D&R Industry Articles | Most Popular | SoC News Alerts |

Embedded Systems Articles

• Debugging multiprocessor code (Jul. 21, 2008)
  Debugging code running on multiprocessor computing systems, and, in particular, parallel code on multicore devices, is an old computing problem that has reached a certain prominence and urgency because of the profound transformation of hardware from single-processor to multiprocessor and multicore solutions in the past few years.
  
  
• Use NAND Flash for cost, density and performance advantages for mobile handsets (Jun. 30, 2008)
  This NAND flash tutorial covers recent trends, alternatives and even misconceptions regarding mobile handset storage subsystems that support multimedia features.
  
  
• SoCs can hold key to system security (Jun. 24, 2008)
  A system is only as secure as its weakest link, and security becomes ever more important as more equipment moves to a system-on-chip approach. Here we look at the security options available to SoC designers.
  
  
• Floating-point emulation: faster than hardware? (Jun. 05, 2008)
  Here's why emulation is faster than floating-point hardware, and how Critical Link migrated from TI's floating-point C6711 to the fixed-point C64x.
  
  
• 20th Anniversary article: Full simulations with partial hardware (May. 12, 2008)
  What do you do when the hardware team needs working software to check out the system and the software team needs stable hardware to complete their design work? Adding partially operational simulator hardware can improve the effieciency and flexibility of your existing simulator or emulator.
  
  
• An architecture for designing reusable embedded systems software, Part 2 (May. 05, 2008)
  Want to make your application software more reusable? Don't change the hardware, operating system, or your tools. Instead change the architectural framework within which you do your design.
  
  
• Asynchronous DSPs: Low power, high performance (May. 05, 2008)
  An asynchronous DSP offers better power, performance, and reliability than one based on standard synchronous logic. It also enables simpler and less expensive PCB and power supplies.
  
  
• The Relevance of System Design (May. 01, 2008)
  Both hardware and software development must continue to address coming system architecture challenges.
  
  
• An architecture for designing reusable embedded systems software, Part 1 (May. 01, 2008)
  Want to make your application software more reusable? Don't change the hardware, operating system, or your tools. Instead change the architectural framework within which you do your design.
  
  
• Development and use of an Instruction Set Simulator of 68000-compatible processor core (Apr. 24, 2008)
  This paper presents an instruction set simulator of a 32-bit CPU and explains its use in embedded software development. Interaction of the ISS with transaction level model of a complex peripheral (Firewire™ link layer controller) is also discussed.
  
  
• Software-defined silicon: Why can't hardware be more like software? (Apr. 15, 2008)
  Why can't hardware be more like software? It can, even though next generation multicore designs mix programmable logic, CPU blocks, and dedicated logic. But it requires a new approach to architectural design--software-defined silicon.
  
  
• Mobile video: ARM vs. DSP vs. hardware (Apr. 11, 2008)
  This article compares fixed-function hardware, DSPs, and RISC processors for video on handsets. It looks at power area, flexibility, and other issues.
  
  
• Reducing Power in Embedded Systems by Adding Hardware Accelerators (Apr. 10, 2008)
  The rule of thumb in embedded system design has been that adding hardware increases power demands. The careful use of hardware accelerators, however, inverts the rule: adding hardware can reduce power.
  
  
• Consolidating the MCU market around the ARM architecture (Apr. 02, 2008)
  It's inevitable. ARM's Cortex-M3 processor core is going dominate the MCU market.
  
  
• High-level parallel programming model simplifies multicore design (Mar. 27, 2008)
  Processors recently have added explicit parallelism in the form of multiple cores, and processor road maps are showing the number of cores increasing exponentially over time
  
  
• DSP system design, part 2: Critical design choices (Mar. 24, 2008)
  Part 2 shows how to choose hardware and software architectures, how to choose an RTOS, and how algorithm and I/O libraries impact the development process.
  
  
• Analysis: OMAP35x brings Cortex-A8 to the mass market (Mar. 13, 2008)
  BDTI analyzes the OMAP35x, the first mass-market chip to use the ARM Cortex-A8.
  
  
• Tutorial: The H.264 Scalable Video Codec (SVC) (Mar. 10, 2008)
  The H.264 Scalable Video Codec (SVC) reduces network bandwidth, eliminates transcoding, and simplifies storage management. Here's how it works.
  
  
• Multi-core analysis made easy with the Nexus 5001 debug spec (Mar. 10, 2008)
  In System on Chip (SoC) architectures, the ability to effectively analyze problems and optimize operations using real time in-system instrumentation is recognized as one of the most effective methods for completing product development.
  
  
• Designing DSP-based motor control using fuzzy logic (Mar. 06, 2008)
  The increased use of variable-speed drive motors to reduce energy consumption will require a shift from PID controllers to systems based on fuzzy logic algorithms to simplify design, reduce development time, and elminate complex math formulas.
  
  
• Optimize inter-processor communication in dual baseband dual mode handsets (Mar. 03, 2008)
  The onset of HSPA capable handsets, combined with improved video and data content quality, brews a perfect storm for many inter-processor communication architectures. Traditional interconnects can no longer support data throughputs in line with baseband processor capabilities and future mobile communication standards. Here's why multi-port interconnects may be a viable solution.
  
  
• Useful design patterns for building embedded multicore systems (Mar. 03, 2008)
  Consolidation is a long-standing trend within the embedded world. It enables more capable, higher-performance embedded devices using fewer components, at lower cost and power budgets.
  
  
• Multicore systems-on-chip can handle embedded designs (Feb. 28, 2008)
  Many design problems are conveniently concurrent and are easy to attack with multiple processor cores, though not necessarily using a symmetric multiprocessing (SMP) architecture.
  
  
• TI's MSP430 vs. ST Microelectronics' ARM Cortex-based processor for battery-powered apps (Feb. 27, 2008)
  Is TI's MSP430 or ST Microelectronics' ARM Cortex-based processor better for handheld devices?
  
  
• Signal Processing on the MIPS 74K (Feb. 25, 2008)
  BDTI evaluates the signal processing features of MIPS' high-performance superscalar core, the 74K.
  
  
• ARM provides the microcontroller solution (Feb. 21, 2008)
  Several semiconductor manufacturers now offer microcontrollers which are based on ARM technology. These microcontrollers provide an extensive peripheral mix combined with an outstanding price/performance ratio.
  
  
• How to manage a billion cycles (Feb. 13, 2008)
  After years discussing verification strategies with hundreds of ASIC designers, it finally hit me: We're at the point where designers are trying to manage billions of cycles of simulation.
  
  
• Using nextgen PCI Express switches to eliminate network I/O bottlenecks (Feb. 07, 2008)
  Controllers in today's network-connected embedded systems often are overwhelmed by the data streaming to and from the various I/O sources; it can be difficult for the system's root complex to absorb high-speed bursty traffic such as 10Gig Ethernet when it competes with very fast streaming data from sources such as InfiniBand and Fibre Channel (FC) storage elements.
  
  
• For smoother embedded systems development, design-out the hardware (Jan. 30, 2008)
  Rather than wait to begin embedded software development until the hardware is complete and until requirements are fully specified, instead separate the "what" from the "how" in your design and design-out the hardware
  
  
• Achieving higher performance in a multicore-based packet processing engine design (Jan. 02, 2008)
  A new class of processor has begun to appear in a variety of storage, security, wireless base stations, and networking applications to replace the very expensive - with long lead times to boot - proprietary Application Specific Integrated Circuits (ASICs) developed by OEM system solution providers as well as those designed by industry giants, such as LSI Logic and IBM.