A high performance floating point coprocessor
- 1 October 1984
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 19 (5) , 690-696
- https://doi.org/10.1109/jssc.1984.1052209
Abstract
A 34000-transistor single-chip floating-point coprocessor fabricated in 3-/spl mu/m double metal NMOS technology is described. The fraction data path, including a shifter and 60-bit carry propagate ALU, is cycled in 100 ns for all operations requiring less than 19 bits of consecutive carry. A versatile carry length detection scheme, which requires minimal additional logic, is used to extend the microcycle for the small percentage of operations in which a long carry exists. Three-bit-per-cycle multiplication and one-and-one-half-bit-per-cycle division algorithms were used to achieve excellent overall performance.Keywords
This publication has 3 references indexed in Scilit:
- ComputerComputer, 1980
- An analysis of floating-point additionIBM Systems Journal, 1965
- High-Speed Arithmetic in Binary ComputersProceedings of the IRE, 1961