Difference between revisions of "GPU610/DPS915 G P Index 20171"
(→Interesting aspects to consider in your project) |
(→Interesting aspects to consider in your project) |
||
| Line 45: | Line 45: | ||
=== Interesting aspects to consider in your project === | === Interesting aspects to consider in your project === | ||
* Try a different language - Javascript (Node.js bindings), Python (pyCUDA bindings) | * Try a different language - Javascript (Node.js bindings), Python (pyCUDA bindings) | ||
| − | * Try APIs - Halide, OpenCV, Caffe, Latte | + | * Try APIs - [http://halide-lang.org/ Halide], OpenCV, Caffe, Latte |
* Compare CPU and GPU performance | * Compare CPU and GPU performance | ||
* Compare different blocksizes | * Compare different blocksizes | ||
Revision as of 22:09, 24 January 2017
GPU610/DPS915 | Student List | Group and Project Index | Student Resources | Glossary
Please add an overview of your group here and create a separate project page for your group!
Contents
Project Rules
- Use the Group page for a Journal of your activities throughout the course of the project
- Project should cover material that differs from the material on the course web site
- Presentation can be in Powerpoint or as a Walkthrough the group project page
- Link to the project page should be included in the Student List table
- Presentation slots are on a first-come first-served basis
- Attendance at all presentations is mandatory - marks will be deducted for absenteeism
- Marks will be awarded for both Group Wiki page and for the Presentation proper
Potential Projects
Suggested Projects
- image processing - [ ]
- data compression - [ ]
- grep - [ ]
- exclusive scan - CMU Assignment 2 Part 2
- simple circle renderer - CMU Assignment 2 Part 3
- object detection/tracking - [ ]
- ray tracing - Khrylx
- sorting algorithms - [ ]
- Jacobi's method for Poisson's equation - [ ]
- Gaussian Regression - cuGP
- Halide - Convolutional Networks
Carnegie-Mellon University Links
Other Links
Reference Papers
- 2008 Survey Paper - you can search this paper for traditional topic ideas
- Nvidia Showcase - probably too challenging - but could lead to simpler ideas
Interesting aspects to consider in your project
- Try a different language - Javascript (Node.js bindings), Python (pyCUDA bindings)
- Try APIs - Halide, OpenCV, Caffe, Latte
- Compare CPU and GPU performance
- Compare different blocksizes
- Compare different algorithms on different machines
- Implement your project on a Jetson TK1 board
Group and Project Index
You can find a sample project page template here
Your Own Project Name
Project Title
#BETTERRED
#BETTERRED
BarraCUDA Boiz
BarraCUDA Boiz
