| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime aocc_0 (%) | Exclusive Coverage aocc_0 (%) | Inclusive Coverage aocc_0 (%) | Max Exclusive Time Over Threads aocc_0 (s) | Max Inclusive Time Over Threads aocc_0 (s) | Exclusive Time w.r.t. Wall Time aocc_0 (s) | Inclusive Time w.r.t. Wall Time aocc_0 (s) | Nb Threads aocc_0 | GFLOPS aocc_0 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing aocc_0 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 531 | libggml-cpu.so - mmq.cpp:1570-1597 [...] | ggml_backend_amx_mul_mat(ggml_compute_params const*, ggml_tensor*)::$_1::operator()(int, int) const::{lambda()#1}::operator()() const | Single | 37.58 | 24.24 | 24.24 | 13.59 | 13.59 | 4.56 | 4.56 | 183 | 78.81 | NA | NA | NA | NA | NA | 2.88 | NA | NA | NA | NA | NA | 0.00 |
| 384 | libggml-cpu.so - mmq.cpp:303-1392 [...] | void parallel_for<(anonymous namespace)::convert_B_packed_format<block_q8_0, 32>(void*, block_q8_0 const*, int, int)::{lambda(int, int)#1}>(int, (anonymous namespace)::convert_B_packed_format<block_q8_0, 32>(void*, block_q8_0 const*, int,... | Innermost | 0.14 | 0.11 | 0.11 | 0.05 | 0.05 | 0.02 | 0.02 | 183 | 0.00 | 90.91 | 38.76 | 1.47 | 1 | 1.41 | 2.39 | 23 | 0 | 0 | 9 | 0 | 85.94 |
| 1232 | libggml-cpu.so - vec.cpp:311-316 | ggml_vec_dot_f16 | Single | 0.41 | 0.10 | 0.10 | 0.15 | 0.15 | 0.02 | 0.02 | 33 | 1168.45 | NA | NA | NA | NA | NA | 1.42 | NA | NA | NA | NA | NA | 0.00 |
| 2437 | libggml-cpu.so - vec.h:491-497 | ggml_compute_forward_flash_attn_ext | Innermost | 0.51 | 0.08 | 0.08 | 0.18 | 0.18 | 0.02 | 0.02 | 35 | 881.41 | NA | NA | NA | NA | NA | 2.14 | NA | NA | NA | NA | NA | 0.00 |
| 696 | libggml-cpu.so - mmq.cpp:520-2488 [...] | ggml_backend_amx_mul_mat(ggml_compute_params const*, ggml_tensor*)::$_2::operator()(int, int) const::{lambda()#1}::operator()() const | InBetween | 0.11 | 0.08 | 0.09 | 0.04 | 0.05 | 0.01 | 0.02 | 150 | 320.56 | NA | NA | NA | NA | NA | 2.14 | NA | NA | NA | NA | NA | 0.00 |
| 2421 | libggml-cpu.so - ops.cpp:8759-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.19 | 0.04 | 0.12 | 0.07 | 0.21 | 0.01 | 0.02 | 39 | 1508.62 | 20.85 | 14.01 | 2.87 | 1.57 | 1.68 | 2.08 | NA | NA | NA | NA | NA | 0.00 |
| 2113 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.11 | 0.04 | 0.04 | 0.04 | 0.04 | 0.01 | 0.01 | 192 | 577.43 | 1.96 | 6.62 | 1.01 | 1.14 | 4.06 | 6.05 | 1 | 2 | 0 | 0 | 0 | 100.00 |
| 108 | libggml-cpu.so - ggml-cpu.c:533-2891 [...] | ggml_graph_compute_thread | Single | 0.06 | 0.02 | 0.02 | 0.02 | 0.02 | 0.00 | 0.00 | 113 | 16.82 | 0 | 9.58 | 1 | 1 | 14.77 | 2.54 | NA | NA | NA | NA | NA | 0.00 |
| 2102 | libggml-cpu.so - ops.cpp:6365-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.06 | 0.01 | 0.02 | 0.02 | 0.04 | 0.00 | 0.00 | 164 | 48.82 | 0 | 9.9 | 3.16 | 3.56 | 28.06 | 6.63 | NA | NA | NA | NA | NA | 0.00 |
| 2419 | libggml-cpu.so - ops.cpp:8885-8886 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.07 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 28 | 0.00 | 0 | 6.25 | 1.33 | 1 | 16 | 2.09 | 0 | 2 | 0 | 0 | 1 | 66.67 |
| 3307 | libggml-cpu.so - quants.c:298-355 [...] | quantize_row_q8_0 | Single | 0.84 | 0.01 | 0.01 | 0.30 | 0.30 | 0.00 | 0.00 | 1 | 877.69 | 58.33 | 28.75 | 1 | 1.38 | 2.83 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 914 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.57 | 0.01 | 0.01 | 0.20 | 0.20 | 0.00 | 0.00 | 6 | 134.05 | 0 | 6.25 | 1 | 1.06 | 16 | 6 | 0 | 3 | 0 | 0 | 0 | 100.00 |
| 2105 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.06 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 32 | 390.18 | 72.73 | 19.13 | 1 | 1.43 | 4.56 | 3.76 | 1 | 2 | 0 | 1 | 0 | 87.50 |
| 1758 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.41 | 0.00 | 0.00 | 0.15 | 0.15 | 0.00 | 0.00 | 6 | 358.82 | 0 | 7.81 | 1 | 1.98 | 13.02 | 6 | 0 | 1 | 0 | 0 | 0 | 100.00 |
| 1236 | libggml-cpu.so - vec.h:1084-1116 [...] | ggml_vec_swiglu_f32 | Single | 0.35 | 0.00 | 0.00 | 0.13 | 0.13 | 0.00 | 0.00 | 1 | 7871.81 | 98 | 98.13 | 1.02 | 1 | 1 | 1 | 0.5 | 0 | 0 | 3 | 0 | 56.25 |
| 816 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.26 | 0.00 | 0.00 | 0.09 | 0.09 | 0.00 | 0.00 | 2 | 274.30 | 0 | 6.25 | 1 | 1.06 | 16 | 2 | 0 | 3 | 0 | 0 | 0 | 100.00 |
| 2992 | exec - sampling.cpp:125-126 [...] | common_sampler::set_logits(llama_context*, int) | Single | 0.21 | 0.00 | 0.00 | 0.07 | 0.07 | 0.00 | 0.00 | 1 | 0.00 | 0 | 6.25 | 3 | 1 | 16 | 1 | 1 | 1 | 2 | 0 | 0 | 87.50 |
| 2207 | libllama.so - stl_heap.h:139-262 [...] | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Outermost | 0.18 | 0.00 | 0.00 | 0.06 | 0.06 | 0.00 | 0.00 | 1 | 0.00 | 0 | 8.48 | 2.33 | 1 | 13.95 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2638 | libllama.so - hashtable.h:1840-1843 [...] | std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai... | Single | 0.06 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0.00 | 0 | 11.33 | 1 | 1 | 2.46 | 1 | NA | NA | NA | NA | NA | 0.00 |