Neutron-Induced Soft Errors in Graphic Processing Units

Rech, Paolo; Aguiar, C.; Ferreira, Ronaldo Rodrigues; Silvestri, Marco; Griffoni, A.; Frost, Christopher; Carro, Luigi

doi:10.1109/redw.2012.6353714

Cited by 19 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The newest technologies are so sensitive to radiation that their usage will be compromised even at the sea level, as predicted in the literature [3]. In [4] it is shown that modern 22nm GPU cards are susceptible to such an error rate that makes their usage unfeasible in critical embedded systems. However, industry is already investing in GPU architectures as the platform of choice for high performance and low power embedded computing, such as the ARM Mali® embedded GPU [5].…”

Section: Introductionmentioning

confidence: 98%

Compiler Optimizations Do Impact the Reliability of Control-Flow Radiation Hardened Embedded Software

Parizi

Ferreira

Carro

et al. 2013

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. This paper characterizes how compiler optimizations impact software control-flow reliability when the optimized application is compiled with a technique to enable the software itself to detect and correct radiation induced softerrors occurring in branches. Supported by a comprehensive fault injection campaign using an established benchmark suite in the embedded systems domain, we show that the careful selection of the available compiler optimizations is necessary to avoid a significant decrease of software reliability while sustaining the performance boost those optimizations provide.

show abstract

Section: Introductionmentioning

confidence: 98%

Compiler Optimizations Do Impact the Reliability of Control-Flow Radiation Hardened Embedded Software

Parizi

Ferreira

Carro

et al. 2013

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

show abstract

“…As we have demonstrated in previous works, radiationinduced errors, including those generated by the terrestrial neutron radiation environment at ground level, are one of the major issues for the newest GPU cores reliability [4], [5]. Still, the state of the art lacks studies describing radiation test methods for extremely parallel systems and parallel algorithm behavior analysis in radiation environments.…”

Section: Introductionmentioning

confidence: 99%

Software-Based Hardening Strategies for Neutron Sensitive FFT Algorithms on GPUs

Pilla

Rech

Silvestri

et al. 2014

IEEE Trans. Nucl. Sci.

Self Cite

View full text Add to dashboard Cite

In this paper we assess the neutron sensitivity of Graphics Processing Units (GPUs) when executing a Fast Fourier Transform (FFT) algorithm, and propose specific software-based hardening strategies to reduce its failure rate. Our research is motivated by experimental results with an unhardened FFT that demonstrate a majority of multiple errors in the output in the case of failures, which are caused by data dependencies. In addition, the use of the built-in error-correction code (ECC) showed a large overhead, and proved to be insufficient to provide high reliability. Experimental results with the hardened algorithm show a two orders of magnitude failure rate improvement over the original algorithm (one order of magnitude over ECC) and an overhead 64% smaller than ECC

show abstract

“…We have already demonstrated in [6][7] that radiation-induced errors, including from the terrestrial neutron radiation environment, are one of the major issues for the newest GPU cores reliability. While CPU radiation responses, test procedure, and hardening techniques are well documented, and standardized [8] [9], only few papers describe possible radiation test methods for extreme parallel systems and fewer analyze parallel algorithms behaviors in radiation environments.…”

Section: Introductionmentioning

confidence: 99%

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

Rech

Pilla

Silvestri

et al. 2013

Proceedings of the 3rd Workshop on Fault-Tolerance for HPC at Extreme Scale

View full text Add to dashboard Cite

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

show abstract

Neutron-Induced Soft Errors in Graphic Processing Units

Cited by 19 publications

References 16 publications

Compiler Optimizations Do Impact the Reliability of Control-Flow Radiation Hardened Embedded Software

Compiler Optimizations Do Impact the Reliability of Control-Flow Radiation Hardened Embedded Software

Software-Based Hardening Strategies for Neutron Sensitive FFT Algorithms on GPUs

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

Contact Info

Product

Resources

About