View in EDS

Bi-Objective Optimization of Data-Parallel Applications on Homogeneous Multicore Clusters for Performance and Energy.

Saved in:
Bibliographic Details
Title: Bi-Objective Optimization of Data-Parallel Applications on Homogeneous Multicore Clusters for Performance and Energy.
Authors: Manumachu, Ravindranath Reddy1, Lastovetsky, Alexey1
Source: IEEE Transactions on Computers. Feb2018, Vol. 67 Issue 2, p160-177. 18p.
Subjects: Central processing units, Multicore processors, Algorithms, Electric power consumption, Multidisciplinary design optimization, Parallel computers
Abstract: Performance and energy are now the most dominant objectives for optimization on modern parallel platforms composed of multicore CPU nodes. The existing intra-node and inter-node optimization methods employ a large set of decision variables but do not consider problem size as a decision variable and assume a linear relationship between performance and problem size and between energy consumption and problem size. We demonstrate using experiments of real-life data-parallel applications on modern multicore CPUs that these relationships have complex (non-linear and even non-convex) properties and, therefore, that the problem size has become an important decision variable that can no longer be ignored. This key finding motivates our work in this paper. In this paper, we first formulate the bi-objective optimization problem for performance and energy (BOPPE) for data-parallel applications on homogeneous clusters of modern multicore CPUs. It contains only one but heretofore unconsidered decision variable, the problem size. We then present an efficient and exact global optimization algorithm called ALEPH that solves the BOPPE. It takes as inputs, discrete functions of performance and dynamic energy consumption against problem size and outputs the globally Pareto-optimal set of solutions. The solutions are the workload distributions, which achieve inter-node optimization of data-parallel applications for performance and energy. While existing solvers for BOPPE give only one solution when the problem size and number of processors are fixed, our algorithm gives a diverse set of globally Pareto-optimal solutions. The algorithm has time complexity of $O(m^2 \times p^2)$ where $m$ is the number of points in the discrete speed/energy function and $p$ is the number of available processors. We experimentally study the efficiency and scalability of our algorithm for two data parallel applications, matrix multiplication and fast Fourier transform, on a modern multicore CPU and homogeneous clusters of such CPUs. Based on our experiments, we show that the average and maximum sizes of the globally Pareto-optimal sets determined by our algorithm are 15 and 34 and 7 and 20 for the two applications respectively. Comparing with load-balanced workload distribution solution, the average and maximum percentage improvements in performance and energy respectively demonstrated for the first application are (13%,97%) and (18%,71%). For the second application, these improvements are (40%,95%) and (22%,127%). Assuming 5 percent performance degradation from the optimal is acceptable, the average and maximum improvements in energy consumption demonstrated for the two applications respectively are 9 and 44 and 8 and 20 percent. Using the algorithm and its building blocks, we also present a study of interplay between performance and energy. We demonstrate how ALEPH can be combined with DVFS-based Multi-Objective Optimization (MOP) methods to give a better set of (globally Pareto-optimal) solutions. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Computers 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: 127333219
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Bi-Objective Optimization of Data-Parallel Applications on Homogeneous Multicore Clusters for Performance and Energy.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Manumachu%2C+Ravindranath+Reddy%22">Manumachu, Ravindranath Reddy</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Lastovetsky%2C+Alexey%22">Lastovetsky, Alexey</searchLink><relatesTo>1</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Computers%22">IEEE Transactions on Computers</searchLink>. Feb2018, Vol. 67 Issue 2, p160-177. 18p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Central+processing+units%22">Central processing units</searchLink><br /><searchLink fieldCode="DE" term="%22Multicore+processors%22">Multicore processors</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Electric+power+consumption%22">Electric power consumption</searchLink><br /><searchLink fieldCode="DE" term="%22Multidisciplinary+design+optimization%22">Multidisciplinary design optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Parallel+computers%22">Parallel computers</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Performance and energy are now the most dominant objectives for optimization on modern parallel platforms composed of multicore CPU nodes. The existing intra-node and inter-node optimization methods employ a large set of decision variables but do not consider problem size as a decision variable and assume a linear relationship between performance and problem size and between energy consumption and problem size. We demonstrate using experiments of real-life data-parallel applications on modern multicore CPUs that these relationships have complex (non-linear and even non-convex) properties and, therefore, that the problem size has become an important decision variable that can no longer be ignored. This key finding motivates our work in this paper. In this paper, we first formulate the bi-objective optimization problem for performance and energy (BOPPE) for data-parallel applications on homogeneous clusters of modern multicore CPUs. It contains only one but heretofore unconsidered decision variable, the problem size. We then present an efficient and exact global optimization algorithm called ALEPH that solves the BOPPE. It takes as inputs, discrete functions of performance and dynamic energy consumption against problem size and outputs the globally Pareto-optimal set of solutions. The solutions are the workload distributions, which achieve inter-node optimization of data-parallel applications for performance and energy. While existing solvers for BOPPE give only one solution when the problem size and number of processors are fixed, our algorithm gives a diverse set of globally Pareto-optimal solutions. The algorithm has time complexity of $O(m^2 \times p^2)$<alternatives> <inline-graphic xlink:href="manumachu-ieq1-2742513.gif"/></alternatives> where $m$<alternatives><inline-graphic xlink:href="manumachu-ieq2-2742513.gif"/> </alternatives> is the number of points in the discrete speed/energy function and $p$<alternatives><inline-graphic xlink:href="manumachu-ieq3-2742513.gif"/> </alternatives> is the number of available processors. We experimentally study the efficiency and scalability of our algorithm for two data parallel applications, matrix multiplication and fast Fourier transform, on a modern multicore CPU and homogeneous clusters of such CPUs. Based on our experiments, we show that the average and maximum sizes of the globally Pareto-optimal sets determined by our algorithm are 15 and 34 and 7 and 20 for the two applications respectively. Comparing with load-balanced workload distribution solution, the average and maximum percentage improvements in performance and energy respectively demonstrated for the first application are (13%,97%) and (18%,71%). For the second application, these improvements are (40%,95%) and (22%,127%). Assuming 5 percent performance degradation from the optimal is acceptable, the average and maximum improvements in energy consumption demonstrated for the two applications respectively are 9 and 44 and 8 and 20 percent. Using the algorithm and its building blocks, we also present a study of interplay between performance and energy. We demonstrate how ALEPH can be combined with DVFS-based Multi-Objective Optimization (MOP) methods to give a better set of (globally Pareto-optimal) solutions. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Computers 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=127333219
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TC.2017.2742513
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 18
        StartPage: 160
    Subjects:
      – SubjectFull: Central processing units
        Type: general
      – SubjectFull: Multicore processors
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Electric power consumption
        Type: general
      – SubjectFull: Multidisciplinary design optimization
        Type: general
      – SubjectFull: Parallel computers
        Type: general
    Titles:
      – TitleFull: Bi-Objective Optimization of Data-Parallel Applications on Homogeneous Multicore Clusters for Performance and Energy.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Manumachu, Ravindranath Reddy
      – PersonEntity:
          Name:
            NameFull: Lastovetsky, Alexey
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2018
              Type: published
              Y: 2018
          Identifiers:
            – Type: issn-print
              Value: 00189340
          Numbering:
            – Type: volume
              Value: 67
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: IEEE Transactions on Computers
              Type: main
ResultId 1