Struct GpuDevice 

pub struct GpuDevice { /* private fields */ }

GPU device abstraction

Implementations

impl GpuDevice

pub fn new(backend: GpuBackend, device_id: usize) -> GpuDevice

Create a new GPU device

pub fn backend(&self) -> GpuBackend

Get the backend type

pub fn device_id(&self) -> usize

Get the device ID

pub fn compile_kernel( &self, _source: &str, entrypoint: &str, ) -> Result<GpuKernel, GpuError>

Compile a kernel from source

pub fn get_info(&self) -> Result<GpuDeviceInfo, GpuError>

Query the capabilities of this device.

Returns a GpuDeviceInfo describing the device name, type, memory, work-group limits and supported floating-point precisions. The values are derived deterministically from this device’s backend.

In the default Pure-Rust build no GPU SDK is linked, so the values for hardware backends are conservative placeholders (see GpuDeviceInfo); the method itself never fails in that configuration. The Result return type reserves the ability to surface real adapter query failures once live introspection is wired in.

Errors

Currently always returns Ok. Reserved for future backends that perform a fallible live adapter query.

Trait Implementations

impl Clone for GpuDevice

fn clone(&self) -> GpuDevice

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for GpuDevice

impl Debug for GpuDevice

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

Formats the value using the given formatter.

impl Eq for GpuDevice

impl PartialEq for GpuDevice

fn eq(&self, other: &GpuDevice) -> 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 GpuDevice