Windows virtual machines are now available on the ARDC Nectar Research Cloud’s National GPU Service, opening up additional analysis options for researchers.
In partnership with the Australian Research Data Commons (ARDC), QCIF has enabled Windows Server 2022 to be one of the operating system choices in the graphics processing units (GPU) reservation service via the ARDC Nectar Research Cloud’s user-friendly dashboard. Until now, the National GPU Service supported the Linux operating system only.
Stephen Bird, QCIF’s Advanced Computing Manager, said: “Introducing this capability to the national reservation service provides researchers with greater flexibility and choice in analysis software applications for their projects.
“Researchers use a wide range of analysis applications that utilise GPUs. Not all of these applications run on Linux, with some of them only supported on a Windows platform. QCIF is delighted to be able to enable this on the NVIDIA A40 GPU nodes for national use,” said Stephen.
GPUs are in high demand by Australian researchers for processing large data sets or images, 3D imaging, machine learning, and computational modelling.
Australian researchers can reserve GPUs and large memory virtual machines for their research in advance via the ARDC Nectar Research Cloud dashboard. This helps share high-end compute resources amongst researchers and provide quicker and more efficient reservation and access to the resources.
The National GPU Service, launched last September, is available for projects that meet the criteria for merit allocation.
Nodes of the ARDC Nectar Research Cloud around Australia, including QCIF as the Queensland node, are also able to use the reservation service to provide access to their local (node-funded) GPU servers for their local users.
QCIF received $620,000 in co-investment from the ARDC to procure specialised compute infrastructure for the National Reservation Service.
QCIF’s infrastructure procurement included a mix of GPU and large-memory compute nodes for data-intensive and large memory workloads, machine learning and inference workloads, and visualisation workloads.
Read more about the National GPU Service.