DocumentCode :
3246254
Title :
Architecture of the NS32580 floating-point controller
Author :
Ben-Chorin, S.
Author_Institution :
Nat. Semicond. Corp., Santa Clara, CA, USA
fYear :
1988
fDate :
Feb. 29 1988-March 3 1988
Firstpage :
213
Lastpage :
217
Abstract :
The author describes the NS32580 floating-point controller, which, together with its companion device, Weitek´s WTL 3164 floating-point data path, provides a high-performance floating point solution for high-end NS32532 based systems. The NS32580-WTL3164 with the NS32532 CPU executes single- and double-precision ADD, SUB, MUL, MACf with a peak throughput of 15 MFLOPS, keeping precise exception-handling. Using an improved slave protocol, the NS32580 interfaces between the NS32532 microprocessor and the WTL 3164 floating-point data path to form a software upwardly compatible floating-point unit.<>
Keywords :
digital arithmetic; microprocessor chips; 15 MFLOPS; ADD; MACf; MUL; NS32532 CPU; NS32532 microprocessor; NS32580 floating-point controller; NS32580 interfaces; SUB; WTL 3164 floating-point data path; exception-handling; peak throughput; slave protocol; Access protocols; Arithmetic; Computer architecture; Control systems; Decoding; Detectors; Flexible printed circuits; Frequency; Pipeline processing; Throughput;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Compcon Spring '88. Thirty-Third IEEE Computer Society International Conference, Digest of Papers
Conference_Location :
San Francisco, CA, USA
Print_ISBN :
0-8186-0828-5
Type :
conf
DOI :
10.1109/CMPCON.1988.4861
Filename :
4861
Link To Document :
بازگشت