Enum NativeReadPath 

pub enum NativeReadPath {
    RegisteredMappedRead,
    GpuDirectNvmePassthrough,
}

Native-read strategy used by NvmeGpuIngestDriver.

Variants

RegisteredMappedRead

IORING_OP_READ_FIXED into a registered GPU-visible mapping.

This removes the userspace bounce buffer but still uses normal file reads submitted by the CPU. It is the compatibility path for filesystems and GPU memory APIs that do not expose BAR1 peer DMA.

GpuDirectNvmePassthrough

IORING_OP_URING_CMD NVMe read into BAR1 peer memory.

This is the canonical native ingest path: CPU submits one NVMe command, the device DMAs bytes directly into GPU-owned memory, and the megakernel consumes the published slot.

Trait Implementations

impl Clone for NativeReadPath

fn clone(&self) -> NativeReadPath

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for NativeReadPath

impl Debug for NativeReadPath

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

Formats the value using the given formatter.

impl Eq for NativeReadPath

impl PartialEq for NativeReadPath

fn eq(&self, other: &NativeReadPath) -> 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 StructuralPartialEq for NativeReadPath