+
Skip to content

Conversation

nkoppel
Copy link
Contributor

@nkoppel nkoppel commented Feb 15, 2023

Closes #451 by retaining broadcasting in reduction operations, computing elems_per_thread as the product of all dims that are both broadcasted and summed, and computing chunk_size as physical_numel / dst_physical_numel. Also adds the test in #451 and renames internal_reshapes to reduction_utils.

Copy link
Owner

@coreylowman coreylowman left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nice, thanks for the quick fix!

@coreylowman coreylowman merged commit 73905f1 into coreylowman:main Feb 15, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

BUG: Example 08 not runnable with Cuda

2 participants

点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载