Spring 2007 Final Project and Resources

Please feel free to look around and find an application group that may be of interest for your final project. If you would like to use your own idea for your final project, please submit a Final Project Application Information sheet (doc) to one of the TAs.

4/2/07: Please submit your team's Final Project Design Documentation (doc) by April 9th.
4/30/07: For uniformity, please use this master slide for your final presentation (ppt).
5/1/07: This is the final project report template, the final report is due May 9th (doc).
Leaders Themes
Jim Phillips, John Stone Theoretical and Computational Biophysics (CUDA Projects Webpage)
Shortcut links to Application Info Sheets:
Molecular Surface Computation (pdf), Lattice Cutoff Computation for Multilevel Summation (pdf),
Grid Generation and Matching for Small Molecule Docking (pdf), Monte Carlo Sampling of Protein Conformations (pdf), Ray Tracing Algorithms (pdf)
Wen-mei Hwu, Shane Ryoo IMPACT - SPEC and related benchmarks with high inherent parallelism:
Application Info Sheets:
MPEG-4 Encoder (doc), Seismic Wave Simulation (doc), Image Recognition/Neural Networks (doc), Molecular Dynamics (doc), Video Compression/Encoding (doc), Chemistry/Molecular Dynamics (doc), Fluid Dynamics Simulation (doc), Quantum Computer Simulator (doc), Physics / Quantum Chromodynamics (doc)
Jianming Jin, Joshua Sulkin Finite-Difference Time-Domain (FDTD) (doc)
Robert J. Brunner, Volodymyr Kindratenko, Dave Semeraro NCSA - Two-point angular correlation function (TPACF) (pdf)
Brad Sutton, Sam Stone, Haoran Yi

Magnetic Resonance Imaging, dynamic MRI reconstruction (pdf)

Kevin Woley

RC5 72-bit decryption challenge (doc)
Alexander Sorokin Fast object recognition training with interactive learning (doc)
Glaucio Paulino, Isaac Dooley, Aaron Becker Explicit Finite Element Modeling for Functionally Graded Materials (doc)
Mayank Tyagi Cactus-CUDA interfaces and Fluid Dynamics solver (doc), Finite-Element coastal ocean model (pdf)
Todd Martinez Martinez Research Group
Ed Seidel Fluid Dynamics
 
Resources:
NVIDIA Official CUDA Page http://developer.nvidia.com/object/cuda.html
CUDA Occupancy Calculator (xls) - 3/22/07 - This just in - a programmer tool that allows you to compute the multiprocessor occupancy of a GPU by a given CUDA kernel. The multiprocessor occupancy is the ratio of active warps to the maximum number of warps supported on a multiprocessor of the GPU, and is helpful in determining how efficient the kernel will be on the GPU.