Loading Events

« All Events

  • This event has passed.

Colloquium – Elisa Heymann & Barton Miller

April 26 @ 9:50 am - 11:30 am

Elisa Heymann
University of Wisconsin‐Madison

April 26, 2017
2250 WEB
refreshments 9:50am
lecture 10:00am

Host: Mary Hall

Can We Make Real World Software More Secure?

Abstract:
Security is crucial to the software that we all develop and use. With the incredible growth of web, cloud, and mobile services, security is becoming even more critical. Typical security practices, such as securing your network and using software assurance tools – tools that scan the source or binary code of a program to find weaknesses – are your first line of defense, but they are not enough. Every service that you deploy is a window into your data center from the outside world, and a window that could be exploited by an attacker. These issues become even more pressing for critical infrastructure, such as systems that support energy or transportation services.

To assess in depth the security of a software project I will present our First Principle Vulnerability Assessment (FPVA) methodology, which is aimed at finding vulnerabilities affecting the most critical parts of a systems, the high value assets. Security is, among other things, an economic process, so we must be able to focus our time and attention on the parts of the system would produce the greatest impact if they were exploited. I will share our experiences gained from performing vulnerability assessments of critical middleware. Finally I will talk about a pioneering project bringing in‐depth software assessment to a new area of critical infrastructure, that of maritime container shipping.


Barton Miller
University of Wisconsin‐Madison

Scaling Up to Large (Really Large) Systems

Abstract:
I will discuss the problem of developing tools and middleware for large scale parallel environments. We are especially interested in systems, both leadership class parallel computers and clusters that have 100,000’s or even millions of processors. The infrastructure that we have developed to address this problem is called MRNet, the Multicast/Reduction Network. MRNet’s approach to scale is to structure control and data flow in a tree‐based overlay network (TBON) that allows for efficient request distribution and flexible data reductions.

I will then present a brief overview of the MRNet design, architecture, and computational model and then discuss a few of the applications of MRNet. The applications include scalable automated performance analysis tools, STAT (a scalable stack trace analyzer running currently on millions of cores), Totalview (a popular and mature parallel debugger), and an extreme‐scale cluster algorithm that we developed (called “Mr. Scan”) that harnessed 32K GPUs.

Details

Date:
April 26
Time:
9:50 am - 11:30 am
Event Category:

Venue

2250 WEB