Thesis Topic Details

Topic ID:
3063
Title:
MapReduce for FPGAs: Accelerating Array Computations
Supervisor:
Manuel Chakravarty
Research Area:
Programming Languages, Compiler, Computer architecuture
Associated Staff
Assessor:
Oliver Diessel
Topic Details
Status:
Active
Type:
R & D
Programs:
CS CE BIOM BINF SE
Group Suitable:
No
Industrial:
No
Pre-requisites:
Previous experience with FPGAs highly recommended
Description:

Accelerate is an embedded language for high-performance array programming implemented in the modern functional language Haskell. It is based on the use of collective array operations, such as Map and Reduce, but adds many more to simplify the development of efficient array computations.



The design of Accelerate supports the implementation of a range of different backends - in particular, a backend targeting modern GPUs and one targeting multicore CPUs are work in progress. It is the aim of the present thesis topic to design and implement a backend targeting reconfigurable architectures, such as FPGAs. The result will be a high-performance array framework with unprecedented flexibility and portability.

Comments:
--
Past Student Reports
 
No Reports Available. Contact the supervisor for more information.

Check out all available reports in the CSE Thesis Report Library.

NOTE: only current CSE students can login to view and select reports to download.