SlideShare a Scribd company logo
STRATEGIES FOR ENERGY-EFFICIENT RESOURCE MANAGEMENT OF
HYBRID PROGRAMMING MODELS
ABSTRACT:
Many scientific applications are programmed using hybrid programming models that use both
message passing and shared memory, due to the increasing prevalence of large-scale systems
with multicore, multisocket nodes. Previous work has shown that energy efficiency can be
improved using software-controlled execution schemes that consider both the programming
model and the power-aware execution capabilities of the system. However, such approaches
have focused on identifying optimal resource utilization for one programming model, either
shared memory or message passing, in isolation. The potential solution space, thus the challenge,
increases substantially when optimizing hybrid models since the possible resource configurations
increase exponentially. Nonetheless, with the accelerating adoption of hybrid programming
models, we increasingly need improved energy efficiency in hybrid parallel applications on
large-scale systems.
In this work, we present new software-controlled execution schemes that consider the effects of
dynamic concurrency throttling (DCT) and dynamic voltage and frequency scaling (DVFS) in
the context of hybrid programming models. Specifically, we present predictive models and novel
algorithms based on statistical analysis that anticipate application power and time requirements
under different concurrency and frequency configurations. We apply our models and methods to
the NPB MZ benchmarks and selected applications from the ASC Sequoia codes. Overall, we
achieve substantial energy savings (8.74 percent on average and up to 13.8 percent) with some
performance gain (up to 7.5 percent) or negligible performance loss.
ECWAY TECHNOLOGIES
IEEE PROJECTS & SOFTWARE DEVELOPMENTS
OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE
CELL: +91 98949 17187, +91 875487 2111 / 3111 / 4111 / 5111 / 6111
VISIT: www.ecwayprojects.com MAIL TO: ecwaytechnologies@gmail.com

More Related Content

DOCX
Multi objective game theoretic scheduling of bag-of-tasks workflows on hybri...
PDF
Predictive control for energy aware consolidation in cloud datacenters
DOCX
ENERGY EFFICIENT VIRTUAL NETWORK EMBEDDING FOR CLOUD NETWORKS
PDF
Energy efficient virtual network embedding for cloud networks
DOCX
Cooperative load balancing and dynamic channel allocation for cluster based m...
DOCX
New analytic model of coupling and substrate capacitance in nanometer technol...
DOCX
Design of Power and Area Efficient Approximate Multipliers
PDF
A hierarchical correlation model for evaluating reliability, performance, and...
Multi objective game theoretic scheduling of bag-of-tasks workflows on hybri...
Predictive control for energy aware consolidation in cloud datacenters
ENERGY EFFICIENT VIRTUAL NETWORK EMBEDDING FOR CLOUD NETWORKS
Energy efficient virtual network embedding for cloud networks
Cooperative load balancing and dynamic channel allocation for cluster based m...
New analytic model of coupling and substrate capacitance in nanometer technol...
Design of Power and Area Efficient Approximate Multipliers
A hierarchical correlation model for evaluating reliability, performance, and...

What's hot (18)

PDF
Cross layer design of congestion control and power control in fast-fading wir...
PDF
Evolutionary multi objective workflow scheduling in cloud
PDF
Exploiting Availability Prediction in Distributed Systems
PDF
Elastic resource utilization framework for high capacity and energy efficienc...
PPTX
排隊理論_An Exploration of The Optimization of Executive Scheduling in The Cloud ...
DOCX
Improving resource utilisation in the cloud environment using multivariate pr...
PDF
Data Veracity Proofs in Cloud Storage Space
DOCX
An experimental analysis on cloud based mobile augmentation in mobile cloud c...
PDF
Ensemble a tool for performance modeling of applications in cloud data centers
PDF
Design and Optimization of Supply Chain Network with Nonlinear Log-Space Mode...
PDF
Demand forecast of PV integrated bioclimatic buildings using ensemble framework
PDF
Secure power grid simulation on cloud
PDF
poster
DOCX
IEEE 2014 DOTNET CLOUD COMPUTING PROJECTS Scalable analytics for iaa s cloud ...
PPTX
Latest Research in MATLAB Projects
PDF
Dotnet distributed processing of probabilistic top-k queries in wireless sen...
Cross layer design of congestion control and power control in fast-fading wir...
Evolutionary multi objective workflow scheduling in cloud
Exploiting Availability Prediction in Distributed Systems
Elastic resource utilization framework for high capacity and energy efficienc...
排隊理論_An Exploration of The Optimization of Executive Scheduling in The Cloud ...
Improving resource utilisation in the cloud environment using multivariate pr...
Data Veracity Proofs in Cloud Storage Space
An experimental analysis on cloud based mobile augmentation in mobile cloud c...
Ensemble a tool for performance modeling of applications in cloud data centers
Design and Optimization of Supply Chain Network with Nonlinear Log-Space Mode...
Demand forecast of PV integrated bioclimatic buildings using ensemble framework
Secure power grid simulation on cloud
poster
IEEE 2014 DOTNET CLOUD COMPUTING PROJECTS Scalable analytics for iaa s cloud ...
Latest Research in MATLAB Projects
Dotnet distributed processing of probabilistic top-k queries in wireless sen...
Ad

Viewers also liked (14)

PDF
Stb pr kanali
PPTX
Riverbed: Conundrum Campaign
PDF
Stb 55015
PDF
Stb 55011
PDF
Stb 48227
PDF
Stb 55022
PDF
Stb 61000 3-2
PDF
CCNA Exploration Network Fundamentals
PPTX
Adelyndiaz♥
PPTX
Presentación 2
PPTX
Terminos bassico estadistica
PDF
About Doc Sitter
PDF
Concurso de canto0001
PPTX
Будущее, которое наступило. Каким быть образованию в XXI веке?
Stb pr kanali
Riverbed: Conundrum Campaign
Stb 55015
Stb 55011
Stb 48227
Stb 55022
Stb 61000 3-2
CCNA Exploration Network Fundamentals
Adelyndiaz♥
Presentación 2
Terminos bassico estadistica
About Doc Sitter
Concurso de canto0001
Будущее, которое наступило. Каким быть образованию в XXI веке?
Ad

Similar to Strategies for energy efficient resource management of hybrid programming models (20)

PDF
Strategies for energy efficient resource management of hybrid programming models
PDF
Dotnet strategies for energy-efficient resource management of hybrid program...
DOCX
Ieee transactions 2018 on wireless communications Title and Abstract
PDF
A MULTI-OBJECTIVE PERSPECTIVE FOR OPERATOR SCHEDULING USING FINEGRAINED DVS A...
PDF
Energy-aware Load Balancing and Application Scaling for the Cloud Ecosystem
PDF
IEEE Emerging topic in computing Title and Abstract 2016
PDF
International Journal of Engineering Research and Development (IJERD)
PDF
Energy aware load balancing and application scaling for the cloud ecosystem
DOCX
ENERGY-AWARE LOAD BALANCING AND APPLICATION SCALING FOR THE CLOUD ECOSYSTEM
DOCX
ENERGY-AWARE LOAD BALANCING AND APPLICATION SCALING FOR THE CLOUD ECOSYSTEM
DOCX
Cost aware cooperative resource provisioning
PDF
ENERGY-AWARE LOAD BALANCING AND APPLICATION SCALING FOR THE CLOUD ECOSYSTEM
PDF
Latest Research Topics on Cloud Computing
PDF
[IJET V2I5P18] Authors:Pooja Mangla, Dr. Sandip Kumar Goyal
PDF
IEEE Cloud computing 2016 Title and Abstract
PDF
An Approach to Reduce Energy Consumption in Cloud data centers using Harmony ...
PDF
An Approach to Reduce Energy Consumption in Cloud data centers using Harmony ...
DOCX
Ieee transactions 2018 topics on wireless communications for final year stude...
PDF
ACSD2016paper20_04013
DOCX
JAVA 2013 IEEE NETWORKING PROJECT Harvesting aware energy management for time...
Strategies for energy efficient resource management of hybrid programming models
Dotnet strategies for energy-efficient resource management of hybrid program...
Ieee transactions 2018 on wireless communications Title and Abstract
A MULTI-OBJECTIVE PERSPECTIVE FOR OPERATOR SCHEDULING USING FINEGRAINED DVS A...
Energy-aware Load Balancing and Application Scaling for the Cloud Ecosystem
IEEE Emerging topic in computing Title and Abstract 2016
International Journal of Engineering Research and Development (IJERD)
Energy aware load balancing and application scaling for the cloud ecosystem
ENERGY-AWARE LOAD BALANCING AND APPLICATION SCALING FOR THE CLOUD ECOSYSTEM
ENERGY-AWARE LOAD BALANCING AND APPLICATION SCALING FOR THE CLOUD ECOSYSTEM
Cost aware cooperative resource provisioning
ENERGY-AWARE LOAD BALANCING AND APPLICATION SCALING FOR THE CLOUD ECOSYSTEM
Latest Research Topics on Cloud Computing
[IJET V2I5P18] Authors:Pooja Mangla, Dr. Sandip Kumar Goyal
IEEE Cloud computing 2016 Title and Abstract
An Approach to Reduce Energy Consumption in Cloud data centers using Harmony ...
An Approach to Reduce Energy Consumption in Cloud data centers using Harmony ...
Ieee transactions 2018 topics on wireless communications for final year stude...
ACSD2016paper20_04013
JAVA 2013 IEEE NETWORKING PROJECT Harvesting aware energy management for time...

Strategies for energy efficient resource management of hybrid programming models

  • 1. STRATEGIES FOR ENERGY-EFFICIENT RESOURCE MANAGEMENT OF HYBRID PROGRAMMING MODELS ABSTRACT: Many scientific applications are programmed using hybrid programming models that use both message passing and shared memory, due to the increasing prevalence of large-scale systems with multicore, multisocket nodes. Previous work has shown that energy efficiency can be improved using software-controlled execution schemes that consider both the programming model and the power-aware execution capabilities of the system. However, such approaches have focused on identifying optimal resource utilization for one programming model, either shared memory or message passing, in isolation. The potential solution space, thus the challenge, increases substantially when optimizing hybrid models since the possible resource configurations increase exponentially. Nonetheless, with the accelerating adoption of hybrid programming models, we increasingly need improved energy efficiency in hybrid parallel applications on large-scale systems. In this work, we present new software-controlled execution schemes that consider the effects of dynamic concurrency throttling (DCT) and dynamic voltage and frequency scaling (DVFS) in the context of hybrid programming models. Specifically, we present predictive models and novel algorithms based on statistical analysis that anticipate application power and time requirements under different concurrency and frequency configurations. We apply our models and methods to the NPB MZ benchmarks and selected applications from the ASC Sequoia codes. Overall, we achieve substantial energy savings (8.74 percent on average and up to 13.8 percent) with some performance gain (up to 7.5 percent) or negligible performance loss. ECWAY TECHNOLOGIES IEEE PROJECTS & SOFTWARE DEVELOPMENTS OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE CELL: +91 98949 17187, +91 875487 2111 / 3111 / 4111 / 5111 / 6111 VISIT: www.ecwayprojects.com MAIL TO: ecwaytechnologies@gmail.com