Struct CudaKernel 

pub struct CudaKernel {
    pub name: String,
    pub params: Vec<CudaParam>,
    pub shared_mem_decls: Vec<SharedMemDecl>,
    pub body: Vec<CudaStmt>,
    pub launch_bounds: Option<LaunchBounds>,
}

A CUDA kernel (__global__ function).

Fields

name: String

Kernel name

params: Vec<CudaParam>

Parameter list

shared_mem_decls: Vec<SharedMemDecl>

Shared memory declarations (emitted at the top of the kernel body)

body: Vec<CudaStmt>

Kernel body statements

launch_bounds: Option<LaunchBounds>

Optional __launch_bounds__ annotation

Implementations

impl CudaKernel

pub fn new(name: impl Into<String>) -> Self

Create a new kernel with no launch bounds.

pub fn add_param(self, p: CudaParam) -> Self

Append a parameter.

pub fn add_shared(self, s: SharedMemDecl) -> Self

Append a shared-memory declaration.

pub fn add_stmt(self, s: CudaStmt) -> Self

Append a body statement.

pub fn with_launch_bounds(self, lb: LaunchBounds) -> Self

Set launch bounds.

Trait Implementations

impl Clone for CudaKernel

fn clone(&self) -> CudaKernel

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CudaKernel

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for CudaKernel

fn eq(&self, other: &CudaKernel) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for CudaKernel