Special Session: Reliability Analysis for AI/ML Hardware

Artificial intelligence (AI) and Machine Learning (ML) are becoming pervasive in today's applications, such as autonomous vehicles, healthcare, aerospace, cybersecurity, and many critical applications. Ensuring the reliability and robustness of the underlying AI/ML hardware becomes our paramoun...

Full description

Saved in:
Bibliographic Details
Main Authors: Kundu, Shamik, Basu, Kanad, Sadi, Mehdi, Titirsha, Twisha, Song, Shihao, Das, Anup, Guin, Ujjwal
Format: Conference Proceeding
Language:English
Subjects:
deep learning accelerator
Degradation
Hardware
Machine learning
neuromorphic computing
Neuromorphics
Performance evaluation
Random access memory
Reliability
Robustness
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial intelligence (AI) and Machine Learning (ML) are becoming pervasive in today's applications, such as autonomous vehicles, healthcare, aerospace, cybersecurity, and many critical applications. Ensuring the reliability and robustness of the underlying AI/ML hardware becomes our paramount importance. In this paper, we explore and evaluate the reliability of different AI/ML hardware. The first section outlines the reliability issues in a commercial systolic array-based ML accelerator in the presence of faults engendering from device-level non-idealities in the DRAM. Next, we quantified the impact of circuit-level faults in the MSB and LSB logic cones of the Multiply and Accumulate (MAC) block of the AI accelerator on the AI/ML accuracy. Finally, we present two key reliability issues- circuit aging and endurance in emerging neuromorphic hardware platforms and present our system-level approach to mitigate them.
ISSN:2375-1053
DOI:10.1109/VTS50974.2021.9441050