[GitHub] [incubator-mxnet] Zha0q1 commented on a change in pull request #19339: [WIP] Numpy Argmax(min) Rewrite

[GitBox <gi...@apache.org>]

Zha0q1 commented on a change in pull request #19339:
URL: https://github.com/apache/incubator-mxnet/pull/19339#discussion_r503613902



##########
File path: src/operator/tensor/broadcast_reduce-inl.cuh
##########
@@ -60,16 +60,18 @@ __global__ void reduce_kernel(const int N, const int M, const bool addto,
           for (int u=0;u < unroll;u++) {
             idx_big[u] = idx_big0 + mxnet_op::unravel_dot(k + u*by, big_shape, big_stride);
           }
-          DType tmp[unroll];
+          AType tmp[unroll];

Review comment:
       I though this was a little cleaner. This way we can get rid of the explicit conversion on line 74




----------------------------------------------------------------
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:
users@infra.apache.org