Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
This library is now an abstraction for OpenCL and CUDA. It can be compiled
with support for either or both, via the feature flags `opencl` and `cuda`.
There is now a `Device`, which can point to an OpenCL and/or CUDA device.
You should be able to execute OpenCL and CUDA kernels with the same code
without modifications. You would pass in two closures with the same function
body into `Program::run()`.
To create two closures with the correct signature but the same body, you
can use the `program_closures()` helper macro.
So your code would look like this:
use rust_gpu_tools::{cuda, program_closures, Device, GPUError, Program};
pub fn main() {
let closures = program_closures!(|program, data: &[u8]| -> Result<Vec<u8>, GPUError> {
let input = program.create_buffer_from_slice(data)?;
let output = unsafe { program.create_buffer::<u8>(128)? };
let kernel = program.create_kernel("foo", 24, 4)?;
kernel.arg(&input).arg(&output).run()?;
let mut out = vec![0u8; 128];
program.read_into_buffer(&output, 0, &mut out)?;
Ok(out)
});
let cuda_device = Device::all().first().unwrap().cuda_device().unwrap();
let cuda_kernel_path = std::ffi::CString::new("/some/path").unwrap();
let cuda_program = cuda::Program::from_binary(cuda_device, &cuda_kernel_path).unwrap();
let program = Program::Cuda(cuda_program);
let data = vec![5u8; 128];
let results = program.run(closures, &data).unwrap();
println!("results: {:?}", results);
}- Loading branch information
