GPGPU Kernel Implementation using an Embedded Language: a Status Report
Rapport, 2010

Obsidian is a domain specific language for general purpose computations on graphics processing units (GPUs) embedded Haskell. This report present examples of GPU kernels written in Obsidian as well as parts of the current implementation of Obsidian. The goal with Obsidian is to raise the level of abstraction for the programmer while not scarifying performance. The kind of decisions and tradeoffs considered by a GPU kernel implementer should be easy to make and change in Obsidian.

Haskell

Embedded Language

Domain Specific Language

Functional Programming

DSeL

DSL

GPGPU

GPU

Författare

Joel Bo Svensson

Chalmers, Data- och informationsteknik, Programvaruteknik (Chalmers)

Koen Lindström Claessen

Chalmers, Data- och informationsteknik, Programvaruteknik (Chalmers)

Mary Sheeran

Chalmers, Data- och informationsteknik, Programvaruteknik (Chalmers)

Ämneskategorier

Datavetenskap (datalogi)

Technical report - Department of Computer Science and Engineering, Chalmers University of Technology and Göteborg University: 1652-926X