Title :
Design and implementation of fast floating point multiplier unit
Author :
Sunesh, N.V. ; Sathishkumar, P.
Author_Institution :
Dept. of Electron. & Commun. Eng., Amrita Vishwa Vidhyapeetham, Bengaluru, India
Abstract :
Floating point numbers are the quantities that cannot be represented by integers, either because they contain fractional values or because they lie outside the range re presentable within the system´s bit width. Multiplication of two floating point numbers is very important for processors. Architecture for a fast floating point multiplier yielding with the single precision IEEE 754-2008 standard has been used in this project. The floating point representation can preserve the resolution and accuracy compared to fixed point. Pipeline is a technique where multiple instructions are overlapped in execution. Multiple operations performed at the same time by pipeline will increase the instruction throughput. In several high performance computing systems such as digital signal processors, FIR filters, microprocessors, etc multipliers are key components. The most important aim of the design is to make the multiplier quicker by decreasing delay. Decrease of delay can be caused by propagation of carry in the adders having smallest amount power delay constant.
Keywords :
IEEE standards; adders; floating point arithmetic; logic design; multiplying circuits; FIR filters; IEEE 754-2008 standard; adders; digital signal processors; fast floating point multiplier; floating point multiplier unit; floating point numbers; integers; microprocessors; Adders; CMOS integrated circuits; Computers; Very large scale integration; FPGA; Floating point number; KoggeStone adder; Synopsys Design Compiler; Wallace tree structure; pipeline; radix 4 Booth Encoder;
Conference_Titel :
VLSI Systems, Architecture, Technology and Applications (VLSI-SATA), 2015 International Conference on
Conference_Location :
Bangalore
Print_ISBN :
978-1-4799-7925-7
DOI :
10.1109/VLSI-SATA.2015.7050478