Experimental Findings on the Sources of Detected Unrecoverable Errors in GPUs

We investigate the sources of Detected Unrecoverable Errors (DUEs) in GPUs exposed to neutron beams. Illegal memory accesses and interface errors are among the more likely sources of DUEs. ECC increases the launch failure events. Our test procedure has shown that ECC can reduce the DUEs caused by Illegal Address access up to 92

READ FULL TEXT

page 3

page 4

research
04/24/2019

Exploring Memory Persistency Models for GPUs

Given its high integration density, high speed, byte addressability, and...
research
10/03/2009

Hard Data on Soft Errors: A Large-Scale Assessment of Real-World Error Rates in GPGPU

Graphics processing units (GPUs) are gaining widespread use in computati...
research
09/10/2019

The Prevalence of Errors in Machine Learning Experiments

Context: Conducting experiments is central to research machine learning ...
research
01/17/2018

Rate-Distortion Performance of Sequential Massive Random Access to Gaussian Sources with Memory

In Sequential Massive Random Access (SMRA), a set of correlated sources ...
research
04/13/2021

ZMCintegral-v5.1: Support for Multi-function Integrations on GPUs

In this new version of ZMCintegral, we have added the functionality of m...
research
08/31/2019

Implicit Hari–Zimmermann algorithm for the generalized SVD on the GPUs

A parallel, blocked, one-sided Hari–Zimmermann algorithm for the general...
research
07/17/2020

EZLDA: Efficient and Scalable LDA on GPUs

LDA is a statistical approach for topic modeling with a wide range of ap...

Please sign up or login with your details

Forgot password? Click here to reset