GNA Interface

Data Structures
struct	gna_config
struct	gna_model_header
struct	gna_model_info
struct	gna_inference_req
struct	gna_inference_stats
struct	gna_inference_resp

Enumerations
enum	gna_result {   GNA_RESULT_INFERENCE_COMPLETE , GNA_RESULT_SATURATION_OCCURRED , GNA_RESULT_OUTPUT_BUFFER_FULL_ERROR , GNA_RESULT_PARAM_OUT_OF_RANGE_ERROR ,   GNA_RESULT_GENERIC_ERROR }

Functions
static int	gna_configure (const struct device *dev, struct gna_config *cfg)
	Configure the GNA device. More...
static int	gna_register_model (const struct device *dev, struct gna_model_info *model, void **model_handle)
	Register a neural network model. More...
static int	gna_deregister_model (const struct device *dev, void *model)
	De-register a previously registered neural network model. More...
static int	gna_infer (const struct device *dev, struct gna_inference_req *req, gna_callback callback)
	Perform inference on a model with input vectors. More...

Detailed Description

This file contains the driver APIs for Intel's Gaussian Mixture Model and Neural Network Accelerator (GNA)

Enumeration Type Documentation

gna_result

enum gna_result

#include <include/drivers/gna.h>

Result of an inference operation

Enumerator
GNA_RESULT_INFERENCE_COMPLETE
GNA_RESULT_SATURATION_OCCURRED
GNA_RESULT_OUTPUT_BUFFER_FULL_ERROR
GNA_RESULT_PARAM_OUT_OF_RANGE_ERROR
GNA_RESULT_GENERIC_ERROR

Function Documentation

gna_configure()

static int gna_configure ( const struct device *  dev, struct gna_config *  cfg  )

inlinestatic

#include <include/drivers/gna.h>

Configure the GNA device.

Configure the GNA device. The GNA device must be configured before registering a model or performing inference

Parameters

dev	Pointer to the device structure for the driver instance.
cfg	Device configuration information

Return values

0	If the configuration is successful
A	negative error code in case of a failure.

gna_deregister_model()

static int gna_deregister_model ( const struct device *  dev, void *  model  )

inlinestatic

#include <include/drivers/gna.h>

De-register a previously registered neural network model.

De-register a previously registered neural network model from the GNA device De-registration may be done to free up memory for registering another model Once de-registered, the model can no longer be used to perform inference

Parameters

dev	Pointer to the device structure for the driver instance.
model	Model handle output by gna_register_model API

Return values

0	If de-registration of the model is successful.
A	negative error code in case of a failure.

gna_infer()

static int gna_infer ( const struct device *  dev, struct gna_inference_req *  req, gna_callback  callback  )

inlinestatic

#include <include/drivers/gna.h>

Perform inference on a model with input vectors.

Make an inference request on a previously registered model with an of input data vector A callback is provided for notification of inference completion

Parameters

dev	Pointer to the device structure for the driver instance.
req	Information required to perform inference on a neural network
callback	A callback function to notify inference completion

Return values

0	If the request is accepted
A	negative error code in case of a failure.

gna_register_model()

static int gna_register_model ( const struct device *  dev, struct gna_model_info *  model, void **  model_handle  )

inlinestatic

#include <include/drivers/gna.h>

Register a neural network model.

Register a neural network model with the GNA device A model needs to be registered before it can be used to perform inference

Parameters

dev	Pointer to the device structure for the driver instance.
model	Information about the neural network model
model_handle	Handle to the registered model if registration succeeds

Return values

0	If registration of the model is successful.
A	negative error code in case of a failure.