Researchers with Intelligence Advanced Research Projects Activity (IARPA) are seeking to break the exaflop barrier in their effort to create a supercomputer with the power and cooling capacities beyond anything in existence today.

The fastest supercomputer on the planet right now is Tianhe-2, which was developed by China’s National University of Defense Technology. Tianhe-2 is capable of performing at 33.86 petaflops, which is in the range of quadrillions of calculations, in every second. One exaflop is 1,000 petaflops and is equivalent to a quintillion calculations per second. According to a recent article published in ComputerWorld, exaflop speed is the next big goal in supercomputing.

This week, IARPA, which is housed in the Office of the Director of National Intelligence, awarded funding of undisclosed amounts to IBM, Northrop Grumman, and Raytheon-BBN to begin working on what the group calls Cryogenic Computer Complexity, or C3.

“The power, space, and cooling requirements for current supercomputers based on [CMOS] technology are becoming unmanageable,” said Marc Manheimer, C3 program manager at IARPA, in a statement. “Computers based on superconducting logic integrated with new kinds of cryogenic memory will allow expansion of current computing facilities while staying within space and energy budgets, and may enable supercomputer development beyond the exascale.”

The C3 program is expected to be a five-year, two-phase endeavor. Phase one will occur in the first three years and will consist of developing or demonstrating a small superconducting processor. Phase two will follow over the final two years and will involve the integration of the new technologies into a small-scale working superconducting computer model.

Key components of the C3 project are cryogenic memory for greatly improved energy efficiency and data capacity and advanced superconducting circuits integrated with memory and other components in a superconducting computer in order to assess performance metrics.