Paddle MKLDNN is slower than native CPU

syqv5f0l  于 2022-11-19  发布在  其他
关注(0)|答案(1)|浏览(129)

问题描述 Please describe your issue

In my model, the speed of MKLDNN is slower than that of native CPU. After profile, it is found that it is caused by the following three operators: split, concat and sub. Please help me to optimize.

Profile results of MKLDNN

Profile results of Native CPU

My model and test script:
model.zip

xriantvc

xriantvc1#

您好,我们已经收到了您的问题,会安排技术人员尽快解答您的问题,请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时,您也可以通过查看 官网API文档常见问题历史IssueAI社区 来寻求解答。祝您生活愉快~

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the APIFAQGithub Issue and AI community to get the answer.Have a nice day!

相关问题