops.cpp:6210-6439 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.07 | 0.01 | 1.25 | 0.00 | 0.10 | 0.00 | 0.06 | 5 | 0 | 27.19 | 1 | 1 | 2.87 | 1 | NA | NA | NA | NA | NA | 0.00 |