# Swift on the GPU

**URL:** <https://forums.swift.org/t/swift-on-the-gpu/90299>\
**Category:** Pitches\
**Tags:** gpu, metal\
**Created:** [October 26, 2026, 10:25pm UTC](https://forums.swift.org/t/swift-on-the-gpu/90299 "2026-10-26T22:25:18Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![tmcdonell](https://sea2.discourse-cdn.com/swift/user_avatar/forums.swift.org/tmcdonell/32/35491_2.png) [@tmcdonell](https://forums.swift.org/u/tmcdonell)\
**Post date:** [November 14, 2026, 11:35am UTC](https://forums.swift.org/t/swift-on-the-gpu/90299/9 "2026-11-14T11:35:04Z")

</div>

I have a proof of concept in this direction. I hope to be able to open source the next version as well...

> [@Announcing the SwiftToGPU project](https://forums.swift.org/t/announcing-the-swifttogpu-project/82884):
>
> I just got approval to open-source my work on lifting Swift code to GPU kernels. It is currently in the proof-of-concept stage, but we are getting good results so far and starting to roll it out into our product. I'm going through final approvals now and am planning to release the code here soon: [https://github.com/dataparallel-swift/swift-to-gpu](https://github.com/dataparallel-swift/swift-to-gpu) Our current target system utilises an integrated NVIDIA GPU, but in principle it could support other GPU backends in the future (if you squint, the S…

---

_[View the full topic](https://forums.swift.org/t/swift-on-the-gpu/90299)._
