PPT-GPU Acceleration in ITK v4

ITK v4 summer meeting June 28 2011 Won Ki Jeong Harvard University Overview Introduction Current status Examples Future work 2 GPU Acceleration GPU as a fast coprocessor Massively parallel. 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 . A CUDA Approach. Gary . Resnick. Scott . Badenhorst. Department of Computer Science. University of Cape Town. 17 March, 2010. Introduction. Approach. Plan. Outcomes. Overview. Radio Astronomy. 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. 21. Active Shape Models. Methods in Medical Image Analysis - . Spring . 2015. . BioE. . 2630 (Pitt) : 16-725 (CMU RI). 18-791 (CMU ECE) : 42-735 (CMU BME). Dr. John . Galeotti. 1. Active . Shape Models (ASM. Sathish. . Vadhiyar. Parallel Programming. GPU. Graphical Processing Unit. A single GPU consists of large number of cores – hundreds of cores.. Whereas a single CPU can consist of 2, 4, 8 or 12 cores. 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. 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 . Evangelia Sitaridi, . Thesis Defense. Columbia University . GPUs for Social Media Analytics. 2. Search terms: . Match . regexp. : “/\B#\w*[a-. zA. -Z] \w*/ . . debate. Filter location. More GPU Data Analytics Use-Cases. 1. Goals for this lecture. Compile, compile, compile. Learn how to use SVN & CMake. Build ITK. Compile several programs that use ITK. Find documentation online. Learn the quirks (if any) of the system you choose to use. Describe the speedometer on a car that is entering a highway, drives for 25 miles and then exits the highway.. Consider the two situations below. When a shuttle bus approaches a stop, the driver begins to apply the brakes to slow down 5.0 s before actually reaching the stop. The speed changes from 9.0 m/s to 0 m/s over time.. CS 179: GPU Programming Lecture 7 Week 3 Goals: Advanced GPU- accelerable algorithms CUDA libraries and tools This Lecture GPU- accelerable algorithms: Reduction Prefix sum Stream compaction Sorting (quicksort) Acceleration is a change in velocity. Speed or direction. Centripetal Acceleration. Acceleration can mean a change in direction, not just speed. Centripetal acceleration. Acceleration that occurs in a circular motion. Bose Perumal. Wenjing Chu. R. Krishnan. S. Hemalatha. . Dell. Peter Wills . . BT. draft-perumal-nfvrg-nfv-compute-acceleration-00.txt. NFV Compute Acceleration– Software Architecture. Compute Acceleration for NFV. 1. Joël Alwen. AWS-. Wickr. Daniel . Jost. NYU. Marta Mularczyk. AWS-. Wickr. Secure group communication. Goal. . :. a dynamic group exchanges . confidential data. Examples:. secure group chats. secure video calls.