A DSP-enhanced programmable processor and software library can be used for efficient implementation of low/mid-end machine learning inference.
By Pieter van der Wolf, Principal R&D Engineer, Synopsys Inc. and Dmitry Zakharov, Senior Software Engineer, Synopsys Inc
Smart IoT devices that interact intelligently with their users are appearing in many application areas. Increasingly, these devices apply machine learning technology for processing captured sensor data, so that smart actions can be taken based on recognized patterns. This white paper presents a programmable processor and an associated software library for the efficient implementation of low/mid-end machine learning inference. The DSP-enhanced ARC EM9D processor offers capabilities, such as vector MAC instructions and XY memory with advanced address generation units, that are key to the efficient implementation of machine learning inference engines. The complete and highly optimized embARC MLI library makes effective use of the ARC EM9D processor to efficiently support a wide range of low/mid-end machine learning applications.
Click here to read more.
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
Leave a Reply