options

Profiling node skylake - process 419776 - thread 419776

NameModuleCoverage (%)Time (s)
main+attention-avx51290.5914.05
Loop 47 - attention.cpp:26-262 - attention-avx512+49.327.65
Loop 48 - attention.cpp:26-262 - attention-avx512+49.327.65
Loop 49 - attention.cpp:27-33 - attention-avx512+49.327.65
Loop 50 - attention.cpp:30-31 - attention-avx51249.327.65
Loop 74 - attention.cpp:26-171 - attention-avx512+12.441.93
Loop 75 - attention.cpp:26-171 - attention-avx512+12.441.93
Loop 76 - attention.cpp:27-33 - attention-avx512+12.441.93
Loop 73 - attention.cpp:30-31 - attention-avx51212.441.93
Loop 69 - attention.cpp:26-193 - attention-avx512+12.061.87
Loop 70 - attention.cpp:26-193 - attention-avx512+12.061.87
Loop 71 - attention.cpp:27-33 - attention-avx512+12.061.87
Loop 68 - attention.cpp:30-31 - attention-avx51212.061.87
Loop 30 - attention.cpp:26-306 - attention-avx512+2.130.33
Loop 31 - attention.cpp:26-30 - attention-avx512+2.130.33
Loop 32 - attention.cpp:27-30 - attention-avx512+2.130.33
Loop 33 - attention.cpp:30-30 - attention-avx5122.130.33
Loop 41 - attention.cpp:43-284 - attention-avx512+0.930.14
Loop 42 - attention.cpp:43-284 - attention-avx512+0.930.14
Loop 40 - attention.cpp:55-56 - attention-avx5120.320.05
Loop 46 - attention.cpp:47-48 - attention-avx5120.160.03
Loop 43 - attention.cpp:55-56 - attention-avx5120.130.02
Loop 38 - attention.cpp:52-53 - attention-avx5120.130.02
Loop 44 - attention.cpp:52-53 - attention-avx5120.130.02
Loop 39 - attention.cpp:52-53 - attention-avx5120.030.00
Loop 45 - attention.cpp:47-48 - attention-avx5120.030.00
Loop 60 - attention.cpp:26-215 - attention-avx512+0.900.14
Loop 61 - attention.cpp:26-30 - attention-avx512+0.900.14
Loop 65 - attention.cpp:27-30 - attention-avx512+0.900.14
Loop 67 - attention.cpp:30-30 - attention-avx5120.610.09
Loop 66 - attention.cpp:30-30 - attention-avx5120.290.04
Loop 55 - attention.cpp:238-241 - attention-avx512+0.190.03
Loop 56 - attention.cpp:239-241 - attention-avx512+0.190.03
Loop 54 - attention.cpp:240-241 - attention-avx5120.190.03
_ZGVeN16v_tanhflibmvec.so.15.610.87
f32subf64xlibm.so.63.130.48
__iscanonicalllibm.so.60.580.09
_dl_mcount_wrapperlibc.so.60.060.01
×