NVIDIA / NVIDIA/cccl

The `cub.bench.segmented_radix_sort.keys.base` benchmark covers too many combinations

Open
#9,041 2 comments 0 reactions 1 assignee Claimed by @elstehle View on GitHub
Dominant language
C++
Stars
2.5k
Forks
486
Avg merge
2d 6h
Merged PRs (30d)
295

Description

When running the ordinary `cub.bench.segmented_radix_sort.keys.base` benchmark, 798 variations are covered. #6731 noted, that this takes 136min of time, which is more than inconvenient for benchmarking a code change.

We should reduce the number of benchmarked combinations to get the benchmark runtime down to a few minutes.

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.