View in EDS PDF Full Text

Soft-error mitigation by means of decoupled transactional memory threads.

Saved in:
Bibliographic Details
Title: Soft-error mitigation by means of decoupled transactional memory threads.
Authors: Sánchez, Daniel1 dsanchez@ditec.um.es, Cebrián, Juan1 jcebrian@ditec.um.es, García, José1 jmgarcia@ditec.um.es, Aragón, Juan1 jlaragon@ditec.um.es
Source: Distributed Computing. Apr2015, Vol. 28 Issue 2, p75-90. 16p.
Subjects: CMOS memory circuits, Fault-tolerant computing, Soft errors, Cache memory, Computer simulation
Abstract: CMOS scaling exacerbates hardware errors making reliability a big concern for recent and future microarchitecture designs. Mechanisms to provide fault tolerance in architectures must accomplish several objectives such as low performance degradation, power consumption and area overhead. Several studies have already proposed fault tolerance for parallel codes. However, these proposals are usually implemented over non-realistic environments including the use of shared-buses among processors or modifying highly optimized hardware designs such as caches. Our attempt to face this multiple challenge is an architectural design called LBRA (Log-Based Redundant Architecture). Based on a Hardware Transactional Memory architecture, LBRA executes redundant threads which communicate through a pair-shared virtual memory log allocated in cache. Our initial version of LBRA executes these redundant threads in SMT cores. To avoid the performance penalty inherent to this architecture, we propose to decouple their execution in different cores, solving the inter-core communication by means of a log buffer empowered by a simple prefetch strategy. Simulation results using a variety of scientific and multimedia applications show that the execution time overhead of our best design is less than 7 % over a base case without fault tolerance. Additionally, we show that LBRA outperforms previous proposals that we have implemented and evaluated in the same framework. [ABSTRACT FROM AUTHOR]
Copyright of Distributed Computing is the property of Springer Nature 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 Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 101792978
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Soft-error mitigation by means of decoupled transactional memory threads.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sánchez%2C+Daniel%22">Sánchez, Daniel</searchLink><relatesTo>1</relatesTo><i> dsanchez@ditec.um.es</i><br /><searchLink fieldCode="AR" term="%22Cebrián%2C+Juan%22">Cebrián, Juan</searchLink><relatesTo>1</relatesTo><i> jcebrian@ditec.um.es</i><br /><searchLink fieldCode="AR" term="%22García%2C+José%22">García, José</searchLink><relatesTo>1</relatesTo><i> jmgarcia@ditec.um.es</i><br /><searchLink fieldCode="AR" term="%22Aragón%2C+Juan%22">Aragón, Juan</searchLink><relatesTo>1</relatesTo><i> jlaragon@ditec.um.es</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Distributed+Computing%22">Distributed Computing</searchLink>. Apr2015, Vol. 28 Issue 2, p75-90. 16p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22CMOS+memory+circuits%22">CMOS memory circuits</searchLink><br /><searchLink fieldCode="DE" term="%22Fault-tolerant+computing%22">Fault-tolerant computing</searchLink><br /><searchLink fieldCode="DE" term="%22Soft+errors%22">Soft errors</searchLink><br /><searchLink fieldCode="DE" term="%22Cache+memory%22">Cache memory</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+simulation%22">Computer simulation</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: CMOS scaling exacerbates hardware errors making reliability a big concern for recent and future microarchitecture designs. Mechanisms to provide fault tolerance in architectures must accomplish several objectives such as low performance degradation, power consumption and area overhead. Several studies have already proposed fault tolerance for parallel codes. However, these proposals are usually implemented over non-realistic environments including the use of shared-buses among processors or modifying highly optimized hardware designs such as caches. Our attempt to face this multiple challenge is an architectural design called LBRA (Log-Based Redundant Architecture). Based on a Hardware Transactional Memory architecture, LBRA executes redundant threads which communicate through a pair-shared virtual memory log allocated in cache. Our initial version of LBRA executes these redundant threads in SMT cores. To avoid the performance penalty inherent to this architecture, we propose to decouple their execution in different cores, solving the inter-core communication by means of a log buffer empowered by a simple prefetch strategy. Simulation results using a variety of scientific and multimedia applications show that the execution time overhead of our best design is less than 7 % over a base case without fault tolerance. Additionally, we show that LBRA outperforms previous proposals that we have implemented and evaluated in the same framework. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Distributed Computing is the property of Springer Nature 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=101792978
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00446-014-0215-6
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 75
    Subjects:
      – SubjectFull: CMOS memory circuits
        Type: general
      – SubjectFull: Fault-tolerant computing
        Type: general
      – SubjectFull: Soft errors
        Type: general
      – SubjectFull: Cache memory
        Type: general
      – SubjectFull: Computer simulation
        Type: general
    Titles:
      – TitleFull: Soft-error mitigation by means of decoupled transactional memory threads.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sánchez, Daniel
      – PersonEntity:
          Name:
            NameFull: Cebrián, Juan
      – PersonEntity:
          Name:
            NameFull: García, José
      – PersonEntity:
          Name:
            NameFull: Aragón, Juan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2015
              Type: published
              Y: 2015
          Identifiers:
            – Type: issn-print
              Value: 01782770
          Numbering:
            – Type: volume
              Value: 28
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Distributed Computing
              Type: main
ResultId 1