Architecture of a Floating-Point Butterfly Execution Unit in a 400-MFLOPS Processor VLSI and Its Implementation

Hironori YAMAUCHI  Hiroshi MIYANAGA  

Publication
IEICE TRANSACTIONS on Electronics   Vol.E74-C    No.11    pp.3852-3860
Publication Date: 1991/11/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Issue on the High Performance ASIC and Microprocessor)
Category: Dedicated Processors
Keyword: 


Full Text: PDF(658.5KB)>>
Buy this Article



Summary: 
Some dedicated floating-point hardware arithmetic modules designed as processing elements for butterfly operations are described. They consist of Input Data Converters (IDC), Output Data Converters (ODC), and a 2's complementary 24-bit (16E8) floating-point Butterfly Execution Unit (BEU). The BEU executes the four multiplication and six additions/subtractions required for a complex butterfly operation in each 25-ns execution cycle by implementing four multipliers and four 3-input adders/subtracters. The arithmetic modules are fabricated using 0.8-µm CMOS technology. An overview of the hardware unit is presented with special attention given to the BEU for parallel pipelined processing. In addition, module design methodologies for hardware implementation and some sophisticated high-speed execution techniques for floating-point multiplication and addition are discussed.