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 2018/03/15 19:41:10 UTC
[GitHub] DickJC123 commented on issue #9396: inference speed drop after updating mxnet from 0.10.0 to 1.0.0
DickJC123 commented on issue #9396: inference speed drop after updating mxnet from 0.10.0 to 1.0.0
URL: https://github.com/apache/incubator-mxnet/issues/9396#issuecomment-373499028
I was not. Is it easy for you to run your perf test on newer architectures than Kepler?
> On March 15, 2018 at 11:38 AM Haibin Lin <no...@github.com> wrote:
>
>
> @nicklhy https://github.com/nicklhy I bisected the changes between 0.10.0 and 1.0 and found the following on a p2.xlarge(K80) instance. The commits are patched with the fix in PR 9055
>
> git checkout xxx;
> git submodule update --recursive;
> git cherry-pick 9cc8ea3be23fb7adf4630e4cf065a2473094fbc8 -X theirs
> make
>
> and below is the result
>
> ff21e1f Changed FullyConnected to use new linalg gemm, plus TensorCore if fp16 I/O. (#7505)
>
> speed test for batch size: 1
> avg forward speed: 24.484983 samples/s
> avg forward time: mean = 0.040839 s, std = 0.000095 s
>
> 56eae58 Fixed Makefile so a null CUDA_ARCH is treated like an unset one. (#7515) - Fast
>
> ########################################################
> speed test for batch size: 1
> avg forward speed: 25.461191 samples/s
> avg forward time: mean = 0.039270 s, std = 0.000095 s
> ########################################################
>
> Looks like the commit ff21e1f https://github.com/apache/incubator-mxnet/commit/ff21e1fd41f118dbbaf55d8f02a9669842ef565f caused the 4% slowdown during inference.
>
> @DickJC123 https://github.com/dickjc123 were you aware of this?
>
> —
> You are receiving this because you were mentioned.
> Reply to this email directly, view it on GitHub https://github.com/apache/incubator-mxnet/issues/9396#issuecomment-373480684 , or mute the thread https://github.com/notifications/unsubscribe-auth/ABn95cDNeZmmZxQZ_Jskw0yivlr9C3eNks5terUOgaJpZM4RcJ9U .
>
>
>
----------------------------------------------------------------
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:
users@infra.apache.org
With regards,
Apache Git Services