DocumentCode :
2934524
Title :
A 32-bit GaAs IEEE floating point multiplier using Trailing-1´s rounding algorithm
Author :
Cui, S. ; Burgess, N. ; Liebelt, M. ; Eshraghian, K.
Author_Institution :
Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
fYear :
1995
fDate :
23-25 May 1995
Firstpage :
246
Lastpage :
252
Abstract :
The paper presents a GaAs 32-bit IEEE floating point multiplier. A modified carry save array is used in conjunction with Booth´s algorithm to reduce the partial product addition and interconnection. A special rounding technique called Trailing-1´s Predictor is used to speed up the final addition and rounding. This chip uses a new layout methodology for easy design structure and improved GaAs technology layout density. The combination of the fast arithmetic architecture and compact layout style achieves 4ns multiplication time with 3.5 W power dissipation at 75°C. The area is 2.43 mm by 3.77 mm (excluding pads) and uses 28000 transistors to give a density of 3056 transistors/mm2 for 0.8μm GaAs technology
Keywords :
floating point arithmetic; gallium arsenide; microprocessor chips; multiplying circuits; roundoff errors; societies; 3.5 W; 32 bit; 32 bit GaAs IEEE floating point multiplier; 75 degC; Booth algorithm; GaAs technology; Trailing-1s rounding algorithm; compact layout style; easy design structure; fast arithmetic architecture; improved GaAs technology layout density; layout methodology; modified carry save array; multiplication time; partial product addition; power dissipation; special rounding technique; transistors; Arithmetic; Delay; Design methodology; Gallium arsenide; Integrated circuit interconnections; Paper technology; Signal processing algorithms; Silicon; Tiles; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electronic Technology Directions to the Year 2000, 1995. Proceedings.
Conference_Location :
Adelaide, SA
Print_ISBN :
0-8186-7085-1
Type :
conf
DOI :
10.1109/ETD.1995.403466
Filename :
403466
Link To Document :
بازگشت