Struct GpuFeatures

pub struct GpuFeatures {
    pub float64: bool,
    pub subgroups: bool,
    pub unified_memory: bool,
    pub max_workgroup_size: u32,
}

Relevant compute features without exposing CUDA, Metal, Vulkan, or WebGPU types in the public kernel contract.

Fields

float64: bool

Native binary64 shader/compute arithmetic.

subgroups: bool

Subgroup/warp operations.

unified_memory: bool

Host-visible unified memory.

max_workgroup_size: u32

Maximum workgroup size reported by the concrete API.

Trait Implementations

impl Clone for GpuFeatures

fn clone(&self) -> GpuFeatures

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for GpuFeatures

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

Formats the value using the given formatter.

impl PartialEq for GpuFeatures

fn eq(&self, other: &GpuFeatures) -> 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 Copy for GpuFeatures

impl Eq for GpuFeatures

impl StructuralPartialEq for GpuFeatures