Arhat is a specialized deep-learning framework that converts neural network descriptions into lean stand-alone executable code, which can be deployed directly on various platforms. The Arhat backend for Intel generates C++ code that directly calls oneAPI Deep Neural Network Library (oneDNN) API functions and can run on any modern Intel® CPU or GPU. Arhat includes the OpenVINO™ toolkit interoperability layer that consumes models produced by the OpenVINO™ Model Optimizer. We have used Arhat for a series of experiments aimed at benchmarking the 11th generation Intel® Core™ i7-1185G7E processor against NVIDIA* Jetson Xavier NX with various object detection neural networks. The benchmarking results demonstrate that the 11th generation Intel Core i7 processor is a powerful competitor in the embedded application domain.



Alexey Gokhberg is a software engineer with more than 25 years of experience in various industrial and academic branches. His professional interests include deep learning, high-performance computing, programming language construction, and computational geophysics.