Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime gcc_3 (%) | Exclusive Coverage gcc_3 (%) | Inclusive Coverage gcc_3 (%) | Max Exclusive Time Over Threads gcc_3 (s) | Max Inclusive Time Over Threads gcc_3 (s) | Exclusive Time w.r.t. Wall Time gcc_3 (s) | Inclusive Time w.r.t. Wall Time gcc_3 (s) | Nb Threads gcc_3 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing gcc_3 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
---|
351 | libggml-cpu.so - quants.c:322-329 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 62.61 | 66.11 | 66.11 | 8.04 | 8.04 | 7.92 | 7.92 | 96 | 53.33 | 61.67 | 1.05 | 2.09 | 1.48 | 1.04 | 0 | 0 | 4 | 2 | 0 | 66.67 |
74 | libggml-cpu.so - ggml-cpu.c:2879-2898 [...] | ggml_graph_compute_thread | Innermost | 0.47 | 0.20 | 0.20 | 0.06 | 0.06 | 0.02 | 0.02 | 93 | 0 | 48.33 | 1 | 1 | 1.28 | 2.51 | NA | NA | NA | NA | NA | 0.00 |
1613 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.74 | 0.17 | 0.24 | 0.10 | 0.12 | 0.02 | 0.03 | 32 | 42.45 | 57.6 | 4.33 | 1.03 | 1.2 | 1.63 | NA | NA | NA | NA | NA | 0.00 |
788 | libggml-cpu.so - vec.cpp:311-311 [...] | ggml_vec_dot_f16 | Single | 0.93 | 0.16 | 0.16 | 0.12 | 0.12 | 0.02 | 0.02 | 32 | 100 | 100 | 1 | 1 | 1 | 2.18 | 0 | 0 | 4 | 6 | 0 | 60.00 |
75 | libggml-cpu.so - ggml-cpu.c:1664-2898 [...] | ggml_graph_compute_thread | Outermost | 0.27 | 0.14 | 0.34 | 0.04 | 0.09 | 0.02 | 0.04 | 94 | 0 | 37.5 | 1 | 1 | 4 | 2.04 | NA | NA | NA | NA | NA | 0.00 |
573 | libggml-base.so - ggml-quants.c:203-219 [...] | quantize_row_q8_0_ref | Innermost | 0.27 | 0.12 | 0.12 | 0.04 | 0.04 | 0.01 | 0.01 | 88 | 33.33 | 50.15 | 2.19 | 1.02 | 1.38 | 2.3 | NA | NA | NA | NA | NA | 0.00 |
64 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.27 | 0.11 | 0.11 | 0.04 | 0.04 | 0.01 | 0.01 | 87 | 0 | 55.94 | 1 | 1 | 1.5 | 2.46 | NA | NA | NA | NA | NA | 0.00 |
820 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.27 | 0.07 | 0.07 | 0.04 | 0.04 | 0.01 | 0.01 | 76 | 2.22 | 26.94 | 1.66 | 1.48 | 3.88 | 3.22 | NA | NA | NA | NA | NA | 0.00 |
65 | libggml-cpu.so - ggml-cpu.c:1125-1397 [...] | ggml_compute_forward_mul_mat | Outermost | 0.19 | 0.05 | 0.25 | 0.03 | 0.06 | 0.01 | 0.03 | 64 | 0 | 100 | 1 | 1 | 1 | 2.88 | NA | NA | NA | NA | NA | 0.00 |
1622 | libggml-cpu.so - vec.h:491-491 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.31 | 0.05 | 0.05 | 0.04 | 0.04 | 0.01 | 0.01 | 32 | 100 | 100 | 1 | 1 | 1 | 2.35 | 1 | 0 | 4 | 4 | 0 | 66.67 |
60 | libggml-cpu.so - ggml-cpu.c:1193-1194 | ggml_compute_forward_mul_mat | Innermost | 0.16 | 0.04 | 0.04 | 0.02 | 0.02 | 0.01 | 0.01 | 59 | 0 | 45 | 1 | 1 | 2.94 | 2.51 | 1 | 0 | 0 | 0 | 0 | 100.00 |
66 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.16 | 0.04 | 0.04 | 0.02 | 0.02 | 0.00 | 0.00 | 56 | 0 | 58.15 | 1 | 1 | 1.75 | 2.46 | NA | NA | NA | NA | NA | 0.00 |
794 | libggml-cpu.so - vec.cpp:390-390 [...] | ggml_vec_swiglu_f32 | Innermost | 2.34 | 0.03 | 0.03 | 0.30 | 0.30 | 0.00 | 0.00 | 1 | 93.94 | 98.48 | 1.07 | 1 | 1 | 1 | 0 | 3 | 0 | 0 | 0 | 100.00 |
785 | libggml-cpu.so - vec.cpp:311-337 [...] | ggml_vec_dot_f16 | Outermost | 0.23 | 0.02 | 0.02 | 0.03 | 0.03 | 0.00 | 0.00 | 20 | 31.54 | 49.52 | 2.1 | 1.14 | 1.64 | 2.5 | NA | NA | NA | NA | NA | 0.00 |
72 | libggml-cpu.so - ggml-cpu.c:1290-1297 | ggml_compute_forward_mul_mat | InBetween | 0.08 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 25 | 0 | 53.62 | 1 | 1 | 1.98 | 1.92 | 1 | 0 | 0 | 1 | 0 | 75.00 |
1612 | libggml-cpu.so - ops.cpp:8818-8826 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.08 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 18 | 0 | 42.86 | 10.67 | 1 | 4 | 1.8 | NA | NA | NA | NA | NA | 0.00 |
816 | libggml-cpu.so - ops.cpp:6210-6407 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.08 | 0.01 | 0.08 | 0.01 | 0.03 | 0.00 | 0.01 | 17 | 0.68 | 36.6 | 2.58 | 1.3 | 1.8 | 1.79 | NA | NA | NA | NA | NA | 0.00 |
815 | libggml-cpu.so - ops.cpp:6210-6475 [...] | 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 | 17 | 0 | 32.41 | 2.04 | 1.51 | 1.66 | 1.89 | NA | NA | NA | NA | NA | 0.00 |
830 | libggml-cpu.so - ops.cpp:6446-6457 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.12 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 13 | 42.86 | 57.14 | 1 | 1 | 2 | 2.17 | 1 | 0 | 0 | 15 | 0 | 53.13 |
1615 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.12 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 12 | 0 | 43.7 | 2.48 | 1.24 | 1.82 | 2.25 | NA | NA | NA | NA | NA | 0.00 |
515 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.55 | 0.01 | 0.01 | 0.07 | 0.07 | 0.00 | 0.00 | 2 | 100 | 100 | 1 | 1 | 1 | 1.87 | 0 | 0 | 3 | 0 | 0 | 75.00 |
821 | libggml-cpu.so - ops.cpp:6210-6490 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.08 | 0.01 | 0.10 | 0.01 | 0.03 | 0.00 | 0.01 | 11 | 19.23 | 43.27 | 1.56 | 1 | 1.5 | 1.69 | NA | NA | NA | NA | NA | 0.00 |
4449 | exec - sampling.cpp:125-126 [...] | common_sampler_sample(common_sampler*, llama_context*, int, bool) | Innermost | 0.51 | 0.01 | 0.01 | 0.06 | 0.06 | 0.00 | 0.00 | 1 | 16.13 | 32.26 | 1.5 | 1 | 4 | 1 | 0 | 0 | 2 | 9 | 0 | 54.55 |
1 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.08 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 12 | 100 | 100 | 1 | 1 | 1 | 1.85 | 2 | 0 | 0 | 0 | 0 | 100.00 |
572 | libggml-base.so - ggml-quants.c:203-219 [...] | quantize_row_q8_0_ref | InBetween | 0.04 | 0.00 | 0.12 | 0.01 | 0.03 | 0.00 | 0.01 | 11 | 0 | 25 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
431 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.39 | 0.00 | 0.00 | 0.05 | 0.05 | 0.00 | 0.00 | 1 | 100 | 100 | 1 | 1 | 1 | 1 | 0 | 0 | 3 | 0 | 0 | 75.00 |
1617 | libggml-cpu.so - vec.h:677-677 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.08 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 5 | 100 | 100 | 1 | 1 | 1 | 1.25 | 0 | 0 | 1 | 3 | 0 | 56.25 |
1193 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.23 | 0.00 | 0.00 | 0.03 | 0.03 | 0.00 | 0.00 | 1 | 100 | 91.11 | 1 | 1 | 1.11 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
103 | libggml-cpu.so - ggml-cpu.cpp:61-64 | ggml_backend_cpu_get_extra_buffer_types() | Single | 0.08 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 5 | 0 | 100 | 1 | 1 | 1 | 1.67 | NA | NA | NA | NA | NA | 0.00 |
62 | libggml-cpu.so - ggml-cpu.c:1397-1397 | ggml_compute_forward_mul_mat | Innermost | 0.04 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 6 | NA | NA | NA | NA | NA | 1 | NA | NA | NA | NA | NA | 0.00 |
67 | libggml-cpu.so - ggml-cpu.c:1132-1165 [...] | ggml_compute_forward_mul_mat | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 6 | 0 | 45.31 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
3550 | libllama.so - stl_algo.h:1594-1595 [...] | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Innermost | 0.19 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 30.83 | 2.17 | 1 | 3.06 | 1 | 1.5 | 0.5 | 0.5 | 0 | 0 | 93.75 |
1614 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.08 | 0.00 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 3 | 45.86 | 64.57 | 4.46 | 1.02 | 1.08 | 1.5 | NA | NA | NA | NA | NA | 0.00 |
1611 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | Outermost | 0.04 | 0.00 | 0.24 | 0.00 | 0.09 | 0.00 | 0.03 | 3 | 0 | 30.77 | 3.22 | 1.34 | 4.25 | 1 | NA | NA | NA | NA | NA | 0.00 |
1197 | libggml-cpu.so - vec.h:677-677 [...] | ggml_compute_forward_rms_norm | Innermost | 0.08 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 100 | 100 | 1 | 1 | 1 | 1 | 0 | 0 | 1 | 3 | 0 | 56.25 |
4616 | libllama.so - basic_string.h:1077-3760 [...] | 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... | Innermost | 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 | 0 | 61.11 |
3847 | libllama.so - basic_string.h:1077-3760 [...] | 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 | NA | NA | NA | NA | NA | 0.00 |
238 | libggml-cpu.so - repack.cpp:1979-1982 | ggml_backend_cpu_repack_buffer_type() | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2 | 0 | 75 | 1 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
35 | libggml-base.so - ggml.c:1363-1388 [...] | ggml_is_contiguous_0 | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2 | 0 | 48.53 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
3912 | libllama.so - hashtable_policy.h:387-2058 [...] | llama_vocab::~llama_vocab() | 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 |
4210 | libllama.so - basic_string.h:1077-3760 [...] | 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 | 0.67 | 0 | 0 | 2 | 0 | 61.11 |
1693 | libllama.so - basic_string.h:198-2708 [...] | replace_all(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<... | Outermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 60.21 | 1 | 1 | 1.36 | 1 | NA | NA | NA | NA | NA | 0.00 |
1281 | libggml-cpu.so - ops.cpp:5551-5563 | ggml_compute_forward_set_rows | InBetween | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 59.64 | 1 | 1 | 1.58 | 1 | NA | NA | NA | NA | NA | 66.67 |
1903 | libllama.so - llama-kv-cache.cpp:1239-1261 [...] | llama_kv_cache::set_input_kq_mask(ggml_tensor*, llama_ubatch const*, bool) const | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 34.77 | 4.25 | 1 | 5.23 | 1 | NA | NA | NA | NA | NA | 0.00 |
330 | exec - stl_uninitialized.h:119-119 [...] | 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... | Outermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 56.5 | 1 | 1 | 1.5 | 1 | NA | NA | NA | NA | NA | 0.00 |
817 | libggml-cpu.so - ops.cpp:6210-6439 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.04 | 0.00 | 0.08 | 0.00 | 0.02 | 0.00 | 0.01 | 1 | 0 | 53.19 | 1 | 1 | 1.66 | 1 | NA | NA | NA | NA | NA | 0.00 |
1624 | libggml-cpu.so - vec.h:740-740 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 100 | 100 | 1 | 1 | 1 | 1 | 0 | 0 | 1 | 3 | 0 | 56.25 |
334 | 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 | 36 | 1 | 1 | 2.82 | 1 | 0 | 0 | 3 | 2 | 0 | 65.00 |
1905 | libllama.so - stl_algobase.h:951-952 | llama_kv_cache::set_input_kq_mask(ggml_tensor*, llama_ubatch const*, bool) const | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 100 | 100 | 1 | 1 | 1 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
4053 | libllama.so - char_traits.h:381-381 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 11.11 | 36.57 | 3 | 1 | 5.45 | 1 | NA | NA | NA | NA | NA | 0.00 |
4419 | libllama.so - unicode.cpp:799-811 [...] | unicode_cpts_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 61.11 | 1 | 1 | 1 | 1 | NA | NA | NA | NA | NA | 0.00 |
4238 | 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 | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 4 | 1 | 40.00 |
1171 | libggml-base.so - stl_uninitialized.h:642-642 [...] | bool gguf_read_emplace_helper<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >(gguf_reader const&, std::vector<gguf_kv, std::allocator<gguf_kv> >&, std::__cxx11::basic_string<c... | Single | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
4071 | libllama.so - llama-vocab.cpp:1575-2004 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Outermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 48.68 | 1 | 1 | 1.33 | 1 | NA | NA | NA | NA | NA | 0.00 |
1195 | libggml-cpu.so - ops.cpp:4319-4365 [...] | ggml_compute_forward_rms_norm | Outermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | NA | NA | NA | NA | NA | 1 | NA | NA | NA | NA | NA | 0.00 |
44 | exec - main.cpp:663-681 [...] | main | Innermost | 0.04 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 8.51 | 41.49 | 7.5 | 1 | 1.32 | 1 | NA | NA | NA | NA | NA | 0.00 |