Programmable DSP architectures. I
- 1 October 1988
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE ASSP Magazine
- Vol. 5 (4) , 4-19
- https://doi.org/10.1109/53.16926
Abstract
The architectural features of single-chip programmable digital signal processors (DSPs) are explored. The focus is on the most basic such feature, the integration of a hardware multiplier/accumulator into the data path, and a more subtle feature, the use of several (up to six) independent memory banks. These features are studied in terms of the performance benefit and the impact on the user. Representative DSPs from three manufacturers AT&T Motorola, and Texas Instruments are used to illustrate the ideas to compare different solutions to the same problems.Keywords
This publication has 12 references indexed in Scilit:
- A 32b floating point CMOS digital signal processorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A floating point DSP with optimizing C compilerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A VLSI signal processor with complex arithmetic capabilityIEEE Transactions on Circuits and Systems, 1988
- A 50ns DSP with parallel processing architecturePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- The Motorola DSP56000 Digital Signal ProcessorIEEE Micro, 1986
- Computer architecture for digital signal processingProceedings of the IEEE, 1985
- An NMOS digital signal processor with multiprocessing capabilityPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985
- A microcomputer with digital signal processing capabilityPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1982
- Digital Signal Processor: Architecture and PerformanceBell System Technical Journal, 1981
- A single-chip digital signal processor for telecommunication applicationsIEEE Journal of Solid-State Circuits, 1981