1 / 12

A Brief Summer Recap

A Brief Summer Recap. Flocking, CUDA, GPU, Ants, and More Jesse St.Charles. Some Terms:. Kernel – A algorithm which executes on the GPU (blueprint for all simultaneous threads) Host – CPU (normal location programs run) Device – Graphics Card (this is the location of the GPU)

Download Presentation

A Brief Summer Recap

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. A Brief Summer Recap Flocking, CUDA, GPU, Ants, and More Jesse St.Charles

  2. Some Terms: Kernel – A algorithm which executes on the GPU (blueprint for all simultaneous threads) Host – CPU (normal location programs run) Device – Graphics Card (this is the location of the GPU) CUDA – Compute Unified Device Architecture (API that allows programming of the GPU) made by NVIDIA

  3. NVIDIA CUDA Single Program Multiple Data architecture (SPMD) • Uses Grid/Block thread spawning • Programmer uses thread ID and block ID to access unique data per thread

  4. CUDA: Flocking and Document Flocking Neighborhood Calculation Kerneland Document Comparison Update Pos and Velocity Kernel Start Main Main() Kernel Call-> Main() Kernel Call-> Threads N N2 One Loop Per Generation

  5. Initial Flocking Results CPU 100x GPU

  6. Document Flocking Results CPU 5x GPU

  7. Document Flocking Results Document comparisons – most expensive 2000 Documents at Generation: 2 52 200

  8. Other Summer Work Shortest Path • Done for traffic simulation and emergency response • Produced an Ant-Colony shortest path implementation on the GPU but had convergence issues when the graph became to large • Implemented Dijkstra’s shortest path algorithm on the GPU; no clear benefit on the GPU

  9. Summer End Products • Ant-Colony shortest path GPU program • Dijkstra’s Shortest path GPU program • Document Flocking GPU program with display • Companion CPU implementations • Paper produced and submitted for publication • Poster produced for presentation

  10. Future Work in Document Flocking • Use dimensionality reduction • Develop document refinement GPU implementation that removes stop words, stems, and calculates TF-ICF • Develop a whole document analysis system for a GPU workstation (one GPU for refinement, one for document clustering) • Find F-measure for flocking cluster accuracy

  11. My Immediate Future Fall 2007 • Last undergraduate semester at UTC • Continuing research collaboration with Xiaohui • Applying for graduate fellowships • Selecting and applying to Graduate CS programs to begin PhD track in Fall 2008

More Related