| 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 |
|---|
| 2275 | libggml-cpu.so - quants.c:1010-1027 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 76.55 | 80.34 | 80.34 | 14.67 | 14.67 | 14.59 | 14.59 | 64 | 53.85 | 61.3 | 1 | 1 | 1 | 1.03 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 86 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 1.04 | 0.32 | 0.49 | 0.20 | 0.28 | 0.06 | 0.09 | 63 | 0 | 19.42 | 1 | 1 | 10.67 | 3.52 | NA | NA | NA | NA | NA | 0.00 |
| 69 | libggml-cpu.so - ggml-cpu.c:1163-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.57 | 0.31 | 0.47 | 0.11 | 0.15 | 0.06 | 0.09 | 64 | 0 | 24.36 | 1 | 1 | 2 | 2.03 | NA | NA | NA | NA | NA | 0.00 |
| 1750 | libggml-cpu.so - ops.cpp:8793-8881 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.60 | 0.20 | 0.35 | 0.11 | 0.19 | 0.04 | 0.06 | 32 | 15.14 | 37.61 | 4.04 | 1 | 1.86 | 1.61 | NA | NA | NA | NA | NA | 0.00 |
| 85 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Innermost | 0.42 | 0.18 | 0.18 | 0.08 | 0.08 | 0.03 | 0.03 | 59 | 0 | 20.57 | 1 | 1 | 6.08 | 2.38 | NA | NA | NA | NA | NA | 0.00 |
| 65 | libggml-cpu.so - ggml-cpu.c:1183-1194 [...] | ggml_compute_forward_mul_mat | Innermost | 0.34 | 0.16 | 0.16 | 0.06 | 0.06 | 0.03 | 0.03 | 63 | 0 | 25 | 1 | 1 | 4 | 2.2 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 2276 | libggml-cpu.so - quants.c:910-948 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 0.18 | 0.15 | 0.15 | 0.04 | 0.04 | 0.03 | 0.03 | 64 | 13.89 | 27.08 | 1.04 | 1.14 | 4.41 | 1.31 | 0 | 0 | 0 | 6 | 0 | 50.00 |
| 1757 | libggml-cpu.so - vec.h:411-458 | ggml_compute_forward_flash_attn_ext | Innermost | 0.55 | 0.15 | 0.15 | 0.10 | 0.10 | 0.03 | 0.03 | 32 | 100 | 100 | 1 | 1 | 1 | 1.96 | 0 | 0 | 0 | 4 | 0 | 50.00 |
| 903 | libggml-cpu.so - vec.cpp:231-262 | ggml_vec_dot_f16 | Single | 0.47 | 0.14 | 0.14 | 0.09 | 0.09 | 0.03 | 0.03 | 32 | 96 | 97 | 1 | 1 | 1 | 1.78 | 0 | 0 | 0 | 16 | 0 | 50.00 |
| 2251 | libggml-cpu.so - quants.c:49-72 [...] | quantize_row_q8_0 | Innermost | 0.18 | 0.07 | 0.07 | 0.04 | 0.04 | 0.01 | 0.01 | 58 | 45.88 | 28.71 | 1.08 | 1.34 | 3.2 | 2.55 | NA | NA | NA | NA | NA | 0.00 |
| 1442 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.13 | 0.06 | 0.06 | 0.03 | 0.03 | 0.01 | 0.01 | 59 | 0 | 12.26 | 1 | 1.64 | 8.73 | 2.17 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 910 | libggml-cpu.so - vec.cpp:385-387 [...] | ggml_vec_swiglu_f32 | Single | 2.17 | 0.04 | 0.04 | 0.41 | 0.41 | 0.01 | 0.01 | 5 | 70.45 | 81.46 | 1 | 1 | 1.24 | 4.77 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 64 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.10 | 0.02 | 0.02 | 0.02 | 0.02 | 0.00 | 0.00 | 37 | 0 | 23.86 | 1 | 1 | 2 | 2.64 | NA | NA | NA | NA | NA | 0.00 |
| 2250 | libggml-cpu.so - quants.c:49-72 [...] | quantize_row_q8_0 | Outermost | 0.08 | 0.02 | 0.09 | 0.01 | 0.04 | 0.00 | 0.02 | 31 | NA | NA | NA | NA | NA | 2.21 | NA | NA | NA | NA | NA | 0.00 |
| 68 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.10 | 0.02 | 0.49 | 0.02 | 0.15 | 0.00 | 0.09 | 24 | 0 | 25 | 1 | 1 | 4 | 2.67 | NA | NA | NA | NA | NA | 0.00 |
| 1437 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.08 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 15 | 35.29 | 19.85 | 1.2 | 1.5 | 4.99 | 2.05 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.18 | 0.01 | 0.01 | 0.03 | 0.03 | 0.00 | 0.00 | 14 | 90.48 | 95.41 | 1 | 1 | 1.05 | 4.45 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1282 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.50 | 0.01 | 0.01 | 0.09 | 0.09 | 0.00 | 0.00 | 1 | 94.12 | 95.59 | 1 | 1 | 1.04 | 1 | 0 | 0 | 0 | 1 | 0 | 50.00 |
| 431 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.50 | 0.01 | 0.01 | 0.09 | 0.09 | 0.00 | 0.00 | 1 | 0 | 12.5 | 1 | 1 | 10.67 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 71 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Innermost | 0.05 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 16 | 0 | 25 | 1 | 1 | 2 | 1.78 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 1433 | libggml-cpu.so - ops.cpp:6210-6409 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.05 | 0.01 | 0.07 | 0.01 | 0.03 | 0.00 | 0.01 | 13 | 0 | 20.94 | 5.47 | 1.45 | 5.76 | 1.73 | NA | NA | NA | NA | NA | 0.00 |
| 541 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.39 | 0.01 | 0.01 | 0.08 | 0.08 | 0.00 | 0.00 | 1 | 0 | 11.84 | 1 | 1 | 10.67 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 67 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.05 | 0.00 | 0.49 | 0.01 | 0.15 | 0.00 | 0.09 | 9 | 0 | 25 | 1 | 1 | 4 | 1.8 | NA | NA | NA | NA | NA | 0.00 |
| 1744 | libggml-cpu.so - vec.h:282-725 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.03 | 0.00 | 0.36 | 0.01 | 0.19 | 0.00 | 0.07 | 9 | 4.26 | 30.35 | 40.28 | 1.01 | 1.61 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 73 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Outermost | 0.03 | 0.00 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 9 | 0 | 25 | 1 | 1 | 4 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 390 | libggml-cpu.so - traits.cpp:13-17 [...] | ggml_cpu_extra_compute_forward | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 7 | 0 | 25 | 1 | 1 | 4 | 1 | 0 | 0 | 1 | 2 | 0 | 62.19 |
| 2221 | libllama.so - stl_heap.h:140-263 [...] | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Outermost | 0.18 | 0.00 | 0.00 | 0.03 | 0.05 | 0.00 | 0.00 | 1 | 0 | 16.49 | 4.67 | 1 | 7 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1760 | libggml-cpu.so - vec.h:646-653 | ggml_compute_forward_flash_attn_ext | Innermost | 0.05 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 5 | 100 | 100 | 1 | 1 | 1 | 1.67 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1434 | libggml-cpu.so - ops.cpp:6210-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.03 | 0.00 | 0.08 | 0.01 | 0.04 | 0.00 | 0.01 | 4 | 7.69 | 21.07 | 5.05 | 1.7 | 6.85 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 72 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | InBetween | 0.05 | 0.00 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 3 | 0 | 25 | 1 | 1 | 4 | 1.5 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 3048 | exec - sampling.cpp:125-126 | common_sampler::set_logits(llama_context*, int) | Innermost | 0.10 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 62.5 | 56.25 | 1 | 1 | 1.47 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
| 2978 | 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 | 0.10 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 66 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Outermost | 0.03 | 0.00 | 0.52 | 0.00 | 0.11 | 0.00 | 0.09 | 3 | 0 | 20.74 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1344 | exec - stl_algobase.h:401-405 [...] | std::vector<std::__cxx11::sub_match<__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::__no... | Single | 0.08 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 19.63 | 1 | 1 | 5.97 | 1 | 0 | 0 | 2 | 0 | 0 | 75.00 |
| 2861 | 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 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 22.72 | 1 | 1 | 5.42 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2571 | libllama.so - basic_string.h:194-1084 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Single | 0.08 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 23.43 | 4.87 | 1 | 1.13 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1347 | 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 | 0.05 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 16.11 | 1 | 1 | 14.99 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1748 | libggml-cpu.so - ops.cpp:8885-8886 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 2 | 85.71 | 89.29 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 108 | libggml-cpu.so - ggml-cpu.cpp:39-63 [...] | ggml_backend_cpu_get_extra_buffer_types() | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 2 | 0 | 25 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2223 | libllama.so - stl_heap.h:229-235 | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Innermost | 0.05 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 14.91 | 1.33 | 1 | 10.67 | 1 | 0 | 0 | 0 | 4 | 0 | 50.00 |
| 2562 | libllama.so - llama-vocab.cpp:2298-2336 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | InBetween | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 20.23 | 1 | 1 | 8.64 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2744 | 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 | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | 0.67 | 0 | 0 | 2 | 1 | 45.83 |
| 252 | libggml-cpu.so - repack.cpp:1968-1981 [...] | ggml_backend_cpu_repack_buffer_type() | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2858 | libllama.so - new_allocator.h:172-172 [...] | llama_vocab::impl::~impl() | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 17.19 | 1 | 1 | 5.82 | 1 | 0 | 0 | 0 | 1.5 | 0 | 50.00 |
| 309 | libggml-base.so - ggml-quants.c:408-412 [...] | dequantize_row_q8_0 | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 34.69 | 26.28 | 1.13 | 1.12 | 3.14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 2603 | libllama.so - new_allocator.h:172-172 [...] | llama_decode_text(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 19.72 | 1 | 1 | 7.39 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2727 | 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 | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1352 | libggml-cpu.so - ops.cpp:5454-5454 | ggml_compute_forward_get_rows | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | NA | NA | 1 | NA | NA | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1283 | libggml-cpu.so - ops.cpp:4319-4365 [...] | ggml_compute_forward_rms_norm | InBetween | 0.03 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 6.32 | 28.8 | 3.8 | 1 | 1.89 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2743 | libllama.so - hashtable.h:2074-2077 [...] | 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 | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1359 | libllama.so - stl_tree.h:1947-1948 [...] | llama_kv_cache::apply_ubatch(llama_kv_cache::slot_info const&, llama_ubatch const&) | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 0 | 0 | 0 | 1 | 0 | 50.00 |
| 2568 | libllama.so - llama-vocab.cpp:2148-2289 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 21.76 | 1 | 1 | 6.97 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2222 | libllama.so - stl_heap.h:140-142 | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 14.58 | 1 | 1 | 8.62 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 2728 | libllama.so - hashtable.h:2627-2644 [...] | 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, int>, std::alloca... | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | 0.67 | 0 | 0 | 2 | 1 | 45.83 |
| 1255 | libllama.so - ostream:578-673 [...] | gguf_kv_to_str[abi:cxx11](gguf_context const*, int) | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 18.5 | 1 | 1 | 11.43 | 1 | NA | NA | NA | NA | NA | 0.00 |
