Struct CudaBackendContext 

pub struct CudaBackendContext {
    pub ctx: Arc<CudaContext>,
    pub stream: Arc<CudaStream>,
    pub module: PtxModuleCache,
    pub arena: Mutex<DeviceArena>,
}

The process-wide device handles every cudarc backend stores after a successful probe: the CudaContext, its default CudaStream, the lazily NVRTC-compiled PtxModuleCache, and the bucketed DeviceArena of reusable f64 device buffers (held under a Mutex because large-scale fits dispatch from multiple rayon worker threads; the mutex is only held during alloc / release, not across kernel launches). Module-specific backends (bms_flex, survival_flex, …) wrap one of these as their inner context so the host-side scaffolding (arena pooling, module cache, mutex around alloc) is uniform instead of duplicated per backend.

Fields

ctx: Arc<CudaContext>

stream: Arc<CudaStream>

module: PtxModuleCache

arena: Mutex<DeviceArena>

Implementations

impl CudaBackendContext

pub fn from_parts(parts: CudaBackendParts) -> Self

Build the stored context from a fresh CudaBackendParts probe result: adopt its context and stream, start an empty module cache (the backend’s eager-compile step fills it), and an empty device arena. The probe’s compute capability is consumed by the probe path itself and is not retained here.