Infinite demand for supercomputing resources has become the norm with a bevy of increasingly powerful applications limited only by the number of available cores. However, according to some climate researchers in Australia, the country’s progress toward climate modeling goals is being threatened by a lack of additional high performance computing resources.
As TechWorld Australia pointed out, Australia has been a hotbed of new HPC developments over the last couple of years as new projects demand vast increases in current resources. Although spending on HPC is ongoing, researchers in climate studies in particular fields are feeling the pinch as they seek new outlets to run their complex simulations.
The author of a recent piece exploring these conflicts of supply and demand claims that, “Demand for supercomputer access is not only coming from the climate science community. Australia’s bid for the $2.1 billion Square Kilometer Array (SKA) radio telescope is a major driver behind the creation of the Pawsey high performance computing center” even those these extended resources will still rely on grid computing to obtain additional power.
Other projects in Australia to feed scientific research, including the Swinburne University plan for a hybrid supercomputer from SGI, have extended Australia’s resources—but not enough according to some in the climate change research community
According to Dave Griggs, director of the Monash Sustainability Institute and CEO of ClimateWorks in Australia, the software piece of the climate modeling puzzle is in place, but there are significant strains on current resources. He claims that this will threaten new research and interfere with Australia’s position as a climate research leader.
As Griggs told Australia’s TechWorld, “We have an infinite demand for supercomputing and the quality of the predictions you can make are a combination f how good you are at the supercomputing you have got to run on it.”
Griggs went on to note that “you need to be competitive in both of those things. There is no point in putting bad science into the best computer in the world. Equally, there is no point in putting good science into a computer that is not competitive.”