cs.virginia/~krw7c/avf.html

http://www.cs.virginia.edu/~krw7c/avf.html

BitRead?

Bit has error

protection

benign faultno error

yes no

Does bit matter?

no

Does bit matter?

Particle StrikeCauses Bit Flip!

Detectiononly

Detection & Correctionbenign fault

no error

benign faultno error

Silent Data Corruption

yes no

True Detected Unrecoverable

Error

False Detected Unrecoverable

Error

yes no

Outliers

We identify strong correlations between structural AVF values and a small set of processor metrics.

Using linear and quadratic regression, we determined an AVF characterization that uses only a few easily measurable variables. These characterizations can be used to predict AVF accurately.

FIT = Failure in Time = 1 failure in a billion hoursIntel Corporation

AVFbit = Probability that a Bit Matters

=

# of Visible Errors

# of Bit Flips from Particle Strikes

As soft errors become more of a problem, protection will be needed even for every day PCs.

Providing total redundancy is too expensive and assumes that AVF is 100%.

Our work shows that AVF varies over time and across applications.

n0

Kristen Walcott, Greg Humphreys, Sudhanva Gurumurthi

University of Virginia{walcott, humper, gurumurthi}@cs.virginia.edu

Dynamic Prediction of Architectural Vulnerability

What bits matter?

Computer Scienceat the UNIVERSITY of VIRGINIA

Rising Problem Dynamic AVF Prediction

Calculating Vulnerability With an accurate predictor, redundancy may be turned on only when vulnerability is high. Preliminary results show that partial redundancy provides a significant performance boost over full redundancy. Next we will perform a more rigorous exploration of the design space of partial redundant multithreading implementations and investigate redundancy toggling policies.

Future Work

Prediction Results

Challenge

2 SimPoints of bzip2

galgel benchmark

• Transient faults due to particle strikes are a key challenge in microprocessor design.

• As transistor counts increase exponentially, per-chip faults are a growing burden.

• Spatial and temporal redundancy techniques are used to protect against faults.

• Redundancy techniques assume that any fault will result in a visible program error (i.e., the Architectural Vulnerability Factor (AVF) is 100 percent).

• Over-design can hurt performance and drain power.

Microarchitectural Metrics

(Cor

rela

tion

to A

VF

)

1

10

100

1000

10000

100000

2003 2004 2005 2006 2007 2008 2009 2010 2011 2012

Dat

a C

orru

ptio

n FI

T F

IT

1000 MTBF Goal Error Rate