Dr Beau Johnston

PhD, Australian National University
Visiting Fellow
College of Engineering & Computer Science

Areas of expertise

  • Computer System Architecture 080302
  • Concurrent Programming 080304
  • Image Processing 080106
  • Stochastic Analysis And Modelling 010406
  • Distributed Computing 0805

Research interests

My mission is to develop tools which allow the better use of computational resources for scientific discovery -- facilitating computer scientists and computational/data scientists to make more discoveries, faster. 

To this end, my current primary research topic is on 'Workload Characterization for Heterogeneous Computing'.
I am broadly interested in Algorithms, Programming Languages and Parallel Computing.
I am also a Researcher at the University of New England where I work in data science, computational modelling and computer vision applied to ecology. I also get to exercise these interests collaborating on developing tools for neuroscience with The Dehorter - Neuronal Development Group.


My PhD was in High-Performance Computing and Programming Languages. More specifically, I investigated the patterns/characteristics of scientific workloads and their impact on performance over a range of accelerator hardware.

I developed a tool to perform Architecture-Independent Workload Characterization (AIWC -- pronounced | \ 'air-wik) -- which extracts features critical to performance. I then built models using machine learning to perform accurate predictions of AIWC features to their performance on different accelerators.

Scientific discovery is increasingly dependant on supercomputers requiring increasingly larger and more complex simulations; Accelerators are critical for the next generation of these supercomputers -- offering energy-efficiency where it is sorely needed. My work is applicable to workload scheduling (to better use these massive machines) and evaluating prospective hardware before manufacture (to allow the most appropriate supercomputers to be built based on the envisaged scientific workloads).

AIWC is also useful to guiding developers to potential software optimizations -- and is my active area of research.


Return to top

Updated:  19 June 2021 / Responsible Officer:  Director (Research Services Division) / Page Contact:  Researchers