feat: add CUDA support

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};

    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);
    }

Cargo.toml

@@ -9,12 +9,19 @@ license = "MIT/Apache-2.0"
 repository = "https://github.com/filecoin-project/rust-gpu-tools"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+[features]
+default = ["opencl", "cuda"]
+opencl = ["opencl3"]
+cuda = ["rustacuda"]
 
 [dependencies]
 dirs = "2.0.2"
 sha2 = "0.8.2"
 thiserror = "1.0.10"
 lazy_static = "1.2"
 log = "0.4.11"
-opencl3 = { version = "0.4.1", default-features = false, features = ["CL_VERSION_1_2"] }
 hex = "0.4.3"
+
+opencl3 = { version = "0.4.1", default-features = false, features = ["CL_VERSION_1_2"], optional = true }
+#rustacuda = { version = "0.1.3", optional = true }
+rustacuda = { git = "https://github.com/vmx/RustaCUDA", branch = "load-from-bytes", optional = true }