| Name | Module | Coverage (%) | Inclusive Time w.r.t. Wall Time(s) | Max Inc. Time over Threads(s) | Nb Threads | Deviation (coverage) | Deviation (time) |
|---|
| orig_default | gcc_default | gcc_2 | orig_default | gcc_default | gcc_2 | orig_default | gcc_default | gcc_2 | orig_default | gcc_default | gcc_2 | orig_default | gcc_default | gcc_2 | orig_default | gcc_default | gcc_2 |
|---|
| kai_run_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm | libggml-cpu.so | 69.76 | 83.64 | 83.96 | 1.20 | 1.77 | 1.77 | 0.88 | 0.87 | 0.88 | 95 | 95 | 95 | 7.50 | 6.40 | 6.59 | 0.08 | 0.08 | 0.08 |
| kmp_flag_64<false, true>::wait(kmp_info*, int, void*) | libomp.so | 19.92 | NA | NA | 0.34 | NA | NA | 0.96 | NA | NA | 96 | NA | NA | 9.80 | NA | NA | 0.11 | NA | NA |
| omp_get_num_procs | libgomp.so.1.0.0 | NA | 6.30 | 6.72 | NA | 0.13 | 0.14 | NA | 0.14 | 0.14 | NA | 96 | 96 | NA | 7.64 | 7.22 | NA | 0.02 | 0.02 |
| ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | libggml-cpu.so | 1.40 | 1.87 | 1.28 | 0.02 | 0.04 | 0.03 | 0.04 | 0.05 | 0.04 | 94 | 94 | 89 | 0.66 | 1.31 | 0.76 | 0.01 | 0.01 | 0.01 |
| ggml_compute_forward_flash_attn_ext | libggml-cpu.so | 1.21 | 1.97 | 1.32 | 0.02 | 0.04 | 0.03 | 0.03 | 0.04 | 0.04 | 92 | 95 | 90 | 0.49 | 1.26 | 1.20 | 0.01 | 0.01 | 0.01 |
| ggml_vec_swiglu_f32 | libggml-cpu.so | 1.66 | 0.69 | 0.62 | 0.03 | 0.01 | 0.01 | 0.04 | 0.03 | 0.02 | 86 | 72 | 71 | 0.58 | 0.50 | 0.47 | 0.01 | 0.00 | 0.00 |
| kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0 | libggml-cpu.so | 0.38 | 0.89 | 0.83 | 0.01 | 0.02 | 0.02 | 0.42 | 0.84 | 0.78 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon | libggml-cpu.so | 0.46 | 0.77 | 0.85 | 0.01 | 0.02 | 0.02 | 0.02 | 0.03 | 0.04 | 51 | 58 | 60 | 0.42 | 0.66 | 0.65 | 0.00 | 0.01 | 0.01 |
| sincosf | libm.so.6 | 0.43 | 0.57 | 0.66 | 0.01 | 0.01 | 0.01 | 0.02 | 0.03 | 0.02 | 57 | 59 | 68 | 0.38 | 0.51 | 0.69 | 0.00 | 0.00 | 0.00 |
| ggml_compute_forward_rms_norm | libggml-cpu.so | 0.49 | 0.47 | 0.44 | 0.01 | 0.01 | 0.01 | 0.03 | 0.02 | 0.02 | 68 | 54 | 56 | 0.38 | 0.54 | 0.36 | 0.00 | 0.00 | 0.00 |
| __expf_finite | libm.so.6 | 0.31 | 0.38 | 0.36 | 0.01 | 0.01 | 0.01 | 0.02 | 0.02 | 0.01 | 50 | 56 | 48 | 0.29 | 0.30 | 0.46 | 0.00 | 0.00 | 0.00 |
| ggml_vec_dot_q6_K_q8_K | libggml-cpu.so | 0.42 | 0.26 | 0.26 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 93 | 48 | 49 | 0.01 | 0.29 | 0.30 | 0.00 | 0.00 | 0.00 |
| rope_yarn(float, float, float*, long, float, float, float*, float*) | libggml-cpu.so | NA | NA | 0.93 | NA | NA | 0.02 | NA | NA | 0.03 | NA | NA | 80 | NA | NA | 0.95 | NA | NA | 0.01 |
| kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check() | libomp.so | 0.92 | NA | NA | 0.02 | NA | NA | 0.04 | NA | NA | 84 | NA | NA | 0.68 | NA | NA | 0.01 | NA | NA |
| ggml_vec_dot_f16 | libggml-cpu.so | 0.23 | 0.37 | 0.28 | 0.00 | 0.01 | 0.01 | 0.01 | 0.02 | 0.01 | 41 | 51 | 42 | 0.21 | 0.35 | 0.28 | 0.00 | 0.00 | 0.00 |
| ggml_compute_forward_add_non_quantized | libggml-cpu.so | 0.24 | 0.26 | 0.27 | 0.00 | 0.01 | 0.01 | 0.02 | 0.01 | 0.02 | 45 | 39 | 36 | 0.19 | 0.23 | 0.40 | 0.00 | 0.00 | 0.00 |
| ggml_cpu_fp32_to_fp16 | libggml-cpu.so | 0.11 | 0.42 | 0.16 | 0.00 | 0.01 | 0.00 | 0.01 | 0.02 | 0.01 | 20 | 54 | 26 | 0.24 | 0.49 | 0.19 | 0.00 | 0.00 | 0.00 |
| ggml_compute_forward_mul | libggml-cpu.so | 0.13 | 0.31 | 0.22 | 0.00 | 0.01 | 0.00 | 0.01 | 0.03 | 0.01 | 28 | 40 | 33 | 0.09 | 0.45 | 0.22 | 0.00 | 0.00 | 0.00 |
| __GI___pthread_mutex_lock | libc.so.6 | 0.23 | 0.20 | 0.21 | 0.00 | 0.00 | 0.00 | 0.01 | 0.01 | 0.01 | 45 | 30 | 32 | 0.15 | 0.30 | 0.28 | 0.00 | 0.00 | 0.00 |
| __GI___sched_yield | libc.so.6 | 0.58 | NA | NA | 0.01 | NA | NA | 0.04 | NA | NA | 68 | NA | NA | 0.56 | NA | NA | 0.01 | NA | NA |
| unknown_function | libggml-cpu.so | 0.09 | 0.08 | 0.08 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 0.01 | 17 | 15 | 11 | 0.15 | 0.07 | 1.40 | 0.00 | 0.00 | 0.00 |
| __GI___memcpy_sve | libc.so.6 | 0.06 | 0.09 | 0.10 | 0.00 | 0.00 | 0.00 | 0.01 | 0.02 | 0.03 | 11 | 13 | 14 | 0.14 | 0.12 | 0.24 | 0.00 | 0.00 | 0.01 |
| unknown_function | [vdso] | 0.21 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 39 | NA | NA | 0.17 | NA | NA | 0.00 | NA | NA |
| __GI___memset_generic | libc.so.6 | 0.05 | 0.03 | 0.07 | 0.00 | 0.00 | 0.00 | 0.05 | 0.03 | 0.06 | 2 | 1 | 1 | 1.74 | 0.00 | 0.00 | 0.03 | 0.00 | 0.00 |
| ggml_graph_compute_thread | libggml-cpu.so | 0.13 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 26 | NA | NA | 0.14 | NA | NA | 0.00 | NA | NA |
| unknown_function | libomp.so | 0.11 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 19 | NA | NA | 0.25 | NA | NA | 0.00 | NA | NA |
| __GI___lll_lock_wait | libc.so.6 | 0.04 | 0.04 | 0.02 | 0.00 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 9 | 6 | 4 | 0.01 | 0.21 | 0.00 | 0.00 | 0.00 | 0.00 |
| 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... | libllama.so | 0.02 | 0.03 | 0.04 | 0.00 | 0.00 | 0.00 | 0.03 | 0.03 | 0.04 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| _IO_fread | libc.so.6 | 0.02 | 0.03 | 0.02 | 0.00 | 0.00 | 0.00 | 0.02 | 0.03 | 0.02 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| __GI___lll_lock_wake | libc.so.6 | 0.03 | 0.03 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 6 | 5 | 1 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 |
| ggml::cpu::kleidiai::extra_buffer_type::get_tensor_traits(ggml_tensor const*) | libggml-cpu.so | 0.02 | 0.02 | 0.01 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 0.00 | 5 | 4 | 2 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 |
| ggml_graph_compute_thread | libggml-cpu.so | NA | 0.03 | 0.02 | NA | 0.00 | 0.00 | NA | 0.01 | 0.00 | NA | 4 | 3 | NA | 0.32 | 0.01 | NA | 0.00 | 0.00 |
| __GI___libc_malloc | libc.so.6 | 0.02 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.02 | 0.01 | 0.01 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::compare(char const*) const | libstdc++.so.6.0.33 | NA | 0.02 | 0.02 | NA | 0.00 | 0.00 | NA | 0.02 | 0.02 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| __GI_memcmp | libc.so.6 | NA | 0.01 | 0.02 | NA | 0.00 | 0.00 | NA | 0.01 | 0.02 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| llama_vocab::~llama_vocab() | libllama.so | NA | 0.01 | 0.02 | NA | 0.00 | 0.00 | NA | 0.01 | 0.02 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| __aarch64_ldadd8_acq_rel | libomp.so | 0.03 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 6 | NA | NA | 0.19 | NA | NA | 0.00 | NA | NA |
| __kmp_yield | libomp.so | 0.03 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 7 | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA |
| llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | libllama.so | 0.01 | NA | 0.02 | 0.00 | NA | 0.00 | 0.01 | NA | 0.02 | 1 | NA | 1 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 |
| std::_Hash_bytes(void const*, unsigned long, unsigned long) | libstdc++.so.6.0.33 | 0.00 | 0.02 | NA | 0.00 | 0.00 | NA | 0.00 | 0.02 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA |
| @plt_start@ | libstdc++.so.6.0.33 | 0.00 | 0.02 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.02 | 0.00 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| std::basic_ostream<char, std::char_traits<char> >& std::__ostream_insert<char, std::char_traits<char> >(std::basic_ostream<char, std::char_traits<char> >&, char const*, long) | libstdc++.so.6.0.33 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 0.01 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| ggml_is_empty | libggml-base.so | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 2 | 1 | 2 | 0.02 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 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... | libllama.so | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 0.00 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| __GI___pthread_mutex_unlock_usercnt | libc.so.6 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 0.00 | 3 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| unlink_chunk.constprop.0 | libc.so.6 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| 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... | libllama.so | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.01 | 0.00 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long) | libstdc++.so.6.0.33 | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.01 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA |
| ggml_cpu_extra_compute_forward | libggml-cpu.so | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA | 3 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA |
| ggml::cpu::repack::extra_buffer_type::get_tensor_traits(ggml_tensor const*) | libggml-cpu.so | NA | 0.02 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 3 | NA | NA | 0.01 | NA | NA | 0.00 | NA |
| 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... | libllama.so | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.01 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| 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<... | libllama.so | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.01 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| __GI___libc_free | libc.so.6 | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.01 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| ggml_compute_forward_set_rows | libggml-cpu.so | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA | 2 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| _dl_lookup_symbol_x | ld-linux-aarch64.so.1 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| malloc_consolidate | libc.so.6 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| __kmp_hyper_barrier_release(barrier_type, kmp_info*, int, int, int, void*) | libomp.so | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 3 | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA |
| __kmp_barrier | libomp.so | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 3 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| _int_free | libc.so.6 | 0.01 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| __kmp_now_nsec | libomp.so | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 3 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| unknown_function | libllama.so | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| 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... | libllama.so | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| llama_vocab::impl::token_to_piece(int, char*, int, int, bool) const | libllama.so | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| __GI___strlen_asimd | libc.so.6 | NA | 0.01 | 0.01 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 |
| do_lookup_x | ld-linux-aarch64.so.1 | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| ggml_compute_forward_add | libggml-cpu.so | 0.00 | 0.01 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA | 1 | 1 | NA | 0.00 | 0.00 | NA | 0.00 | 0.00 | NA |
| unicode_cpts_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) | libllama.so | 0.00 | NA | 0.01 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 | 1 | NA | 1 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 |
| ggml_cpu_get_sve_cnt | libggml-cpu.so | 0.00 | NA | 0.01 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 | 1 | NA | 1 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 |
| __GI_memchr | libc.so.6 | 0.00 | NA | 0.01 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 | 1 | NA | 1 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 |
| ggml_compute_forward_glu | libggml-cpu.so | 0.00 | NA | 0.01 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 | 1 | NA | 1 | 0.00 | NA | 0.00 | 0.00 | NA | 0.00 |
| __kmp_hyper_barrier_gather(barrier_type, kmp_info*, int, int, void (*)(void*, void*), void*) | libomp.so | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 2 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| _int_malloc | libc.so.6 | 0.01 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| 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... | libllama.so | 0.01 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| ggml::cpu::kleidiai::tensor_traits::compute_forward_q4_0(ggml_compute_params*, ggml_tensor*) | libggml-cpu.so | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 2 | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA |
| llama_vocab::impl::token_get_attr(int) const | libllama.so | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| unicode_cpt_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, unsigned long&) | libllama.so | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| ggml_format_name | libggml-base.so | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| __GI___pthread_create | libc.so.6 | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| ggml_compute_forward_view | libggml-cpu.so | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| ggml_barrier | libggml-cpu.so | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| __vfscanf_internal | libc.so.6 | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| ggml_new_tensor_impl.constprop.0 | libggml-base.so | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA |
| void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_construct<char*>(char*, char*, std::forward_iterator_tag) [clone .constprop.0] | libllama.so | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| 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... | libggml-base.so | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| ggml_backend_cpu_kleidiai_buffer_type | libggml-cpu.so | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| kai_get_rhs_packed_offset_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm | libggml-cpu.so | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_construct<char*>(char*, char*, std::forward_iterator_tag) [clone .constprop.0] | libggml-base.so | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| __GI_strcmp | libc.so.6 | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| _IO_file_xsgetn | libc.so.6 | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| ggml_compute_forward_mul_mat | libggml-cpu.so | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| ggml_compute_forward_dup | libggml-cpu.so | NA | NA | 0.01 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 |
| _dl_fixup | ld-linux-aarch64.so.1 | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| __GI___libc_read | libc.so.6 | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| std::pair<std::__detail::_Node_iterator<std::pair<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<c... | libllama.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| 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... | libllama.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| llama_vocab::impl::~impl() | libllama.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| ggml_type_size | libggml-base.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| llama_vocab::impl::token_to_piece_for_cache[abi:cxx11](int, bool) const | libllama.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| llama_model::load_tensors(llama_model_loader&)::$_3::operator()(LLM_TN_IMPL const&, std::initializer_list<long> const&, int) const | libllama.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| __kmpc_barrier | libomp.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| __GI_memcpy | libc.so.6 | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| __kmp_get_global_thread_id_reg | libomp.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.01 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| llama_kv_cache::set_input_kq_mask(ggml_tensor*, llama_ubatch const*, bool) const | libllama.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| ggml::cpu::kleidiai::tensor_traits::compute_forward(ggml_compute_params*, ggml_tensor*) | libggml-cpu.so | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
| std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_append(char const*, unsigned long) | libstdc++.so.6.0.33 | 0.00 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA | 1 | NA | NA | 0.00 | NA | NA | 0.00 | NA | NA |
