Spring 2022 Home Page of
EE599-001 GPU & Multi-Core Computing (undergrads)
EE699-001 GPU & Multi-Core Computing (grads)

This is the official home page for GPU & Multi-Core Processor Computing -- a selected topics course about large-scale parallel processing within a modern computer. In-person meetings will be MWF Noon-12:50 in 253 FPAT and all attendees are expected to be properly masked. We'll be using Canvas, but many things will be posted at this homepage.

GPU & Multi-Core Processor Computing is about the large-scale parallel processing within a modern computer (although a bit about cluster computing will also be covered). Multi-core refers to the multiple conventional processors now found within a processor chip. Graphics Processing Units (GPUs) were once all about video output, but have mutated into the dominant general-purpose many-core parallel computing architecture. In this course, you'll not only learn about the key architectural features of both, but also how to use them effectively -- primarily by directly programming them, but we'll also discuss some libraries. The goal is for students to be able to write efficient programs using these forms of parallel processing. Somewhat different from previous offerings, the intent is to spend relatively little time discussing computer architecture and to instead add coverage of program optimization tools and techniques that may be used both for sequential and parallel programs. All the projects will be C/C++ based, but you'll be using various other languages/libraries/tools, including CUDA and OpenMP, for your projects.

Course Materials

All course materials will be posted here... note that I said will be.... As per UK policy, all content for this course, including handouts, assignments, and lectures are the intellectual property of the instructor and cannot be reproduced or sold without prior permission from him. A student may use the material for reasonable educational and professional purposes extending beyond this class.

• The Syllabus, which has been updated for Spring 2022 and may still be subject to change due to the special circumstances of the COVID19 pandemic (last update: January 9, 2022)
• Introductory slides
• There are texts we could use, e.g., Multicore and GPU Programming: Integrated Approach, but the options are all light on architecture and I don't think a book is necessary for programming given that freely-available online references are, and stay, more up-to-date. For example, NVIDIA essentially controls CUDA, so their latest CUDA C Programming Guide is generally the most correct reference.
• A little survey about what background you have and what you want to get from this course is posted on Canvas. Please fill it out before class on Friday, August 21, 2020.

Projects

Information about the projects will be posted here.

• Implementor's notes guidelines
• For class January 14, some C code exploring data layout: layout.tgz;
  for class January 21, that has been updated and there's also chess.tgz (derived from a PDP-11 version of Belle)
  for class January 26, here's DUMGA.tgz and gpgo.c; there's also Koza's video
• Performance Tools references
• Tricks of the Trade
• Tools to help make more efficient code
• Stuff about MIMD computers and programming
• gppgo.c, my sample solution to the project parallelizing using OpenMP
• Stuff about SIMD computers and programming

Course Staff

Professor Hank Dietz would normally be in the Davis Marksbury Building; see his home page for complete contact info. Regular Zoom office hour times will soon be listed there. He has an "open-door" policy that whenever his door is open and he's not busy with someone else, he's available -- and yup, there really is a slow-update live camera in his office so you can check. However, during the pandemic things are far less certain. The best method to contact him is to email hankd@engr.uky.edu using "EE699" in the subject line for anything related to this course. If appropriate, individual Zoom meetings also can be scheduled via email.

Note that the graduate (EE699) and undergrad (EE599) sections meet together and cover the same material; the primary difference is that the graduate projects will be somewhat enhanced.