Enum GpuCapability 

pub(crate) enum GpuCapability {
    Float64,
    Int64,
    Atomic64,
    CooperativeGroups,
    Subgroups,
    SharedMemory,
    DynamicParallelism,
    Float16,
}

GPU capability flags that can be required by a kernel (internal use only).

Variants

Float64

64-bit floating point support.

Int64

64-bit integer support.

Atomic64

64-bit atomics support.

CooperativeGroups

Cooperative groups / grid-wide sync.

Subgroups

Subgroup / warp / SIMD operations.

SharedMemory

Shared memory / threadgroup memory.

DynamicParallelism

Dynamic parallelism (launching kernels from kernels).

Float16

Half-precision (f16) support.

Implementations

impl GpuCapability

pub(crate) fn from_str(s: &str) -> Option<Self>

pub(crate) fn as_str(&self) -> &'static str

pub(crate) fn supported_by(&self, backend: GpuBackend) -> bool

Check if a backend supports this capability.

Trait Implementations

impl Clone for GpuCapability

fn clone(&self) -> GpuCapability

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GpuCapability

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

Formats the value using the given formatter.

impl PartialEq for GpuCapability

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

impl Eq for GpuCapability

impl StructuralPartialEq for GpuCapability