ptrendx commented on a change in pull request #17462: Updated PartialSortSmallK
for LT support
URL: https://github.com/apache/incubator-mxnet/pull/17462#discussion_r381417450
##########
File path: src/operator/tensor/ordering_op-inl.h
##########
@@ -362,7 +362,7 @@ MSHADOW_FORCE_INLINE void TopKSort(const Tensor<gpu, 1,
DType>& dat,
}
} else {
const int nthreads(mshadow::cuda::kBaseThreadNum);
- PartialSortSmallK<<<M, nthreads, nthreads*K*(sizeof(int)+sizeof(DType)),
+ PartialSortSmallK<<<M, nthreads, nthreads*K*(sizeof(IType)+sizeof(DType)),
Review comment:
Ok, thanks. So the only real limit here is that we can't request more than
48 kB of shared memory for this kernel, and the change from int to index_t
should not matter be problematic here: `256 * (8 + sizeof(DType)) * K <= 256 *
(8 + 8) * K = 4096 * K`. K is small (5), so it is nowhere near the limit.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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
