In one of its first computational projects for the University, Dell’s Wiener high-performance computing (HPC) system may enable a non-invasive disease-modifying strategy for the disease.
The HPC system built by Dell for the university’s Research Computing Centre (RCC), is a GPU-accelerated supercomputer.
Dell says GPUs, with significantly more cores than CPUs, are well-suited to processing massive amounts of computational tasks in parallel, including intensive tasks such as data visualisation and machine learning.
|
The modelling calculates what happens to each element of the brain when an ultrasound is passed through the skull and it is hoped that ultrasound can be used to temporarily allow direct delivery of therapeutic drugs to the brain, something not currently possible due to the presence of a blood-brain barrier and activate cells that can digest the plaques that are a hallmark of Alzheimer’s disease.
“Australia prides itself on its research achievements, especially in medicine,” said Chris Kelly, vice president, Infrastructure Solutions Group, Dell Technologies, Asia Pacific and Japan.
“With this supercomputer, the University of Queensland can harness machine learning to drive innovation, across a broad range of use cases, that previously wasn’t possible. We’re honoured to play our part in the resulting discoveries that can change lives for the better.”
Dell says the research at the University of Queensland is just one of the Weiner’s many workloads, and demand to implement the supercomputer in projects across the university has led to the expansion of the system’s power and size - allowing for a broader range of applications, including climate modelling, psychological testing and learning, and disease identification.
“It’s become a whole ecosystem,” said Jake Carroll, chief technology officer, Research Computing Centre at The University of Queensland.
“Wiener has become a plethora of massive machine learning and deep learning capabilities in the organisation. It’s the focal point of AI computing infrastructure at The University of Queensland.”
Dell says that in other projects, The University of Queensland’s School of Information Technology and Electrical Engineering is working on developing new digital pathology techniques for faster blood samples results, while another machine learning algorithm will be able to diagnose the presence of skin cancer from histology slides with the accuracy of a trained pathologist.