| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime armclang_4 (%) | Exclusive Coverage armclang_4 (%) | Inclusive Coverage armclang_4 (%) | Max Exclusive Time Over Threads armclang_4 (s) | Max Inclusive Time Over Threads armclang_4 (s) | Exclusive Time w.r.t. Wall Time armclang_4 (s) | Inclusive Time w.r.t. Wall Time armclang_4 (s) | Nb Threads armclang_4 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing armclang_4 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|
| 2365 | libggml-cpu.so - quants.c:1089-1112 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 77.48 | 79.49 | 79.49 | 13.25 | 13.25 | 12.86 | 12.86 | 64 | 50 | 34.82 | 1.2 | 1.33 | 2.25 | 1.07 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 58 | libggml-cpu.so - ggml-cpu.c:1163-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.76 | 0.27 | 0.38 | 0.13 | 0.15 | 0.04 | 0.06 | 64 | 0 | 25.51 | 1 | 1 | 2 | 3.03 | NA | NA | NA | NA | NA | 0.00 |
| 75 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 0.53 | 0.24 | 0.43 | 0.09 | 0.14 | 0.04 | 0.07 | 61 | 0 | 20.54 | 1 | 1 | 8 | 2.32 | NA | NA | NA | NA | NA | 0.00 |
| 74 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Innermost | 0.47 | 0.20 | 0.20 | 0.08 | 0.08 | 0.03 | 0.03 | 51 | 0 | 25 | 1 | 1 | 5.4 | 2.07 | NA | NA | NA | NA | NA | 0.00 |
| 1840 | libggml-cpu.so - vec.h:375-751 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.73 | 0.18 | 0.34 | 0.13 | 0.19 | 0.03 | 0.06 | 32 | 5.65 | 21.88 | 2.25 | 1.96 | 1.23 | 2.16 | NA | NA | NA | NA | NA | 0.00 |
| 2366 | libggml-cpu.so - quants.c:910-948 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 0.20 | 0.17 | 0.17 | 0.04 | 0.04 | 0.03 | 0.03 | 64 | 81.25 | 42.19 | 1 | 1.07 | 2.44 | 1.32 | 0 | 0 | 0 | 7 | 0 | 50.00 |
| 1852 | libggml-cpu.so - vec.h:491-497 | ggml_compute_forward_flash_attn_ext | Innermost | 0.44 | 0.16 | 0.16 | 0.07 | 0.07 | 0.03 | 0.03 | 32 | 100 | 80 | 1 | 2 | 1 | 1.54 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 857 | libggml-cpu.so - vec.cpp:311-316 | ggml_vec_dot_f16 | Single | 0.47 | 0.15 | 0.15 | 0.08 | 0.08 | 0.02 | 0.02 | 32 | 100 | 75 | 1 | 2 | 1.22 | 1.68 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 2350 | libggml-cpu.so - ggml-impl.h:355-404 [...] | quantize_row_q8_0 | Single | 0.26 | 0.10 | 0.10 | 0.05 | 0.05 | 0.02 | 0.02 | 61 | 70.21 | 39.74 | 1.13 | 1.33 | 1.89 | 2.67 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 54 | libggml-cpu.so - ggml-cpu.c:1183-1194 [...] | ggml_compute_forward_mul_mat | Innermost | 0.20 | 0.10 | 0.10 | 0.04 | 0.04 | 0.02 | 0.02 | 61 | 0 | 27.27 | 1 | 1 | 4 | 2.08 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1536 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.15 | 0.06 | 0.06 | 0.03 | 0.03 | 0.01 | 0.01 | 54 | 27.27 | 18.18 | 1 | 2 | 6.1 | 2.14 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 53 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.09 | 0.04 | 0.04 | 0.02 | 0.02 | 0.01 | 0.01 | 45 | 0 | 26.52 | 1 | 1 | 2 | 1.85 | NA | NA | NA | NA | NA | 0.00 |
| 865 | libggml-cpu.so - vec.h:1045-1072 [...] | ggml_vec_swiglu_f32 | Single | 1.46 | 0.02 | 0.02 | 0.25 | 0.25 | 0.00 | 0.00 | 1 | 85.42 | 46.35 | 1.03 | 1.38 | 1.66 | 1 | 2 | 1 | 0 | 0 | 0 | 100.00 |
| 57 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.09 | 0.01 | 0.39 | 0.01 | 0.15 | 0.00 | 0.06 | 22 | 0 | 25 | 1 | 1 | 4 | 2.2 | NA | NA | NA | NA | NA | 0.00 |
| 60 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Innermost | 0.09 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 23 | 0 | 25 | 1 | 1 | 2 | 2.38 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 1531 | 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 | 16 | 54.55 | 23.86 | 1.07 | 1.61 | 4.62 | 2.67 | 0 | 1 | 0 | 2 | 0 | 66.67 |
| 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 | 7 | 97.22 | 50.69 | 1 | 1.03 | 2 | 2.55 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 61 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | InBetween | 0.06 | 0.00 | 0.02 | 0.01 | 0.02 | 0.00 | 0.00 | 9 | 0 | 26.79 | 1 | 1 | 3.72 | 1.8 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 1527 | libggml-cpu.so - ops.cpp:6210-6462 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.03 | 0.00 | 0.07 | 0.01 | 0.03 | 0.00 | 0.01 | 9 | 6.58 | 26.15 | 5.92 | 1.45 | 4.21 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1858 | libggml-cpu.so - vec.h:677-682 | ggml_compute_forward_flash_attn_ext | Innermost | 0.06 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 8 | 100 | 75 | 1 | 2 | 1.13 | 1.78 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1528 | 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 | 0.03 | 0.00 | 0.01 | 8 | 0 | 21.75 | 1 | 1 | 4.8 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 56 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.03 | 0.00 | 0.40 | 0.01 | 0.16 | 0.00 | 0.06 | 7 | 0 | 25 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 484 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.20 | 0.00 | 0.00 | 0.03 | 0.03 | 0.00 | 0.00 | 1 | 0 | 14.47 | 1 | 1 | 8 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 380 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.20 | 0.00 | 0.00 | 0.03 | 0.03 | 0.00 | 0.00 | 1 | 0 | 15 | 1 | 1 | 8 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 347 | libggml-cpu.so - traits.cpp:13-17 [...] | ggml_cpu_extra_compute_forward | Single | 0.06 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 6 | 0 | 25 | 1 | 1 | 4 | 1.71 | 0 | 1 | 0 | 2 | 0 | 74.38 |
| 2499 | 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 | 0.03 | 0.00 | 0.00 | 1 | 0 | 18.75 | 4.67 | 1 | 5.74 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 55 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Outermost | 0.03 | 0.00 | 0.43 | 0.00 | 0.12 | 0.00 | 0.07 | 5 | 0 | 23.11 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1295 | libggml-cpu.so - vec.h:677-682 | ggml_compute_forward_rms_norm | Innermost | 0.12 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 100 | 75 | 1 | 2 | 1.13 | 1 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1294 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.09 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 91.67 | 47.92 | 1 | 1.25 | 2.22 | 1 | 0 | 1 | 0 | 0 | 0 | 100.00 |
| 3373 | 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 | 0.09 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 3223 | 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 | 0.06 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1837 | libggml-cpu.so - vec.h:375-751 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.03 | 0.00 | 0.35 | 0.01 | 0.09 | 0.00 | 0.06 | 2 | 0 | 25.77 | 2.01 | 1.34 | 1.34 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1446 | libggml-cpu.so - vec.h:89-89 | ggml_compute_forward_get_rows | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 66.67 | 75 | 1 | 1 | 1.14 | 1 | 0 | 2 | 0 | 0 | 0 | 100.00 |
| 62 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Outermost | 0.03 | 0.00 | 0.02 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 2873 | libllama.so - new_allocator.h:172-172 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 7.92 | 24.94 | 4.87 | 1 | 1.13 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 3346 | exec - sampling.cpp:125-126 | common_sampler::set_logits(llama_context*, int) | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 75 | 62.5 | 1 | 1 | 1.37 | 1 | 0 | 1 | 0 | 1 | 0 | 75.00 |
| 1259 | libggml-cpu.so - ops.cpp:4319-4365 [...] | ggml_compute_forward_rms_norm | Outermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 7.41 | 31.02 | 2.4 | 1 | 3.35 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1438 | libggml-cpu.so - ops.cpp:5352-5517 [...] | ggml_compute_forward_get_rows | Outermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 28.75 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 541 | libllama.so - stl_algobase.h:401-456 [...] | std::vector<bool, std::allocator<bool> >::_M_fill_insert(std::_Bit_iterator, unsigned long, bool) | InBetween | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 1.32 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 3081 | 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... | Innermost | 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 |
| 1395 | libllama.so - ostream:578-673 [...] | gguf_kv_to_str[abi:cxx11](gguf_context const*, int) | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 21.19 | 1 | 1 | 9.49 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1357 | exec - regex_executor.tcc:47-88 [...] | 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 | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 22.81 | 1 | 1 | 5.27 | 1 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 3220 | 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 | 22.92 | 1 | 1 | 5.07 | 1 | 0 | 0 | 0 | 1.5 | 0 | 50.00 |
| 2864 | 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 | 21.18 | 1 | 1 | 7.03 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 3073 | libllama.so - stl_uninitialized.h:642-642 [...] | std::vector<llama_vocab::token_data, std::allocator<llama_vocab::token_data> >::_M_default_append(unsigned long) | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 39.29 | 1 | 1 | 2.4 | 1 | 0 | 0 | 0 | 1 | 0 | 50.00 |
| 1991 | libllama.so - stl_tree.h:1963-1964 [...] | std::_Rb_tree<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, llama_model_loader::ll... | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 22.37 | 1 | 1 | 5.23 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1387 | 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 | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 17.66 | 1 | 1 | 14.77 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2863 | libllama.so - char_traits.h:381-381 [...] | 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 | 24.04 | 1 | 1 | 8 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 3079 | 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 |
| 2870 | 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 | 22.39 | 1 | 1 | 6.92 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 97 | libggml-cpu.so - ggml-cpu.cpp:39-63 [...] | ggml_backend_cpu_get_extra_buffer_types() | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 31.25 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1472 | libllama.so - llama-kv-cache.cpp:556-557 [...] | llama_kv_cache::prepare(std::vector<llama_ubatch, std::allocator<llama_ubatch> > const&) | InBetween | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 7.24 | 27.45 | 4.54 | 1 | 1.48 | 1 | NA | NA | NA | NA | NA | 0.00 |
