Current Research
Research at the Scalable Computing Laboratory broadly deals with the area of parallel scientific computing.
Dr. Raghavan's group main area of research concerns sparsity as a unifying abstraction from computational science to computer architecture, toward increasing computational performance by constant factors to orders of magnitude. Sparse representations of data arise from many different contexts, for example, from partial differential equations models where an associated matrix is populated mostly with zeroes and the number of non zeroes in the matrix is bounded by a small constant times its dimension, or from largely local connections in a system represented as a sparse graph or network. Her publications concern: parallel scientific computing; energyaware supercomputing, i.e., performance and power scalability of advanced computer systems; and scalable algorithms for knowledge extraction.
The group focuses on the following research areas:

Energy Aware Performance Scaling

Computational Modeling, Simulation and Knowledge Extraction

Parallel Scientific Computing
Dr. Madduri's group conducts research on the design of new parallel algorithms and software tools for analyzing massive data sets and in support of large computational science simulations. His current research focuses on four topics: algorithms for graph analysis on emerging parallel systems, computational genomics, indexing and query strategies for highdimensional scientific data sets, and algorithms for particle simulations in plasma physics. Graph analysis refers to the use of graphtheoretic abstractions and algorithms to analyze to large data sets. Graph analysis has applications in health care, intelligence and surveillance, processing sociallygenerated data from the web and mobile devices, and several science and engineering disciplines. Madduri's group is creating new parallel algorithmic frameworks that capture broad classes of graphbased computations: traversalbased static graph computations, dynamic graph analytics, subgraph enumeration and pattern search computations, and multiscale and multilevel graph computations.