Colloquia: Y. Charlie Hu/Purdue University Program-Counter-Based Prediction Techniques in Operating Systems in ACES 6.304

Contact Name: 
Jenna Whitney
Date: 
May 31, 2006 11:00am - 12:00pm


There is a signup schedule for this event.

Speak

er Name/Affiliation: Y. Charlie Hu/Purdue University

Talk Title: P

rogram-Counter-Based Prediction Techniques in Operating Systems

Date

/Time: May 31 2006 at 11:00 a.m.

Location: ACES 6.304

Host

: Mike Dahlin

Talk Abstract:
Program instructions uniquely ide

ntified by their program
counters (PCs) provide a convenient and accura

te means of
recording the context
of program execution and PC-based

prediction techniques
have been widely used for performance optimizatio

ns at the
architectural
level. Operating systems on the other hand
have not fully
explored
the benefits of PC-based prediction for res

ource management.
This work explores the potential benefits provided by
PC-based
prediction in operating systems (PCOS). In particular we
investigate the potential of using PC-based prediction techniques
for

managing I/O devices in operating systems.

As a first demonstration

of PCOS we developed a PC-based
access pattern classification techniqu

e (PCC) for buffer
cache management.
PCC allows the operating system
to correlate the I/O operations
with the program context in which they
are issued via the
PCs of the call instructions that trigger the I/O r

equests.
This correlation allows the operating system to classify
I

/O access pattern on a per-call-site
basis which achieves significantly

better accuracy than
previous per-file or per-application classificatio

n techniques.

We have also developed a PC-based technique (PCAP) for
power
management that dynamically learns the application I/O access patterns
and associated disk idle times to predict when an I/O device

can be shut down to save energy. PCAP uses path-based correlation
t

o observe
a particular sequence of I/O triggering instructions leading <

br>to each
idle period and accurately predicts future occurrences of that idle period.

Speaker Bio:
Y. Charlie Hu is an Assistant

Professor of Electrical and Computer
Engineering and Computer Science at
Purdue University. He received his
Ph.D. in Computer Science from Harva

rd University in 1997 and was a
research scientist at Rice University f

rom 1997 to 2001. Charlie
co-founded the IEEE Percom International Works

hop on Mobile
Peer-to-Peer Computing (MP2P) in 2004. He received the Hon

da
Initiation Grant Award in 2002 and the NSF CAREER Award in 2003. His

research interests are in operating systems distributed systems
ov

erlay networking wireless networking and high performance
computing.