marcoabreu commented on issue #8302: Refactor operators & MKLDNN URL: https://github.com/apache/incubator-mxnet/pull/8302#issuecomment-357816146 No, this is not an option. Compiling can only happen on C5 instances. G3 are reserved for GPU tests only. On Tue, Jan 16, 2018 at 12:59 AM, Da Zheng <[email protected]> wrote: > I think I have figured out the problems with mkldnn+gpu in Jenkins. > If I build everything in Dockerfile.gpu_mklml and test all unit tests in > tests/python/gpu, it works fine. > I think the problem is that the code is built in Dockerfile.build_cuda in > C5 and run in Dockerfile.gpu_mklml in G3. This is how things messed up. > @marcoabreu <https://github.com/marcoabreu> could you build the GPU code > on G3 as well? > > ? > You are receiving this because you were mentioned. > Reply to this email directly, view it on GitHub > <https://github.com/apache/incubator-mxnet/pull/8302#issuecomment-357815594>, > or mute the thread > <https://github.com/notifications/unsubscribe-auth/ARxB62H1-q-XRLaATGaBcSo8T-b-tswzks5tK-ZtgaJpZM4P7Qml> > . >
---------------------------------------------------------------- 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
