1 / 13

Cellular Automata

Semester Project for Parallel Computing. Mid Defense. Cellular Automata. Group Members: Bibrak Qamar Jahanzeb Maqbool Muhammad Imran Bilawal Sarwar Mehreen Nadeem. Project Description. We have chosen 'Game of Life' and 'Fish and Shark Problem' .

osman
Télécharger la présentation

Cellular Automata

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. Semester Project for Parallel Computing Mid Defense Cellular Automata Group Members: Bibrak Qamar Jahanzeb Maqbool Muhammad Imran Bilawal Sarwar Mehreen Nadeem

  2. Project Description • We have chosen 'Game of Life' and 'Fish and Shark Problem' . • We are using CUDA to implement these simulations as they are not only compute intensive but also best fits in the CUDA paradigm, for having many threads. • Work Completed • Implementation Game of Life on CUDA is completed • Implementation Fish and Shark on CUDA is completed

  3. Game of Life Kernel Host memory = NxNxsizeof(int) one array Device memory = NxNxsizeof(int) two arrays

  4. Implementation Game of Life in CUDA using OpenGL Initialized the grid

  5. After 700 generations

  6. Fish and Shark Kernel

  7. #define fishes 0 • #define sharks 1 • #define fish_breed 2 • #define shark_breed 3 ----------------------------------------------------------------------------- • int FS_Data[4]; • FS_Data[fishes] = 0; // fishes • FS_Data[sharks] = 0; // sharks • FS_Data[fish_breed] = 0; // fishes breed • FS_Data[shark_breed] = 0; // sharks breed Good use of registers ( with block size = 256, compute capability = 1.1) nvcc --ptxas-options=-v shows registers used ptxas info : Used 10 registers, 8+16 bytes smem, 60 bytes cmem[1]

  8. Yellow = Shark • Implementation “Fish and Shark “ on CUDA is completed Red = Fish Black = Dead Initialized the grid

  9. After 1263 generations

  10. Remaining Work • Using a new technique MPI + CUDA • We intend to use MPJ + JCUDA • We have successfully run JCUDA program on linux and windows, and have merged both MPJ and JCUDA.

More Related