HPC Garage

  • Increase font size
  • Default font size
  • Decrease font size
Vuduc Research Lab at Georgia Tech.

Back to school.

E-mail

The HPC Garage at Cypress

The HPC Garage and friends at Cypress to kick-off the 2010-2011 academic year.
 

GT named an NVIDIA CCOE.

E-mail

Georgia Tech has been named an NVIDIA CUDA Center of Excellence, to be led by Prof. Jeffrey Vetter, an Oak Ridge National Laboratory computer scientist with a joint appointment in our very own School of Computational Science and Engineering. Congratulations to Jeff and Georgia Tech!

http://www.marketwatch.com/story/nvidia-names-georgia-institute-of-technology-a-cuda-center-of-excellence-2010-08-23?reflink=MW_news_stmp 

 

CScADS'10 Autotuning.

E-mail

Attendees of the 2010 CScADS Workshop on Libraries and Autotuning for Petascale Applications  Just returned from the DOE-sponsored CScADS Workshop on Libraries and Autotuning for Petascale Applications, held this year in the lovely Snowbird, Utah. The agenda featured exciting developments in domain-specific optimization, software engineering, compilers, languages, and mechanized derivation techniques. Click here for the full agenda and slides.

CScADS Meeting Room at Snowbird Climbing the multicore/manycore mountain (Snowbird, Utah, USA)

 

realworldtech.com blurb.

E-mail

More blurbs! This one by realworldtech.com appears in a summary of HotPar'10:

http://www.realworldtech.com/page.cfm?ArticleID=RWT072610001641&p=6

Update: HPCwire mention:

http://www.hpcwire.com/blogs/Postcards-From-the-Edge-of-Parallel-Computing-99592644.html

 

SC'10 papers.

E-mail

Logo: 2010 ACM/IEEE Int'l. Conf. HPC, Networking, Storage, and Analysis (Supercomputing / SC)

We have two papers that will appear at this year's ACM/IEEE International Conference for High-Performance Computing, Networking, Storage, and Analysis, a.k.a., "Supercomputing" or "SC", to be held in New Orleans in November, including one by Aparna and another that is a Gordon Bell Prize Finalist!

Read more...
 

PMAA'10 in Basel.

E-mail

Jee and Rich just returned from the Sixth International Workshop on Parallel Matrix Algorithms and Applications (PMAA 2010), which the University of Basel in Switzerland hosted this year. There were many interesting talks, including a keynote by colleague and collaborator, George Biros, sessions on GPUs and autotuning in matrix computations, as well as Jee's reprise of his PPoPP 2010 talk on sparse matrix-vector multiply on GPUs.

View of the Rhine river in Basel, Switzerland.

The University of Basel campus abuts the Rhine river. Rich wonders how students and faculty there still manage to get so much great work done.

 

HotPar'10 & the real HP Garage.

E-mail

Rich just got back from the USENIX Workshop on Hot Topics in Parallelism (HotPar), where he presented the lab's meta-analysis of the potential and limitations of GPU systems. Slides for the talk should soon appear on the HotPar'10 page if they are not there already.

The workshop itself was great fun! In particular, it had a uniquely lively atmosphere, with highly interactive talk sessions, a prominent and high-quality poster session, great lunch discussions, all at an amazing price! (To reduce cost, we stayed and "workshopped" on Berkeley's Clark Kerr facilities. Lodging + all meals + registration was only about $600 or so. Amazing!)

The Original HP Garage. 

As an added bonus, Rich accidentally missed his flight back to ATL and so took a minute to drop by the original Hewlett-Packard Garage, depicted above. It's a great reminder of the kind of impact the HPC Garage hopes to have some day.

 

 

Bon voyage, CRUISE'10 crew!

E-mail

CRUISE 2010 Interns: Piyush Sao (IIT Madras) and Japnik Singh (IIT Bombay) 

Summer is over, meaning it's time to bid farewell to this year's CRUISE students. We were fortunate to have Japnik Singh (IIT Bombay) and Piyush Sao (IIT Madras) working with us. Keep an eye out for future publications based on their work.

Indeed, we can say confidently that their stay was quite an adventure, in the positive sense! Click on the link below to watch Japnik jumping out of an airplane (the big event is at the 1:30 mark):

http://www.youtube.com/watch?v=PPnqIM0e9OI 

 

TeraGrid'10.

E-mail

Brandon Hill presenting at TeraGrid'10 Tutorial on Analysis and Tuning for GPUsHyesoon Kim presenting at TeraGrid'10 Tutorial on Analysis and Tuning for GPUsRich Vuduc presenting at TeraGrid'10 Tutorial on Analysis and Tuning for GPUs

During the first week in August, we helped organize a GPU tutorial for the annual TeraGrid conference, held this year in Pittsburgh. Many thanks to Hyesoon Kim (GT), Brandon Hill (Purdue), Bruce Loftis (UT/NICS), and Tabitha Samuel (UT/NICS) for putting it together.

(UPDATE Aug 19) Slides are available at: http://hpcgarage.org/tg10--gpu-tutorial 

 

insideHPC blurb.

E-mail

insideHPC logo   An interview with Rich on his NSF CAREER Award:

http://insidehpc.com/2010/07/27/vuduc-wins-nsf-career-award-to-make-hpc-better-by-any-means-necessary/ 

 

SciDAC'10.

E-mail

Rich just returned from Chattanooga, where he had a chance to discuss the group's work on multicore CPUs and GPUs at the US Dept. of Energy's Scientific Discovery through Advanced Computing (SciDAC) meeting. The session in which he spoke was filled with great talks on advances in autotuning and the future of MPI.

The slides for Rich's talk are available here:

Note that Chattanooga is the home of Sugar's Ribs, which provides gorgeous views of Lookout Mountain and might also be one of the South's great contributions to the culinary world.

Ribs at Sugar's 

 

HPCwire blurb.

E-mail

Our HotPar'10 paper has gotten a couple of views, including this nice write-up in HPCwire by editor Michael Feldman. It's nice to be noticed!

 HPCwire logo

 

APGCS'10 talk by Sooraj.

E-mail

Sooraj Bhat 

On Monday, May 31, Sooraj Bhat presented his work on mechanizing the derivation of statistical machine learning algorithms, which is joint work with Ashish AgarwalAlex Gray, and Rich, at the Workshop on Automated Program Generation for Computational Science (co-located with ICCS'10 in Amsterdam). This is a key first-step toward the automatic production of highly tuned parallel code for data analysis applications. [workshop-page | schedule]

 
  • «
  •  Start 
  •  Prev 
  •  1 
  •  2 
  •  3 
  •  4 
  •  Next 
  •  End 
  • »


Page 1 of 4

Polls

Are you using CUDA?
 

Login