-
Notifications
You must be signed in to change notification settings - Fork 945
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[WIP][DISCUSS] Initial work on JCuda bindings #302
Conversation
andy@micheal:~/sandbox/mahout_cuda/cuda$ export SIZE_N=5000 andy@micheal:~/sandbox/mahout_cuda/cuda$ export SIZE_M=5000 andy@micheal:~/sandbox/mahout_cuda/cuda$ export SIZE_S=5000 andy@micheal:~/sandbox/mahout_cuda/cuda$ export DENSITY=.2 andy@micheal:~/sandbox/mahout_cuda/cuda$ export NUM_RUNS=2 andy@micheal:~/sandbox/mahout_cuda/cuda$ export SEED=1234
… into AP-UNIT-TEST
@@ -57,6 +57,14 @@ final object RootSolverFactory extends SolverFactory { | |||
def getOperator[C: ClassTag]: MMBinaryFunc = { | |||
|
|||
try { | |||
logger.info("Creating scala.cuda.GPUMMul solver") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Does this remove ViennaCL from the picture all together then?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@rawkintrevo No, we'll maintain separate profiles for ViennaCL (-Pviennacl
and -Pcuda
) and JCuda to begin with. RootSolverFactory
has a a lot of work to be done on it and will be completely reworked/refactored, in the coming releases. In fact we have Jiras open for much of this work for 0.13.1.
Currently its not a huge issue to simply check the classpath at runtime (from the source build), however we will need to do some thinking on how and where to place these jars when this is released for the binary distro.
see #310 |
Initial work On JCuda Bindings by @nsakharnykh + some quick timing tests.