http://www.eecg.toronto.edu/~moshovos/CUDA08/ 2009-07-15T10:53:05-04:00 http://www.eecg.toronto.edu/~moshovos/CUDA08/ http://www.eecg.toronto.edu/~moshovos/CUDA08/lib/images/favicon.ico text/html 2009-05-05T11:18:38-04:00 http://www.eecg.toronto.edu/~moshovos/CUDA08/doku.php?id=course_staff&rev=1241536718&do=diff Instructor Andreas Moshovos, EA310 TA Hassan Shojania text/html 2009-05-04T20:58:31-04:00 http://www.eecg.toronto.edu/~moshovos/CUDA08/doku.php?id=course_structure_meeting_times&rev=1241485111&do=diff First Thematic Section - January/February: We will be building the background for performance programming using CUDA. We will first discuss the CUDA programming constructs, then overview the NVIDIA GTX280 architecture, and then proceed to explain how the architectural features impact performance. text/html 2009-05-04T21:22:28-04:00 http://www.eecg.toronto.edu/~moshovos/CUDA08/doku.php?id=lab_assignments&rev=1241486548&do=diff Write a CUDA program, which should be named “arradd”, that adds a number X to all elements of a one-dimensional array A. The elements of A and X should be single precision floating-point numbers. Using the CUT timer calls, have your program report the time needed to copy data from the CPU to the GPU, the time needed to add X to all elements of A in the GPU, and the time needed to copy the data back from the GPU to the CPU. The elements of A should be initialized so that A[i] = i / 3.0f. text/html 2009-05-04T21:04:45-04:00 http://www.eecg.toronto.edu/~moshovos/CUDA08/doku.php?id=lecture_slides&rev=1241485485&do=diff Introduction to the Course <http://www.eecg.toronto.edu/~moshovos/CUDA08/slides/lecture-001.ppt> (1.148 Mb) Overview of the CUDA execution model, and of a typical NVIDIA GPU containing system. Also, overview of the course. Introduction to CUDA Programming <http://www.eecg.toronto.edu/~moshovos/CUDA08/slides/002 - Introduction to CUDA Programming_1.ppt> (412.5 Kb) text/html 2009-06-30T12:50:04-04:00 http://www.eecg.toronto.edu/~moshovos/CUDA08/doku.php?id=project_presentations_reports_source_code&rev=1246380604&do=diff John Pazelli, Tijmen Tieleman Electrical Engineering, Computer Science john.pazelli AT utoronto.ca, tijmen AT cs.toronto.edu Abstract We will describe our project in 250 words or less: We used a GPU to efficiently optimize the parameters to various technical indicators often used on chart analysis for currency trading. Issues encountered include: the limited amount of shared memory; how to precompute some values using parallelism; how to distribute tasks over the multiprocessors; and figuring… text/html 2009-05-05T14:55:35-04:00 http://www.eecg.toronto.edu/~moshovos/CUDA08/doku.php?id=start&rev=1241549735&do=diff My hope is that people from various disciplines will attend the course. I will assume very little in terms of background preparation (i.e., basic understanding of computers and programming in C). The goal of the course is to bring together people with strong programming expertise and skills with people with a strong need for solving compute-intensive programs that can potentially benefit from CUDA.