Struct AlgeonGpuDeviceConfig 

pub struct AlgeonGpuDeviceConfig { /* private fields */ }

Canonical device profile bound to an explicit process-scoped GPU memory ownership promise.

Re-exports runtime-owned device construction types under application-facing names. They share type identity with runtime definitions without introducing adapter-specific defaults or separate validation. Pure per-device construction value binding a profile to deployment ownership.

The profile owns every device-local default; this value only completes the binding with the process owner’s explicit GpuMemoryOwnership. Backend construction resolves installation bounds and validates the bound value.

Implementations

impl GpuBackendDeviceConfig

pub fn homogeneous( device_ordinals: impl IntoIterator<Item = usize>, template: &GpuBackendDeviceProfile, memory_ownership: GpuMemoryOwnership, ) -> Vec<GpuBackendDeviceConfig>

Builds one device config per ordinal from a shared template profile.

Every returned config clones the template policy (capacity, reserve, query limit, attempts, bounds, capabilities, telemetry) and rebinds only the device ordinal; the template’s own ordinal is ignored. The deployment ownership is shared by every device. This is the shorthand for the common homogeneous multi-device deployment; heterogeneous devices still declare one Self::new each.

pub fn new( profile: GpuBackendDeviceProfile, memory_ownership: GpuMemoryOwnership, ) -> GpuBackendDeviceConfig

Binds a device profile to the deployment ownership promise. Validation occurs when the backend builder validates or builds this config.

pub fn profile(&self) -> &GpuBackendDeviceProfile

Returns the device-local construction policy bound to this ownership promise.

pub fn device_ordinal(&self) -> usize

Returns the CUDA device ordinal selected by this declaration.

pub fn device_capabilities(&self) -> &DeviceCapabilities

Immutable native execution capabilities selected for this device.

pub fn memory_ownership(&self) -> GpuMemoryOwnership

Returns the deployment ownership promised by the process owner.

pub fn memory_limit(&self) -> GpuDeviceMemoryLimit

Returns the unresolved admission capacity policy, resolved at device discovery.

pub fn backend_reserve_bytes(&self) -> u64

Returns bytes reserved outside managed query and cache capacity. The default is zero.

pub fn cache_cap_bytes(&self) -> u64

Returns the accounted resident-cache ceiling in bytes. The default is zero.

pub fn default_query_limit_bytes(&self) -> Option<u64>

Returns the explicit default query grant in bytes. None requests floor((managed_capacity_bytes - cache_cap_bytes) / max_active_attempts) after device capacity resolution.

pub fn source_work_per_attempt(&self) -> usize

Returns auxiliary source-work slots reserved for each active attempt. The default is one.

pub fn max_active_attempts(&self) -> usize

Returns the maximum simultaneously admitted attempts on this device. The default is two.

pub fn install_telemetry(&self) -> bool

Returns whether device telemetry is installed. New profiles enable it.

Trait Implementations

impl Clone for GpuBackendDeviceConfig

fn clone(&self) -> GpuBackendDeviceConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GpuBackendDeviceConfig

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

Formats the value using the given formatter.

impl Eq for GpuBackendDeviceConfig

impl PartialEq for GpuBackendDeviceConfig

fn eq(&self, other: &GpuBackendDeviceConfig) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for GpuBackendDeviceConfig