NVIDIA / NVIDIA/cuCollections

[FEA] Block level bulk APIs

Open
#148 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

helps: rapids P3: Backlog type: feature request
Dominant language
Cuda
Stars
667
Forks
120
Avg merge
7d 5h
Merged PRs (30d)
4

Description

Currently the bulk APIs are host calls which operate on one map. We have a use case where we have multiple small maps defined on a slice of pre-allocated slot space. For this we duplicate the insert kernel code from cuco and initializing one map per block.

It would be nice to have cub style block level bulk APIs for initialize, insert etc.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the linked cuDF chunk_dict.cu example and the existing host bulk APIs in cuCollections. Determine the block-level initialization and insertion API scope, then identify the relevant implementation and test locations; done means block-based APIs support the stated multi-map use case with coverage for initialization and insertion.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.