News for hackers. Stuff that matters.

A comment on CubeCL: GPU Kernels in Rust for CUDA, ROCm, and WGPU. Parent comment

Re:CubeCL: GPU Kernels in Rust for CUDA, ROCm, and WGPU by ashvardanian on Thursday April 24, 2025 @06:34AM (#43781052)
Agreed! I was looking through the summation example < https://github.com/tracel-ai/cubecl/blob/main/examples/sum_t...> and it seems like the primary focus is on the more traditional pre-2018 GPU programming without explicit warp-level operations, asynchrony, atomics, barriers, or countless tensor-core operations.

The project feels very nice and it would be great to have more notes in the README on the excluded functionality to better scope its applicability in more advanced GPGPU scenarios.

[ Parent | on HN ]
Re:CubeCL: GPU Kernels in Rust for CUDA, ROCm, and WGPU by nathanielsimard on Thursday April 24, 2025 @08:11AM (#43781764)
We support warp operations, barriers for Cuda, atomics for most backends, tensor cores instructions as well. It's just not well documented on the readme!
[ Parent | on HN ]
Re:CubeCL: GPU Kernels in Rust for CUDA, ROCm, and WGPU by ashvardanian on Thursday April 24, 2025 @04:27PM (#43787121)
Amazing! Would love to try them! If possible, would also ask for a table translating between CubeCL and CUDA terminology. It seems like CUDA Warps are called Planes in CubeCL, and it’s probably not the only difference.
[ Parent | on HN ]
Re:CubeCL: GPU Kernels in Rust for CUDA, ROCm, and WGPU by 0x7cfe on Thursday April 24, 2025 @07:44AM (#43781557)
CubeCL is the computation backend for Burn (https://burn.dev/) - ML framework done by the same team which does all the tensor magic like autodiff, op fusion and dynamic graphs.
[ Parent | on HN ]