rust-gpu-tools
An abstraction library to run kernels on both CUDA and OpenCL.
Example
You need to write the code that interacts with the GPU only once. Below is such code that runs a
kernel on CUDA and/or OpenCL. For a full working example, please see the examples
directory. You can run it via cargo run --example add
.
let closures = program_closures!;
Environment variables
-
RUST_GPU_TOOLS_CUSTOM_GPU
rust-gpu-tools has a hard-coded list of GPUs and their CUDA core count. If your card is not part of that list, you can add it via
RUST_GPU_TOOLS_CUSTOM_GPU
. The value is a comma separated list ofname:cores
. Example:RUST_GPU_TOOLS_CUSTOM_GPU="GeForce RTX 2080 Ti:4352,GeForce GTX 1060:1280"
License
Licensed under either of
- Apache License, Version 2.0, (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0)
- MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT)
at your option.
Contribution
Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.