23  * Gaussian Mixture Model and Neural Network Accelerator (GNA)
41  * GNA Neural Network model header
42  * Describes the key parameters of the neural network model
61  * GNA Neural Network model information to be provided by application
62  * during model registration
71  * Request to perform inference on the given neural network model
120 				struct gna_model_info *model,
143  * registering a model or performing inference
161  * @brief Register a neural network model
163  * Register a neural network model with the GNA device
164  * A model needs to be registered before it can be used to perform inference
167  * @param model Information about the neural network model
168  * @param model_handle Handle to the registered model if registration succeeds
170  * @retval 0 If registration of the model is successful.
174 				     struct gna_model_info *model,  in gna_register_model()  argument
180 	return api->register_model(dev, model, model_handle);  in gna_register_model()
184  * @brief De-register a previously registered neural network model
186  * De-register a previously registered neural network model from the GNA device
187  * De-registration may be done to free up memory for registering another model
188  * Once de-registered, the model can no longer be used to perform inference
191  * @param model Model handle output by gna_register_model API
193  * @retval 0 If de-registration of the model is successful.
196 static inline int gna_deregister_model(const struct device *dev, void *model)  in gna_deregister_model()  argument
201 	return api->deregister_model(dev, model);  in gna_deregister_model()
205  * @brief Perform inference on a model with input vectors
207  * Make an inference request on a previously registered model with an of