![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Friday 22 October 2010, 16:00-17:00
Performance-portable Programming Abstraction for Image Processing
- đ¤ Speaker: Richard Membarth, University of Erlangen-Nuremberg (currently ARM intern)
- đ Date & Time: Friday 22 October 2010, 16:00 - 17:00
- đ Venue: GS15, Computer Laboratory
Abstract
We present a framework for representing image processing kernels based on decoupled access/execute metadata, which allow the programmer to specify both execution constraints and memory access pattern of a kernel. The framework performs source-to-source translation of kernels expressed in high-level framework-specific C++ classes into low-level CUDA or OpenCL code with effective device-dependent optimizations such as global memory padding for avoiding partition conflicts. We evaluate the framework on two kernels on GPU and CPU systems, and concur with previous work that access/execute metadata is a suitable performance-portable abstraction for image processing.
Series This talk is part of the Computer Laboratory Programming Research Group Seminar series.
Included in Lists
- All Talks (aka the CURE list)
- bld31
- Cambridge talks
- Computer Laboratory Programming Research Group Seminar
- Department of Computer Science and Technology talks and seminars
- GS15, Computer Laboratory
- Interested Talks
- School of Technology
- Trust & Technology Initiative - interesting events
- yk449
Note: Ex-directory lists are not shown.