Please select from the list below to download articles, application notes and white papers for embedded computing products.
Introducing the FPGA Mezzanine Card: Emerging VITA 57 standard brings modularity to FPGA designs
FPGAs are popular in today's military embedded systems, but I/O can become a problem with its tight coupling to the FPGA and resulting limited design reusability. This also limits the availability of COTS FPGA boards because it can be difficult to design an FPGA with the right I/O for a wide customer base. The new VITA 57 FPGA Mezzanine Card (FMC) standard is stepping in, however, to help engineers face these challenges. (Reprinted from VME and Critical Systems Magazine) Download the complete article
|
4/2008
 |
VPX: le VME <<flexible>> du futur (in French)
Avec l’avènement de la spécification Vita 46, ou VPX, le VME quitte les rives traditionnelles des communications série en fond de panier, pour passer à des technologies de commutation entre cartes. Avec à la clé une bande passante disponible très élevée et une flexibilité sans précédent dans la mise en oeuvre d’un système. (Copyright Electronique N° 189 Mars 2008) Download the complete article
|
3/2008
|
VME & its Follow-Ons Solve ELINT problems
Converting the analog world to digital has been a driving force behind signal-intensive computing for decades. The real world is analog while computing, for the most part, is digital. Military applications, like radar or video imaging, are attempting to create a very precise digital picture of real-world data in greater detail using higher resolution sensors and cameras that can produce orders of magnitude more data than previous-generation acquisition devices. Application requirements have driven and continue to drive the need for more processing and communication bandwidth. (Reprinted from COTS Journal) Download the complete article
|
3/2008
|
Integrated VXS SIGINT Digital Receiver/Processor - Application Note
This application note describes an integrated solution combining a high-performance digital receiver from DRS Signal Solutions and a high-performance data processing solution from VMETRO. The combination of the DRS SI-9146 Dual Tuner and the VMETRO Phoenix VPF1 VXS DSP engine demonstrates a low-risk approach to the development of Signals Intelligence (SIGINT) and Electronic Warfare (EW) systems that are deployed in air-cooled and rugged conduction-cooled environments. This combination reduces integration risk by providing a reliable, high-performance system with a high throughput data interface between the tuner and signal processing hardware.
The SI-9146 and VPF1 provides a processing solution capable of processing either two coherent or two independent RF tuners covering a range from 20-3000MHz with an instantaneous IF bandwidth of 30 MHz for each of the RF channels. Additional channels can be scaled with additional module pairs (SI 9146 and VPF1) added to a VXS chassis. Download the complete article
|
2/2008
|
Configurable PMCs put an FPGA to work
Reconfigurable computing isn't a novel concept, but the idea of a configurable PMC using an FPGA, swappable I/O adapter modules and I/O specific IP is a new wrinkle. These configurable PMCs can help reduce design time by providing a platform for adding I/O to a single board computer with PMC sites. We explore the key architectural points to consider in designing around the configurable PMC concept. (reprinted from Military Embedded Systems) Download the complete article
|
7/2007
|
10Gb Ethernet for high-performance real-time embedded systems: what you need to know
Ethernet is now running at 10 Gb rates, making it a viable option for high-speed interprocessor and I/O communications. To help ensure a successful system implementation, designers should consider an FPGA-based protocol offload architecture. (reprinted from Military Embedded Systems) Download the complete article
|
6/2007
|
The right stuff: FPGAs fit EW & ISR system needs
Developers of today's embedded Electronic Warfare (EW) and Intelligence, Surveillance and Reconnaissance (ISR) applircations need to achieve higher levels of performance while meeting very limited space, weight and power (SWAP) budgets. The key to success for these embedded EW and ISR programs is the proper utilization of high-performance FPGAs for interfacing to sensors, reducing data and moving data to a CPU for post processing. (reprinted from VME and Critical Systems) Download the complete article
|
4/2007
|
Point-to-Point Serial Interconnects Edge Out Switched Schemes
High-speed serial interconnect schemes are vital in a lot of high-bandwidth military applications. While switched fabrics get a lot of attention, simpler point-to-point interconnect schemes are a better choice for some situations. High-speed serial interconnect (HSSI) technology can fill several roles in military embedded systems: chip-to-chip, board-to-mezzanine, board-to-board and sensor-to-subsystem interconnects to name a few. Use of HSSIs simplifies cabling, improves bandwidth and enhances system architecture by allowing more flexible interconnects than parallel buses. Military applications with a large appetite for fast interconnect links range from radar processing to SIGINT to integrated missile defense systems. (reprinted from COTS Journal) Download the complete article
|
3/2007
|
FPGA-Based Stack Acceleration & Processor Board Architecture Underpin 10GbE Performance
10GbE realizes the long-coveted goal of having an accessible, off-the-shelf fat data pipe that uses a widely accepted and deployed data transfer protocol. But to smoothly utilize that pipe in the embedded space you need some key foundations such as protocol acceleration, processor carrier board and driver architecture, and one that may seem particularly non-intuitive: FPGA-based technology. The use of FPGAs can be insurance against disaster in getting the true potential performance out of implementing 10 Gigabit Ethernet. (reprinted from RTC Magazine) Download the complete article
|
2/2007
|
Utilizing FPGA DSP Slices with serial fabrics
In the twilight of 2006, the concept of utilizing FPGAs for DSP operations is fairly well understood, established and recognized within the signal processing industry. However, the degree of benefits that FPGAs can provide for specific applications is still debated in terms of constraints such as development time, effective heat dissipation and the actual DSP operations being performed. Many of these factors depend on an optimal implementation. As an example, to maximize the benefits that FPGAs can provide, DSP operations should, if possible, be implemented in fixed point arithmetic. While floating point functions can also be implemented in FPGAs and doing so has been made much simpler with advanced compliers, implementing those same operations in fixed point will yield higher performance because fixed point is inherently well suited for execution in hardware circuits. (reprinted from RTC Magazine) Download the complete article
|
1/2007
|
Using Virtex-5 FPGAs in COTS Board-Level Products
In the fast-paced world of FPGA development, Xilinx has struck again with its second-generation ASMBL™ architecture devices, the Virtex™-5 family. This device family has many upgrades from its predecessor, the Virtex-4 family, and likewise continues the evolution of the ASMBL architecture, with scalable FPGAs catering to the application-specific marketplace. For commercial off-the-shelf (COTS) developers, this means a platform that is low cost, light on power consumption, and optimized for high performance. (reprinted from XCELL Journal) Download the complete article
|
12/2006
|
VXS versus VPX: A Question of Maturity
If you're designing a next-generation electronic warfare or Intelligence, Surveillance, Reconnaissance system, can you base your design on VITA 41 (VXS) or should you wait for VITA 46 (VPX)? VPX has a lot of potential, addressing both 6U and 3U solutions, but can you base a design on it today? The key to providing a useful answer has a lot to do with longevity. (reprinted from MIL/COTS Digest) Download the complete article
|
12/2006
|
Next-generation DSP applications empowered by latest VME technologies
VME technology continues to evolve, and developers are looking at the VXS or VPX standards for many high-end, embedded, real-time DSP applications, especially in defense and aerospace. Each has strengths and weaknesses, but are VXS and VPX competing for the same applications or are they complementary technologies? How are these technologies being used today and how might they be used in the future? Here, we sort out fact from fiction. (reprinted from VMEbus Systems Magazine) Download the complete article
|
10/2006
|
VXS: Jump Start to High Performance for VME Users
VXS provides a path to get substantially more performance into systems, but at the same time provides an opportunity for reuse of existing hardware, software and experience by leveraging familiar VMEbus technology. (reprinted from RTC Magazine) Download the complete article
|
10/2006
|
Moving Real-Time Data around FPGA-Centric Systems
Support for real-time FPGA networks is emerging from board level vendors. As larger FPGAs and solutions that are more sophisticated are required, this will become increasingly important. (reprinted from COTS Journal) Download the complete article
|
5/2006
|
Deploying High-Power, Conduction Cooled VXS in Military Applications
VXS (VITA 41) is a relatively new industry standard which is garnering support in compute-intensive military applications as the industry continues the move to COTS products. VXS is becoming accepted because today’s airborne DSP applications such as electronic warfare EW, ELINT, SIGINT, radar, and image processing require higher levels of processing power and data bandwidth, which is an excellent match for VXS. The VXS processing boards utilized in these demanding DSP applications incorporate the latest generation of FPGAs, CPUs, and DSP processors, often in large quantities, to provide the highest performance levels possible. Typical VXS processing boards are based on quad-FPGA, quad-PowerPC 74xx, or hybrid FPGA/PowerPC designs. With all this power, how do you cool them? (reprinted from MIL/COTS Digest) Download the complete article
|
2/2006
|
FPGA memory controllers improve DSP performance
Signal processors spend a significant portion of time and resources moving data, shuffling it in prepartion for manipulation. This inefficiency can be significantly reduced for downstream DSP processors by using a large, multi-ported memory buffer tightly integrated with a user-programmable FPGA logic block and a corner-turning Direct Memory Access (DMA) engine. This allows DSP and other processors to spend a higher percentage of time and resources on intelligent data manipulation, reducing overhead and system complexity. This article examines design issues and technology advances that can increase efficiency and optimize performance. (reprinted from Military Embedded Systems) Download the complete article
|
10/2005
|
Consider Mezzanine Sites and Optimized Bridging When utilizing FPGAs for DSP chores
Utilizing FPGAs for digital signal processing is gaining larger market acceptance and popularity at a rate few would have dared to predict just two or three short years ago. This can primarily be attributed to three factors: 1) The priority being placed on increasing processing power while reducing total system volume and heat dissipation 2) The pace of advancement in FPGA technology, specifically as it pertains to size in the number of logic slices and speed in terms of the FPGA's running clock frequency 3) Ease-of-use provided by FPGA development tools, algorithmic modeling tools and compilers. (reprinted from Electronic Design) Download the complete article
|
9/2005
|
Is VXS Ready for Prime Time?
There has been considerable progress this year in the VITA 41 VXS (VME Switched Serial) arena, but is VXS to the point that OEMs and system integrators can actually use it in their next-generation system designs? The answer is a resounding “yes,” although many of the switched serial fabrics are not as readily available as is required. The good news, however, is that FPGAs can substitute for in-development fabric ICs, and non-switch architectures can still use serial fabrics in direct, “switchless” interconnect schemes. (reprinted from VMEBus Systems Magazine) Download the complete article
|
6/2005
|
The need for optimized bridging between PCI and Serial RapidIO
RapidIO has distinct advantages over alternative architectures for distributed multiprocessor systems. Instead of a hierarchal, spanning tree topology, such as found with PCI-X and PCI Express, RapdIO supports peer-to-peer communications with dual-star, mesh, daisy-chained or tree topologies (reprinted from RapidIO Connections Newsletter) Download the complete article
|
2005
|
