(New page: The goal of this course is to utilize the supercomputing power of programmable PC graphics cards (Graphics Processing Units-GPUs) for scientific, entertainment, and management applications...) |
|||
| (One intermediate revision by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | The goal of this course is to utilize the supercomputing power of programmable PC graphics cards (Graphics Processing Units-GPUs) for scientific, entertainment, and management applications. | + | The goal of this course is to utilize the supercomputing power of programmable PC graphics cards (Graphics Processing Units-GPUs) for scientific, entertainment, and management applications. |
| − | :Data prepresentation methods | + | The topics for class projects includes the following: |
| + | |||
| + | *<B>Data prepresentation methods</B> | ||
::Sparse matrix representation and multiplication | ::Sparse matrix representation and multiplication | ||
| − | + | *<B>Data Analysis algorithms</B> | |
::Kernel Density Estimation algorithm | ::Kernel Density Estimation algorithm | ||
::Distance map generation algorithm | ::Distance map generation algorithm | ||
::Difference of Gaussian algorithm | ::Difference of Gaussian algorithm | ||
::Likelyhood ratio test algorithm | ::Likelyhood ratio test algorithm | ||
| + | [http://cobweb.ecn.purdue.edu/~vip/teams/GPU.html Click here] for VIP webpage | ||
Latest revision as of 11:37, 30 November 2009
The goal of this course is to utilize the supercomputing power of programmable PC graphics cards (Graphics Processing Units-GPUs) for scientific, entertainment, and management applications.
The topics for class projects includes the following:
- Data prepresentation methods
- Sparse matrix representation and multiplication
- Data Analysis algorithms
- Kernel Density Estimation algorithm
- Distance map generation algorithm
- Difference of Gaussian algorithm
- Likelyhood ratio test algorithm
Click here for VIP webpage
