# About

I'm a Research Associate under the supervision of Wayne Luk in the Custom Computing research group. Previously, I was a member of the Software Performance Optimisation research group under the supervision of Paul Kelly.

My current research involves the simulation of chaotic systems on FPGAs in the context of atmospheric modelling.

My previous research involved the investigation of the applicability of Domain Specific Languages to the quantum chemistry package ONETEP. Further details can be found in slides I've presented on this work here.

Before that, I looked at the use of active libraries in the context of optimising the finite element method. The outcome of this work was a library, Excafé, that generated optimised C code for performing finite element local assembly. This work was presented at the FEniCS'11 workshop.

# Presentations

# Publications

# Reports

In this thesis, I explore an approach called "active libraries". These are libraries that take part in their own optimisation, enabling both high-performance code and the presentation of intuitive abstractions.

I investigate the use of active libraries in two domains. Firstly, dense and sparse linear algebra, particularly, the solution of linear systems of equations. Secondly, the specification and solution of finite element problems.

Extending my earlier (MEng) thesis work, I describe the modifications to my linear algebra library "DESOLA" required to perform sparse-matrix code generation. I show that optimisations easily applied in the dense case using code-transformation must be applied at a higher level of abstraction in the sparse case. I present performance results for sparse linear system solvers generated using DESOLA and compare against an implementation using the Intel Math Kernel Library. I also present improved dense linear-algebra performance results.

Next, I explore the active-library approach by developing a finite element library that captures runtime representations of basis functions, variational forms and sequences of operations between discretised operators and fields. Using captured representations of variational forms and basis functions, I demonstrate optimisations to cell-local integral assembly that this approach enables, and compare against the state of the art.

As part of my work on optimising local assembly, I extend the work of Hosangadi et al. on common sub-expression elimination and factorisation of polynomials. I improve the weight function presented by Hosangadi et al., increasing the number of factorisations found. I present an implementation of an optimised branch-and-bound algorithm inspired by reformulating the original matrix-covering problem as a maximal graph biclique search problem. I evaluate the algorithm's effectiveness on the expressions generated by our finite element solver.