me shubho
sengupta

[ contact ]

[ presently at ]

I am a graduate student at Department of Computer Science, University of California Davis. I work with Prof. John Owens on parallel algorithms on current and upcoming graphics processors. I am also affliated with Institute of Data Analysis and Visualization (IDAV).

My current research focuses on parallel-prefix scan and its variants and their efficient implementations on graphics hardware. The goal is to use it as a primitive in developing fast parallel sort and sparse solvers.

I have also worked with Aaron Lefohn on rendering techniques and parallel algorithms on graphics processors (GPUs) which currently enable interactive film preview and will enable high-quality graphics for games in the near future. During 2005 and 2006, I worked on generating high-quality shadows for dynamic scenes at interactive rates on GPUs. This work has also highlighted the importance of basic parallel algorithms in doing high-quality rendering. We have developed the fastest known implementation of the parallel scan algorithm on the GPU and have identified the need for fast implementations of other key algorithms . I also worked with Aaron on Glift, which provides the multi-dimensional hierarchical data structure needed to generate high-quality shadows.

[ past life ]

In my past life, I was working in the SunONE Application Server group at Sun Microsystems. I was there for four years and through two generations of the product, before the call of graphics proved irresistible. My non-graphics work also involves working on StorageTek's (now part of Sun Microsystems) REELs tape library management software. I also did a short stint in Tokyo, designing a large-scale online system.

Prior to starting my professional life, I did my Masters and Bachelors from Indian Institute of Technology(IIT), Kharagpur (India) in Mathematics.

[ publications ]

  • Scan Primitives for GPU computing S. Sengupta, Mark Harris, Yao Zhang, J. D. Owens Graphics Hardware 2007, pages 97-106, August 2007, Best paper award
  • Parallel Prefix Sum (Scan) with CUDA Mark Harris, S. Sengupta, J. D. Owens GPU Gems 3, Hubert Nguyen, editor, chapter 39, Addison Wesley, August 2007
  • Resolution Matched Shadow Maps A Lefohn, S. Sengupta, J. D. Owens ACM Transactions on Graphics, to appear, 2007
  • A Work-Efficient Step-Efficient Prefix Sum Algorithm. S. Sengupta, A. Lefohn, J. Owens. Proceedings of the 2006 Workshop on Edge Computing using New Commodity Architectures
  • Dynamic Adaptive Shadow Maps on Graphics Hardware. A Lefohn, S. Sengupta, J. Kniss, R. Strzodka, J. Owens SIGGRAPH 2005 Technical Sketch
  • Octree Textures on Graphics Hardware. J. Kniss, A. Lefohn, R. Strzodka, S. Sengupta, J. Owens. SIGGRAPH 2005 Technical Sketch
  • Glift: Generic, Effiicient, Random-Access GPU data structure. A. Lefohn, J. Kniss, R. Strzodka, S. Sengupta, J. Owens. ACM Transactions on Graphics, 25(1), Jan 2006 (accepted to SIGGRAPH 2005 with major revisions)
  • Assessment of Graphics Processing Units (GPUs) for Department of Defense (DOD) Digital Signal Processing (DSP) Applications. J. Owens, S. Sengupta, D. Horn. Technical Report ECE-CE-2005-3, Computer Engineering Research Laboratory, University of California, Davis

    • [ fellowships and awards ]

  • Best paper award at Graphics Hardware 2007
  • NVIDIA Fellowship 2007-2008

    • [ resume ]

    My resume in PDF format