The Netherlands.
Abstract:
In this paper we investigate small depth linear threshold element networks for multi-operand addition. In particular, we consider depth-2 linear threshold element networks and block save addition. We improve the overall cost in terms of gates and wires of the block save addition with the inclusion of the telescopic sums proposed by Minnick. We show that previously proposed schemes require about twice the number of linear threshold gates for common operand lengths. Furthermore, we show that the number of wires required by an implementation for previously proposed schemes is also about two times higher than the number of wires required for the scheme we describe for commonly architected operand sizes.
Citations
| 97 | Computer Arithmetic: Principles, Architecture, and Design – HWANG - 1979 |
| 66 | Some schemes for parallel multipliers – Dadda - 1965 |
| 57 | Introduction to Arithmetic for Digital Systems Designers – Waser, Flynn - 1982 |
| 35 | Neural computation of arithmetic functions – Siu, Bruck - 1990 |
| 33 | Depth Efficient Neural Networks for Division and Related Problems – Siu, Bruck, et al. - 1993 |
| 26 | High-speed arithmetic in binary computers – MacSorley - 1961 |
| 20 | Linear-Input Logic – Minnick - 1961 |
| 15 | Hard-wired multipliers with encoded partial products – Vassiliadis, Schwarz, et al. - 1991 |
| 13 | Efficient Implementation of a Neural Multiplier – Lauwereins, Bruck - 1991 |
| 6 | Block Save Addition with Telescopic Sums – Vassiliadis, Hoekstra, et al. - 1995 |
| 3 | A General Proof for Multi-bit Scanning Multiplications – Vassiliadis, Schwarz, et al. - 1989 |
| 2 | Block Save Addition with Threshold Gates – Vassiliadis, Cotofana, et al. - 1995 |

