Seismic data processing is one of the biggest users of computer power and technology on Earth. To provide our service to the industry, we’ve invested in one of the largest privately-owned supercomputer networks in the world, with data centres in Perth, Houston, London, and Kuala Lumpur. The Perth computer, affectionately known as “Bruce”, is the largest supercomputer in Australia.  At 5 PFlops capacity (that’s 5,000,000,000,000,000 floating point operations per second), Bruce processes massive volumes of seismic data faster than most machines on Earth. DUG’s newest installation in Houston (“Bubba”) is already larger than Bruce, and the data centre is currently being upgraded to accommodate a 120+ PF machine by 2018.

Not surprisingly, supercomputers of this size generate considerable heat and require incredibly efficient cooling technology. Installations such as this are traditionally air-cooled, which is inefficient, very expensive, and environmentally unfriendly. DUG has developed (Patent Publication WA 2017/091862 A1) an advanced, flexible, and modular dielectric-fluid cooling solution which has greatly reduced our energy usage and costs, increased the life and efficiency of our hardware, and given us some of the greenest compute centres in the world.


The cooling system fully submerges standard high-performance computing (HPC) servers into specially-designed tanks that are filled with polyalphaolefin dielectric fluid. The fluid is non-toxic, non-flammable, biodegradable, non-polar, has low viscosity, and most importantly, doesn’t conduct electricity. The unique part of this design is that the heat exchangers are very simple and submerged with the computer equipment, meaning that no dielectric fluid ever leaves the tank. A water loop runs through the rooms and to each heat exchanger.

The dielectric fluid is cooled and circulated around the extremely hot components in the compute servers. This innovative oil-cooling solution has high thermal capabilities and a large operating temperature range.

The fluid is able to be cooled using whatever cooling water sources are available on site: ranging from conventional chilled water to warm water-based systems such as cooling towers, ground loops, or even seawater heat rejection.


Traditionally, companies like DUG spend half of their revenue on compute centres. Energy use can be a significant and crippling expense in a conventional data centre. With DUG Cool, the thermal qualities of the fluid mean that condensed-water chillers can be used rather than refrigeration, saving 25-30% of total power usage. Removing all server fans, which aren’t needed in a fluid-immersion system, reduces power consumption by a further 20%. That’s a total power saving of at least 45%.

The running costs of HPC systems are commonly evaluated using the Power Usage Effectiveness (PUE) metric. The table to the right summarises PUE for typical operators and DUG HPC.


Submerging computers into dielectric fluid has some surprising advantages. Electrical components last longer due to the lack of oxidation of physical joins, solder joints, wires, and connecting materials. There is no oxide build-up on the components, so less maintenance is required.

The > 1000x thermal capacity of the fluid (vs. air) means that components never get hot, reducing their mean time to failure. In our experience, fluid-immersed computers fail at a much lower rate, considerably reducing maintenance costs and expensive down-time.

The fluid itself is also extremely long-lasting, with current indications that it has a lifespan of 20 years. In addition, its clean material safety data sheet (MSDS) means that there are no restrictions on its transport, storage, or usage.

The DUG Cool system is setting new standards: It's modular, using inexpensive standard components. It can be customised for any space and output requirements. It can save you considerable money in your operation costs. Find out how much the DUG HPC cooling system can save you by contacting Our smarts are making sure… orange is the new green.