Embedded Hotspot

DRAM chip density continues to climb. But the hunger for more memory seems insatiable, especially with virtual systems running on multicore processors. One way to get more memory in a system is to support more memory sockets, though this requires more motherboard space and more drivers. Another is to use higher-density chips, yet this can be more costly. MetaRAM puts a DDR3 cont rol ler between the memory socket and memor y chips (...

Texas Instruments’ C2000 digital signal controller (DSC) gets a major boost with the Control Law Accelerator (CLA). This 32-bit floating-point controller speeds up the processing, often by a factor of five, of analog chores such as motor control and power-supply management. It executes programs stored in shared SRAM, up to 64 kbytes. The main 60-MHz C28x core has its own SRAM, flash, and boot ROM. It also has access to the full peripheral complement, while...

Recording data on flash has limitations, so Cypress Semiconductor turned to nonvolatile SRAM (nvSRAM) with its latest PSoC family of 8-bit configurable microcontrollers. The PSoC NV can offer up to 256 kbytes of nvSRAM plus 2 kybtes of conventional SRAM and 32 kbytes of flash. The nvSRAM has a transfer rate of 1 Mbyte/s and eliminates the wear issues of flash. This can be critical in embedded data logging applications where replacement is not ...

Logic design at the gate or module level for discrete implementations has effectively gone away, with the exception of buffers and analog designs. The move to micros has turned much of today’s system design into large chips and software. Custom logic is still needed, but it often resides in ASICs, complex programmable logic devices (CPLDs), and FPGAs. ASICs aren’t a bad choice if you have gobs of money and time, along with an engineering team. ...

The Hydra 100 from Lucid Technologies turns two or more graphics adapters into a single, cooperative graphics compute engine. It starts as a basic PCI Express switch, allowing any kind of device to be plugged in downstream. But it shows its multifaceted personality when GPUs such as those from NVidia and AMD/ATI are downstream. Its RISC engine makes multiple graphics boards appear as a single, more powerful device, distributing graphics operations...

The military’s rapid move toward network-centric, IP-based (intellectual property) architectures is driving a number of design considerations for current and next-generation embedded commercial off-the-shelf (COTS) subsystems deployed on unmanned aerial vehicles (UAVs). The push toward network-centric architectures is speeding the adoption of these platforms and of newer data communications interfaces such as Gigabit Ethernet (GE) and serial rapid IO...

Unmanned vehicles represent the new cornerstone of the military. The U.S. Army’s Future Combat Systems (FCS) augmented its latest manned ground vehicles (MGVs) with an array of unmanned air and ground vehicles. The U.S. Air Force and Navy also have a number of unmanned vehicles in the works and deployed around the world. Because of their lower cost, these vehicles are quickly finding their way into every military organization on the planet. The U.S. Army...

Sometimes I don’t hear a rumble until it becomes a roar. I’m not sure if CUDA has become a roar yet, but my ears have perked up based on a bunch of announcements I’ve received over the past few months. If CUDA hasn’t registered on your radar yet, here’s a brief summary. CUDA, which stands for Compute Unified Device Architecture, is a C language environment developed by Nvidia Corp. (www.nvidia.com)...

Hypervisor and software virtualization is seen as a cure for the common IT problem of supporting multiple operating systems (OSs) and their applications running across the same hardware environments. This has fueled the widespread adoption of software virtualization across servers and datacenters worldwide. But what about the embedded world? There are two types of hypervisor. One runs on bare hardware, often forming a component part of a small microkernel. ...

Along with the many digital video processing chips available to designers, intellectual- property (IP) options are available for those who need to design their own chips to meet highly customized requirements. These options include RTL cores for system-on-a-chip (SoC) design as well as soft IP for FPGA-based development. IP providers typically offer substantial software support, too. Hardware video-codec IP is available from companies such as On2 Technologies....

After a decade of development and standardization efforts, digital video is now poised to take over broadcast television. With this transition, some digital video processor ICs are moving toward commodity status while others embrace innovation and diversification. The result of this shift is a growing range of product offerings as well as an open door to a host of new video applications. General-purpose DSPs from companies like Analog Devices and Texas...

The Neo FreeRunner looks like an innocuous device on par with a typical cell phone (see the figure). Yet this pocket package from OpenMoko is open to all comers—literally. Its software is all open-source, and even the CAD packages and schematics are available for download. Designers can also use them to create their own products, but why do so when OpenMoko is a source already? The phone...

I f you have lemons, you make lemonade. That’s what Intel will be doing with its x86 architecture when it comes to Larrabee, a massive multicore solution that will take aim at high-performance graphics rivals such as NVidia and AMD/ATI (see the figure). While NVidia and AMD/ATI are taking their graphics processing unit (GPU) offerings into the more general computational realm (see “What Will You Do With 1 TFLOLOPS...

The driving forces behind Samsung’s 50-in. HL-T5089S display are Texas Instruments’ MEMS-based Digital Light Processor (DLP) Discovery Digital Micromirror Device (DMD) and Luminus Devices’ Phlatlight LEDs (see the figure). The HL-T5089S delivers a great HDTV picture for less money and uses less power than large-screen LCDs and plasma displays. It’s surprising that the core of this large-screen rear-projection...

In 1990, the IEEE ratified the 1149.1 standard known as boundary scan. Developed by the Joint Task Action Group (JTAG), it was created to help solve the overwhelming testing problems caused by ever-increasing larger-scale ICs and densely packed multilayer printed-circuit boards (PCBs). The old “bed of nails” method of testing PCBs no longer worked as well, and the inaccessible circuits and even pins on ICs made testing difficult if not impossible. With boundary scan, IC and...

The parallel programming challenge will continue to grow as multicore platforms become more common and their complexity and number of cores continue to increase. The domination of sequential programming languages like C/C++ and, in some areas, Java must give way to extensions or new languages to manage multicore platforms. Tools such as Intel’s Task Building Blocks (TBB) enhance C/C++. The latest version of TBB adds the parallel_do construct that operates like...

Texas Instruments’ $149 Beagle Board can be purchased from DigiKey’s Web site. It contains a dual-core OMAPOMAPOMAPOMAP3 platform with a 600-MHMHz Cortex-A8 and C64+ DSP processor with video accelerator. The chip also has hardware support for Open GL ES 2.0 that can render up to 10 Mpolygons/s. The 430-MHMHz C64+ can handle HD video. Linux and Windows CE are available for the Cortex-A8, while DSP-BIOIOS and codecs run on the C64+. Open-source codecs are in the works. For...

Intel’s Thread Building Blocks 2.1 adds a host of features, including the ability to terminate tasks. This is handy when a thread within a group determines that a solution has been found or an error has been detected such that the rest of the related computation can be terminated. Other new features include a parallel_do function that operates like a foreach loop found in other programming languages, recursive mutex support, and a new thread abstraction. The memory...

During this year’s NINI Week, National Instruments announced LabVIEWIEWIEW 8.6 in addition to a wide range of other NINI hardware and software. And, this latest version of LabVIEW continues to push the limits of parallel processing. Many of its more than 1200 multicore optimized analysis and signal processing routines can take advantage of Intel’s Thread Building Block runtime. LabVIEW applications can push 1 million fast Fourier transforms a second (FFTs/s)...

Looking for a low-cost, low-power PC/104 SBC? Check out Diamond Systems’ Rhodeus. This fanless SBC is based on a 500-MHz AMAMD Geode LX800. Interfaces include Ethernet, two USB 2.0 ports, two serial ports, two PS/2 ports, and a floppy and IDE port. It can handle up to a 1-Gbyte SODIMM. Pricing starts at $350 with 256 Mbytes of DDR SDRAMRAMRAM. Diamond Systems ...