At the recent AES convention in Munich, audio technology house APTX (formerly APT, Audio Processing Technology) announced that it is developing a new, scalable variant of its “apt-X” audio compression algorithm. The new codec is called “apt-X Scalable,” and is intended to be used as a single-codec solution in products that process a range of audio inputs, such as mobile devices that include voice, music, ringtones, and other forms of audio.

In February when Xilinx announced its new Virtex-6 and Spartan-6 families, the company also discussed its intention to provide more domain-oriented development tools and development paradigms. In April the company began to make good on its promise by announcing domain-specific tool bundles as part of its new release of the ISE Design Suite, Rev 11.1.

Time-to-market pressures mean that system designers, software developers and integrators require more than just hardware from their chip vendors. They demand reliable, easy-to-use software development tools, OS support, middleware and application software components, I/O support, and more—right out of the box. To win design-ins, a chip vendor must deliver much more than just processing performance on a board.

This month Microchip announced a “high-performance” software library of common DSP functions for its 32-bit microcontroller family, the PIC32. This library replaces Microchip’s earlier DSP library for the PIC32, which was quietly released last October. The library includes 16- and 32-bit vector math routines, 16-bit filters, and 16- and 32-bit FFTs.  Library components are implemented as C-callable assembly and are free of charge; support for the new functions has been added to the MPLAB C compiler for the chip.  

BDTI recently completed a benchmark analysis of the Toshiba MeP “Media embedded Processor” core and “IVC2” SIMD coprocessor, both of which are used in Toshiba’s Venezia mobile multimedia platform.

The MeP is a licensable core that is intended to be used as a building block in multi-core, multimedia-oriented SoCs, typically with multiple MeP cores on a chip.  Each MeP core can be customized with specialized instructions, co-processors, and memory sizes.

To paraphrase business guru Peter Drucker, "If you can't measure it, you can't design it."  In the world of embedded processing, processor developers and users alike rely on benchmarks to measure and assess the capabilities of embedded processors on their target applications.  Benchmark results enable processor developers to understand where they stand in relation to their design targets and their competitors.  For processor users, high-quality benchmark results are a uniquely critical resource in the design of new systems.  And in order to build compet

Multicore and massively parallel chips are gaining momentum in embedded applications, and their increasing market acceptance is likely to have some interesting consequences. One of these, I believe, may be that companies that make massively parallel chips and tools—and their customers—will have to grapple with “stickier” software.

The news in our industry certainly is discouraging these days.

Every week we read about high-tech companies succumbing to the economic crisis. Big companies are having big layoffs, and small companies are quietly disappearing. Start-ups are unable to secure funding.