You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/04/02 09:39:57 UTC

[GitHub] [incubator-mxnet] sxjscience commented on issue #14073: Fp16 support for layernorm

sxjscience commented on issue #14073: Fp16 support for layernorm
URL: https://github.com/apache/incubator-mxnet/issues/14073#issuecomment-478921540
 
 
   Current I propose to solve the issue following these two steps:
   
   - [ ] Add a new 'fp16_mixed_reduce' flag to the LayerNorm operator. When the flag is turned on, the reduction will be performed in fp32 when the input/output have dtype=fp16.
   - [ ] Accelerate the implementation of LayerNorm by taking advantage of the techniques in https://github.com/NVIDIA/apex/blob/master/csrc/layer_norm_cuda_kernel.cu, e.g., welford online sum (https://en.wikipedia.org/wiki/Algorithms_for_calculating_variance)

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


With regards,
Apache Git Services