Where communities thrive
your own community
Explore more communities
A CPU and GPU-accelerated matrix library for data mining
Hello guys - I am looking for a way to use BIDMat in a parallel way when having multiple GPU devices. The thing I noticed is SciFunctions.setGPU(i: Int)
but that looks kind-of global, while I would like a parallel approach to using GPUs. is there a way to do that?
I have been trying to run LDA using BIDMach jar in java
But when i am trying to extract the topic-document matrix it is giving me all set to same value. i.e. topic-document distribution is uniform.
Can anyone help