cudarc 0.19.4

Safe and minimal CUDA bindings
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38

use cudarc::{
    driver::{CudaContext, DriverError, LaunchConfig, PushKernelArg},
    nvrtc::Ptx,
};

fn main() -> Result<(), DriverError> {
    let ctx = CudaContext::new(0)?;
    let stream = ctx.default_stream();

    // You can load a function from a pre-compiled PTX like so:
    let module = ctx.load_module(Ptx::from_file("./examples/sin.ptx"))?;

    // and then load a function from it:
    let f = module.load_function("sin_kernel").unwrap();

    let a_host = [1.0, 2.0, 3.0];

    let a_dev = stream.clone_htod(&a_host)?;
    let mut b_dev = a_dev.clone();

    // we use a buidler pattern to launch kernels.
    let n = 3i32;
    let cfg = LaunchConfig::for_num_elems(n as u32);
    let mut launch_args = stream.launch_builder(&f);
    launch_args.arg(&mut b_dev);
    launch_args.arg(&a_dev);
    launch_args.arg(&n);
    unsafe { launch_args.launch(cfg) }?;

    let a_host_2 = stream.clone_dtoh(&a_dev)?;
    let b_host = stream.clone_dtoh(&b_dev)?;

    println!("Found {b_host:?}");
    println!("Expected {:?}", a_host.map(f32::sin));
    assert_eq!(&a_host, a_host_2.as_slice());

    Ok(())
}