Telecomm DSP Can Process 8/16/32-Bit & Floating-Point Data

March 1, 2000
The firm's TigerSHARC architecture has been tapped to create the first of a new breed of digital signal processors (DSPs) capable of processing on-chip 8-, 16- and 32-bit and floating-point data at high speeds. Each data category is said to be

The firm's TigerSHARC architecture has been tapped to create the first of a new breed of digital signal processors (DSPs) capable of processing on-chip 8-, 16- and 32-bit and floating-point data at high speeds. Each data category is said to be critical to next generation telecomm protocols currently under development, including IMT-2000 (i.e., 3G wireless) and xDSL. For example, 8-bit data processing is well-suited for handling Viterbi channel decoder algorithms, as well as image processing; 16-bit data types are of importance to telecomm infrastructure and voice and channel coders; and 32-bit and floating-point data processing are useful in attacking signal quality problems.
In addition to fixed- and floating-point cores, the new ADSP-TS001 TigerSHARC DSP integrates on-chip 6 Mb of SRAM, four bi-directional link ports, a 64-bit external port, 14 DMA channels, and 128 registers. And it offers high-bandwidth internal memory access, with the equivalent of more than 900,000 simultaneous phone calls moved in just one second. The DSP comes in 360-pin SBGAs, costs $150 each/10K, and is sampling now, with production scheduled for the second half of 2000.

Company: ANALOG DEVICES INC.

Product URL: Click here for more information

About the Author

Staff

Articles, galleries, and recent work by members of Electronic Design's editorial staff.

Sponsored Recommendations

Comments

To join the conversation, and become an exclusive member of Electronic Design, create an account today!