View in EDS

Mapping-Aware Kernel Partitioning Method for CGRAs Assisted by Deep Learning.

Saved in:
Bibliographic Details
Title: Mapping-Aware Kernel Partitioning Method for CGRAs Assisted by Deep Learning.
Authors: Kojima, Takuya1 tkojima@am.ics.keio.ac.jp, Ohwada, Ayaka1 ohwawa@am.ics.keio.ac.jp, Amano, Hideharu1 hunga@am.ics.keio.ac.jp
Source: IEEE Transactions on Parallel & Distributed Systems. May2022, Vol. 33 Issue 5, p1213-1230. 18p.
Subjects: Deep learning, Convolutional neural networks, Genetic algorithms, Energy consumption
Abstract: Coarse-grained reconfigurable architectures (CGRAs) provide high energy efficiency with word-level programmability rather than bit-level ones such as FPGAs. The coarser reconfigurability brings about higher energy efficiency and reduces the complexity of compiler tasks compared to the FPGAs. However, application mapping process for CGRAs is still time-consuming. When the compiler tries to map a large and complicated application data-flow-graph(DFG) onto the reconfigurable fabric, it tends to result in inefficient resource use or to fail in mapping. In case of failure, the compiler must divide it into several sub-DFGs and goes back to the same flow. In this work, we propose a novel partitioning method based on a genetic algorithm to eliminate the unmappable DFGs and improve the mapping quality. In order not to generate unmappable sub-DFGs, we also propose an estimation model which predicts the mappability and resource requirements using a DGCNN (Deep Graph Convolutional Neural Network). The genetic algorithm with this model can seek the most resource-efficient mapping without the back-end mapping process. Our model can predict the mappability with more than 98% accuracy and resource usage with a negligible error for two studied CGRAs. Besides, the proposed partitioning method demonstrates 53-75% of memory saving, 1.28-1.39x higher throughput, and better mapping quality over three comparative approaches. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Parallel & Distributed Systems is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 153880638
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Mapping-Aware Kernel Partitioning Method for CGRAs Assisted by Deep Learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kojima%2C+Takuya%22">Kojima, Takuya</searchLink><relatesTo>1</relatesTo><i> tkojima@am.ics.keio.ac.jp</i><br /><searchLink fieldCode="AR" term="%22Ohwada%2C+Ayaka%22">Ohwada, Ayaka</searchLink><relatesTo>1</relatesTo><i> ohwawa@am.ics.keio.ac.jp</i><br /><searchLink fieldCode="AR" term="%22Amano%2C+Hideharu%22">Amano, Hideharu</searchLink><relatesTo>1</relatesTo><i> hunga@am.ics.keio.ac.jp</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Parallel+%26+Distributed+Systems%22">IEEE Transactions on Parallel & Distributed Systems</searchLink>. May2022, Vol. 33 Issue 5, p1213-1230. 18p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Genetic+algorithms%22">Genetic algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Energy+consumption%22">Energy consumption</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Coarse-grained reconfigurable architectures (CGRAs) provide high energy efficiency with word-level programmability rather than bit-level ones such as FPGAs. The coarser reconfigurability brings about higher energy efficiency and reduces the complexity of compiler tasks compared to the FPGAs. However, application mapping process for CGRAs is still time-consuming. When the compiler tries to map a large and complicated application data-flow-graph(DFG) onto the reconfigurable fabric, it tends to result in inefficient resource use or to fail in mapping. In case of failure, the compiler must divide it into several sub-DFGs and goes back to the same flow. In this work, we propose a novel partitioning method based on a genetic algorithm to eliminate the unmappable DFGs and improve the mapping quality. In order not to generate unmappable sub-DFGs, we also propose an estimation model which predicts the mappability and resource requirements using a DGCNN (Deep Graph Convolutional Neural Network). The genetic algorithm with this model can seek the most resource-efficient mapping without the back-end mapping process. Our model can predict the mappability with more than 98% accuracy and resource usage with a negligible error for two studied CGRAs. Besides, the proposed partitioning method demonstrates 53-75% of memory saving, 1.28-1.39x higher throughput, and better mapping quality over three comparative approaches. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Parallel & Distributed Systems is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=153880638
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TPDS.2021.3107746
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 18
        StartPage: 1213
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Genetic algorithms
        Type: general
      – SubjectFull: Energy consumption
        Type: general
    Titles:
      – TitleFull: Mapping-Aware Kernel Partitioning Method for CGRAs Assisted by Deep Learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kojima, Takuya
      – PersonEntity:
          Name:
            NameFull: Ohwada, Ayaka
      – PersonEntity:
          Name:
            NameFull: Amano, Hideharu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 10459219
          Numbering:
            – Type: volume
              Value: 33
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: IEEE Transactions on Parallel & Distributed Systems
              Type: main
ResultId 1