use cuda_device::{cuda_module, kernel, thread, DisjointSlice};
use cuda_core::{CudaContext, DeviceBuffer, LaunchConfig};

#[cuda_module]
mod kernels {
    use super::*;

    #[kernel]
    fn vecadd(a: &[f32], b: &[f32], mut c: DisjointSlice<f32>) {
        let idx = thread::index_1d();
        let i = idx.get();
        if let Some(c_elem) = c.get_mut(idx) {
            *c_elem = a[i] + b[i];
        }
    }
}

fn main() {
    let ctx = CudaContext::new(0).unwrap();
    let stream = ctx.default_stream();
    let module = kernels::load(&ctx).unwrap();

    let a = DeviceBuffer::from_host(&stream, &[1.0f32; 1024]).unwrap();
    let b = DeviceBuffer::from_host(&stream, &[2.0f32; 1024]).unwrap();
    let mut c = DeviceBuffer::<f32>::zeroed(&stream, 1024).unwrap();

    module
        .vecadd(&stream, LaunchConfig::for_num_elems(1024), &a, &b, &mut c)
        .unwrap();

    let result = c.to_host_vec(&stream).unwrap();
    assert_eq!(result[0], 3.0);
}