Within the program, Vuduc and Jason Reidy (CSE) are organizing mini-symposia (details below).

The Society for Industrial and Applied Mathematics is proud to present the Fourteenth Conference on Parallel Processing for Scientific Computing. This series of conferences has played a key role in promoting parallel scientific computing, algorithms for parallel systems, and parallel numerical algorithms. The conference is unique in its emphasis on the intersection between high performance scientific computing and scalable algorithms, architectures, and software. The conference provides a forum for communication among the applied mathematics, computer science, and computational science and engineering communities.

Energy Aware High Performance Computing
Feb. 15

Organizer: Costas Bekas
IBM Research-Zurich, Switzerland
Richard Vuduc
Georgia Institute of Technology, USA
Enrique S. Quintana-Ortí
Universidad Jaume I, Spain
Piotr Luszczek
University of Tennessee, Knoxville, USA

Part 1: 10:00 AM - 12:00 PM

Part 2: 2:30 PM - 4:30 PM

Power provisioning and energy consumption have become major challenges in the field of high performance computing. Energy costs over the lifetime of an HPC installation are in the range of the acquisition costs. The quest for Exascale computing has made it clear that addressing the power challenge will require the synergy of several major advances. These will range widely starting from algorithmic design and performance modeling all the way to HPC hardware and data center design. We assembled a speaker list of experts and pioneers in energy aware HPC in an attempt to cover the wide range of needed solutions.

Parallel Analysis of Massive Social Networks

Feb. 15

Part 1: 10:00 AM - 12:00 PM 

Part 2: 2:30 PM - 4:30 PM

Organizer: Jason Riedy
Georgia Institute of Technology, USA
Henning Meyerhenke
Karlsruhe Institute of Technology, Germany

Social networks represented by graphs present unique challenges for high-performance parallel analysis. Social network graphs are massive, dynamic, approximate representations of streaming real-world relationships. Unlike graphs from physical simulations, social networks lack high-quality separators and often have small diameters and massive differences in degrees. However, social networks are rich in community structures relative to many clustering metrics. This minisymposium investigates parallel algorithms for analyzing and clustering social network graphs at current and future applications' massive scales.