|
Date
|
Topic
|
Homeworks/Labs |
Readings
|
Handouts
|
| 03/16 |
Introduction and overview |
|
Kirk/Hwu: Chapters 1, 2
|
intro |
| 03/18 |
Basics on Architecture
and Programming |
|
Kirk/Hwu: Chapters 3 |
basics |
| 03/23 |
Programmer Interface |
|
Kirk/Hwu:
Chapters 4 |
progInterface |
| 03/25 |
Programmer
Interface |
|
|
see above |
| 03/29 |
Threads |
|
Kirk/Hwu: Chapter 4 |
threads |
| 04/01 |
Therads |
|
Kirk/Hwu: Chapter 4 |
see above |
| 04/06 |
Threads |
|
Kirk/Hwu: Chapter 4 |
see above |
| 04/08 |
Memory -- registers and shared memory |
lab1 |
Kirk/Hwu: Chapter 5 |
memories_part1 |
| 04/20 |
Memory -- radix and merge sort |
|
Kirk/Hwu: Chapter 5 |
see above |
| 04/22 |
Memory -- constant memory |
|
Kirk/Hwu: Chapter 5 |
memories_part2 |
| 04/27 |
Memory -- global memory |
|
Kirk/Hwu: Chapter 5 |
memories_part3 |
| 04/29 |
Memory -- tiling, usinbg CUDA in practice |
|
Kirk/Hwu: Chapter 5 |
memories CUDA_practice |
| 05/04 |
Optimizations |
lab2 |
Kirk/Hwu: Chapter 9 |
reduction optimize optimize2 |
| 05/06 |
Optimizationss |
|
Kirk/Hwu: Chapter 9 |
see above |
| 05/11 |
Application: Medical imaging |
|
|
intro CT |
| 05/13 |
Application: CT reconstruction |
|
|
coneBeam sigProc |
| 05/18 |
Application: GPU acceleration case study |
final projects |
|
caseStudy |
| 05/20 |
Multi GPU programming |
|
|
multiGPU |
| 05/25 |
Buddha's Birthday - No classes in session |
|
|
|
| 05/27 |
Appplication: Numerical optimization |
|
|
iterativeCT |
| 06/01 |
Final projects discussion |
|
|
|
| 06/03 |
Libraries, Open ACC |
|
|
libraries OpenACC |
| 06/08 |
Parallel programming principles |
|
|
parallelProgPrinciples |
| 06/10 |
Final projects discussion |
|
|
|
| 06/19 |
(10 am) final project presentations |
|
|
|
