cjolivier01 commented on issue #8686: Kernel operator tuning
URL: https://github.com/apache/incubator-mxnet/pull/8686#issuecomment-345419483
 
 
   OMP overhead this run, ~8500 ns. 
   
   unary and binary op times: 0.5-200 ns
   
   OperatorTuneBase::duration_t OperatorTuneBase::omp_overhead_ns_ = 8495;
   mshadow::op::identity time: 1.33008 ns 
   mxnet::op::mshadow_op::identity time: 1.32959 ns 
   mxnet::op::mshadow_op::identity_grad time: 1.22754 ns 
   mxnet::op::mshadow_op::negation time: 1.56836 ns 
   mxnet::op::mshadow_op::reciprocal time: 1.53467 ns 
   mxnet::op::mshadow_op::reciprocal_grad time: 2.48975 ns 
   mxnet::op::mshadow_op::sigmoid time: 29.3955 ns 
   mxnet::op::mshadow_op::sigmoid_grad time: 2.18262 ns 
   mxnet::op::mshadow_op::relu time: 1.77295 ns 
   mxnet::op::mshadow_op::relu_grad time: 2.14844 ns 
   mxnet::op::mshadow_op::tanh time: 38.1255 ns 
   mxnet::op::mshadow_op::tanh_grad time: 2.25098 ns 
   mxnet::op::mshadow_op::softrelu time: 51.7314 ns 
   mxnet::op::mshadow_op::softrelu_grad time: 33.5557 ns 
   mxnet::op::mshadow_op::exp time: 17.4258 ns 
   mxnet::op::mshadow_op::exp time: 18.1758 ns 
   mxnet::op::mshadow_op::expm1 time: 23.189 ns 
   mxnet::op::mshadow_op::log time: 25.1323 ns 
   mxnet::op::mshadow_op::log_grad time: 2.08008 ns 
   mxnet::op::mshadow_op::log1p time: 24.5527 ns 
   mxnet::op::mshadow_op::log1p_grad time: 2.52344 ns 
   mxnet::op::mshadow_op::log2 time: 24.1777 ns 
   mxnet::op::mshadow_op::log2_grad time: 2.0459 ns 
   mxnet::op::mshadow_op::log10 time: 26.4624 ns 
   mxnet::op::mshadow_op::log10_grad time: 2.08057 ns 
   mxnet::op::mshadow_op::sin time: 12.6177 ns 
   mxnet::op::mshadow_op::sin_grad time: 13.1626 ns 
   mxnet::op::mshadow_op::sinh time: 41.6372 ns 
   mxnet::op::mshadow_op::sinh_grad time: 29.5659 ns 
   mxnet::op::mshadow_op::arcsin time: 16.2319 ns 
   mxnet::op::mshadow_op::arcsin_grad time: 6.37695 ns 
   mxnet::op::mshadow_op::arcsinh time: 38.6709 ns 
   mxnet::op::mshadow_op::arcsinh_grad time: 15.4478 ns 
   mxnet::op::mshadow_op::cos time: 10.5376 ns 
   mxnet::op::mshadow_op::cos_grad time: 12.9243 ns 
   mxnet::op::mshadow_op::cosh time: 27.4175 ns 
   mxnet::op::mshadow_op::cosh_grad time: 41.7739 ns 
   mxnet::op::mshadow_op::arccos time: 19.2676 ns 
   mxnet::op::mshadow_op::arccos_grad time: 6.41064 ns 
   mxnet::op::mshadow_op::arccosh time: 15.2773 ns 
   mxnet::op::mshadow_op::arccosh_grad time: 19.4717 ns 
   mxnet::op::mshadow_op::tan time: 26.4966 ns 
   mxnet::op::mshadow_op::tan_grad time: 2.11426 ns 
   mxnet::op::mshadow_op::arctan time: 19.2329 ns 
   mxnet::op::mshadow_op::arctan_grad time: 3.00098 ns 
   mxnet::op::mshadow_op::arctanh time: 38.6025 ns 
   mxnet::op::mshadow_op::arctanh_grad time: 3.06934 ns 
   mxnet::op::mshadow_op::square time: 1.50049 ns 
   mxnet::op::mshadow_op::square_grad time: 1.90967 ns 
   mxnet::op::mshadow_op::square_root time: 13.1631 ns 
   mxnet::op::mshadow_op::square_root_grad time: 2.08008 ns 
   mxnet::op::mshadow_op::reciprocal_square_root time: 13.7085 ns 
   mxnet::op::mshadow_op::reciprocal_square_root_grad time: 16.062 ns 
   mxnet::op::mshadow_op::cube_root time: 38.6367 ns 
   mxnet::op::mshadow_op::cube_root_grad time: 3.00098 ns 
   mxnet::op::mshadow_op::reciprocal_cube_root time: 38.1255 ns 
   mxnet::op::mshadow_op::reciprocal_cube_root_grad time: 40.2393 ns 
   mxnet::op::mshadow_op::abs time: 1.50049 ns 
   mxnet::op::mshadow_op::sign time: 3.54639 ns 
   mxnet::op::mshadow_op::sign time: 4.09229 ns 
   mxnet::op::mshadow_op::sign_grad time: 1.53467 ns 
   mxnet::op::mshadow_op::round time: 7.74121 ns 
   mxnet::op::mshadow_op::floor time: 5.25146 ns 
   mxnet::op::mshadow_op::trunc time: 6.20654 ns 
   mxnet::op::mshadow_op::rint time: 9.10498 ns 
   mxnet::op::mshadow_op::fix time: 10.3667 ns 
   mxnet::op::mshadow_op::gamma time: 107.555 ns 
   mxnet::op::mshadow_op::gamma_grad time: 208.938 ns 
   mxnet::op::mshadow_op::gammaln time: 74.5112 ns 
   mxnet::op::mshadow_op::gammaln_grad time: 95.3125 ns 
   mxnet::op::mshadow_op::ceil time: 4.43311 ns 
   mxnet::op::mshadow_op::degrees time: 1.50049 ns 
   mxnet::op::mshadow_op::degrees_grad time: 1.50049 ns 
   mxnet::op::mshadow_op::radians time: 1.50049 ns 
   mxnet::op::mshadow_op::radians_grad time: 1.50049 ns 
   mshadow::op::plus time: 1.53467 ns 
   mshadow::op::minus time: 1.53467 ns 
   mshadow::op::mul time: 1.53467 ns 
   mshadow::op::div time: 1.63672 ns 
   mshadow::op::right time: 1.32959 ns 
   mxnet::op::mshadow_op::rminus time: 1.80762 ns 
   mxnet::op::mshadow_op::rdiv time: 1.84131 ns 
   mxnet::op::mshadow_op::div_grad time: 1.53467 ns 
   mxnet::op::mshadow_op::div_grad time: 1.90967 ns 
   mxnet::op::mshadow_op::div_rgrad time: 2.28467 ns 
   mxnet::op::mshadow_op::div_rgrad time: 2.83057 ns 
   mxnet::op::mshadow_op::rdiv_grad time: 2.62598 ns 
   mxnet::op::mshadow_op::mod time: 41.8423 ns 
   mxnet::op::mshadow_op::mod_grad time: 1.26172 ns 
   mxnet::op::mshadow_op::mod_rgrad time: 4.97852 ns 
   mxnet::op::mshadow_op::rmod time: 42.5581 ns 
   mxnet::op::mshadow_op::rmod_grad time: 5.0127 ns 
   mxnet::op::mshadow_op::left time: 1.19336 ns 
   mxnet::op::mshadow_op::left time: 1.53418 ns 
   mxnet::op::mshadow_op::right time: 1.22803 ns 
   mxnet::op::mshadow_op::right time: 1.50049 ns 
   mxnet::op::mshadow_op::power time: 71.7827 ns 
   mxnet::op::mshadow_op::rpower time: 68.4067 ns 
   mxnet::op::mshadow_op::power_grad time: 70.9302 ns 
   mxnet::op::mshadow_op::rpower_grad time: 22.0293 ns 
   mxnet::op::mshadow_op::power_rgrad time: 91.1865 ns 
   mxnet::op::mshadow_op::maximum time: 1.56836 ns 
   mxnet::op::mshadow_op::minimum time: 1.53467 ns 
   mxnet::op::mshadow_op::hypot time: 25.5757 ns 
   mxnet::op::mshadow_op::hypot_grad_left time: 19.3013 ns 
   mxnet::op::mshadow_op::hypot_grad_left time: 13.8789 ns 
   mxnet::op::mshadow_op::hypot_grad_right time: 13.1973 ns 
   mxnet::op::mshadow_op::hypot_grad_right time: 13.231 ns 
   mxnet::op::mshadow_op::lt time: 1.77295 ns 
   mxnet::op::mshadow_op::lt time: 2.5918 ns 
   mxnet::op::mshadow_op::le time: 1.73926 ns 
   mxnet::op::mshadow_op::le time: 2.62598 ns 
   mxnet::op::mshadow_op::gt time: 2.5918 ns 
   mxnet::op::mshadow_op::gt time: 2.08008 ns 
   mxnet::op::mshadow_op::ge time: 2.01172 ns 
   mxnet::op::mshadow_op::ge time: 2.55762 ns 
   mxnet::op::mshadow_op::ne time: 2.11426 ns 
   mxnet::op::mshadow_op::ne time: 2.62598 ns 
   mxnet::op::mshadow_op::eq time: 2.11426 ns 
   mxnet::op::mshadow_op::eq time: 2.62598 ns 
   mxnet::op::mshadow_op::smooth_l1_loss time: 4.29639 ns 
   mxnet::op::mshadow_op::smooth_l1_gradient time: 3.85352 ns 
   mxnet::op::mxnet_op::set_to_int<0> time: 1.09131 ns 
   mxnet::op::mxnet_op::set_to_int<1> time: 0.647949 ns 
   mxnet::op::PopulateFullIdxRspKernel time: 0.647949 ns 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


With regards,
Apache Git Services

Reply via email to