Delay-Insensitive Floating Point Multiply-Add-Subtract Unit

Sokolov, I.A.; Rozhdestvenskij, Yu.V.; Diachenko, Yu.G.; Stepchenkov, Yu.A.; Morozov, N.V.; Stepchenkov, D.Yu.; Djachenko, D.Yu.

Home Authors Papers Year of conference Themes Organizations To MES conference

Delay-Insensitive Floating Point Multiply-Add-Subtract Unit

Authors

Sokolov I.A.

Rozhdestvenskij Yu.V.

Date of publication

2018

DOI

10.31114/2078-7707-2018-2-170-177

Abstract

The subject of this paper is a floating point unit implementing fused multiply-add-subtract operation. It belongs to the delay-insensitive self-timed circuits which do not depend on delays both in cells and on wires. It is fully compliant with IEEE 754 Standard and processes both a sum and difference between product of first two operands and third operand. Each 64-bit input operand contains either one double precision number, or two single precision numbers. Thus presented unit calculates either one operation with double precision numbers, or two simultaneous operations with single precision numbers. Multiplier utilizes modified Booth algorithm. In order to increase its performance, it is divided into two pipeline stages with accelerated forced switching to a spacer phase. Booth encoder circuit is integrated into an input FIFO. FIFO is implemented as a register file with an output multiplexer and read and write address counters. Usage a ternary redundant self-timed code for multiplying, adding and subtracting provides a reduction of unit's complexity. Indication subcircuit considers the constrains imposed by an equichronous zone for chosen fabrication technology. For decreasing energy consumption, the fused multiply-add-subtract unit implements one-channel pipeline. The unit is designed for 65-nm CMOS bulk technology using an industrial standard cell library supplemented by self-timed cells. It provides 3 Gflops performance and 2.9-ns latency.

Keywords

redundant coding, ternary adder, Wallace tree, equichronous zone, FIFO.

Library reference

Sokolov I.A., Rozhdestvenskij Yu.V., Diachenko Yu.G., Stepchenkov Yu.A., Morozov N.V., Stepchenkov D.Yu., Djachenko D.Yu. Delay-Insensitive Floating Point Multiply-Add-Subtract Unit // Problems of Perspective Micro- and Nanoelectronic Systems Development - 2018. Issue 2. P. 170-177. doi:10.31114/2078-7707-2018-2-170-177

URL of paper

http://www.mes-conference.ru/data/year2018/pdf/D055.pdf