I am affiliated with the Scientific Data Management research group in the Computational Research division at LBNL. I will be working on research problems in massive data analysis and high-performance computing.

My PhD dissertation was on efficiently solving large-scale graph traversal, centrality and shortest path problems on HPC systems. Graph theoretic problems are representative of fundamental kernels in traditional and emerging scientific applications such as VLSI design, network analysis, data mining and computational biology, as well as applications in national security. Graph abstractions are also extensively used to understand and solve challenging problems in scientific computing. Real-world systems such as the internet, telephone networks, the world-wide web, social interactions, and transportation networks are analyzed by modeling them as graphs. These graphs may contain billions of vertices with degrees ranging from small constants to thousands. There are plenty of theoretically fast parallel algorithms for graph problems in the literature, e.g., work-time optimal PRAM algorithms and communication-optimal BSP algorithms; however, in practice there are seldom any parallel implementations that beat the best sequential implementations for arbitrary, sparse graphs. My work addresses this specific problem with contributions in the following areas: Parallel algorithms that exploit the small-world topology; efficient implementations on shared memory multithreaded architectures, multi/many-core systems and symmetric multiprocessors; experimental studies and performance characterization of graph theoretic problems on high performance computing systems; and applying these techniques to real-world applications.

For more details, please see my research statement (pdf, 5 pages) and a shorter summary of my dissertation research (pdf, 2 pages).