Search:

home theater basics home theater build a home theater room surround sound setup speakers plasma hdtv lcd projector dvd oled speaker wire home theater lighting seating blu-ray home theater setups HDMI 3D television bluray players 3D tv



Running Large Graph Algorithms: Evaluation of Current State-Of-the-Art and Lessons Learned

Build a Home Theater
Build a Home Theater Build a Home Theater
Build a Home Theater

Google Tech TalkFebruary 11, 2010ABSTRACTPresented by Dr. Andy Yoo, Lawrence Livermore National Laboratory.Graphs have gained a lot of attention in recent years and have been a focal point in many emerging disciplines such as web mining, computational biology, social network analysis, and national security, just to name a few. These so-called scale-free graphs in the real world have very complex structure and their sizes already have reached unprecedented scale. Furthermore, most of the popular graph algorithms are computationally very expensive, making scalable graph analysis even more challenging. To scale these graph algorithms, which have different run-time characteristics and resource requirements than traditional scientific and engineering applications, we may have to adopt vastly different computing techniques than the current state-of-art. In this talk, I will discuss some of the findings from our studies on the performance and scalability of graph algorithms on various computing environments at LLNL, hoping to shed some light on the challenges in scaling large graph algorithms.Andy Yoo is a computer scientist in the Center for Applied Scientific Computing (CASC). His current research interests are scalable graph algorithms, high performance computing, large-scale data management, and performance evaluation. He has worked on the large graph problems since 2004. In 2005, he developed a scalable graph search algorithm and demonstrated it by searching a graph with billions of edges on IBM BlueGene/L, then the largest and fastest supercomputer. Andy was nominated for 2005 Gordon Bell award for this work. He is currently working on finding right combination of architecture, systems, and programming model to run large graph algorithms.Andy earned his Ph.D. degree in Computer Science and Engineering from the Pennsylvania State University in 1998. He joined LLNL in 1998. Andy is a member of the ACM, IEEE and the IEEE Computer Society, and SIAM.

Channel: Science & Technology
Uploaded: November 30, 1999 at 12:00 am
Author: GoogleTechTalks

Length: 50:37
Rating: 4.714286
Views: 14558

Tags: google  tech  talk  mathematics  web  mining  

Video Url:


Embed Code:

Video Comments

alinasofials (November 30, 1999 at 12:00 am)
Asian wives alone and try to chat her #lushfmlk.info#
jenssoderberg (November 30, 1999 at 12:00 am)
For the love of god, Google, the company who would like to index all of the worlds information. ..A bit of interference, not the first time in google tech talks. But, the first time ought to be enough. -You lost me
NuncNuncNuncNunc (November 30, 1999 at 12:00 am)
Google, how about community driven caption correction as a youtube app. "breadth first search" and "naive" were fairly consistently incorrect & "huddle" may have been "how to"
desitodo (November 30, 1999 at 12:00 am)
it's good that there are subs
Qulopuaa (November 30, 1999 at 12:00 am)
Does this have any implications in online communitys like world of warcraft or is this 20 years in the future and then its obsolete
lordoftheweb2006 (November 30, 1999 at 12:00 am)
Comment on this video
beardymonger (November 30, 1999 at 12:00 am)
Put the computer generated CC for some fun ;-)I guess the accent didn't help either.
0MoTheG (November 30, 1999 at 12:00 am)
there is somekind of volume pumpingand papershifting going on, the offsites didn't deactivate their mics.in a dataflow model, isn't there a lot of datapassing because the context/progress has to be passed with the data? there is no locality to the current state of processing.? is that what he said at 45:20 ?

Build a Home Theater © 2008 All Rights Reserved.