Date: 16/04/2012

32-bit DSP from CEVA for voice pre-process and audio post-process

CEVA, Inc., has introduced the CEVA-TeakLite-4 scalable 32-bit DSP architecture framework for a voice pre-processing and audio post-processing algorithms. This architecture also addresses the multi-channel audio codecs, for smartphones, mobile computing and digital home devices.

Ceva says CEVA-TeakLite-4 consumes up to 25% less die area and requires up to 30% less power than the previous generation CEVA-TeakLite-III DSP for decoding MP3 with Dolby Mobile 3+ post-processing.

Eran Briman, vice president of marketing at CEVA stated: "In architecting the CEVA-TeakLite-4, we built upon the vast knowledge and experience gained in the last five years from our first generation 32-bit audio processors to significantly improve the performance and power efficiency of our new architecture. As a result, the CEVA-TeakLite-4 architecture can address the specific requirements of any advanced audio and voice enabled SoC through a choice of scalable and flexible DSPs, which share a common instruction set architecture, software ecosystem and tool set. Furthermore, the integration of our second generation smart power management technology, PSU 2.0, enables the CEVA-TeakLite-4 architecture to deliver the lowest power consumption package possible, for each specific application."

The CEVA-TeakLite-4 architecture is initially available as a series of four compatible digital signal processors. The CEVA-TL410 and CEVA-TL411 DSPs offer single and dual 32x32 bit multipliers, respectively, targeting voice and audio codecs and hubs. The CEVA-TL420 and CEVA-TL421 DSPs offer additional fully cached memory subsystems and AXI system interfaces, targeting application processors and home audio ICs. Due to a variable 10 stage pipeline, the CEVA-TeakLite-4 architecture scales from an area-optimized implementation of less than 100K gates and low power consumption, up to a 1.5GHz implementation at 28nm for high-end system on chips.

Linley Gwennap, principal analyst of The Linley Group stated: "To stay competitive, OEMs must constantly improve the user experience for voice and audio in handset, consumer and automotive applications. From tomorrow's smartphones to Smart TVs and in-car entertainment, every multimedia-enabled device is expected to deliver noise-free voice in any environment along with high-quality audio features. The CEVA-TeakLite-4 addresses all of these diverse applications using a single architecture that is power efficient and yet capable of leading-edge audio and voice processing. For example, the architecture supports between one to four 32-bit and 16-bit MACs with up to 128-bit data memory bandwidth, more than any competing audio solution today, offering customers a wide choice of alternatives for their specific needs."

The CEVA-TeakLite-4 is fully compatible with every previous generation of the CEVA-TeakLite, ensuring that the full portfolio of voice and audio codecs optimized for the CEVA-TeakLite architecture runs on the CEVA-TeakLite-4 with improved efficiency.

The CEVA-TeakLite-4 DSPs are supported by CEVA-toolbox, enables the entire architecture to be programmed in C-level. The memory sub-systems and the entire system are verified by an integrated simulator. The CEVA-Toolbox includes libraries, a graphical debugger, and a complete optimization tool chain named CEVA application optimizer. The application optimizer enables automatic and manual optimization applied in the C source code.

Availability: The first members of the CEVA-TeakLite-4 DSP family will be available for licensing in Q2 and Q3 of 2012.

For more information, visit www.ceva-dsp.com/CEVA-TeakLite-4.html