University of British Columbia
Structural coding : a low-cost scheme to protect CNNs from large-granularity memory errors
Abstract
dc:descriptionConvolutional Neural Networks (CNNs) are broadly used in safety-critical applications such as autonomous vehicles. While demonstrating high accuracy, CNN models are vulnerable to Dynamic Random Access Memory (DRAM) errors corrupting their parameters, thereby degrading their accuracy. Unfortunately, existing techniques for protecting CNNs from memory errors are either costly or not complete, meaning that they fail to protect from large-granularity, multi-bit DRAM errors. In this thesis, we propose a software-implemented coding scheme, Structural Coding, which is able to achieve three orders of magnitude reduction in Silent Data Corruption (SDC) rates of CNNs under large-granularity memory errors. Its error correction coverage is also significantly higher than other software-techniques to protect CNNs from faults in the memory. Additionally, its average performance overhead on a real machine is less than 3%. The memory footprint overhead of Structural Coding is <27%, but can be reduced to 4.3% with application-specific tuning.
Degree
thesis:*- Name thesis:degree_name
- Master of Applied Science - MASc
- Level thesis:degree_level
- master's
- Discipline thesis:degree_discipline
- Electrical and Computer Engineering
- Grantor dc:publisher
- University of British Columbia
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Asgari Khoshouyeh, Ali
- Contributors dc:contributor
-
- Pattabiraman, Karthik
- Nair, Prashant J.
Rights
dc:rights- Statement dc:rights
-
- Attribution-NonCommercial-NoDerivatives 4.0 International
- Language dc:language
- eng
Identifiers
dc:identifier.*- Handle dc:identifier
- http://hdl.handle.net/2429/83530