projects / platform / upstream / caffe.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 24d2f67) | patch
Add Pascal to all cuda architectures
authorMax Ehrlich <max.ehr@gmail.com>
Fri, 2 Dec 2016 15:13:50 +0000 (10:13 -0500)
committerMax Ehrlich <max.ehrlich@sri.com>
Fri, 2 Dec 2016 17:49:49 +0000 (12:49 -0500)
commit8cd5c3df98734f4c43e1b7f43c05401fda0a94ac
tree6e1258d2a8782553e7a7aadcf6873601e18c8cd8tree | snapshot
parent24d2f67173db3344141dce24b1008efffbfe1c7dcommit | diff
Add Pascal to all cuda architectures

The known gpu architectures were missing the Pascal sm_60 and sm_61 compute capabilities. When building for this GPU, but on a separate machine, like a CI server or inside a docker image, caffe would be built for at most capability sm_50 and crash when run on the Pascal GPU.
cmake/Cuda.cmake diff | blob | history
Domain: Machine Learning / ML Framework;