| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime orig_0 (%) | Exclusive Coverage orig_0 (%) | Inclusive Coverage orig_0 (%) | Max Exclusive Time Over Threads orig_0 (s) | Max Inclusive Time Over Threads orig_0 (s) | Exclusive Time w.r.t. Wall Time orig_0 (s) | Inclusive Time w.r.t. Wall Time orig_0 (s) | Nb Threads orig_0 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing orig_0 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|
| 2220 | libggml-cpu.so - quants.c:979-1002 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 65.60 | 67.23 | 67.23 | 8.49 | 8.49 | 8.24 | 8.24 | 96 | NA | NA | NA | NA | NA | 1.06 | NA | NA | NA | NA | NA | 0.00 |
| 72 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Innermost | 1.08 | 0.47 | 0.47 | 0.14 | 0.14 | 0.06 | 0.06 | 82 | 0 | 50 | 1 | 1 | 1.08 | 2.16 | NA | NA | NA | NA | NA | 0.00 |
| 73 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 0.97 | 0.38 | 0.84 | 0.13 | 0.23 | 0.05 | 0.10 | 94 | 0 | 41.07 | 1 | 1 | 4 | 2.74 | NA | NA | NA | NA | NA | 0.00 |
| 56 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | InBetween | 0.39 | 0.17 | 0.33 | 0.05 | 0.08 | 0.02 | 0.04 | 94 | 0 | 50.29 | 1 | 1 | 1.27 | 2.38 | NA | NA | NA | NA | NA | 0.00 |
| 879 | libggml-cpu.so - vec.cpp:231-262 | ggml_vec_dot_f16 | Single | 0.81 | 0.15 | 0.15 | 0.11 | 0.11 | 0.02 | 0.02 | 32 | 100 | 100 | 1 | 1 | 1 | 1.9 | 0 | 0 | 0 | 14 | 0 | 50.00 |
| 1719 | libggml-cpu.so - vec.h:411-458 | ggml_compute_forward_flash_attn_ext | Innermost | 0.66 | 0.14 | 0.14 | 0.09 | 0.09 | 0.02 | 0.02 | 32 | 100 | 100 | 1 | 1 | 1 | 1.74 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 53 | libggml-cpu.so - ggml-cpu.c:1183-1194 [...] | ggml_compute_forward_mul_mat | Innermost | 0.31 | 0.13 | 0.13 | 0.04 | 0.04 | 0.02 | 0.02 | 91 | 0 | 52.17 | 1 | 1 | 1.7 | 2.5 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1711 | libggml-cpu.so - vec.h:282-662 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.54 | 0.11 | 0.13 | 0.07 | 0.08 | 0.01 | 0.02 | 32 | 16.83 | 57.18 | 3.04 | 1.03 | 1.34 | 1.72 | NA | NA | NA | NA | NA | 0.00 |
| 886 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 7.42 | 0.09 | 0.09 | 0.96 | 0.96 | 0.01 | 0.01 | 4 | 70.45 | 84.66 | 1 | 1 | 1.19 | 3.94 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 1408 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.23 | 0.08 | 0.08 | 0.03 | 0.03 | 0.01 | 0.01 | 84 | 15.38 | 32.69 | 1 | 1.64 | 3.27 | 2.67 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 2223 | libggml-cpu.so - quants.c:910-948 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 0.12 | 0.06 | 0.06 | 0.02 | 0.02 | 0.01 | 0.01 | 86 | 72.22 | 77.08 | 1.04 | 1 | 1.12 | 2.03 | 0 | 0 | 0 | 6 | 0 | 50.00 |
| 1714 | libggml-cpu.so - vec.h:282-725 [...] | ggml_compute_forward_flash_attn_ext | Outermost | 0.31 | 0.05 | 0.33 | 0.04 | 0.17 | 0.01 | 0.04 | 30 | 16.49 | 54.9 | 5.71 | 1 | 1.39 | 1.92 | NA | NA | NA | NA | NA | 0.00 |
| 2199 | libggml-cpu.so - quants.c:49-72 [...] | quantize_row_q8_0 | Innermost | 0.15 | 0.05 | 0.05 | 0.02 | 0.02 | 0.01 | 0.01 | 73 | 62.35 | 67.5 | 1.08 | 1.05 | 1.15 | 2.81 | NA | NA | NA | NA | NA | 0.00 |
| 54 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.12 | 0.03 | 0.03 | 0.02 | 0.02 | 0.00 | 0.00 | 54 | 0 | 55 | 1 | 1 | 1 | 2.1 | NA | NA | NA | NA | NA | 0.00 |
| 1722 | libggml-cpu.so - ops.cpp:8777-8919 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.12 | 0.02 | 0.02 | 0.02 | 0.02 | 0.00 | 0.00 | 23 | 0 | 51.47 | 80 | 1.14 | 1.6 | 1.86 | NA | NA | NA | NA | NA | 0.00 |
| 2198 | libggml-cpu.so - quants.c:49-72 [...] | quantize_row_q8_0 | Outermost | 0.08 | 0.01 | 0.06 | 0.01 | 0.02 | 0.00 | 0.01 | 30 | NA | NA | NA | NA | NA | 1.76 | NA | NA | NA | NA | NA | 0.00 |
| 520 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.77 | 0.01 | 0.01 | 0.10 | 0.10 | 0.00 | 0.00 | 1 | 0 | 28.95 | 1 | 1 | 4 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 413 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.70 | 0.01 | 0.01 | 0.09 | 0.09 | 0.00 | 0.00 | 1 | 0 | 30 | 1 | 1 | 4 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 1399 | libggml-cpu.so - ops.cpp:6210-6409 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.08 | 0.01 | 0.09 | 0.01 | 0.03 | 0.00 | 0.01 | 14 | 3.33 | 55.83 | 5.47 | 1.81 | 1.3 | 1.56 | NA | NA | NA | NA | NA | 0.00 |
| 1400 | libggml-cpu.so - ops.cpp:6210-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.08 | 0.01 | 0.11 | 0.01 | 0.04 | 0.00 | 0.01 | 16 | 10.26 | 45.51 | 5.05 | 1.53 | 1.22 | 1.88 | NA | NA | NA | NA | NA | 0.00 |
| 58 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Innermost | 0.08 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 14 | 0 | 50 | 1 | 1 | 2 | 1.65 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 1403 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.12 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 13 | 47.06 | 44.12 | 1.2 | 1.33 | 2.4 | 2.29 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 1249 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.62 | 0.01 | 0.01 | 0.08 | 0.08 | 0.00 | 0.00 | 1 | 94.12 | 97.06 | 1 | 1 | 1.03 | 1 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.12 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 12 | 97.5 | 98.75 | 1 | 1 | 1 | 2.4 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 3062 | exec - sampling.cpp:125-126 | common_sampler::set_logits(llama_context*, int) | Innermost | 0.31 | 0.00 | 0.00 | 0.04 | 0.04 | 0.00 | 0.00 | 1 | 75 | 87.5 | 1 | 1 | 1.1 | 1 | 0 | 1 | 0 | 1 | 0 | 75.00 |
| 59 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | InBetween | 0.04 | 0.00 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 8 | 0 | 53.57 | 1 | 1 | 1.54 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 2227 | libllama.so - stl_heap.h:140-263 [...] | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Outermost | 0.27 | 0.00 | 0.00 | 0.04 | 0.04 | 0.00 | 0.00 | 1 | 0 | 37.5 | 4.67 | 1 | 2.87 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 95 | libggml-cpu.so - ggml-cpu.cpp:39-63 [...] | ggml_backend_cpu_get_extra_buffer_types() | Single | 0.04 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 7 | 0 | 62.5 | 1 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1723 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_flash_attn_ext | Innermost | 0.04 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 6 | 100 | 100 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1318 | libggml-cpu.so - ops.cpp:5352-5517 [...] | ggml_compute_forward_get_rows | Outermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 5 | 0 | 57.5 | 1 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1710 | libggml-cpu.so - vec.h:474-662 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.08 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 3 | 12.24 | 55.1 | 16.23 | 1.01 | 1.35 | 1.5 | NA | NA | NA | NA | NA | 0.00 |
| 1418 | exec - regex_executor.tcc:180-513 [...] | std::__detail::_Executor<__gnu_cxx::__normal_iterator<char const*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::__cxx11::sub_match<__gnu_cxx::__normal_iterator<ch... | Single | 0.15 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 35.31 | 1 | 1 | 7.38 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1252 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_rms_norm | Innermost | 0.12 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 100 | 100 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2750 | libllama.so - hashtable.h:2627-2644 [...] | 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 | 0.08 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0.67 | 0 | 0 | 2 | 1 | 45.83 |
| 60 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Outermost | 0.04 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.00 | 2 | 0 | 50 | 1 | 1 | 2 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 2867 | libllama.so - new_allocator.h:172-172 [...] | 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 | 0.08 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 46.35 | 1 | 1 | 2.53 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 365 | libggml-cpu.so - traits.cpp:13-17 [...] | ggml_cpu_extra_compute_forward | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 1 | 0 | 2 | 0 | 74.38 |
| 2984 | libllama.so - hashtable.h:2077-2077 [...] | std::_Hashtable<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, unsigned char>, s... | Single | 0.08 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2229 | libllama.so - stl_heap.h:229-235 | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 33.85 | 1.33 | 1 | 4 | 1 | 0 | 0 | 0 | 4 | 0 | 50.00 |
| 120 | libggml-base.so - ggml-alloc.c:804-842 [...] | ggml_gallocr_alloc_graph | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 55 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Outermost | 0.04 | 0.00 | 0.33 | 0.01 | 0.06 | 0.00 | 0.04 | 1 | NA | NA | NA | NA | NA | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2567 | libllama.so - char_traits.h:381-381 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 48.08 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1725 | libggml-cpu.so - ops.cpp:8884-8885 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 87.5 | 81.25 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 100.00 |
| 2733 | libllama.so - hashtable.h:2077-2077 [...] | std::__detail::_Map_base<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, st... | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2609 | libllama.so - new_allocator.h:172-172 [...] | llama_decode_text(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 40.44 | 1 | 1 | 4.39 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1259 | libllama.so - ostream:578-673 [...] | gguf_kv_to_str[abi:cxx11](gguf_context const*, int) | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 42.38 | 1 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2578 | libllama.so - llama-vocab.cpp:1216-2608 [...] | llama_vocab::impl::init_tokenizer(llama_vocab_type) | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 16 | 58 | 3.42 | 1 | 1.05 | 1 | NA | NA | NA | NA | NA | 0.00 |
