Possibly fix atomicMaxf and atomicMinf for doubles
#431
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
|
Thanks! |
coreylowman
added a commit
that referenced
this pull request
Feb 13, 2023
* impl Cpu kernels for num_traits::Float * Update examples * Fixing cuda issues * Add dtype skeleton to cuda kernels * Working commit of TestDtype & cuda kernels * Adding test-f64 feature * Temp commit * Moving more things to generic dtype * Possibly fix max_to and min_to for doubles (#431) * Temp commit * Fixing optim tests * Compiling * Tests passing for Cpu * Cuda compiling * f64 cuda tests passing * Fixing warnings * Requiring minimum compute_60 * f64 nightly tests passing for cpu * pool2d f64 kernels * Conv & pool passing on cuda * Making nn/dropout.rs generic over dtype * Styling & using DeviceBuildExt * Cleanup optimizers * Minifying cuda kernels * Adding f64 cmp kernels * Removing macros in optim * Reduce macro usage in cuda kernels * minify cuda kernel impls * Fixing docs --------- Co-authored-by: Viliam Vadocz <viliam.vadocz@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
I implemented my suggestion of converting to
long long intin the atomic max/min functions. I could not test it since the Rust portion of the code does not compile.I also added a missing header that is needed to use
__half.