Graph Algorithms Building Blocks (GABB’2014)
Arizona Grand Resort
Phoenix, AZ
19 May 2014
Scope and Goals:
The Basic Linear Algebra Subprograms, introduced over 30 years ago, had a transformative effect on software for linear algebra. With the BLAS, researchers spend less time mapping algorithms onto specific features of hardware platforms and more time on interesting new algorithms.
Would it be practical to define an analogous set of basic building blocks for graph algorithms? Can we define a core set of mathematical primitives from which we can build most (if not all) important graph algorithms? If we can agree on the mathematical foundations, how would these interact with the data structures used in graph algorithms and result in an API the graph algorithms research community could support?
These questions will be the topic for the first “Graph Algorithms Building Blocks” workshop. Our invited speakers will address a specific proposal for standard primitives when graph algorithms are expressed in the language of linear algebra. Our goal is an interactive workshop where the full range of issues behind “Graph Algorithms Building Blocks” will be explored. Therefore, we will include speakers from the “think like a vertex” as well as other perspectives on the best foundations for graph algorithms.
Please see the GraphBLAS effort at http://istc-bigdata.org/GraphBlas/
Location:
This workshop is co-located with IPDPS 2014, held 19 - 23 May 2014, at the Arizona Grand Resport in Phoenix, AZ. Registration information for IPDPS2014 can be found at here.
GABB Preliminary Agenda
| Time | Speaker | Topic |
| 09:00 - 09:30 | Tim Mattson, Intel | Welcome, Goals, and a bit of Math [SLIDES] |
| 09:30 - 10:00 | John Gilbert, UCSB | Applications |
| 10:00 - 10:30 | Joseph Gonzalez, Berkeley | GraphX and Linear Algebra [SLIDES] |
| 10:30 - 11:00 | Break | |
| 11:00 - 11:30 | David Mizell, YarcData | Effective Graph-algorithmic Building Blocks for Graph Databases [SLIDES] |
| 11:30 - 12:00 | Jeremy Kepner, MIT | Adjacency Matrices, Incidence Matrices, Database Schemas, and Associative Arrays [SLIDES] |
| 12:00 - 01:30 | Lunch | |
| 01:30 - 02:00 | Dylan Stark, Jon Berry, Sandia | Graph Exploration: to Linear Algebra (and Beyond?) [SLIDES] |
| 02:00 - 02:30 | Jason Riedy and David A. Bader, Georgia Tech | Multi-threaded graph streaming |
| 02:30 - 03:00 | Saeed Maleki, UIUC | Linear algebra operator extensions for graph algorithms |
| 03:00 - 03:30 | Break | |
| 03:30 - 04:00 | Aydin Buluç, LBNL | Communication-Avoiding Linear-Algebraic Primitives for Graph Analytics, Aydin Buluç (presenter), Grey Ballard, James Demmel, John Gilbert, Laura Grigori, Ben Lipshitz, Adam Lugowski, Oded Schwartz, Edgar Solomonik, Sivan Toledo [SLIDES] |
| 04:00 - 04:30 | Andrew Lumsdaine, Indiana Univ | Standardization: Lessons Learned |
| 04:30 - 05:00 | Panel | What’s next as we standardize the “BLAS of Graph Algorithms”? |
Workshop Organizers:
Workshop chair:
- Tim Mattson, Intel Corp
Steering committee:
- Jeremy Kepner (MIT Lincoln Labs)
- John Gilbert (UC Santa Barbara)
- David A. Bader (Georgia Institute of Technology)
- Aydın Buluç (LBNL)