UTCS/Architecture: Vijay Pai/Purdue University Hardware and Software Support for Parallel Network Services ACES 2.402 Monday November 26 2007 3:00 p.m.

Contact Name: 
Jenna Whitney
Date: 
Nov 26, 2007 3:00pm - 4:00pm

There is a sign up schedule for this event:
htt

p://www.cs.utexas.edu/department/webevent/utcs/events/cgi/list_events.cgi
Type of Talk: UTCS Colloquium/Architecture

Speaker Name/Affil

iation: Vijay Pai/Purdue University

Date/Time: Monday November 26
2007 3:00 p.m.

Location: ACES 2.402

Host: Yale Patt
<

br>Talk Title: Hardware and Software Support for Parallel Network Services

Talk Abstract:
Although multicore processors are now pervasi

ve the
performance of such systems depends entirely on the
ability

of the target applications to exploit parallelism.
This talk first pre

sents Aspen a parallel programming
language and runtime system that cu

rrently targets
network service applications. Aspen programs resemble <

br>task flowcharts with the nodes being instances of compu-
tational mo

dules and the edges being unidirectional
communication channels. Aspen
automatically and
transparently supports task-level parallelism among

module instances and data-level parallelism across
different flows i

n an application or in some cases across
different work items within a
flow. Aspen adaptively
allocates threads to modules according to the

dynamic
workload seen at those modules. Experimental results
indic

ate performance competitive with (and sometimes
better than) current se

rver programming models while
using 54-96% fewer lines of user code.

This talk also presents LineSnort a self-securing programmable
Eth

ernet controller. LineSnort parallelizes the Snort network
intrusion de

tection system (NIDS) using concurrency across TCP
sessions and executes
those parallel tasks on multiple
low-frequency/low-power RISC cores. Li

neSnort additionally
exploits opportunities for intra-session concurrenc

y based on
domain-specific characteristics of NIDS. The system includes<

br>dedicated hardware for high-bandwidth data transfers and for
high-per

formance string matching. Detailed simulation results
show that LineSnor

t can achieve intrusion detection throughputs
in excess of 1 Gbps for fa

irly large rule sets thus offloading
the computationally difficult task
of intrusion detection from
a server''s host CPU and enabling protectio

n against both
external and LAN-based attacks.

This talk includes
research performed jointly with Derek
Schuff Gautam Upadhyaya and Sam
Midkiff.

Speaker Bio:

Vijay S. Pai received a BSEE degree in
1994 an MS degree
in Electrical and Computer Engineering in 1997 and
a Ph.D.
degree in Electrical and Computer Engineering in 2000 all
from Rice University. He joined the faculty of Purdue University
in Au

gust 2004. Prior to that he had served as an assistant
professor at Ri

ce University (2001-2004) and as a senior
developer at iMimic Networking
(1999-2001). He received the
NSF CAREER award in 2003 and Purdue%92s W

ilfred %93Duke%94
Hesselberth Award for Teaching Excellence in 2007.