The use of Graphics Processing Units for rendering is well known, but their power for general parallel computation has only recently been explored. Parallel algorithms running on GPUs can often achieve up to 100x speedup over similar CPU algorithms, with many existing applications for physics simulations, signal processing, financial modeling, neural networks, and countless other fields.
This course will cover programming techniques for the GPU. The course will introduce NVIDIA's parallel computing language, CUDA. Beyond covering the CUDA programming model and syntax, the course will also discuss GPU architecture, high performance computing on GPUs, parallel algorithms, CUDA libraries, and applications of GPU computing. Problem sets will cover performance optimization and specific GPU applications in numerical mathematics, medical imaging, finance, and other fields.
Labwork will require significant programming. A working knowledge of the C programming language will be necessary. Although CS 24 is not a prerequisite, it (or equivalent systems programming experience) is recommended.
9 units; third term.
Andrew Zhao - email@example.com
Parker Won - firstname.lastname@example.org
Nailen Matschke - email@example.com
Jordan Bonilla - firstname.lastname@example.org
Matthew Cedeno - email@example.com
Albert Yang - firstname.lastname@example.org
|Supervising professors:|| Professor
Al Barr - email@example.com
|Time and place:|| MWF 3:00-3:55 PM
Jordan Bonilla - Sundays, 9-11 PM
Andrew Zhao - Mondays, 9-11 PM
Albert Yang - Mondays, 8-10 PM
Parker Won - Tuesdays, 6-8 PM
Nailen Matschke - Tuesdays, 8-10 PM
Matthew Cedeno - Tuesdays, 10-12 AM
104 Annenberg, instructional laboratory
|Grading policy:|| Here is the grading scheme for the class:
Homework extensions may be granted if the TA's see it as appropriate. E grades will not be granted except under extreme circumstances.
Project info will be posted after midterms.
Week 1 (Introduction), MW Parker, F Nailen
Lecture 1 (Mon. 03/28): PPT PDF
Lecture 2 (Wed. 03/30): PPT PDF
Lecture 3 (Fri. 04/01): PPT PDF
Week 2 (Shared Memory), MW Parker, F Jordan
Lecture 4 (Mon. 04/04): PPT PDF
Lecture 5 (Wed. 04/06): PPT PDF
Lecture 6 (Fri. 04/08): PPT PDF
Week 3 (Reductions, FFT), M Albert, WF Andrew
Lecture 7 (Mon. 04/11): PPT PDF
Lecture 8 (Wed. 04/13): PPT PDF
Lecture 9 (Fri. 04/15): PPT PDF
Week 4 (MRI), MWF Matt
Lecture 10 (Mon. 04/18): PPT PDF
Lecture 11 (Wed. 04/20): PPT PDF
Lecture 12 (Fri. 04/22): PPT PDF
Week 5 (SVD, streaming, etc), MW Jordan, F Nailen
Lecture 13 (Mon. 04/25): PPT PDF
Lecture 14 (Wed. 04/27): PPT PDF
Lecture 15 (Fri. 04/29): PPT PDF
Week 6 (MPI, Multi-GPU, etc.), MW Jordan, F Andrew
Week 7 (Projects) MW (Parker), F (in-class office hour) Nailen
Week 8 (Projects) MW no class, F (in-class office hour) TBD
Week 9 (Projects) MW no class, F (in-class office hour) TBD
Week 10 (Projects) MW no class, F (in-class office hour) TBD
Lab 1: assignment text UNIX files Windows files
Lab 2: assignment text UNIX files Windows files
Lab 3: assignment text UNIX files Windows files
Lab 4: assignment text UNIX files Windows files
Lab 5: assignment text UNIX files Windows files
The CUDA Handbook: A Comprehensive Guide to GPU Programming is
recommended but not required. The book is a little more advanced than
other CUDA books and might not be very approachable at first, but by
the end of the course you should find it to be a valuable reference
for both your project as well as any future GPU programming you
find yourself doing.
the author's site for a discount.
|CUDA Installation Guides:||
Linux: see our installation guide.
OS X: you shouldn't have too much trouble with NVIDIA's official installation guide, though "CUDA-7.0" should be replaced with "CUDA-7.5" wherever applicable.
Windows: see our installation guide.
IMPORTANT: use this script to retrieve your hardware info after you setup CUDA.
CUDA C Programming Guide
List of NVIDIA GPUs
Mapping from GPU name to Compute Capability
|Material from previous year(s):||
|Less useful, but cool resources:||
NVIDIA's Parallel Forall Blog
Videos from last several years of NVIDIA's conference on CUDA
How to Write Code the Compiler Can Actually Optimize (2015)
Excellent CPU optimization manuals
What Every Programmer Should Know About Memory
GPU focused systems guide to deep learning