API

The ElcoreNN API consists of the following parts:

• elcorenn/elcorenn.h: ElcoreNN CPU library API.

ElcoreNN CPU library API

elcorenn/elcorenn.h defines the ElcoreNN CPU library API functions.

void InitBackend()

Initializes internal DSPs resources.

void ReleaseDevice()

Releases internal DSPs resources.

typedef unsigned int ENNModelId

Model ID.

ENNModelId is a model descriptor. That descriptor refers to the model loaded into DSP (Elcore50) memory. Use LoadModel function to easily load model into DSP memory.

ENNModelId LoadModel(const char *model_json, const char *model_weights)

Loads model from files.

Parameters

• model_json – [in] The description of the model saved in json format

• model_weights – [in] The binary file of model’s weights

Returns

Model ID

void InvokeModel(ENNModelId model_id, float *input_data, float *output_data, uint32_t batch_size)

Runs model inference.

Parameters

• model_id – [in] Model ID

• input_data – [in] Input data

• output_data – [out] Output data

• batch_size – [in] Batch size dimension in input data

The function takes model input as a float array and puts network’s result into a float array.

Note

ElcoreNN uses the data parallelization paradigm. Input data distributes between DSP cores by batch dimension.

void SaveModelStatisticToCSV(ENNModelId model_id, const char *file_path)

Saves model time statistic to a CSV file.

Parameters

• model_id – [in] Model ID

• file_path – [in] Path to CSV file

During inference, ElcoreNN collects number of cores cycles instructions for each layer. This can be useful for performance analysis.