By John KellerEditor in Chief
The military embedded computer industry has been turning backflips since last month amidst the excitement surrounding the 7 Jan. introduction by microprocessor giant Intel Corp. of the latest versions of its Core i7, i5, and i3 processors at the International Consumer Electronics Show in Las Vegas.
Although several of Intel’s powerful new microprocessors are based on the company’s 32-nanometer submicron processing technology, what has the military computer board industry excited most is the floating-point processing capability of the i7 device. It’s interesting to note that Intel is incorporating floating-point processing in its latest processors for reasons that have little, if anything, to do with embedded processing for aerospace and defense applications.
Intel and its customers are attracted to floating-point capability to help power new generations of desktop computers; floating-point processing helps desktop and laptop computers handle video faster and more efficiently than ever before. It’s difficult to surf the Internet today without being prodded to view some kind of video, and it is becoming common for personal computer users to stream movie-length videos to their machines. Floating-point processing helps make that happen.
It’s not video capability that is of interest to the military embedded computing community. Systems designers and single-board computer makers in this space see floating point and think digital signal processing (DSP) to crunch the complex and fast-moving data streams from radar, sonar, electronic warfare, and signals intelligence systems.
While stand-alone DSP chips have existed for years, systems designers would rather use processors able to perform DSP as well as general-purpose processing on a single chip. This approach not only helps shrink substantial processing capability into small spaces, but it also helps defense systems designers benefit from the price and reliability advantages that come from the massive scale of manufacturing that Intel will see in its newest desktop microprocessors.
It’s funny that Intel sees the floating-point capability of its Core i7 processor as the gateway to a new generation of complex graphics and fast streaming video, while military systems designers see it as the latest and greatest way to implement signal processing for electronic and electro-optical applications with commercial off-the-shelf (COTS) single-board computers.
Within hours of Intel’s introduction of the Core i7 processor and the other chips in the company’s new Core family, embedded computing heavyweights Curtiss-Wright Controls Embedded Computing in Leesburg, Va., GE Intelligent Platforms in Charlottesville, Va., and Extreme Engineering Solutions Inc. of Middleton, Wis., had introduced embedded computers based on the Intel Core i7. Companies like Advantech and ADLINK soon followed, and more Core i7 embedded products are expected.
In the grand microprocessor wars that have been entertaining the military embedded computing industry now for nearly 30 years, it is becoming clear that a tectonic shift is in progress that could swing preferences for high-performance embedded DSP computing power—which now revolve around the Freescale Semiconductor Power Architecture—back into Intel’s camp.
While Intel is out of the gate with big momentum for its Core i7 devices, Freescale has a lot of catching up to do. The company disappointed many military systems integrators when it abandoned the AltiVec floating-point capability in its latest microprocessors.
It remains to be seen in the coming weeks just how big a deal this shift in the microprocessor industry will be. With the likes of Curtiss-Wright, GE, and Extreme Engineering on board, it’s bound to be significant for the military embedded industry.