Feature/opencl#2610
Closed
gmeeker wants to merge 16 commits intoKhronosGroup:mainfrom
Closed
Conversation
|
|
Contributor
|
OpenCL support has come up before but it was rejected. There is absolutely no bandwidth to take on another backend. And seeing a 40 ksloc+ PR dumped on me without any prior discussion is absolutely not a great first impression. |
Author
|
Thanks, I understand. We will go in a different direction. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implements the OpenCL side of #1602 (no CUDA support) and validates with clang. #1602 is pretty old so I'm curious if there's still interest in this, but I need OpenCL/CUDA and support for legacy reasons. While this backend is smaller due to being compute only, it requires some changes in spirv_glsl to deal with OpenCL being a C-based language. The tests have mostly been copied from MSL, with more tests to cover subgroup emulation. Nvidia and AMD never fully implemented the subgroup extensions this more complicated emulation is necessary.
Please let me know if you think this would be a useful backend and if you have any thoughts about the design. I'm looking at CUDA as well.