Macro launch 

macro_rules! launch {
    ($kernel:expr, grid($g:expr), block($b:expr), shared($s:expr), $stream:expr, $args:expr) => { ... };
    ($kernel:expr, grid($g:expr), block($b:expr), $stream:expr, $args:expr) => { ... };
}

Launch a GPU kernel with a concise syntax.

This macro constructs LaunchParams from the provided grid and block dimensions, then calls Kernel::launch.

Syntax

launch!(kernel, grid(G), block(B), shared(S), stream, args)?;
launch!(kernel, grid(G), block(B), stream, args)?;  // shared_mem = 0

Where:

• kernel — a Kernel instance.
• G — grid dimensions (anything convertible to Dim3).
• B — block dimensions (anything convertible to Dim3).
• S — dynamic shared memory in bytes (u32).
• stream — a reference to a Stream.
• args — a reference to a tuple implementing KernelArgs.

Returns

CudaResult<()> — use ? to propagate errors.

Examples

let n: u32 = 1024;
let a_ptr: u64 = 0;
let b_ptr: u64 = 0;
let c_ptr: u64 = 0;

// With explicit shared memory
launch!(kernel, grid(4u32), block(256u32), shared(0), &stream, &(a_ptr, b_ptr, c_ptr, n))?;

// Without shared memory (defaults to 0)
launch!(kernel, grid(4u32), block(256u32), &stream, &(a_ptr, b_ptr, c_ptr, n))?;