Configurable architectures for multi-mode floating point adders

Manish Kumar Jaiswal, B Sharat Chandra Varma, Hayden K-H So, M Balakrishnan, Kolin Paul, Ray CC Cheung

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper presents two architectures for floating point (FP) adders, which operates in multi-mode configuration with multi-precision support. First architecture (named QPdDP) works in dual-mode which can operates either for quadruple precision or two-parallel double precision. The second architecture (named QPdDPqSP) works in tri-mode which is able to compute either of a quadruple precision, two-parallel double precision and four-parallel single precision computations. The architectures are based on the standard state-of-the-art flow for FP adder which supports the computation of normal and sub-normal operands, along with the support for the exceptional case handling. The key components in the architecture, such as comparator, swap, dynamic shifters, leading-one-detector (LOD), mantissa adders/subtractors, and rounding circuit, are re-designed and optimized for multi-mode computation, to enable efficient resource sharing for multi-precision operands. The data-path in each multi-mode architecture is tuned for multi-precision support with minimal multiplexing circuitry overhead. These proposed architectures provide multi-precision SIMD support for lower precision operands, along with high precision computational support, and thus, have a better resource utilization. A fully pipelined version of both adder architectures are presented. The proposed adder architectures are synthesized using UMC 90 nm technology ASIC implementation. The proposed architectures are compared with the best available literature works, and have shown better design metrics in terms of area, delay and area×period, along with more computational support.
LanguageEnglish
Pages2079-2090
Number of pages12
JournalIEEE Transactions on Circuits and Systems I: Regular Papers
Volume62
Issue number8
DOIs
Publication statusPublished - Aug 2015

Fingerprint

Adders
Application specific integrated circuits
Multiplexing
Detectors
Networks (circuits)

Cite this

Jaiswal, Manish Kumar ; Varma, B Sharat Chandra ; So, Hayden K-H ; Balakrishnan, M ; Paul, Kolin ; Cheung, Ray CC. / Configurable architectures for multi-mode floating point adders. In: IEEE Transactions on Circuits and Systems I: Regular Papers. 2015 ; Vol. 62, No. 8. pp. 2079-2090.
@article{bd357ef140ec4e2abe093140cea64bd8,
title = "Configurable architectures for multi-mode floating point adders",
abstract = "This paper presents two architectures for floating point (FP) adders, which operates in multi-mode configuration with multi-precision support. First architecture (named QPdDP) works in dual-mode which can operates either for quadruple precision or two-parallel double precision. The second architecture (named QPdDPqSP) works in tri-mode which is able to compute either of a quadruple precision, two-parallel double precision and four-parallel single precision computations. The architectures are based on the standard state-of-the-art flow for FP adder which supports the computation of normal and sub-normal operands, along with the support for the exceptional case handling. The key components in the architecture, such as comparator, swap, dynamic shifters, leading-one-detector (LOD), mantissa adders/subtractors, and rounding circuit, are re-designed and optimized for multi-mode computation, to enable efficient resource sharing for multi-precision operands. The data-path in each multi-mode architecture is tuned for multi-precision support with minimal multiplexing circuitry overhead. These proposed architectures provide multi-precision SIMD support for lower precision operands, along with high precision computational support, and thus, have a better resource utilization. A fully pipelined version of both adder architectures are presented. The proposed adder architectures are synthesized using UMC 90 nm technology ASIC implementation. The proposed architectures are compared with the best available literature works, and have shown better design metrics in terms of area, delay and area×period, along with more computational support.",
author = "Jaiswal, {Manish Kumar} and Varma, {B Sharat Chandra} and So, {Hayden K-H} and M Balakrishnan and Kolin Paul and Cheung, {Ray CC}",
year = "2015",
month = "8",
doi = "10.1109/TCSI.2015.2452351",
language = "English",
volume = "62",
pages = "2079--2090",
journal = "IEEE Transactions on Circuits and Systems I: Regular Papers",
issn = "1549-8328",
number = "8",

}

Configurable architectures for multi-mode floating point adders. / Jaiswal, Manish Kumar; Varma, B Sharat Chandra; So, Hayden K-H; Balakrishnan, M; Paul, Kolin; Cheung, Ray CC.

In: IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 62, No. 8, 08.2015, p. 2079-2090.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Configurable architectures for multi-mode floating point adders

AU - Jaiswal, Manish Kumar

AU - Varma, B Sharat Chandra

AU - So, Hayden K-H

AU - Balakrishnan, M

AU - Paul, Kolin

AU - Cheung, Ray CC

PY - 2015/8

Y1 - 2015/8

N2 - This paper presents two architectures for floating point (FP) adders, which operates in multi-mode configuration with multi-precision support. First architecture (named QPdDP) works in dual-mode which can operates either for quadruple precision or two-parallel double precision. The second architecture (named QPdDPqSP) works in tri-mode which is able to compute either of a quadruple precision, two-parallel double precision and four-parallel single precision computations. The architectures are based on the standard state-of-the-art flow for FP adder which supports the computation of normal and sub-normal operands, along with the support for the exceptional case handling. The key components in the architecture, such as comparator, swap, dynamic shifters, leading-one-detector (LOD), mantissa adders/subtractors, and rounding circuit, are re-designed and optimized for multi-mode computation, to enable efficient resource sharing for multi-precision operands. The data-path in each multi-mode architecture is tuned for multi-precision support with minimal multiplexing circuitry overhead. These proposed architectures provide multi-precision SIMD support for lower precision operands, along with high precision computational support, and thus, have a better resource utilization. A fully pipelined version of both adder architectures are presented. The proposed adder architectures are synthesized using UMC 90 nm technology ASIC implementation. The proposed architectures are compared with the best available literature works, and have shown better design metrics in terms of area, delay and area×period, along with more computational support.

AB - This paper presents two architectures for floating point (FP) adders, which operates in multi-mode configuration with multi-precision support. First architecture (named QPdDP) works in dual-mode which can operates either for quadruple precision or two-parallel double precision. The second architecture (named QPdDPqSP) works in tri-mode which is able to compute either of a quadruple precision, two-parallel double precision and four-parallel single precision computations. The architectures are based on the standard state-of-the-art flow for FP adder which supports the computation of normal and sub-normal operands, along with the support for the exceptional case handling. The key components in the architecture, such as comparator, swap, dynamic shifters, leading-one-detector (LOD), mantissa adders/subtractors, and rounding circuit, are re-designed and optimized for multi-mode computation, to enable efficient resource sharing for multi-precision operands. The data-path in each multi-mode architecture is tuned for multi-precision support with minimal multiplexing circuitry overhead. These proposed architectures provide multi-precision SIMD support for lower precision operands, along with high precision computational support, and thus, have a better resource utilization. A fully pipelined version of both adder architectures are presented. The proposed adder architectures are synthesized using UMC 90 nm technology ASIC implementation. The proposed architectures are compared with the best available literature works, and have shown better design metrics in terms of area, delay and area×period, along with more computational support.

U2 - 10.1109/TCSI.2015.2452351

DO - 10.1109/TCSI.2015.2452351

M3 - Article

VL - 62

SP - 2079

EP - 2090

JO - IEEE Transactions on Circuits and Systems I: Regular Papers

T2 - IEEE Transactions on Circuits and Systems I: Regular Papers

JF - IEEE Transactions on Circuits and Systems I: Regular Papers

SN - 1549-8328

IS - 8

ER -