| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime aocc_4 (%) | Exclusive Coverage aocc_4 (%) | Inclusive Coverage aocc_4 (%) | Max Exclusive Time Over Threads aocc_4 (s) | Max Inclusive Time Over Threads aocc_4 (s) | Exclusive Time w.r.t. Wall Time aocc_4 (s) | Inclusive Time w.r.t. Wall Time aocc_4 (s) | Nb Threads aocc_4 | GFLOPS aocc_4 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing aocc_4 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 548 | libggml-cpu.so - mmq.cpp:1570-1597 [...] | ggml_backend_amx_mul_mat(ggml_compute_params const*, ggml_tensor*)::$_1::operator()(int, int) const::{lambda()#1}::operator()() const | Single | 37.15 | 24.99 | 24.99 | 13.08 | 13.08 | 4.53 | 4.53 | 183 | 79.33 | NA | NA | NA | NA | NA | 2.79 | NA | NA | NA | NA | NA | 0.00 |
| 399 | libggml-cpu.so - mmq.cpp:303-1392 [...] | void parallel_for<(anonymous namespace)::convert_B_packed_format<block_q8_0, 32>(void*, block_q8_0 const*, int, int)::{lambda(int, int)#1}>(int, (anonymous namespace)::convert_B_packed_format<block_q8_0, 32>(void*, block_q8_0 const*, int,... | Innermost | 0.16 | 0.11 | 0.11 | 0.05 | 0.05 | 0.02 | 0.02 | 178 | 0.00 | 90.91 | 38.76 | 1.47 | 1 | 1.41 | 2.59 | 23 | 0 | 0 | 9 | 0 | 85.94 |
| 1232 | libggml-cpu.so - vec.cpp:311-316 | ggml_vec_dot_f16 | Single | 0.47 | 0.09 | 0.09 | 0.17 | 0.17 | 0.02 | 0.02 | 32 | 1325.00 | NA | NA | NA | NA | NA | 1.67 | NA | NA | NA | NA | NA | 0.00 |
| 713 | libggml-cpu.so - mmq.cpp:520-2488 [...] | ggml_backend_amx_mul_mat(ggml_compute_params const*, ggml_tensor*)::$_2::operator()(int, int) const::{lambda()#1}::operator()() const | InBetween | 0.14 | 0.08 | 0.09 | 0.05 | 0.05 | 0.02 | 0.02 | 150 | 329.15 | NA | NA | NA | NA | NA | 2.63 | NA | NA | NA | NA | NA | 0.00 |
| 2304 | libggml-cpu.so - vec.h:491-497 | ggml_compute_forward_flash_attn_ext | Innermost | 0.36 | 0.08 | 0.08 | 0.13 | 0.13 | 0.02 | 0.02 | 32 | 917.75 | NA | NA | NA | NA | NA | 1.41 | NA | NA | NA | NA | NA | 0.00 |
| 2294 | libggml-cpu.so - ops.cpp:8759-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.21 | 0.04 | 0.12 | 0.07 | 0.20 | 0.01 | 0.02 | 32 | 1547.59 | 18.59 | 12.3 | 2.43 | 1.6 | 9.79 | 1.8 | NA | NA | NA | NA | NA | 0.00 |
| 2015 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.09 | 0.04 | 0.04 | 0.03 | 0.03 | 0.01 | 0.01 | 192 | 581.05 | 0 | 6.25 | 1 | 1.12 | 4 | 4.65 | 1 | 2 | 0 | 0 | 0 | 100.00 |
| 117 | libggml-cpu.so - ggml-cpu.c:533-2891 [...] | ggml_graph_compute_thread | Single | 0.07 | 0.02 | 0.02 | 0.03 | 0.03 | 0.00 | 0.00 | 108 | 14.76 | 0 | 9.58 | 1 | 1 | 14.77 | 3.51 | NA | NA | NA | NA | NA | 0.00 |
| 2004 | libggml-cpu.so - ops.cpp:6365-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.07 | 0.01 | 0.02 | 0.03 | 0.03 | 0.00 | 0.00 | 166 | 46.22 | 0 | 9.87 | 4.2 | 3.1 | 25.84 | 9.12 | NA | NA | NA | NA | NA | 0.00 |
| 3150 | libggml-cpu.so - quants.c:298-355 [...] | quantize_row_q8_0 | Single | 0.85 | 0.01 | 0.01 | 0.30 | 0.30 | 0.00 | 0.00 | 1 | 888.56 | 60.7 | 29.66 | 1 | 1.31 | 2.68 | 1 | 0 | 2 | 0 | 0 | 0 | 100.00 |
| 2292 | libggml-cpu.so - ops.cpp:8885-8886 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.06 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 26 | 0.00 | 0 | 6.25 | 1.33 | 1 | 16 | 2.17 | 0 | 2 | 0 | 0 | 1 | 66.67 |
| 2007 | libggml-cpu.so - ops.cpp:6446-6457 | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.06 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 33 | 165.34 | 0 | 6.25 | 1 | 1.5 | 16 | 3 | 0 | 2 | 0 | 2 | 0 | 75.00 |
| 914 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.62 | 0.01 | 0.01 | 0.22 | 0.22 | 0.00 | 0.00 | 7 | 110.66 | 0 | 6.25 | 1 | 1.06 | 16 | 7 | 0 | 3 | 0 | 0 | 0 | 100.00 |
| 1240 | libggml-cpu.so - vec.h:1084-1115 [...] | ggml_vec_swiglu_f32 | Single | 0.45 | 0.00 | 0.00 | 0.16 | 0.16 | 0.00 | 0.00 | 7 | 6147.90 | 98 | 98.13 | 1 | 1 | 1 | 7 | 0.5 | 0 | 0 | 3 | 0 | 56.25 |
| 3069 | exec - sampling.cpp:125-126 [...] | common_sampler::set_logits(llama_context*, int) | Single | 0.26 | 0.00 | 0.00 | 0.09 | 0.09 | 0.00 | 0.00 | 1 | 0.00 | 0 | 6.25 | 3 | 1 | 16 | 1 | 1 | 1 | 8 | 0 | 0 | 80.00 |
| 826 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.23 | 0.00 | 0.00 | 0.08 | 0.08 | 0.00 | 0.00 | 1 | 343.39 | 0 | 6.25 | 1 | 1.06 | 16 | 1 | 0 | 3 | 0 | 0 | 0 | 100.00 |
| 2303 | libllama.so - stl_heap.h:139-262 [...] | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Outermost | 0.20 | 0.00 | 0.00 | 0.07 | 0.07 | 0.00 | 0.00 | 1 | 0.00 | 0 | 8.48 | 2.33 | 1 | 13.95 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2775 | libllama.so - hashtable.h:2386-2403 [...] | 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 | 11.93 | 1 | 1 | 2.46 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1734 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.06 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 3628.12 | 75 | 18.75 | 1 | 1.38 | 5.18 | 1 | 0 | 1 | 0 | 0 | 0 | 100.00 |