NVIDIA / NVIDIA/cccl

Implementation of load balance algorithlms

Open
#711 0 comments 0 reactions 0 assignees View on GitHub
thrust
Dominant language
C++
Stars
2.5k
Forks
486
Avg merge
2d 6h
Merged PRs (30d)
295

Description

Hi, I find it very convenient to use load balance interface like in moderngpu:
[https://github.com/moderngpu/moderngpu/wiki/Load-balancing-search](url).
Many of the problems I encounter is given many segments of workload, while each segment has different and irregular granularity of workload, which makes the parallelizing difficult.
With 'transform_lbs' provided by moderngpu, I can pass in a lambda function with the arguments
(int index, int seg, int rank), where index is global position, seg is the segment id, and rank is the offset inside the segment.
I wonder why thrust does not provide this kind of interface. Or Thrust can actually support it, but need to implement it with several API calls.

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.