Fall 2007 Syllabus (Tentative)

Date Lecture Material Assignments
Week 1: Wed, 8/22 Lecture 1 - Introduction Slides (ppt)
Voice (mp3)
MP-0 Released - CUDA installation, run hello world.
Week 2: Tuesday, 8/28 (Make up, class in 163EL) Lecture 2 - GPU Computing and CUDA Intro Slides (ppt)
Voice (mp3)
Read CUDA Programming Guide 1.0.
Wed, 8/29 Lecture 3 - GPU Computing and CUDA Intro Slides (ppt)
Voice (mp3)
MP-1, Simple Matrix Multiplication and Simple Vector Reduction released

Week 3: Tuesday, 9/4 (Make up, class in 1109 Siebel Center.)

Lecture 4 - CUDA memory model, tiling
Slides (ppt)
Voice (mp3)
Joke (mp3)
 
Wed, 9/5: (DK in IL) Lecture 5 - GPU History
Slides (ppt)
Voice (mp3)
MP-2, Tiled Matrix Multiplication released
MP-1 (both parts) Due: Wednesday, September 5th at 11:59pm.
Week 4: Mon, 9/10 Lecture 6 - CUDA Hardware
Slides (ppt)
Voice (mp3)
 
Tues, 9/11 (Make up, 1109 Siebel) Lecture 7 - GPU Compute Core
Slides (ppt)
Voice (mp3)
 
Wed, 9/12 Lecture 8 – GPU Compute Core Slides (ppt)
Voice (mp3)
 
Fri, 9/14     MP-2 Due: Friday, September 14th at 11:59pm.
Week 5: Mon, 9/17 Lecture 9 - Bank Conflicts and PTX Slides (ppt)
Voice (mp3)

MP-3, Tiled 2D Convolution released
Read PTX Manual 1.0.

Tues, 9/18 No Class    
Wed, 9/19 No Class    
Week 6: Mon, 9/24 Lecture 10 - Control Flow in CUDA Slides (ppt)
Voice (mp3)
 
Tues, 9/25

Lecture 11 - Floating Point Performance, precision and Accuracy

Prof. Hwu's Floating Point notes (doc)

Slides (ppt)
Voice (mp3)
 
Wed, 9/26 Lecture 12 - Parallel Programming - Application Performance (part 1) Slides (ppt)
Voice (mp3)
MP-3 Due: Wed, Sept. 26th at 11:59pm.
MP-4, Tiled Scan released
Week 7: Mon, 10/1

Lecture 13 - Parallel Programming - Application Performance (part 2)

John Stratton's methodology for computing bank conflicts in Scan (doc).

Slides (ppt)
Voice (mp3)
 
Tue, 10/2 Lecture 14 - Parallel programming - algorithm styles Slides (ppt)
Voice (mp3)
 
Wed,10/3 Lecture 15 - Parallel programming - coding style Slides (ppt)
Voice (mp3)
MP-4 Due: Wed, Oct 3rd at 11:59pm.
MP-5, Parallel Sort released (Speed Competition)
Week 8: Mon, 10/8 Lecture 16 - Application performance insight, matrix multiplication, convolution Slides (ppt)
Voice (mp3)
 
Tue, 10/9 Lecture 17 - (Guest lecture, Dan Vivoli) GPU computing market and applications Voice (mp3)  
Wed, 10/10 Lecture 18 - Application performance insight, scan VMD, NAMD, etc. Slides (ppt)
Voice (mp3)
 
Week 9: Mon, 10/15 Lecture 19 - (Guest lecture, John Stone) Application performance insight, scan VMD, NAMD, etc. Slides (ppt)
Voice (mp3)
 
Tue, 10/16 Lecture 20 - (Guest lecture, Sam Stone) Other types of parallelism Slides (pdf)
Voice (mp3)
© ACM, 2008. This is the author’s version of the work. It is posted here by permission of the ACM for your personal use. Not for redistribution. The definitive version will appear under the title ‘Accelerating Advanced MRI Reconstructions on GPUs’ in Proceedings of the 5th International Conference on Computing Frontiers, May 5-7, 2008.
Wed, 10/17 Lecture 21 - (Guest lecture, Sanjay Patel) Other types of parallel processors Voice (mp3) MP-5 Due: Wed, Oct 17th at 11:59pm.
Week 10: Mon, 10/22 Final project work time, no lectures    
Wed, 10/24 Project Proposal Workshop (6 hours, 4 lectures)    
Week 11: 10/29-10/31 Final project work time, no lectures    
Week 12: Mon, 11/5 Final project work time, no lectures    
Wed, 11/7 Final Exam    
Week 13: 11/12-11/14 (SC) Final project work time, no lectures    
Week 14: 11/19-11/21 Fall Break - no lectures    
Week 15: 11/26-11/28 Final project work time, no lecture
Project checkup - TA feedback
   
Week 16: 12/3-12/5 Final project work time, no lectures    
Fri, 12/14 Project Presentations (6 hours, 4 lectures)

   
       
       

 

  Archived lectures/recordings from previous semester(s):  
  Spring 2007 - First-time course offering by Prof. Hwu (UIUC) and Prof. Kirk (NVIDIA)!