mxnet-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Zhao, Patric" <>
Subject RE: MKLDNN Integration Stable Release
Date Wed, 04 Jul 2018 02:36:59 GMT
Hi Alex,

Regarding RNN, the first version of MKL-DNN RNN API is available in the MKL-DNN master branch.
We have integrated it in our local branch and you can try our code (still in developments).

We plan to PR our integration into MXNET master when both functionality and performance are



> -----Original Message-----
> From: Alex Zai []
> Sent: Wednesday, July 4, 2018 1:17 AM
> To:
> Subject: MKLDNN Integration Stable Release
> We are preparing a stable release of MKL-DNN integration in 1.3.0
> (experimental since 1.2.0), which supports acceleration of operations such as
> Convolution, Deconvolution, FullyConnected, Pooling, Batch Normalization,
> Activation, LRN, Softmax. Currently the RNN operator is not supported as the
> MKL-DNN API is still experimental; however, they hope to release a more
> stable version RNN API this or next week in MKL-DNN 0.15.
> We will have CPP unit test support on these operators and I am planning to
> write python unit tests to compare a RNN network's results from the MKLDNN
> backend with that of the GPU to test accuracy. Is there any additional coverage
> that you think we should cover in the next two weeks?
> Alex
View raw message