Struct KernelConfig

pub struct KernelConfig {
    pub block_size: (u32, u32, u32),
    pub grid_size: (u32, u32, u32),
    pub shared_memory_size: u32,
}

Kernel configuration parameters

Fields

block_size: (u32, u32, u32)

grid_size: (u32, u32, u32)

shared_memory_size: u32

Implementations

impl KernelConfig

pub fn for_matrix_multiply(rows: usize, cols: usize) -> Self

Create optimal configuration for matrix multiplication

pub fn for_vector_operation(size: usize) -> Self

Create optimal configuration for vector operations

pub fn for_convolution( batch_size: usize, out_channels: usize, out_height: usize, out_width: usize, ) -> Self

Create optimal configuration for convolution

Trait Implementations

impl Clone for KernelConfig

fn clone(&self) -> KernelConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for KernelConfig

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

Formats the value using the given formatter.