A large-scale study of soft-errors on GPUs in the field

Parallelism provided by the GPU architecture has enabled domain scientists to simulate physical phenomena at a much faster rate and finer granularity than what was previously possible by CPU-based large-scale clusters. Architecture researchers have been investigating reliability characteristics of G...

Full description

Saved in:
Bibliographic Details
Main Authors: Bin Nie, Tiwari, Devesh, Gupta, Saurabh, Smirni, Evgenia, Rogers, James H.
Format: Conference Proceeding
Language:English
Subjects:
Architecture (computers)
Clusters
Computer architecture
Computer simulation
Correlation
Data processing
Devices
Error correction codes
Graphics processing units
Kernels
Projection
Reliability
Resource management
Simulators
Supercomputers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Parallelism provided by the GPU architecture has enabled domain scientists to simulate physical phenomena at a much faster rate and finer granularity than what was previously possible by CPU-based large-scale clusters. Architecture researchers have been investigating reliability characteristics of GPUs and innovating techniques to increase the reliability of these emerging computing devices. Such efforts are often guided by technology projections and simplistic scientific kernels, and performed using architectural simulators and modeling tools. Lack of large-scale field data impedes the effectiveness of such efforts. This study attempts to bridge this gap by presenting a large-scale field data analysis of GPU reliability. We characterize and quantify different kinds of soft-errors on the Titan supercomputer's GPU nodes. Our study uncovers several interesting and previously unknown insights about the characteristics and impact of soft-errors.
ISSN:2378-203X
DOI:10.1109/HPCA.2016.7446091