| Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime armclang_3 (%) | Exclusive Coverage armclang_3 (%) | Inclusive Coverage armclang_3 (%) | Max Exclusive Time Over Threads armclang_3 (s) | Max Inclusive Time Over Threads armclang_3 (s) | Exclusive Time w.r.t. Wall Time armclang_3 (s) | Inclusive Time w.r.t. Wall Time armclang_3 (s) | Nb Threads armclang_3 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing armclang_3 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
|---|
| 2416 | libggml-cpu.so - quants.c:1089-1112 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 69.50 | 70.99 | 70.99 | 7.77 | 7.77 | 7.49 | 7.49 | 96 | 53.85 | 63.46 | 1.2 | 1.08 | 1.42 | 1.06 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 72 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Innermost | 1.34 | 0.61 | 0.61 | 0.15 | 0.15 | 0.06 | 0.06 | 85 | 0 | 50 | 1 | 1 | 1.08 | 2.1 | NA | NA | NA | NA | NA | 0.00 |
| 73 | libggml-cpu.so - ggml-cpu.c:533-2897 [...] | ggml_graph_compute_thread | Outermost | 0.89 | 0.35 | 0.97 | 0.10 | 0.22 | 0.04 | 0.10 | 91 | 0 | 41.07 | 1 | 1 | 4 | 2.6 | NA | NA | NA | NA | NA | 0.00 |
| 908 | libggml-cpu.so - vec.cpp:311-316 | ggml_vec_dot_f16 | Single | 1.21 | 0.28 | 0.28 | 0.13 | 0.13 | 0.03 | 0.03 | 32 | 100 | 100 | 1 | 1 | 1 | 1.54 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 56 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | InBetween | 0.49 | 0.22 | 0.34 | 0.05 | 0.07 | 0.02 | 0.04 | 94 | 0 | 50.29 | 1 | 1 | 1.27 | 2.39 | NA | NA | NA | NA | NA | 0.00 |
| 1898 | libggml-cpu.so - ops.cpp:8792-8880 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.72 | 0.17 | 0.29 | 0.08 | 0.13 | 0.02 | 0.03 | 32 | 8.42 | 38.16 | 2.26 | 2.5 | 1.18 | 1.51 | NA | NA | NA | NA | NA | 0.00 |
| 1910 | libggml-cpu.so - vec.h:491-497 | ggml_compute_forward_flash_attn_ext | Innermost | 0.54 | 0.12 | 0.12 | 0.06 | 0.06 | 0.01 | 0.01 | 32 | 100 | 100 | 1 | 1 | 1 | 1.65 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 53 | libggml-cpu.so - ggml-cpu.c:1183-1194 [...] | ggml_compute_forward_mul_mat | Innermost | 0.18 | 0.08 | 0.08 | 0.02 | 0.02 | 0.01 | 0.01 | 84 | 0 | 52.17 | 1 | 1 | 1.7 | 2.01 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 1596 | libggml-cpu.so - ops.cpp:6220-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.31 | 0.06 | 0.06 | 0.04 | 0.04 | 0.01 | 0.01 | 68 | 27.27 | 36.36 | 1 | 1.88 | 3.05 | 3.84 | 2 | 0 | 0 | 1 | 0 | 83.33 |
| 2401 | libggml-cpu.so - ggml-impl.h:355-404 [...] | quantize_row_q8_0 | Single | 0.18 | 0.06 | 0.06 | 0.02 | 0.02 | 0.01 | 0.01 | 69 | 70.21 | 72.86 | 1.13 | 1.03 | 1.13 | 2.24 | 0 | 0 | 0 | 0 | 0 | 0.00 |
| 2417 | libggml-cpu.so - quants.c:910-948 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 0.13 | 0.04 | 0.04 | 0.02 | 0.02 | 0.00 | 0.00 | 65 | 81.25 | 84.38 | 1 | 1 | 1.16 | 2.38 | 0 | 0 | 0 | 7 | 0 | 50.00 |
| 54 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.18 | 0.04 | 0.04 | 0.02 | 0.02 | 0.00 | 0.00 | 53 | 0 | 55 | 1 | 1 | 1 | 2.72 | NA | NA | NA | NA | NA | 0.00 |
| 916 | libggml-cpu.so - vec.h:1045-1072 [...] | ggml_vec_swiglu_f32 | Innermost | 2.19 | 0.02 | 0.02 | 0.24 | 0.24 | 0.00 | 0.00 | 1 | 83.33 | 91.67 | 1.04 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 58 | 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 | 50 | 1 | 1 | 2 | 1.7 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 1588 | libggml-cpu.so - ops.cpp:6210-6484 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.09 | 0.01 | 0.09 | 0.01 | 0.03 | 0.00 | 0.01 | 17 | 0 | 43.5 | 1 | 1 | 2.74 | 1.7 | NA | NA | NA | NA | NA | 0.00 |
| 1591 | libggml-cpu.so - ops.cpp:6446-6456 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.18 | 0.01 | 0.01 | 0.02 | 0.02 | 0.00 | 0.00 | 15 | 66.67 | 47.22 | 1.07 | 1.58 | 2.31 | 3.16 | 0 | 1 | 0 | 2 | 0 | 66.67 |
| 541 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.67 | 0.01 | 0.01 | 0.07 | 0.07 | 0.00 | 0.00 | 2 | 0 | 28.95 | 1 | 1 | 4 | 1.87 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 437 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.45 | 0.01 | 0.01 | 0.05 | 0.05 | 0.00 | 0.00 | 1 | 0 | 30 | 1 | 1 | 4 | 1 | 0 | 0 | 0 | 3 | 0 | 50.00 |
| 59 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | InBetween | 0.04 | 0.00 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 8 | 0 | 53.57 | 1 | 1 | 1.54 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 0 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.04 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 7 | 97.22 | 98.61 | 1 | 1 | 1 | 1 | 2 | 0 | 0 | 0 | 0 | 100.00 |
| 2503 | 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 | 0.03 | 0.04 | 0.00 | 0.00 | 1 | 0 | 37.5 | 4.67 | 1 | 2.87 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1353 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.27 | 0.00 | 0.00 | 0.03 | 0.03 | 0.00 | 0.00 | 1 | 91.67 | 87.5 | 1 | 1 | 1.11 | 1 | 0 | 1 | 0 | 0 | 0 | 100.00 |
| 3374 | 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 | 0.22 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1895 | libggml-cpu.so - vec.h:375-751 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.09 | 0.00 | 0.29 | 0.01 | 0.13 | 0.00 | 0.03 | 3 | 0 | 47.6 | 2.01 | 1.34 | 1.34 | 1.2 | NA | NA | NA | NA | NA | 0.00 |
| 1587 | libggml-cpu.so - ops.cpp:6210-6462 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.04 | 0.00 | 0.07 | 0.01 | 0.02 | 0.00 | 0.01 | 5 | 6.58 | 52.3 | 5.92 | 1.7 | 1.35 | 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 | 0.35 | 0.01 | 0.04 | 0.00 | 0.04 | 4 | NA | NA | NA | NA | NA | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1916 | libggml-cpu.so - vec.h:677-682 | ggml_compute_forward_flash_attn_ext | Innermost | 0.04 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 4 | 100 | 100 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 100.00 |
| 3379 | exec - sampling.cpp:125-126 | common_sampler::set_logits(llama_context*, int) | Single | 0.18 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 75 | 87.5 | 1 | 1 | 1.1 | 1 | 0 | 1 | 0 | 1 | 0 | 75.00 |
| 3227 | 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 | 0.13 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 299 | libggml-cpu.so - repack.cpp:1968-1981 [...] | ggml_backend_cpu_repack_buffer_type() | Single | 0.04 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 3 | 0 | 62.5 | 1 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 60 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Outermost | 0.04 | 0.00 | 0.02 | 0.00 | 0.00 | 0.00 | 0.00 | 2 | 0 | 50 | 1 | 1 | 2 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 1487 | 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 | 0.09 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 35.31 | 1 | 1 | 7.38 | 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 | 2 | 0 | 62.5 | 1 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 407 | 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 |
| 3085 | 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 | 0.09 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1894 | libggml-cpu.so - ops.cpp:8884-8885 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.04 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 87.5 | 81.25 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 100.00 |
| 3224 | libllama.so - new_allocator.h:172-172 [...] | llama_vocab::impl::~impl() | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 45.83 | 1 | 1 | 1.7 | 1 | 0 | 0 | 0 | 1.5 | 0 | 50.00 |
| 483 | libllama.so - llama-batch.cpp:95-100 | llama_batch_allocr::init(llama_batch const&, llama_vocab const&, llama_memory_i const*, unsigned int, unsigned int, bool) | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 33.33 | 1 | 1 | 3.64 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
| 1317 | libggml-cpu.so - ops.cpp:4319-4365 [...] | ggml_compute_forward_rms_norm | InBetween | 0.04 | 0.00 | 0.00 | 0.00 | 0.04 | 0.00 | 0.00 | 1 | 3.94 | 56.1 | 3.45 | 1.14 | 1.35 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 2505 | 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 | 35.71 | 6 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 427 | libllama.so - stl_tree.h:1963-1964 [...] | LLM_TN_IMPL::str[abi:cxx11]() const | 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 | 1 | 0 | 50.00 |
| 490 | libllama.so - new_allocator.h:172-172 [...] | llama_batch_allocr::clear() | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 47.5 | 1 | 1 | 2.29 | 1 | 0 | 0 | 0 | 1 | 0 | 50.00 |
| 1355 | libggml-cpu.so - ops.cpp:4319-4338 [...] | ggml_compute_forward_rms_norm | InBetween | 0.04 | 0.00 | 0.00 | 0.00 | 0.03 | 0.00 | 0.00 | 1 | 8.35 | 51.92 | 1.82 | 1.24 | 1.48 | 1 | 0 | 0 | 0 | 2.33 | 0 | 50.00 |
| 3083 | 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 | 0.04 | 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 |
| 2868 | libllama.so - llama-vocab.cpp:2310-2348 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | InBetween | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 42.36 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1136 | exec - basic_string.h:198-433 [...] | std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >* std::__do_uninit_copy<__gnu_cxx::__normal_iterator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > co... | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 42.05 | 1 | 1 | 3.17 | 1 | NA | NA | NA | NA | NA | 0.00 |
| 1484 | 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 | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 35.42 | 1 | 1 | 3.01 | 1 | 0 | 0 | 2 | 0 | 0 | 75.00 |
| 2504 | libllama.so - stl_heap.h:140-142 | 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 | 37.5 | 1 | 1 | 3.29 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
| 1014 | libggml-base.so - new_allocator.h:172-172 [...] | void std::_Destroy_aux<false>::__destroy<gguf_kv*>(gguf_kv*, gguf_kv*) | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 0.5 | 0 | 0 | 75.00 |
| 2478 | libllama.so - llama-sampling.cpp:364-451 [...] | llama_sampler_chain_accept(llama_sampler*, int) | Single | 0.04 | 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 |
| 2874 | libllama.so - llama-vocab.cpp:2160-2301 [...] | 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 | 44.79 | 1 | 1 | 4.52 | 1 | NA | NA | NA | NA | NA | 0.00 |
