G-MAC: an application-specific MAC/co-processor synthesizer

A modern special-purpose processor (e.g., for image and graphical applications) usually contains a set of instructions supporting complex multiply-operations. These instructions perform a variety of multiply-operations with various data bit-widths and concurrent-execution requirements. For instance,...

Full description

Saved in:
Bibliographic Details
Published in2003 Design, Automation and Test in Europe Conference and Exhibition pp. 1134 - 1135
Main Authors Chang, A.C.-Y., Wu-An Kuo, Wu, A.C.-H., Ting Ting Hwang
Format Conference Proceeding
LanguageEnglish
Published IEEE 2003
Subjects
Online AccessGet full text
ISBN0769518702
9780769518701
ISSN1530-1591
DOI10.1109/DATE.2003.1253769

Cover

Abstract A modern special-purpose processor (e.g., for image and graphical applications) usually contains a set of instructions supporting complex multiply-operations. These instructions perform a variety of multiply-operations with various data bit-widths and concurrent-execution requirements. For instance, such an instruction set may include instructions to perform signed/unsigned 32/spl times/32, signed/unsigned dual 16/spl times/16, signed/unsigned 8/spl times/8 MAC, and etc. Typically, a co-processor or a complex MAC (Multiplier-ACcumulator) unit is required to execute those instructions. Developing such a complex MAC/co-processor involves a series of design tasks including micro-architecture design, component allocation/binding, interconnect binding, pipeline insertion and control generation. This design process is non-trivial, time-consuming and error-prone, which is usually performed by experienced design engineers. In this paper, we present a synthesis method for application-specific MAC/coprocessor generation. The MAC/co-processor synthesis problem is defined as: Given a set of instructions and the number of execution cycles for each instruction, generate a MAC/co-processor design (including a data-path and a control unit) such that the total area-cost is minimized subject to the given execution-cycle constraints. The MAC/co-processor generation consists of the following two steps. In the first step, we determine a set of minimum-cost components required to realize the given instruction set. In the second step, we perform micro-architectural-level synthesis tasks, including component mapping, interconnect synthesis, pipeline insertion, and control synthesis to generate the MAC/co- processor design.
AbstractList A modern special-purpose processor (e.g., for image and graphical applications) usually contains a set of instructions supporting complex multiply-operations. These instructions perform a variety of multiply-operations with various data bit-widths and concurrent-execution requirements. For instance, such an instruction set may include instructions to perform signed/unsigned 32/spl times/32, signed/unsigned dual 16/spl times/16, signed/unsigned 8/spl times/8 MAC, and etc. Typically, a co-processor or a complex MAC (Multiplier-ACcumulator) unit is required to execute those instructions. Developing such a complex MAC/co-processor involves a series of design tasks including micro-architecture design, component allocation/binding, interconnect binding, pipeline insertion and control generation. This design process is non-trivial, time-consuming and error-prone, which is usually performed by experienced design engineers. In this paper, we present a synthesis method for application-specific MAC/coprocessor generation. The MAC/co-processor synthesis problem is defined as: Given a set of instructions and the number of execution cycles for each instruction, generate a MAC/co-processor design (including a data-path and a control unit) such that the total area-cost is minimized subject to the given execution-cycle constraints. The MAC/co-processor generation consists of the following two steps. In the first step, we determine a set of minimum-cost components required to realize the given instruction set. In the second step, we perform micro-architectural-level synthesis tasks, including component mapping, interconnect synthesis, pipeline insertion, and control synthesis to generate the MAC/co- processor design.
Author Chang, A.C.-Y.
Ting Ting Hwang
Wu, A.C.-H.
Wu-An Kuo
Author_xml – sequence: 1
  givenname: A.C.-Y.
  surname: Chang
  fullname: Chang, A.C.-Y.
  organization: Comput. Sci. Dept., Tsing Hua Univ., Hsin-Chu, Taiwan
– sequence: 2
  surname: Wu-An Kuo
  fullname: Wu-An Kuo
  organization: Comput. Sci. Dept., Tsing Hua Univ., Hsin-Chu, Taiwan
– sequence: 3
  givenname: A.C.-H.
  surname: Wu
  fullname: Wu, A.C.-H.
  organization: Comput. Sci. Dept., Tsing Hua Univ., Hsin-Chu, Taiwan
– sequence: 4
  surname: Ting Ting Hwang
  fullname: Ting Ting Hwang
  organization: Comput. Sci. Dept., Tsing Hua Univ., Hsin-Chu, Taiwan
BookMark eNotj8tqwzAURAVNoXl9QOnGPyBH17Jsq10ZN00LKdl4H6SrK6qS2sbyJv36GprZnMVwBmbFFl3fEWOPIFIAoXevdbtPMyFkCpmSZaHv2ErMUFCVIluwJSgpOCgND2wb47eYI3UOhVyylwP_rJvnxHSJGYZLQDOFvuNxIAw-YDKXO-z5MPZIMfZjEq_d9EUx_NK4YffeXCJtb1yz9m3fNu_8eDp8NPWRBy0mLiuwHpTx6LyxJVntqHJFrshigd6j9baQaI3D3ErhFOYloZ0d8DbLnFyzp__ZQETnYQw_Zryeb1flH8oDS0c
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/DATE.2003.1253769
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EndPage 1135
ExternalDocumentID 1253769
GroupedDBID 123
29F
29O
6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
FEDTE
IEGSK
IPLJI
KZ1
LMP
M43
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i90t-381bf15afcdfab7eb9de8d645ebc6cffcbfb63cbadc4b30d5c47ecbbf11fb22d3
IEDL.DBID RIE
ISBN 0769518702
9780769518701
ISSN 1530-1591
IngestDate Tue Aug 26 16:52:03 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-381bf15afcdfab7eb9de8d645ebc6cffcbfb63cbadc4b30d5c47ecbbf11fb22d3
PageCount 2
ParticipantIDs ieee_primary_1253769
PublicationCentury 2000
PublicationDate 20030000
PublicationDateYYYYMMDD 2003-01-01
PublicationDate_xml – year: 2003
  text: 20030000
PublicationDecade 2000
PublicationTitle 2003 Design, Automation and Test in Europe Conference and Exhibition
PublicationTitleAbbrev DATE
PublicationYear 2003
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000394163
ssj0005329
Score 1.5093383
Snippet A modern special-purpose processor (e.g., for image and graphical applications) usually contains a set of instructions supporting complex multiply-operations....
SourceID ieee
SourceType Publisher
StartPage 1134
SubjectTerms Coprocessors
Costs
Design engineering
Partitioning algorithms
Pipelines
Process design
Resource management
Sorting
Synthesizers
Title G-MAC: an application-specific MAC/co-processor synthesizer
URI https://ieeexplore.ieee.org/document/1253769
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8JAEJ4AJ72ggPGdHjy60O1j29UTQZCYYDxgwo3s7CMhJoXwOMivd7stoMaDt22bpt3tTmY6833fANzl-iyxiBVJU2NIJJERwe1ICJpo6ScidPTo0Ssbvkcvk3hSgfs9F0Zr7cBnup0PXS1fzeUmT5V1rDO29sCrUE1SVnC19vkUP-R5bHGAd4SuQ5k1aJ9Yl02LX3YbT9gNGpTKO7tjWpY7qc87T91x38mEtsun_Wi74rzOoA6j3fsWYJOP9maNbbn9JeX43wmdQOvA7_Pe9p7rFCo6a0B91-DBK-29Acff1Aqb8PhMRt3egycy71vZm-RczRxv5NmLHTkni4J6MF96q8_Mhper2VYvWzAe9Me9ISl7L5AZ99fE-nE0NBZGKiMw0ciVThWLYo2SSWMkGmShRKFkhKGvYhnZT4v2HmowCFR4BrVsnulz8LjgiiXKGKZURClHHaVUBDqIFSIT8gKa-cJMF4W6xrRck8u_T1_BkYPTuSTINdTWy42-sWHBGm_dfvgCN8SyiQ
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8JAEJ4gHtQLChjf9uDRhW67W1g9EQRRgXjAhBvZZ0JMCuFxkF_vdlseGg_etm2adrc7menM930DcJfos1BOFarXjUFEighxZkec45qWfo2Hjh7d60edD_I6pMMc3G-4MFprBz7TlWToavlqIpdJqqxqnbG1B7YH-5QQQlO21iaj4ocsiS62AI_Q9SizJu0j67Rx-tNuIwq7RYNMe2d9jLOCJ_ZZ9akxaDmh0Er2vB-NV5zfaRegt37jFG7yWVkuREWufok5_ndKx1DeMvy8943vOoGcjotQWLd48DKLL8LRjl5hCR6fUa_RfPB47O0UvlHC1kwQR569WJUTNE3JB5OZN_-KbYA5H6_0rAyDdmvQ7KCs-wIaM3-BrCcXBlNupDJc1LRgStdVRKgWMpLGSGFEFErBlSQi9BWVxH5cYe_BRgSBCk8hH09ifQYe40xFNWVMpBTBmAlN6pgHOqBKiIjLcyglCzOapvoao2xNLv4-fQsHnUGvO-q-9N8u4dCB61xK5Aryi9lSX9sgYSFu3N74BsW0tdY
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2003+Design%2C+Automation+and+Test+in+Europe+Conference+and+Exhibition&rft.atitle=G-MAC%3A+an+application-specific+MAC%2Fco-processor+synthesizer&rft.au=Chang%2C+A.C.-Y.&rft.au=Wu-An+Kuo&rft.au=Wu%2C+A.C.-H.&rft.au=Ting+Ting+Hwang&rft.date=2003-01-01&rft.pub=IEEE&rft.isbn=9780769518701&rft.issn=1530-1591&rft.spage=1134&rft.epage=1135&rft_id=info:doi/10.1109%2FDATE.2003.1253769&rft.externalDocID=1253769
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-1591&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-1591&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-1591&client=summon