NVIDIA / NVIDIA/cccl

[FEA]: C++ bindings for cuFile

Open
#6,149 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
2.5k
Forks
486
Avg merge
2d 6h
Merged PRs (30d)
295

Description

### Area

CUDA Experimental (cudax)

### Is your feature request related to a problem? Please describe.

GDS team would like to add cuFile bindings to CUDAX. In the past, @jvera-nvidia created a [document](https://docs.google.com/document/d/1gzaJBl7CgoN5-FG_nPxZzy7lUxZpQR94hzmQr5xoyxA/edit?usp=sharing) with the initial design followed by the PR #5532 with the implementation.

The PR is huge and there are many points to discuss, so we decided to split it into separate PRs.

### Progress

1. [x] Implement driver wrappers (#5941)
2. [ ] Implement file handle wrappers (#6122)
3. [ ] Implement read/write APIs (#6283)
4. [ ] Implement mechanism for buffer and stream registration
5. [ ] Implement batch APIs (#6284)
6. [ ] Implement statistics APIs

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.