Electronic device and controlling method of electronic device

A method for controlling an electronic apparatus, the electronic apparatus comprising memory configured to store data corresponding to a neural network model, and a neural network accelerator comprising a buffer configured to temporarily store the data corresponding to the neural network model and a core configured to perform a computation on the neural network model based on the data stored in the buffer, and the method comprising:

• determining a plurality of combinations comprising fused layers and non-fused layers based on a method of selecting and fusing adjacent layers of the neural network model;
• based on a capacity of the buffer, determining a size of a tile capable of being processed in one computation in the core to acquire feature values output by the fused layers and the non-fused layers;
• based on a first memory usage and computation time for storing the feature values in the buffer, determining whether to store the feature values in the memory;
• based on determining the size of the tile and determining to store the feature values in the memory, identifying a first combination among the plurality of combinations to be used in a computation of the neural network model by:
• calculating a data transmission time between the buffer and the memory, and
• calculating a computation time of the core according to the plurality of combinations
• converting the data corresponding to the neural network model into a first graph of a predetermined form;
• converting the first graph into a second graph corresponding to the first combination;
• and
• based on the second graph, generating code in which the data corresponding to the neural network model can be processed in the neural network accelerator.

A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor of an electronic apparatus, the electronic apparatus comprising:

• memory configured to store data corresponding to a neural network model;
• and
• a neural network accelerator comprising a buffer configured to temporarily store the data corresponding to the neural network model and a core configured to perform a computation on the neural network model based on the data stored in the buffer,
• cause the at least one processor to:
• determine a plurality of combinations comprising fused layers and non-fused layers based on a method of selecting and fusing adjacent layers of the neural network model;
• based on a capacity of the buffer, determine a size of a tile capable of being processed in one computation in the core to acquire feature values output by the fused layers and the non-fused layers;
• based on a first memory usage and computation time for storing the feature values in the buffer, determine whether to store the feature values in the memory;
• based on determining the size of the tile and determining to store the feature values in the memory, identify a first combination among the plurality of combinations to be used in a computation of the neural network model by:
• calculating a data transmission time between the buffer and the memory, and
• calculating a computation time of the core according to the plurality of combinations,
• convert the data corresponding to the neural network model into a first graph of a predetermined form,
• convert the first graph into a second graph corresponding to the first combination, and
• based on the second graph, generate code in which the data corresponding to the neural network model can be processed in the neural network accelerator.