NVIDIA / NVIDIA/cccl

Multi-CTA `cub::DeviceBatchedTopK`: Carve out and add the `BlockFilter` building block

Open
#10,980 0 comments 0 reactions 1 assignee Claimed by @elstehle View on GitHub
Dominant language
C++
Stars
2.5k
Forks
487
Avg merge
2d 7h
Merged PRs (30d)
296

Description

The `BlockFilter` building block maps to the `early_stop` scenario, as outlined in https://github.com/NVIDIA-dev/cccl_private/issues/659, where all the remaining candidates are written to the user-provided output iterator. This is kind of a "stream compaction" scenario, distinguishing only selected and rejected items.

The issue can be closed once the PR that adds the `BlockFilter` building block has been merged.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.