Input recoding for reducing power in distributed arithmetic

J. Sacha; M. J. Irwin

Input recoding for reducing power in distributed arithmetic

J. Sacha
, M. J. Irwin

Research output: Contribution to conference › Paper › peer-review

Abstract

Distributed arithmetic provides a multiplication-free method for calculating inner products of fixed-point data, based on table lookups of precalculated partial products. A method is proposed for reducing switching activity, and hence power dissipation, in distributed arithmetic systems used for processing signed data. By performing a recoding of the two's complement inputs into a nonredundant signed-digit representation, the table lookups and accompanying accumulations corresponding to the sign extensions in the higher-order bit positions can be reduced.

Original language	English (US)
Pages	599-608
Number of pages	10
State	Published - 1998
Event	Proceedings of the 1998 IEEE Workshop on Signal Processing Systems, SIPS - Cambridge, MA, USA Duration: Oct 8 1998 → Oct 10 1998

Other

Other	Proceedings of the 1998 IEEE Workshop on Signal Processing Systems, SIPS
City	Cambridge, MA, USA
Period	10/8/98 → 10/10/98

All Science Journal Classification (ASJC) codes

Signal Processing
Media Technology

Cite this

@conference{9d68d3fb546f40fb93e50f5f6b7a2314,

title = "Input recoding for reducing power in distributed arithmetic",

abstract = "Distributed arithmetic provides a multiplication-free method for calculating inner products of fixed-point data, based on table lookups of precalculated partial products. A method is proposed for reducing switching activity, and hence power dissipation, in distributed arithmetic systems used for processing signed data. By performing a recoding of the two's complement inputs into a nonredundant signed-digit representation, the table lookups and accompanying accumulations corresponding to the sign extensions in the higher-order bit positions can be reduced.",

author = "J. Sacha and Irwin, \{M. J.\}",

year = "1998",

language = "English (US)",

pages = "599--608",

note = "Proceedings of the 1998 IEEE Workshop on Signal Processing Systems, SIPS ; Conference date: 08-10-1998 Through 10-10-1998",

}

TY - CONF

T1 - Input recoding for reducing power in distributed arithmetic

AU - Sacha, J.

AU - Irwin, M. J.

PY - 1998

Y1 - 1998

N2 - Distributed arithmetic provides a multiplication-free method for calculating inner products of fixed-point data, based on table lookups of precalculated partial products. A method is proposed for reducing switching activity, and hence power dissipation, in distributed arithmetic systems used for processing signed data. By performing a recoding of the two's complement inputs into a nonredundant signed-digit representation, the table lookups and accompanying accumulations corresponding to the sign extensions in the higher-order bit positions can be reduced.

AB - Distributed arithmetic provides a multiplication-free method for calculating inner products of fixed-point data, based on table lookups of precalculated partial products. A method is proposed for reducing switching activity, and hence power dissipation, in distributed arithmetic systems used for processing signed data. By performing a recoding of the two's complement inputs into a nonredundant signed-digit representation, the table lookups and accompanying accumulations corresponding to the sign extensions in the higher-order bit positions can be reduced.

UR - https://www.scopus.com/pages/publications/0031643613

UR - https://www.scopus.com/pages/publications/0031643613#tab=citedBy

M3 - Paper

AN - SCOPUS:0031643613

SP - 599

EP - 608

T2 - Proceedings of the 1998 IEEE Workshop on Signal Processing Systems, SIPS

Y2 - 8 October 1998 through 10 October 1998

ER -

Input recoding for reducing power in distributed arithmetic

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this