Neutron sensitivity and software hardening strategies for matrix multiplication and FFT on graphics processing units

Authors:
Paolo Rech;Laercio Pilla;Francesco Silvestri;Philippe Navaux;Luigi Carro
Affiliations:
UFRGS, Porto Alegre, Brazil;UFRGS, Porto Alegre, Brazil;Università di Padova, Padova, Italy;UFRGS, Porto Alegre, Brazil;UFRGS, Porto Alegre, Brazil
Venue:
Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale
Year:
2013

Citing 8
Cited 0

Linear algebra operators for GPU implementation of numerical algorithms

ACM SIGGRAPH 2003 Papers
Efficient randomized pattern-matching algorithms

IBM Journal of Research and Development - Mathematics and computing
Algorithm-Based Fault Tolerance for Matrix Operations

IEEE Transactions on Computers
NVIDIA Tesla: A Unified Graphics and Computing Architecture

IEEE Micro
High-speed convolution and correlation

AFIPS '66 (Spring) Proceedings of the April 26-28, 1966, Spring joint computer conference
Bioinformatics
Programming Massively Parallel Processors: A Hands-on Approach

Programming Massively Parallel Processors: A Hands-on Approach
Neutron radiation test of graphic processing units

IOLTS '12 Proceedings of the 2012 IEEE 18th International On-Line Testing Symposium (IOLTS 2012)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we compare the radiation response of GPUs executing matrix multiplication and FFT algorithms. The provided experimental results demonstrate that for both algorithms, in the majority of cases, the output is affected by multiple errors. The architectural and code analysis highlight that multiple errors are caused by shared resources corruption or thread dependencies. The experimental data and analytical studies can be fruitfully employed to evaluate the expected error rate of GPUs in realistic applications and to design specific and optimized software-based hardening procedures.