TaoLv commented on issue #8302: Refactor operators & MKLDNN URL: https://github.com/apache/incubator-mxnet/pull/8302#issuecomment-359171544 @marcoabreu Thanks for your comments. We will update the perf data with other batch sizes later. I am not very sure about what are the exact `edge-devices` you mentioned here. Since our optimization is about mkldnn and mainly for Intel x86 architectures. So for edge-devices like Raspberry Pi or ARM, I don't think it will run into these new mkldnn operators. Please correct me if I missed anything.
---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
