Exploring Software Models for the Resilience Analysis of Deep Learning Accelerators: the NVDLA Case Study

Deep learning accelerator models described with software imperative languages are frequently used for their large-scale reliability analysis in order to overcome the prohibitive simulation times of logic-level and RTL models. However, they are faced with the challenge of preserving consistency betwe...

Full description

Saved in:
Bibliographic Details
Main Authors: Veronesi, A., Dall'Occo, F., Bertozzi, D., Favalli, M., Krstic, M.
Format: Conference Proceeding
Language:English
Subjects:
Analytical models
Deep learning
Hardware
Microarchitecture
Software
Software algorithms
Software reliability
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning accelerator models described with software imperative languages are frequently used for their large-scale reliability analysis in order to overcome the prohibitive simulation times of logic-level and RTL models. However, they are faced with the challenge of preserving consistency between software-visible variables and faulty microarchitectural states. The goal of this work is to determine a suitable accelerator modelling that enables analysis without overloading the simulation engine. Toward this goal, the paper explores different accelerator modelling strategies featuring increasing levels of hardware visibility. They are compared in their capability to gain insights into the reliability of the multiply-and-accumulate (MAC) pipeline of an industry-standard deep learning accelerator from NVIDIA. Our results show that subtle microarchitectural details that are typically overlooked by competing approaches play a relevant role in determining accelerator reliability.
ISSN:2473-2117
DOI:10.1109/DDECS54261.2022.9770169