Floating point unit generation and evaluation for FPGAs
- 31 October 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Most commercial and academic floating point librariesfor FPGAs provide only a small fraction of all possiblefloating point units. In contrast, the floating point unit generationapproach outlined in this paper allows for the creationof a vast collection of floating point units with differingthroughput, latency, and area characteristics. Givenperformance requirements, our generation tool automaticallychooses the proper implementation algorithm and architectureto create a compliant floating point unit. Ourapproach is fully integrated into standard C++ using ASC,a stream compiler for FPGAs, and the PAM-Blox II modulegeneration environment. The floating point units created byour approach exhibit a factor of two latency improvementversus commercial FPGA floating point units, while consumingonly half of the FPGA logic area.Keywords
This publication has 15 references indexed in Scilit:
- PAM-Blox II: design and evaluation of C++ module generation for computing with FPGAsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Using floating-point arithmetic on FPGAs to accelerate scientific N-Body simulationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- PAM-Blox: high performance FPGA design for adaptive computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A re-evaluation of the practicality of floating-point operations on FPGAsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The SNAP project: design of floating point arithmetic unitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Object-oriented domain specific compilers for programming FPGAsIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2001
- Leading-one prediction with concurrent position correctionIEEE Transactions on Computers, 1999
- Implementation of IEEE single precision floating point addition and multiplication on FPGAsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Field programmable gate arrays and floating point arithmeticIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 1994
- An algorithmic and novel design of a leading zero detector circuit: comparison with logic synthesisIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 1994