Machine Learning based Parallelisation for Heterogeneous multi-cores
The School of Informatics, University of Edinburgh invites
applications for two posts of Research Associate on the project "A
Predictive Modelling based Approach to Portable Parallel Compilation
for Heterogeneous Multi-cores". This is an EPSRC funded project in the
area of applying machine learning to parallelisation. This
project is a collaboration between the Compiler group headed by Prof. Michael O'Boyle, within the
Institute for Computing Systems Architecture, at the
School of Informatics,and ARM UK.
Project
The Research Associates (RAs) will we expected to work on a variety of
areas including the development of new techniques for mapping
parallelism using machine learning; investigating dynamic compilation
in the presence of workload and prototyping OpenCL (or similar)
implementations where appropriate. For one of the positions a track
record in using machine learning for parallelisation and mapping is
essential.
Both positions are research rather than development orientated. The
potential for publishing at the highest level is important. Applicants
for the post should normally hold a PhD or be near completion, in a
relevant area. They should be capable of developing new theory and
contributing to tool development. Knowledge and experience of using
compilers such as LLVM, OpenCL or JIKES is highly
desirable. Candidates with experience in dynamic compilation or
related areas are also invited to apply.
Application Process
The start date is flexible but can be as early as 1 September 2010
Fixed Term: 24 months (in the first instance with a possibility of extension)
Salary Scale: £29,853 - £35,646 pa
Please Quote Ref: 3013099
Closing Date: Monday 16th August 2010
Further details:
Job description