Is This the Exascale Breakthrough We’ve Been Waiting For?
An animated video, narrated by the inimitable Professor Heinz Wolff, popped up on YouTube last month, detailing a prototype optical processor with some remarkable claims. The company behind the effort, UK-based startup Optalysys, says it is on track to deliver exascale levels of processing power on a standard-sized desktop computer within the next few years.
As Professor Wolff explains, Optalysys is pioneering a new technology that uses light rather than electricity to perform compute-intensive mathematical functions at speeds well in excess of what can be achieved with electronics, and at a fraction of the cost and power consumption.
A 340 gigaflops proof-of-concept model is slated for launch in January 2015, sufficient to analyze large data sets, and produce complex model simulations in a laboratory environment, according to the company.
Unlike current supercomputers, which still use what are essentially serial processors, the Optalysys Optical Processor takes advantage of the properties of light to perform the same computations in parallel and at the speed of light.
“Optalysys’ technology applies the principles of diffractive and Fourier optics to calculate the same processor intensive mathematical functions used in CFD (Computational Fluid Dynamics) and pattern recognition,” explains founder and CEO Dr. Nick New. “Using low power lasers and high resolution liquid crystal micro-displays, calculations are performed in parallel at the speed of light.”
The company is developing two products: a ‘Big Data’ analysis system and an Optical Solver Supercomputer, both on track for a 2017 launch.
The analysis unit works in tandem with a traditional supercomputer. Initial models will start at 1.32 petaflops and will ramp up to 300 petaflops by 2020.
The Optalysys Optical Solver Supercomputer will initially offer 9 petaflops of compute power, increasing to 17.1 exaflops by 2020.
Perhaps the most impressive trait of all is the reduced energy footprint. Power remains one of the foremost barriers to reaching exascale with a traditional silicon processor approach, but these optical computers are said to need only a standard mains supply. Estimated running cost: just £2,100 per year (US$3,500).
To compare, scaling up today’s technology to exascale levels would require at least 200MW of power, and the current fastest supercomputer, Tianhe-2 in Guangzhou, China, requires 24 MW per year (including cooling) at a cost of about $21 million per year.
Optalysys Ltd. raised over £400,000 (US$675,000) in seed money earlier this year, which enabled it to bring its innovative technology to NASA Technology Readiness Level 4 ahead of schedule.
The startup will be targeting these systems at the CFD market, which encompasses a quarter of a million engineers and scientists around the world. CFD is essential for a number of disciplines, including weather prediction, automotive and aerospace design and more.
“Early conversations with potential customers have been extremely positive and one of the largest weather centres have said they are keen to collaborate with us because the energy cost to produce such high quality forecasts, and deal with the huge data volumes, is unaffordable with current processor technologies,” said the CEO. “Whilst our goals are ambitious they are definitely achievable and we are confident that Optalysys technology will be a game-changer for the global science and engineering communities.”