options

Profiling node gmz12.benchmarkcenter.megware.com - process 7224 - thread 7224

NameModuleCoverage (%)Time (s)
main+attention-avx51296.389.06
Loop 31 - attention.cpp:26-306 - attention-avx512+40.693.82
Loop 32 - attention.cpp:26-306 - attention-avx512+40.693.82
Loop 33 - attention.cpp:26-33 - attention-avx512+40.693.82
Loop 30 - attention.cpp:30-31 - attention-avx51240.693.82
Loop 48 - attention.cpp:26-262 - attention-avx512+30.002.82
Loop 49 - attention.cpp:26-262 - attention-avx512+30.002.82
Loop 50 - attention.cpp:27-33 - attention-avx512+30.002.82
Loop 47 - attention.cpp:30-31 - attention-avx51230.002.82
Loop 64 - attention.cpp:26-193 - attention-avx512+7.550.71
Loop 65 - attention.cpp:26-193 - attention-avx512+7.550.71
Loop 66 - attention.cpp:26-33 - attention-avx512+7.550.71
Loop 63 - attention.cpp:30-31 - attention-avx5127.550.71
Loop 70 - attention.cpp:26-171 - attention-avx512+7.450.70
Loop 71 - attention.cpp:26-171 - attention-avx512+7.450.70
Loop 72 - attention.cpp:26-33 - attention-avx512+7.450.70
Loop 69 - attention.cpp:30-31 - attention-avx5127.450.70
Loop 58 - attention.cpp:26-215 - attention-avx512+7.230.68
Loop 59 - attention.cpp:26-215 - attention-avx512+7.230.68
Loop 60 - attention.cpp:26-33 - attention-avx512+7.230.68
Loop 57 - attention.cpp:30-31 - attention-avx5127.230.68
Loop 40 - attention.cpp:43-284 - attention-avx512+0.530.05
Loop 41 - attention.cpp:43-284 - attention-avx512+0.530.05
Loop 39 - attention.cpp:55-56 - attention-avx5120.160.01
Loop 38 - attention.cpp:52-53 - attention-avx5120.110.01
Loop 43 - attention.cpp:55-56 - attention-avx5120.110.01
Loop 44 - attention.cpp:52-53 - attention-avx5120.110.01
Loop 46 - attention.cpp:47-48 - attention-avx5120.050.00
Loop 54 - attention.cpp:238-241 - attention-avx512+0.110.01
Loop 55 - attention.cpp:239-241 - attention-avx512+0.110.01
Loop 53 - attention.cpp:240-241 - attention-avx5120.110.01
amd_opt_expflibalm.so0.800.07
call_v16_f32libalm.so0.740.07
amd_vrs16_expf_zn5libalm.so0.640.06
alm_expf_speciallibalm.so0.480.04
amd_expf_zn5libalm.so0.430.04
amd_vrs8_expf_zn5libalm.so0.370.04
__memset_avx512_unaligned_ermslibc.so.60.050.00
amd_expf_zn5@pltlibalm.so0.050.00
×