Dell Powers Alzheimer’s Disease Breakthrough at The University of Queensland

Print Friendly, PDF & Email

Today Dell Technologies announced one of the first computational projects for The University of Queensland’s Dell HPC system may enable a non-invasive disease-modifying strategy for Alzheimer’s Disease.

The “Wiener” HPC system, built by Dell Technologies for the university’s Research Computing Centre (RCC), is a GPU-accelerated supercomputer. 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 visualization and machine learning (ML). It is also used for modeling possible treatments for some of the most debilitating illnesses, such as Alzheimer’s Disease.

The Queensland Brain Institute, the university’s neuroscience research institute, is using the Wiener system to model the behavior of ultrasound using an analysis technique called Finite Element Method (FEM). The modeling calculates what happens to each element of the brain when an ultrasound is passed through the skull. It is hoped that ultrasound can be used to provide direct access to the brain, something not currently possible due to the presence of two proteins associated with Alzheimer’s disease. The promising results will now be confirmed in a sheep study, an animal with similar skull properties as humans, and may be instrumental in developing treatments that stop or reserve degeneration, rather than just relieving symptoms.

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 honored to play our part in the resulting discoveries that can change lives for the better.”

Growing to Meet Demand

This research is just one of the Weiner’s many workloads. 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 modeling, psychological testing and learning, and disease identification.

Lattice light sheet imaging of live, ruffling macrophages

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 organization. It’s the focal point of AI computing infrastructure at The University of Queensland.”

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.

The Wiener supercomputer also supports the university’s lattice light sheet microscope (LLSM), using an image restoration technique called deconvolution to provide clear, real-time 4D biology imaging.

Staying on the Leading Edge

The Wiener system, initially built on Dell EMC PowerEdge R740 servers provided a consistent building block for processing data sets across 15 compute and analysis nodes, along with two additional nodes for visualization.

The system’s expansion, this year, has been driven by demand from multiple departments and research teams – both at the university and with external research partners. The University of Queensland team worked in close collaboration with Dell Technologies to engineer and develop the system’s new capabilities, using PowerEdge C4140, doubling the initial nodes and tripling the compute performance.

Dell Technologies provided a new form factor for accelerated computing using a PowerEdge C4140 platform that does not use a PCI Express switch to get information back to the CPUs, resulting in 11% faster training for machine learning and allowing for lower latency internodal communication for distributed deep learning (DL) workloads. Together, these provide the university with measured competitive capability. And, as an early adopter of dedicated NVIDIA Volta-based GPU-accelerated supercomputing in Australia, it is an advantage the university plans to maintain.

The new NVIDIA Volta V100 Tensor Cores gives the Wiener system a total performance of 11.3 PetaFLOPS. This gives it the processing power to restore the images at the edge of the university’s network, where the scientific instruments are, providing a fully-interactive experience to researchers viewing 4D data sets in real-time.

We are seeing exponential growth in both velocity and volume of data being generated by scientific instruments around the world,” said Andrew Underwood, field chief technology officer, HPC and Artificial Intelligence, Dell Technologies, Asia Pacific and Japan. “This is driving Dell Technologies and our customers to collaborate on approaches that leverage parallel processing power from our Dell EMC PowerEdge platforms, in order to unlock the confluence of simulation, analytics and machine learning.”

Sign up for our insideHPC Newsletter