A New Hardware/Software Platform and a New 1/E Neutron Source for Soft Error Studies: Testing FPGAs at the ISIS Facility

Abstract-We investigate atmospheric neutron effects on floating-gate cells in NAND Flash memory devices. Charge loss is shown to occur, particularly at the highest program levels, causing raw bit errors in multilevel cell NAND, but to an extent that does not challenge current mandatory error correction specifications. We discuss the physical mechanisms and analyze scaling trends, which show a rapid increase in sensitivity for decreasing feature size.

show abstract

“…The VESUVIO neutron spectrum reasonably reproduces the terrestrial environment, with several orders of magnitude of acceleration [17], [18].…”

Section: Experiments and Devicesmentioning

confidence: 75%

Neutron-Induced Upsets in NAND Floating Gate Memories

Gerardin

Bagatin

Ferrario

et al. 2012

IEEE Trans. Device Mater. Relib.

View full text Add to dashboard Cite

show abstract

“…LANSCE flux is suitable to mimic the terrestrial neutron effects on electronic devices [48]. This means that error rates measured at LANSCE scaled down to the natural flux provide the predicted error rates on a realistic application expressed in Failure In Time (FIT).…”

Section: Neutron Beam Setupmentioning

confidence: 99%

Experimental and analytical study of Xeon Phi reliability

Oliveira

Pilla

DeBardeleben

et al. 2017

Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

We present an in-depth analysis of transient faults effects on HPC applications in Intel Xeon Phi processors based on radiation experiments and high-level fault injection. Besides measuring the realistic error rates of Xeon Phi, we quantify Silent Data Corruption (SDCs) by correlating the distribution of corrupted elements in the output to the application's characteristics. We evaluate the benefits of imprecise computing for reducing the programs' error rate. For example, for HotSpot a 0.5% tolerance in the output value reduces the error rate by 85%.We inject different fault models to analyze the sensitivity of given applications. We show that portions of applications can be graded by different criticalities. For example, faults occurring in the middle of LUD execution, or in the Sort and Tree portions of CLAMR, are more critical than the remaining portions. Mitigation techniques can then be relaxed or hardened based on the criticality of the particular portions.

show abstract

“…LANSCE and ISIS fluxes are suitable to mimic the terrestrial neutron flux effects on electronic devices [42]. This means that error rates measured at LANSCE or ISIS scaled down to the natural flux provide the predicted error rates on a realistic application expressed in Failure In Time (FIT).…”

Section: Neutron Beam Test Experimental Setupmentioning

confidence: 99%

Radiation-Induced Error Criticality in Modern HPC Parallel Accelerators

Oliveira

Pilla

Hanzich

et al. 2017

2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)

View full text Add to dashboard Cite

Abstract-In this paper, we evaluate the error criticality of radiation-induced errors on modern High-Performance Computing (HPC) accelerators (Intel Xeon Phi and NVIDIA K40) through a dedicated set of metrics. We show that, as long as imprecise computing is concerned, the simple mismatch detection is not sufficient to evaluate and compare the radiation sensitivity of HPC devices and algorithms. Our analysis quantifies and qualifies radiation effects on applications' output correlating the number of corrupted elements with their spatial locality. Also, we provide the mean relative error (dataset-wise) to evaluate radiation-induced error magnitude.We apply the selected metrics to experimental results obtained in various radiation test campaigns for a total of more than 400 hours of beam time per device. The amount of data we gathered allows us to evaluate the error criticality of a representative set of algorithms from HPC suites. Additionally, based on the characteristics of the tested algorithms, we draw generic reliability conclusions for broader classes of codes. We show that arithmetic operations are less critical for the K40, while Xeon Phi is more reliable when executing particles interactions solved through Finite Difference Methods. Finally, iterative stencil operations seem the most reliable on both architectures.

show abstract

A New Hardware/Software Platform and a New 1/E Neutron Source for Soft Error Studies: Testing FPGAs at the ISIS Facility

Cited by 79 publications

References 16 publications

Neutron-Induced Upsets in NAND Floating Gate Memories

Neutron-Induced Upsets in NAND Floating Gate Memories

Experimental and analytical study of Xeon Phi reliability

Radiation-Induced Error Criticality in Modern HPC Parallel Accelerators

Contact Info

Product

Resources

About