PPT-GPU System Architecture

Alan Gray EPCC The University of Edinburgh Outline Why do we wantneed accelerators such as GPUs Architectural reasons for accelerator performance advantages Latest accelerator Products NVIDIA and AMD GPUs. . Acknowledgement: the lecture materials are based on the materials in NVIDIA teaching center CUDA course materials, including materials from Wisconsin (. Negrut. ), North Carolina Charlotte (. Wikinson. Dr A . Sahu. Dept of Comp Sc & . Engg. . . IIT . Guwahati. 1. Outline. Graphics System . GPU Architecture. Memory Model. Vertex Buffer, Texture buffer. GPU Programming Model. DirectX. , OpenGL, . Chris Rossbach, Microsoft Research. Jon Currey, Microsoft Research. Emmett . Witchel. , University of Texas at Austin. HotOS. 2011. Lots of GPUs. Must they be so hard to use?. We need dataflow…. GPU Haiku . ITK v4 . . w. inter . meeting. Feb 2. nd. 2011. Won-. Ki. . Jeong. , . Harvard University. (. wkjeong@seas.harvard.edu. ). Overview. Introduction. Current status in GPU ITK v4. GPU managers. GPU image. ITS Research Computing. Lani. Clough, Mark Reed. markreed@unc.edu. . Objectives. Introductory. level MATLAB course for people who want to learn . parallel and GPU computing . in MATLAB.. Help participants . Lecture 2: more basics. Recap. Can use GPU to solve highly parallelizable problems. Straightforward extension to C++. Separate CUDA code into .cu and .. cuh. files and compile with . nvcc. to create object files (.o files). Prof. Miriam Leeser. Department of Electrical and Computer Engineering. Northeastern University . Boston, MA. mel@coe.neu.edu. Typical Radar Processing . http://www.codesourcery.com/vsiplplusplus/ssar_http://www.codesourcery.com/vsiplplusplus/ssahttp://www.codesourcery.com/vsiplplusplus/ssar_whitepaper.pdfr_whitepaper.pdfwhitepaper.pdf. M. Zollhöfer, E. Sert, G. Greiner and J. Süßmuth. Computer Graphics Group, University Erlangen-Nuremberg, Germany. Motivation/Requirements. Intuitive modeling. Handle-based. Direct manipulation. 2. Lecture 2: more basics. Recap. Can use GPU to solve highly parallelizable problems. Straightforward extension to C++. Separate CUDA code into .cu and .. cuh. files and compile with . nvcc. to create object files (.o files). Andy Luedke. Halo Development Team. Microsoft Game Studios. Why do Histogram Analysis?. Dynamically adjust post-processing settings based on rendered scene content. Drive tone adjustments by discovering intensity levels and adjusting . Alex Wade. CAP6938 Final Project. Introduction. GPU based implementation of . A Computational Approach to Edge Detection. by John Canny. Paper presents an accurate, localized edge detection method. Purpose. Add GPUs: Accelerate Science Applications. © NVIDIA 2013. Small Changes, Big Speed-up. Application Code. . GPU. C. PU. Use GPU to Parallelize. Compute-Intensive Functions. Rest of Sequential. CPU Code. Hui. Li. Geoffrey Fox. Research Goal. provide . a uniform . MapReduce programming . model that works . on HPC . Clusters or . Virtual Clusters cores . on traditional Intel architecture chip, cores on . Cooperative Computing. Di Wu, Fan Zhang, . Naiyong. . Ao. , Gang Wang, . Xiaoguang. Liu, Jing Liu. Nankai. -Baidu Joint Lab, . Nankai. University. Introduction. Cooperative Model. GPU Batching Algorithm.