COM Express Module enhances power-/size-constrains with GPGPU.

Press Release Summary:




Based on 192-core NVIDIA® Tegra® K1 Kepler SoC, mCOM10K1 Type 10 Mini COM Express Module delivers 326 GFLOPS of performance and brings GPGPU (general purpose processing on graphics processor) capability within reach of applications where power consumption needs to be ≤10 W. Features include full CUDA® support and 2 GB of memory as well as integrated HDMI and LVDS interfaces, GbE and SATA interfaces, PCIe (Gen 2) support, USB ports, and one USB 3.0 port.



Original Press Release:



New COM Express Module from GE Brings New Levels of Performance to Applications Constrained by Power Consumption and Size



mCOM10K1 delivers 326 GFLOPS of performance, consumes 10 watts or less

Benefits from NVIDIA Tegra K1 192-core Kepler GPU for data-intensive applications

Provides “GERugged” reliability in harsh environments



HUNTSVILLE, AL — GE’s Intelligent Platforms  business (NYSE: GE) today announced at Embedded World (Nuremberg, Germany – 24-26 February) the mCOM10K1 Type 10 Mini COM Express Module. Based on the NVIDIA® Tegra® K1 system-on-chip (SOC) - enabling it to deliver 326 GFLOPS of performance, well beyond the performance typically associated with Mini COM Express - it is ideal for applications where very high performance in data-intensive applications, rugged reliability in harsh environments and very compact size need to be combined.



As well as extending GE’s COM Express offering still further, the mCOM10K1  also brings GE’s powerful GPGPU (general purpose processing on a graphics processor) capability within reach of the significant number of applications where power consumption needs to be 10 watts or less.



In the commercial environment, devices with the level of capability of the mCOM10K1 will be key enablers for the Industrial Internet and the Internet of Things, and will see deployment in industrial process automation, automotive and transportation, medical imaging and so on. In military/aerospace, target applications include image and video processing, sensor processing and electronic warfare.



The mCOM10K1’s on-board components are specifically selected for their reliability in demanding conditions. Unlike solutions designed for benign environments, the processor and memory are soldered to the board for maximum resistance to shock and vibration. Extended mechanical construction protects the module, which is designed for optional conformal coating to provide additional resistance to moisture, dust, chemicals, and temperature extremes.



“GPGPU technology has been widely adopted in a broad range of applications, spanning such diverse disciplines as healthcare, astronomy, machine learning, and artificial intelligence,” said Simon Collins, Product Manager at GE’s Intelligent Platforms business. “Much of this work has taken place in the cloud or on big server hardware; low-end hardware has previously required about 100 Watts supply.  The Tegra K1 at the heart of the mCOM10K1 delivers a significant opportunity to exploit GPGPU technology on a scale that was previously unimaginable, creating a sophisticated processing capability at the edge nodes of the network.”



With full CUDA® support, Tegra K1 brings two compute-intensive benefits. First, GPGPU code can be easily ported to other platforms, meaning that an application need be developed only once for a broad range of performance/watt solutions. Second, it leverages the extensive infrastructure of third party tools and open standards libraries that mean that application development is faster and at lower cost.



“Our Tegra K1 mobile processor and Jetson TK1 dev kit provide embedded developers with tremendous computing power and flexibility,” said Jesse Clayton, Product Manager for Mobile Embedded at NVIDIA. “GE’s new module is a perfect example of what Tegra K1 can do in a compact size where high performance and low-power usage are critical.”



The COM Express architecture extends the useful life of the subsystem by allowing a simple, cost-effective upgrade of the processor alone. The long-term cost of ownership is reduced while ensuring that performance keeps pace with changing needs.



The mCOM10K1 features 2 GB of memory; integrated HDMI and LVDS interfaces; Gigabit Ethernet; a SATA interface; PCI Express (Gen 2); and five USB ports and a USB 3.0 port.



About GE’s Intelligent Platforms business

GE’s Intelligent Platforms business (NYSE: GE) is headquartered in Charlottesville, VA and part of GE Energy Management. The company’s work in the military/aerospace segment, headquartered in Huntsville, AL, and Towcester, England, provides one of the industry’s broadest ranges of high performance, rugged, SWaP-optimized embedded computing platforms. Backed by programs that provide  responsive customer support and minimize long term cost of ownership for multi-year programs, GE’s solutions are designed to help customers minimize program risk and cost, and to speed time-to-market. For more information, visit defense.ge-ip.com.



For more information, contact:

Ian McMurray

Media Relations Manager

GE Intelligent Platforms

+44 (0) 1327 322821

ian.mcmurray@ge.com



NVIDIA, Tegra and CUDA are registered trademarks or trademarks of NVIDIA Corporation. All other trademarks are the property of their respective owners.

More from Optics & Photonics

All Topics