xidulu commented on issue #15928: [RFC] A faster version of Gamma sampling on
GPU.
URL:
https://github.com/apache/incubator-mxnet/issues/15928#issuecomment-528001954
@ptrendx @yzhliu
I will create a PR for `np.random.gamma` implemented using the method I
proposed before the end of
xidulu commented on issue #15928: [RFC] A faster version of Gamma sampling on
GPU.
URL:
https://github.com/apache/incubator-mxnet/issues/15928#issuecomment-522469258
@ptrendx
The device-side api I mentioned is the `RandGenerator` class. (the one used
in `ndarray.random()`), it
xidulu commented on issue #15928: [RFC] A faster version of Gamma sampling on
GPU.
URL:
https://github.com/apache/incubator-mxnet/issues/15928#issuecomment-522209814
Hi @ptrendx , thanks for your reply, according to my discussion with @yzhliu
, device-side API is much slower than
xidulu commented on issue #15928: [RFC] A faster version of Gamma sampling on
GPU.
URL:
https://github.com/apache/incubator-mxnet/issues/15928#issuecomment-521933621
> cc @apache/mxnet-committers I think we can gradually refactor current
implementation (ndarray api) by adopting this new