Skip to main content

Crate ironaccelerator_qnn

Crate ironaccelerator_qnn 

Source
Expand description

§ironaccelerator-qnn

Qualcomm AI Engine backend, dispatching through the QNN SDK:

  • HTP (Hexagon Tensor Processor) — primary NPU path; INT8 / FP16 with HMX matrix-engine acceleration on Hexagon v73+.
  • HVX — fallback Hexagon vector path for ops not yet supported by HMX.
  • Adreno GPU — alternative target for FP16 graphs.

Scope is the same as every other backend here: probe the runtime, enumerate targets, report capability bits. QNN graphs are built ahead of time by the SDK, so graph construction and quantisation calibration belong to the consumer, not to this crate.

§Status

v0.1 scaffold. Library probe via libloading; FFI bindings for QnnApi.h, QnnContext.h, QnnGraph.h, QnnHtp.h are tracked next.

Re-exports§

pub use backend::QnnBackend;
pub use backend::QNN_BACKEND;
pub use iron_qnn_sys as sys;

Modules§

backend
QNN Backend impl. Enumerate-by-probing: try HTP / GPU / CPU / DSP and emit a DeviceDescriptor for each target whose library loads.
drv
Safe QNN driver layer. Opens a backend library, creates a context, and exposes graph construction + execute in an API that mirrors the CUDA/ROCm drv modules.

Functions§

register
Registers the QNN backend with reg.