Print FLOPs and GFLOPs per second in profiler.

[qingqing01]

like:

------------------------->     Profiling Report     <-------------------------

Place: All
Time unit: ms
Sorted by total time in descending order in the same thread

Event                                                                 Calls       Total       Min.        Max.        Ave.        Ratio.      FLOPs.      GFLOPsPerSec.
thread0::multiclass_nms                                               1           33.8452     33.8452     33.8452     33.8452     0.578611
thread0::conv2d_fusion                                                35          7.85149     0.03088     3.00003     0.224328    0.134228
thread0::conv2d_fusion/conv1/                                         1           2.92042     2.92042     2.92042     2.92042     0.049927    447897600   153.367733
thread0::softmax                                                      1           2.1207      2.1207      2.1207      2.1207      0.0362552
thread0::softmax/                                                     1           2.11693     2.11693     2.11693     2.11693     0.0361907
thread0::concat                                                       5           1.17491     0.02384     0.89056     0.234982    0.0200861
thread0::concat/                                                      5           1.09261     0.020448    0.852576    0.218522    0.0186791
thread0::conv2d_fusion/conv1_add/                                     1           0.843776    0.843776    0.843776    0.843776    0.0144251   1791590400  2123.301002
thread0::pool2d                                                       5           0.664608    0.037344    0.360896    0.132922    0.011362
thread0::fusion_transpose_flatten_concat                              2           0.640736    0.197152    0.443584    0.320368    0.0109539
thread0::pool2d/                                                      5           0.609696    0.033952    0.357056    0.121939    0.0104233
thread0::fusion_transpose_flatten_concat/                             2           0.586848    0.193536    0.393312    0.293424    0.0100327
thread0::conv2d_fusion/conv3_2/                                       1           0.315008    0.315008    0.315008    0.315008    0.00538533  300810240   954.928847
thread0::conv2d_fusion/conv4_2/                                       1           0.267936    0.267936    0.267936    0.267936    0.00458059  79626240    297.183815
thread0::density_prior_box                                            3           0.23472     0.053088    0.117056    0.07824     0.00401274
thread0::conv2d_fusion/inception_a1_3x3/                              1           0.23152     0.23152     0.23152     0.23152     0.00395803  28200960    121.807880
thread0::density_prior_box/                                           3           0.21696     0.04592     0.113536    0.07232     0.00370911
thread0::conv2d_fusion/conv3_2_mbox_loc_context_face/                 1           0.190688    0.190688    0.190688    0.190688    0.00325997  9400320     49.296862
thread0::conv2d_fusion/conv2/                                         1           0.186144    0.186144    0.186144    0.186144    0.00318229  338411520   1818.009338
thread0::conv2d_fusion/inception_a3_concat_mbox_loc_context_face/     1           0.147968    0.147968    0.147968    0.147968    0.00252964  394813440   2668.235398
thread0::conv2d_fusion/inception_a1_3x3_2/                            1           0.126016    0.126016    0.126016    0.126016    0.00215435  28200960    223.788715
thread0::conv2d_fusion/inception_a1_3x3_2_reduce/                     1           0.11968     0.11968     0.11968     0.11968     0.00204603  6266880     52.363635
thread0::conv2d_fusion/conv4_2_mbox_loc_context_face/                 1           0.118752    0.118752    0.118752    0.118752    0.00203017  2488320     20.953920
thread0::conv2d_fusion/conv3_2_mbox_conf_context_face/                1           0.113312    0.113312    0.113312    0.113312    0.00193716  4700160     41.479808
thread0::conv2d_fusion/conv3_1/                                       1           0.103264    0.103264    0.103264    0.103264    0.00176538  66846720    647.338107
thread0::conv2d_fusion/inception_a1_3x3_3/                            1           0.102624    0.102624    0.102624    0.102624    0.00175444  37601280    366.398506
thread0::conv2d_fusion/inception_a2_3x3_2_reduce/                     1           0.09856     0.09856     0.09856     0.09856     0.00168497  12533760    127.168834
thread0::conv2d_fusion/conv4_2_mbox_conf_context_face/                1           0.09424     0.09424     0.09424     0.09424     0.00161111  1244160     13.202037

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
2 out of 3 committers have signed the CLA.

:white_check_mark: qingqing01
:white_check_mark: NHZlX
:x: Dang Qingqing

---

Dang Qingqing seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[paddle-bot[bot]]

很抱歉，经过我们的反复讨论，你的PR暂未达到合入标准，请阅读飞桨原生算子开发规范，你可以重新提交新的PR，我们先将此PR关闭，感谢你的贡献。 Sorry to inform you that through our discussion, your PR fails to meet the merging standard (Reference: Paddle Custom Operator Design Doc). You can also submit an new one. Thank you.