Fix support of float atomics in threadgroup memory.#1
Conversation
|
This What we can do is to create an integration branch, that contains both our fixes. e.g. Or I suppose we could treat |
|
Change looks reasonable to me. Please could you post a self-declaration. Choose your preferred self-declaration: "I have read every line added in this PR, and reviewed the lines. I take responsibilty for the lines added and removed in this PR, and won't blame any issues on Opus, or any other AI." "I wrote this code myself. I take responsibilty for the lines added and removed in this PR, and won't blame any issues on Opus or any other AI." (or propose another that aligns with my intentions here, but avoids raising any concerns you may have over my own choice of wording) |
|
Also, please could you submit a PR to upstream, and submit a link here. |
|
I was assisted by Claude Opus to write this PR. I have read every line added in this PR, and reviewed the lines. I take full responsibility for the lines added and removed in this PR. I won't blame any issue on Claude Opus. |
|
Could we add a unit test for this issue please, that fails without this change, and passes with this change. |
|
Note: revoked requiemetn for unit tset for this PR, because it 'plays poorly' with the requirement to hvae read and understood all lines of the code. Baby steps. We will ensure first that hte tests on Quadrants are passing though. |
Cross-referencing upstream PR: KhronosGroup#2611