DARPA announces program to create polymorphous computing architecture
Officials at the Defense Advanced Research Products Agency (DARPA) in Arlington, Va., are kicking off the Polymorphous Computing Architecture (PCA) program.
By John McHale
ARLINGTON, Va. — Officials at the Defense Advanced Research Products Agency (DARPA) in Arlington, Va., are kicking off the Polymorphous Computing Architecture (PCA) program. This initiative addresses obsolescence issues of military platforms that must operate in the field for decades — or longer.
The goal of the PCA program "is to develop a revolutionary embedded computing architecture that will support multi-mission, multi-sensor, and in-flight retargetable missions, says Robert Graybill, PCA program manager at DARPA.
The architecture will be optimized for each unique mix of applications and or missions and be able to morph in response to changing requirements, he explains.
"Payload adaptation, optimization, and verification will be reduced from years, to days, to minutes," Graybill continues. "The historic, and problematic, computing system development approach of hardware first, software last, will be replaced with software first, hardware last. This makes a lot of sense if you think about the fact that today's application software far outlives the [commercial-off-the-shelf (COTS)] computing hardware in military systems."
Future system architectures "must be able to support a broad spectrum of functionality by morphing on-demand over time," Graybill says. "At the same time, each unique mission's functionality, size, weight, energy, performance, and time requirements, must still be satisfied, and hence the term polymorphous computing."
This is especially true for a military that increasingly relies on COTS technology, Graybill says. "A comment that I often hear is: "all we have to do is to monitor and insert [COTS]," he continues. However, it is not that simple, he adds, and this where a PCA type of system is needed.
For example the embedded computing system of a medium-sized tactical unmanned aerial vehicle (UAV) application with a plug-and-play sensor mission strategy is required to support a broad spectrum of diverse processing requirements and platform constraints, driven by different mission objectives and platform sensor configurations, Graybill says. "The short-term answer is to provide unique computing hardware. The long-term challenge is to provide a common, evolvable computing architecture with no loss of efficiency."
Another example would be the B-52 long-range jet bomber, Graybill continues. "The platform life, in this case on the order of 70 years, far exceeds the functional lifecycle of the electronics," he says. "This type of aging platform, loaded with legacy electronics, represents a significant challenge to the services from an operational readiness and life cycle cost perspective."
Three DARPA embedded computing programs have laid the foundation for the PCA program by addressing specific computing technology issues, Graybill says. They are:
— the Adaptive Computing Systems Program, which focuses primarily on providing rapid adaptation and acceleration of sensor front-end signal processing algorithms using field programmable gate array (FPGA)-based computing devices and software;
— the Data Intensive Systems program, which deals with providing processor in memory and adaptive memory management solutions for data starved applications; and
— the Power Aware Computing and Communications program, a five-year program to develop an integrated power management approach that will implement energy management at all levels, while optimizing performance, energy, and power demands against instantaneous mission requirements or "just in time power," Graybill says.
These programs "are all focused on very specific computing technical innovations," Graybill says. "In order to satisfy the computing requirements for the new set of emerging dynamic military missions, a major revolutionary embedded computing change must take place. A polymorphic layer stable hardware and software interfaces will enable the architecture to morph as a function of the mission objectives and constraints."
Current general-purpose computers enable instructions, data transfers, cache management, and external I/O to flow only one way, Graybill says. "Polymorphous computing will allow the architecture to be morphed to specific needs. At the top level, the PCA concept may be viewed as three models: system description, programming, and hardware, he says.
"From an application developers point of view, user-developed software may be specified in domain-specific format residing on a stable application programming interface or API," Graybill says. The PCA's mission-aware morph ware will use "malleable software and hardware service elements bounded on both sides by stable software APIs and stable architecture abstraction layers," he explains.
The "morph ware" will be independent of the hardware architecture enabling it adapt to changing requirements in a cost effective way, Graybill says.
For more information on the DARPA PCA program go to the World Wide Web at http://www.da