End-to-end synthesis of dynamically controlled machine learning accelerators

S Curzel, NB Agostini, VG Castellana… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Edge systems are required to autonomously make real-time decisions based on large
quantities of input data under strict power, performance, area, and other constraints. Meeting …

Towards automatic and agile AI/ML accelerator design with end-to-end synthesis

JJ Zhang, NB Agostini, S Song, C Tan… - 2021 IEEE 32nd …, 2021 - ieeexplore.ieee.org
Domain-specific designs offer greater energy efficiency and performance gain than general-
purpose processors. For this reason, modern system-on-chips have a significant portion of …

[PDF][PDF] Accelerating Data Processing at the Edge with Extreme Specialization

A Tumeo, M Minutoli, V Castellana… - ASCR Workshop on …, 2022 - re.public.polimi.it
Challenges and Current Approaches. The US Department of Energy (DOE) operates the
largest collection of experimental scientific instruments in the world for a variety of scientific …