The Optalysys technology is pioneering in that it will allow mathematical functions and operations to be performed optically, using low power laser light instead of electricity. These operations may be combined to produce larger functions including pattern recognition and derivatives. Our goal is to provide the step change in high performance computing power that is required in Big Data and Computational Fluid Dynamics (CFD) applications.
The technology will be in the form of enclosed, compact optical systems which can sit on the desktop and are powered from a normal mains supply. They will be driven from a software wrapper and will feature interfaces to commonly used tools like OpenFOAM and Matlab.
As a co-processor, the technology development will initially focus on interfacing with large simulations and data sets to provide analysis of the data as it is produced, providing new levels of capability in areas where the volume of data is such that detailed analysis is not possible. Looking further ahead the technology will be able to the produce the actual simulation data at speeds and resolutions far beyond the capabilities of traditional computing.
We use the natural properties of light travelling through tiny liquid crystal micro display pixels that are thousandths of a millimetre across, to form interference patterns. These patterns are the same as certain mathematical operations, which form the basis of many large processes and simulations that the most powerful processor arrays and supercomputers are made specifically to do. However these processes are fundamentally parallel operations, with each resulting data point in the output resulting from a calculation involving all the data points in the input. In contrast, electronic processing is fundamentally serial, processing one calculation after the other. This results in big data management problems when the resolutions are increased, with improvements in processor speed only resulting in incremental improvements in performance.
The Optalysys technology, however, is truly parallel – once the data is loaded into the liquid crystal grids, the processing is done at the speed of light, regardless of the resolution. The Optalysys technology we are developing is highly innovative and we have filed several patents in the process.
We announced our first demonstrator in early 2015 and are now scaling up the technology through collaborative projects. If all goes to plan we aim to have the first completed systems available by 2017.
All the components used in the Optalysys systems will be low voltage driven, allowing large processing tasks to be carried at a fraction of the running cost of a large processor array or supercomputer. The current largest supercomputer Tianhe-2, reportedly consumes 24MegaWatts of power at peak performance and costs millions of dollars per year to run. In comparison the Optalysys systems will run from a standard mains power supply.
The technology employs the principles of diffractive optics, with high resolution liquid crystal micro displays and low power lasers. Coupled with the novel Optalysys designs, we are able to produce a set of core mathematical operations that can be combined to produce larger functions, at speeds and resolutions behind traditional computing methods.
We hope the technology will be used by everyone, but to begin with we envisage the first users to be the users of high power Computational Fluid Dynamics (CFD) simulations and Big Data sets. However, we also aim to make the technology accessible to as wide an audience as possible, including universities and schools, through the use of remote access / online systems.
Specialist boards, such as graphics cards, are now commonly used to perform specific mathematical operations in large simulations and analysis. However, the Optalysys technology can offer a step increase in processing power over such boards. Future technologies such as Quantum computing offer potentially huge increases in processing power, but it is not clear yet exactly what functionality they will provide or when they will become available.