TY - GEN
T1 - Combined integer and floating point multiplication architecture(CIFM) for FPGAs and its reversible logic implementation
AU - Thapliyal, Himanshu
AU - Arabnia, Hamid R.
AU - Vinod, A. P.
PY - 2006
Y1 - 2006
N2 - In this paper, the authors propose the idea of a combined integer and floating point multiplier(CIFM) for FPGAs. The authors propose the replacement of existing 18×18 dedicated multipliers in FPGAs with dedicated 24×24 multipliers designed with small 4×4 bit multipliers. It is also proposed that for every dedicated 24×24 bit multiplier block designed with 4×4 bit multipliers, four redundant 4×4 multiplier should be provided to enforce the feature of self repairability (to recover from the faults). In the proposed CIFM reconfigurability at run time is also provided resulting in low power. The major source of motivation for providing the dedicated 24×24 bit multiplier stems from the fact that single precision floating point multiplier requires 24×24 bit integer multiplier for mantissa multiplication. A reconfigurable, self-repairable 24×24 bit multiplier (implemented with 4×4 bit multiply modules) will ideally suit this purpose, making FPGAs more suitable for integer as well floating point operations. A dedicated 4×4 bit multiplier is also proposed in this paper. Moreover, in the recent years, reversible logic has emerged as a promising technology having its applications in low power CMOS, quantum computing, nanotechnology, and optical computing. It is not possible to realize quantum computing without reversible logic. Thus, this paper also paper provides the reversible logic implementation of the proposed CIFM. The reversible CIFM designed and proposed here will form the basis of the completely reversible FPGAs.
AB - In this paper, the authors propose the idea of a combined integer and floating point multiplier(CIFM) for FPGAs. The authors propose the replacement of existing 18×18 dedicated multipliers in FPGAs with dedicated 24×24 multipliers designed with small 4×4 bit multipliers. It is also proposed that for every dedicated 24×24 bit multiplier block designed with 4×4 bit multipliers, four redundant 4×4 multiplier should be provided to enforce the feature of self repairability (to recover from the faults). In the proposed CIFM reconfigurability at run time is also provided resulting in low power. The major source of motivation for providing the dedicated 24×24 bit multiplier stems from the fact that single precision floating point multiplier requires 24×24 bit integer multiplier for mantissa multiplication. A reconfigurable, self-repairable 24×24 bit multiplier (implemented with 4×4 bit multiply modules) will ideally suit this purpose, making FPGAs more suitable for integer as well floating point operations. A dedicated 4×4 bit multiplier is also proposed in this paper. Moreover, in the recent years, reversible logic has emerged as a promising technology having its applications in low power CMOS, quantum computing, nanotechnology, and optical computing. It is not possible to realize quantum computing without reversible logic. Thus, this paper also paper provides the reversible logic implementation of the proposed CIFM. The reversible CIFM designed and proposed here will form the basis of the completely reversible FPGAs.
UR - http://www.scopus.com/inward/record.url?scp=34748919736&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34748919736&partnerID=8YFLogxK
U2 - 10.1109/MWSCAS.2006.382306
DO - 10.1109/MWSCAS.2006.382306
M3 - Conference contribution
AN - SCOPUS:34748919736
SN - 1424401739
SN - 9781424401734
T3 - Midwest Symposium on Circuits and Systems
SP - 438
EP - 442
BT - Proceedings of the 2006 49th Midwest Symposium on Circuits and Systems, MWSCAS'06
T2 - 2006 49th Midwest Symposium on Circuits and Systems, MWSCAS'06
Y2 - 6 August 2006 through 9 August 2007
ER -