CS/EE 147 GPU Computing and Programming - Spring 2024
Course Information
-
Time and Location:
- Lecture: Tuesday/Thursday 9:30 AM - 10:50 AM @ Spieth Hall 2200
- Discussion: Friday 2:00 PM - 2:50 PM @ Student Success Center 316
-
Instructor: Daniel Wong
- Email: danwong@ucr.edu
- Homepage: http://www.danielwong.org
- Office Hours: Thursday 3-4PM @ WCH425
-
TA: Mohammadreza Rezvani
- Email: mrezv002@ucr.edu
- Office Hours: Friday 3-4PM @ SSC 316 (Right after discussion)
- eLearn (for grades): http://eLearn.ucr.edu
- Piazza (for discussions): Now embedded in eLearn.
- Github Classroom (for assignment submission)
Announcements
Welcome to CS/EE 147!
Class Syllabus
Class webpage and communication
The class webpage is located at http://teaching.danielwong.org/csee147/spring24
Information, resources, and announcements related to the class will be posted to the webpage.
In addition, we will be using eLearn for assignments, and Piazza (which can be accessed inside of eLearn) for discussions and help.
You will need an ENGR account. EE and CEN students should already have one. If you do not, you can create one here: https://www.engr.ucr.edu/secured/systems/login.php
Course Description
Graphics processing units (GPUs) play key roles in many modern application domains, such as image processing, machine learning, and scientific computing. GPUs provide programmers with the massive parallelism required for modern data intensive applications.
This course introduces the principles and practices of programming GPUs using the CUDA parallel programming environment. Topics include CUDA memory/threading models, common data-parallel programming patterns and libraries needed to develop high-performance parallel computing applications. Students will gain hands-on experience with designing and implementing high performance applications on GPU platforms.
Prerequisite: CS/EE 120B or equivalent; consent of instructor.
The course will assume the knowledge of the C++ programming language.
Textbook
- Programming Massively Parallel Processors, by D. Kirk and W Hwu (primary textbook)
- CUDA by example, Sanders and Kandrot (recommended)
Grade Breakdown
- Assignments: 28% (7% each assignment)
- Final Project: 25%
- Midterm Exam 1: 25%
- Midterm Exam 2: 20%
- Participation/Discussion: 2%
- Extra credit: 2%
| Letter Grade | Percentage |
|---|---|
| A | > 93% |
| A- | > 90% |
| B+ | > 87% |
| B | > 83% |
| B- | > 80% |
| C+ | > 77% |
| C | > 73% |
| C- | > 70% |
Assignment Policies
- You have 3 slip days that you can use on any assignment (not final project). If you exceed your slip days, there will be a 15% penalty per late day (counting weekends).
- Slip days CANNOT be applied to the final project. We need ample time to grade the last assignment before grades are due.
- No extensions for assignments will be given (see slip days). Even if you're one minute late, it will be considered late.
- All assignments will be due at the end on the day (midnight Pacific time).
- All assignments should be uploaded to eLearn or Github Classroom.
Policies
- You are responsible for all materials covered in lectures.
- All assignments, quizzes, and exams are individual effort.
- Cheating in assignments, quizzes, projects, and exams are absolutely prohibited. The minimum penalty for a violation of the regulations will be a zero for the assignment; the maximum penalty will be failure in the course.
- Examinations must be taken in class on the day they are given. There will be no exceptions.
Academic Integrity
Here at UCR we are committed to upholding and promoting the values of the Tartan Soul: Integrity, Accountability, Excellence, and Respect. As a student in this class, it is your responsibility to act in accordance with these values by completing all assignments in the manner described, and by informing the instructor of suspected acts of academic misconduct by your peers. By doing so, you will not only affirm your own integrity, but also the integrity of the intellectual work of this University, and the degree which it represents. Should you choose to commit academic misconduct in this class, you will be held accountable according to the policies set forth by the University, and will incur appropriate consequences both in this class and from Student Conduct and Academic Integrity Programs. For more information regarding University policy and its enforcement, please visit: http://conduct.ucr.edu.
Attendance
You are expected to attend lectures. While the slides contain all the information you need to know, some of the contents don't make sense unless you attend lecture.
However, COVID is still around and people get sick all the time...so strict attendance won't be enforced. If you're sick, please stay home. You are still responsible for keeping up with recorded course lectures and assignments.
Tentative Schedule
The following schedule is tentative and is subject to change.
Note: You need to be logged into eLearn to access the lecture slides. The slide links to the course's eLearn Files page.
| Week | Date | Topic | Assignments | Slides |
|---|---|---|---|---|
| 1 | April 2, T | Introduction and Logistics, OS/Architecture Review | Introduction.pdf Review.pdf |
|
| 1 | April 4, Th | CUDA C | Assignment 1 | CUDA-C.pdf |
| 2 | April 9, T | CUDA Parallelism | CUDA-Parallelism.pdf | |
| 2 | April 11, Th | CUDA Parallelism (cont.) - TB / Warp Scheduling | Assignment 1 due Friday | |
| 3 | April 16, T | SIMT Stack, CUDA Memories, Reduction Algorithm / Control Divergence | SimtStack.pdf SimtStack.pptx Reduction.pdf |
|
| 3 | April 18, Th | Reduction Algorithm / Control Divergence (cont.) | Assignment 2 | |
| 4 | April 23, T | Modern CUDA - Streams | CUDA-Streams.pdf | |
| 4 | April 25, Th | Modern CUDA / High-level Libraries | Final Project | Libraries-CUDA10 Libraries-Numba Libraries-ModernC++ |
| 5 | April 30, T | Exam Review | Assignment 2 due | SampleMidterm.pdf |
| 5 | May 2, Th | Midterm Exam | MidtermSolution.pdf | |
| 6 | May 7, T | Modern CUDA - Unified Memory | Final project proposal due | UnifiedMemory.pdf |
| 6 | May 9, Th | CUDA Memories, Matrix Multiply | Assignment 3 | MatrixMultiply.pdf |
| 7 | May 14, T | Matrix Mutiply (cont.), DRAM / Memory Coalescing | Extra Credit | MemoryCoalescing.pdf |
| 7 | May 16, Th | Histogram & Atomic Operations | Assignment 4 | Histogram.pdf |
| 8 | May 21, T | Multi-GPU Programming / Communication | Assignment 3 due | Multi-GPU.pdf |
| 8 | May 23, Th | Final project meeting | https://piazza.com/class/luenbaltnnzdm/post/113 https://zcal.co/i/cRyPMC-s |
|
| 9 | May 28, T | Modern GPU Architecture - Emerging GPU Trends | Chiplets.pdf | |
| 9 | May 30, Th | Final project meeting | Assignment 4 due | https://piazza.com/class/luenbaltnnzdm/post/113 https://zcal.co/i/cRyPMC-s |
| 10 | June 4, T | Exam Review | SampleFinal.pdf SampleFinal-Blank.pdf |
|
| 10 | June 6, Th | Midterm Exam 2 | FinalExamSolution.pdf | |
| Final | June 12, W | Final Project Due | ||
UCR ACADEMIC POLICIES AND STUDENT SUPPORT
ITS Help and Student Technology Support
ITS Student Technology Services supports 9 student computer labs, including 7 public labs and 2 nonpublic labs, with approximately 293 public lab hours per week (with reduced hours during breaks and summer) available for academic use by all UCR students.
Whether you need a machine to work on your paper, need to use specialized software required by your class, assistance with your R'Mail or iLearn accounts, getting on the network, or any other services used by UCR students, contact BearHelp@ucr.edu.
Academic Misconduct
In addition to the course conduct policies outlined by your professor in the Course Syllabus in the online classroom, please review the Graduate Student Handbook.
It is the responsibility of each student to be familiar with the definitions, policies, and procedures concerning academic misconduct. Please revisit our Academic Integrity Policies and Procedures for more information. This site also defines misconduct, provides examples of prohibited conduct, and explains the sanctions available for those found guilty of misconduct.
Plagiarism
Plagiarism is the most common form of academic misconduct at UCR. It is the appropriation of another person's ideas, processes, results, or words without giving appropriate credit. This includes the copying of language, structure, or ideas of another and attributing (explicitly or implicitly) the work to one's own efforts. Plagiarism means using another's work without giving credit.
For more information about plagiarism, see Academic Integrity Policies and Procedures.
Reasonable Accommodation for Disabilities
UCR is committed to providing reasonable accommodation for all students with disabilities. Students with disabilities who require accommodations in this course should contact their professor as early in the semester as possible.
Students with disabilities must be registered with the Student Disability Resource Center prior to receiving accommodations in this course.
If you have a disability and you would like to make a request for reasonable accommodation, please see the Graduate Student Handbook or get in touch with the Student Disability Resource Center.
Adjustments for Pregnancy/Childbirth Related Issues
Should you need modifications or adjustments to your course requirements because of documented pregnancy-related or childbirth-related issues, please contact me as soon as possible to discuss your options. Generally, modifications will be made where medically necessary and similar in scope to accommodations based on temporary disability. Learn more about the rights of pregnant and parenting students by consulting the Office of Diversity, Equity, and Inclusion.
Title IX Resources
For any concerns regarding gender-based discrimination, sexual harassment, sexual misconduct, stalking, or intimate partner violence, the University offers a variety of resources, including advocates on-call 24/7, counseling services, mutual no contact orders, scheduling adjustments, and disciplinary sanctions against the perpetrator. Please see the Title IX website for more information. They can be reached at (951)827-7070. You can also file a report.
Student Needs
Student Health Services, Counseling & Psychological Services (CAPS), Residential Life, Dining, and R’Pantry are available to support students.
Religious Holidays
It is the policy of the University to excuse absences of students that result from religious observances and to provide for the rescheduling of examinations and additional required classwork that may fall on religious holidays without penalty. It is the responsibility of the student to make alternate arrangements with the instructor at least one week prior to the actual date of the religious holiday.
Copyright Policy
It is illegal to download, upload, reproduce, or distribute any copyrighted material, in any form and in any fashion, without permission from the copyright holder or his/her authorized agent. UCR expects all members of its community to comply fully with federal copyright laws.
Registration and Withdrawal
If you choose to withdraw from this course, you must complete the appropriate University form and turn the form in before the deadline. Deadlines are shown in the Academic Calendar, which is available from the Office of the Registrar.