Struct GpuRuntime 

pub struct GpuRuntime {
    pub device: GpuDeviceInfo,
    pub devices: Vec<GpuDeviceInfo>,
    pub policy: GpuDispatchPolicy,
    pub memory_budget_bytes: usize,
}

Fields

device: GpuDeviceInfo

Highest-scoring probed CUDA device. Existing dispatch code routes one-shot kernels through this device.

devices: Vec<GpuDeviceInfo>

All usable CUDA devices discovered at probe time, ordered by score.

policy: GpuDispatchPolicy

memory_budget_bytes: usize

Implementations

impl GpuRuntime

pub fn probe() -> Result<Option<Self>, GpuError>

pub fn global() -> Option<&'static Self>

pub fn is_available() -> bool

pub fn global_or_fail(mode: GpuMode) -> Result<&'static Self, GpuError>

Fail-closed accessor for the process-wide runtime under a [GpuMode] contract (issue #1017).

• [GpuMode::Required] — the device MUST be present: when the probe found no usable runtime this returns Err(GpuError::DriverLibraryUnavailable) carrying the recorded CPU reason, so the resident path surfaces a structured error instead of silently falling back to the CPU.
• [GpuMode::Auto] / [GpuMode::Off] — preserve the existing probe-first behavior bit-for-bit: this is a thin wrapper over Self::global that maps the None case to the same typed error without ever forcing the runtime on or changing any numerics. Auto callers treat the Err exactly as they treated global().is_none() today (fall back to CPU); only the Required caller propagates it.

This does NOT alter global()/cuda_context_for/ensure_cuda_runtime_device; it only adds the residency gate on top of the working Auto path.

pub fn policy(&self) -> &GpuDispatchPolicy

pub fn selected_device(&self) -> &GpuDeviceInfo

impl GpuRuntime

pub fn device_ordinals(&self) -> Vec<usize>

Ordinals of all usable devices, highest-score first.

self.devices is already score-sorted at probe time, so this simply projects out the ordinals. Empty only if the probe somehow produced no devices (the public probe() guarantees at least one on Ok(Some(_))).

pub fn device_count(&self) -> usize

Number of usable devices in the pool.

pub fn memory_budget_for(&self, ordinal: usize) -> usize

Per-device byte budget: free memory capped at half of total, matching the primary-device budget computed in device_runtime::probe. Falls back to the primary memory_budget_bytes when the ordinal is not in the pool so a caller that passes a stale ordinal still gets a usable (conservative) budget rather than zero.

Trait Implementations

impl Clone for GpuRuntime

fn clone(&self) -> GpuRuntime

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GpuRuntime

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

Formats the value using the given formatter.