Increase the minimum CUDA version to 12.0 and the default arch to compute_75.
#312
Conversation
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
nnethercote
force-pushed
the
increase-min-cuda-version
branch
2 times, most recently
from
d9aff16 to
c8ffbdf
Compare
Open
LegNeato
force-pushed
the
increase-min-cuda-version
branch
from
c8ffbdf to
00c90c0
Compare
Contributor
|
rebasing force pushes? lame. sorry for that |
LegNeato
requested changes
Nov 21, 2025
Contributor
LegNeato
left a comment
LegNeato
left a comment
There was a problem hiding this comment.
We should remove the cuda11 docker files and the CI step that builds and pushes them if it exists.
The docs on the `CudaBuilder::arch` method are a subset of those on the `CudaBuilder::arch` field. So just remove all the method docs except for the pointer to the arch docs. XXX: NVVM IR 1.6 -> 2.0 https://docs.nvidia.com/cuda/archive/12.0.0/cuda-toolkit-release-notes/index.html
It can be used in `NvvmOption::from_str`, and will also be used in a subsequent commit in compiletests.
It's possible with the `#[default]` attribute.
…mpute_75`. CUDA 12.0 was released in December 2022, and CUDA 13.0 was released in August 2025. It feels like a good time to drop CUDA 11.x support. This means later Kepler devices with compute capabilities of 3.5 and 3.7 will no longer be supported. The minimum version of NVVM IR increases from 1.6 to 2.0, because that's what CUDA 12.0 uses. Along with this, change the default compiler target to `compute_75`. This is a good choice because it's the minimum supported by CUDA 13.0, and gets Rust CUDA a step closer to working with CUDA 13.0. The existing defaults were all over the place. - `NvvmArch::default()` was `compute_52`. - `CudaBuilder`'s default was `compute_61`. - compiletest's default was `compute_70`. This commit makes the latter two determined by `NvvmArch::default()`, which is changed to `compute_75`. Currently CI runs compiletests on `compute_61`, `compute_70`, and `compute_90`; this commit changes the `compute_70` to `compute_75`. It seems sensible to have the default value as one of the things tested by CI. This comment also adds a comment on NvvmArch with a table of CUDA/`compute_*` values, which I found very useful. Resources: - https://en.wikipedia.org/wiki/CUDA#GPUs_supported for compute capabilities supported by different CUDA versions. - https://docs.nvidia.com/cuda/archive/12.0.0/cuda-toolkit-release-notes/index.html for NVVM IR version information.
nnethercote
force-pushed
the
increase-min-cuda-version
branch
from
00c90c0 to
5204d42
Compare
Collaborator
Author
|
I have added another commit that removes the CUDA 11 docker file. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
CUDA 12.0 was released in December 2022, and CUDA 13.0 was released in August 2025. It feels like a good time to drop CUDA 11.x support. This means later Kepler devices with compute capabilities of 3.5 and 3.7 will no longer be supported. The minimum version of NVVM IR increases from 1.6 to 2.0, because that's what CUDA 12.0 uses.
Along with this, change the default compiler target to
compute_75. This is a good choice because it's the minimum supported by CUDA 13.0, and gets Rust CUDA a step closer to working with CUDA 13.0.More details in individual commits.