By Brett Daniel Shehadey
Special Contributor for In Homeland Security
The Cryogenic Computer Complexity Program (C3) is a supercomputer attempt to break the exaFLOP barrier. The exascale is measures in quintillions of calculations per second. The C3 Program is being run by the U.S. Intelligence Community’s Intelligence Advanced Research Projects Activity (IARPA).
IARPA was formed in 2006 and modeled after the success of the Department of Defense’s Defense Advanced Research Projects Agency (DARPA). IARPA’s mission is to basically do for national intelligence what DARPA has done for national defense.
IARPA’s director, Lisa Porter, said in 2010, “The intelligence community needs to place bets on high-risk, high-payoff research that might not work, (but if it did) would give us an overwhelming intelligence advantage over future adversaries.”
Marc Manheimer, the C3 program manager at IARPA said, “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 fastest computer in the world is China’s Tianhe-2, processing 33.86 petaFLOPS or almost 34 quadrillion calculations per second. America’s fastest supercomputer, the Titan, reached over 17 petaFLOPS in 2012 but was beaten shortly thereafter by China’s Tianhe-2 as the world’s fastest computer in 2013. America could respond with a Titan 2 and reclaim the title, which would divert China’s attention and resources and drive the race for faster and faster computing.
The U.S. is hard pressed to reach the exascale soon as competing nation’s edge ahead. In fact, whichever nation succeeds in constructing the most intelligent cognitive computing platforms running within a revolutionary supercomputer will perhaps be more than a few quintillion steps ahead of the other.
Supercomputing is about all about power. More speed requires more energy. Also, more energy, more heat. That is a major problem with the present architecture. How does one cool the system down enough to maintain and exceed such speeds and use less power in doing so? The hardware at present is reaching its limits with the complementary metal-oxide-semiconductor (CMOS) switching systems that will not be able to keep-up with computing demands of the future.
Superconducting supercomputers like the Cryogenic Computer Complexity Program are expected to offer a potentially promising push beyond the constraints of what seems like diminishing returns over the horizon.
The supercomputer race of today is not just about building the fastest and most energy efficient computers but about building the smartest ones for tomorrow. For intelligence agencies, Big Data collection from mass sources was a first step. Fortunately, the U.S. leads the charge in this field and in cryptology without question, but the gap is narrowing here as well. Big Data Analytics is now the necessity, including in intelligence. Superior Big Data Analytics innovations will lead to greater intelligent systems from the collection, analysis, production and even at the strategic and policy planning levels.