An IEEE compliant floating-point adder that conforms with the pipeline packet-forwarding paradigm

作者: A.M. Nielsen , D.W. Matula , C.N. Lyu , G. Even

DOI: 10.1109/12.822562

关键词: Parallel computingIEEE floating pointFloating pointPacket forwardingComputer scienceOperandOperand forwardingMultiplier (economics)AdderBinary numberRounding

摘要: This paper presents a floating-point addition algorithm and adder pipeline design employing packet forwarding paradigm. The format the proposed algorithms constitute new paradigm for handling data hazards in deeply pipelined pipelines. rounding employ four stage execution phase with each suitable implementation short clock period, assuming about 15 logic levels per cycle. first two cycles are related to proper focus of this paper. last perform have been covered by D.W. Matula A.M. Nielsen (1997). accepts one operand standard binary formal at start cycle one. second is represented format: namely, it divided into parts: sign bit, exponent string, principal part significant, carry-round packet. three parts input two. result output formats that both represent rounded as required IEEE 754 standard. end allow an effective latency cycles. also retirement register. thus available or cooperating multiplier accepting operand. successive dependent operations while perceiving compatibility.

参考文章(8)
Michael J. Flynn, Nhon T. Quach, An improved algorithm for high-speed floating-point addition Stanford University. ,(1990)
J. Duprat, Y. Herreros, J.-M. Muller, Some results about on-line computation of functions symposium on computer arithmetic. pp. 112- 118 ,(1989) , 10.1109/ARITH.1989.72816
A. Guyot, Y. Herreros, J.-M. Muller, JANUS, an on-line multiplier/divider for manipulating large numbers symposium on computer arithmetic. pp. 106- 111 ,(1989) , 10.1109/ARITH.1989.72815
Paul Michael Farmwald, On the design of high performance digital arithmetic units Stanford University. ,(1981)
S.F. Oberman, H. Al-Twaijry, M.J. Flynn, The SNAP project: design of floating point arithmetic units symposium on computer arithmetic. pp. 156- 165 ,(1997) , 10.1109/ARITH.1997.614891
A.M. Nielsen, D.W. Matula, C.N. Lyu, G. Even, Pipelined packet-forwarding floating point. II. An adder symposium on computer arithmetic. pp. 148- 155 ,(1997) , 10.1109/ARITH.1997.614890
D.C. Matula, A.M. Nielsen, Pipelined packet-forwarding floating point. I. Foundations and a rounder symposium on computer arithmetic. pp. 140- 147 ,(1997) , 10.1109/ARITH.1997.614889
Ansi Ieee, IEEE Standard for Binary Floating Point Arithmetic Std 754-1985 ed.. ,(1985)