The Experts below are selected from a list of 1323 Experts worldwide ranked by ideXlab platform
Theresa L. Windus - One of the best experts on this subject based on the ideXlab platform.
-
Improving efficiency of semi-direct møller-plesset second-order perturbation methods through Oversubscription on multiple nodes.
Journal of computational chemistry, 2019Co-Authors: Ellie L. Fought, Vaibhav Sundriyal, Masha Sosonkina, Theresa L. WindusAbstract:The purpose of this work is to evaluate the efficacy of Oversubscription, at the 1n, 2n, and 3n levels for n physical cores, on semi-direct MP2 methods within NWChem when using two and three Intel nodes. Semi-direct MP2 energy and gradient calculations were performed on chemical systems ranging from 824 to 1626 basis functions using the cc-pVDZ basis set. Wall times for semi-direct MP2 energies were reduced by as much as 36% using two nodes and 44% using three nodes compared to no Oversubscription. Total energy consumed by the CPU and DRAM was also reduced by as much as 12% using two nodes and as much as 20% using three nodes when oversubscribing. MP2 gradient wall times improved by as much as 16% using two nodes and 18% using three nodes compared to execution at the 1n level; however, energy savings were insignificant. Intel performance-counter data show a strong correlation between total wall time saved and less time spent in the idle state, indicating a more efficient use of the processors when oversubscribing. © 2019 Wiley Periodicals, Inc.
-
Saving time and energy with Oversubscription and semi-direct Møller-Plesset second order perturbation methods.
Journal of Computational Chemistry, 2017Co-Authors: Ellie L. Fought, Vaibhav Sundriyal, Masha Sosonkina, Theresa L. WindusAbstract:In this work, the effect of Oversubscription is evaluated, via calling 2n, 3n, or 4n processes for n physical cores, on semi-direct MP2 energy and gradient calculations and RI-MP2 energy calculations with the cc-pVTZ basis using NWChem. Results indicate that on both Intel and AMD platforms, Oversubscription reduces total time to solution on average for semi-direct MP2 energy calculations by 25-45% and reduces total energy consumed by the CPU and DRAM on average by 10-15% on the Intel platform. Semi-direct gradient time to solution is shortened on average by 8-15% and energy consumption is decreased by 5-10%. Linear regression analysis shows a strong correlation between time to solution and total energy consumed. Oversubscribing during RI-MP2 calculations results in performance degradations of 30-50% at the 4n level. © 2017 Wiley Periodicals, Inc.
Ellie L. Fought - One of the best experts on this subject based on the ideXlab platform.
-
Improving efficiency of semi-direct møller-plesset second-order perturbation methods through Oversubscription on multiple nodes.
Journal of computational chemistry, 2019Co-Authors: Ellie L. Fought, Vaibhav Sundriyal, Masha Sosonkina, Theresa L. WindusAbstract:The purpose of this work is to evaluate the efficacy of Oversubscription, at the 1n, 2n, and 3n levels for n physical cores, on semi-direct MP2 methods within NWChem when using two and three Intel nodes. Semi-direct MP2 energy and gradient calculations were performed on chemical systems ranging from 824 to 1626 basis functions using the cc-pVDZ basis set. Wall times for semi-direct MP2 energies were reduced by as much as 36% using two nodes and 44% using three nodes compared to no Oversubscription. Total energy consumed by the CPU and DRAM was also reduced by as much as 12% using two nodes and as much as 20% using three nodes when oversubscribing. MP2 gradient wall times improved by as much as 16% using two nodes and 18% using three nodes compared to execution at the 1n level; however, energy savings were insignificant. Intel performance-counter data show a strong correlation between total wall time saved and less time spent in the idle state, indicating a more efficient use of the processors when oversubscribing. © 2019 Wiley Periodicals, Inc.
-
Saving time and energy with Oversubscription and semi-direct Møller-Plesset second order perturbation methods.
Journal of Computational Chemistry, 2017Co-Authors: Ellie L. Fought, Vaibhav Sundriyal, Masha Sosonkina, Theresa L. WindusAbstract:In this work, the effect of Oversubscription is evaluated, via calling 2n, 3n, or 4n processes for n physical cores, on semi-direct MP2 energy and gradient calculations and RI-MP2 energy calculations with the cc-pVTZ basis using NWChem. Results indicate that on both Intel and AMD platforms, Oversubscription reduces total time to solution on average for semi-direct MP2 energy calculations by 25-45% and reduces total energy consumed by the CPU and DRAM on average by 10-15% on the Intel platform. Semi-direct gradient time to solution is shortened on average by 8-15% and energy consumption is decreased by 5-10%. Linear regression analysis shows a strong correlation between time to solution and total energy consumed. Oversubscribing during RI-MP2 calculations results in performance degradations of 30-50% at the 4n level. © 2017 Wiley Periodicals, Inc.
Yuanyuan Yang - One of the best experts on this subject based on the ideXlab platform.
-
multicast fat tree data center networks with bounded link Oversubscription
International Conference on Computer Communications, 2013Co-Authors: Zhiyang Guo, Yuanyuan YangAbstract:Many data center networks (DCNs) adopt a multirooted tree structure called fat-tree, which has the potential to deliver large bisection bandwidth through rich path multiplicity. However, unbalanced traffic load distribution may prevent efficient utilization of such high degree of parallelism. Meanwhile, high bandwidth multicast communication is critical to many data center services and applications. Hence, in this paper we consider multicast traffic load balance problem in fat-tree DCNs from a novel angle, aiming to find the most cost-effective way to build a multicast fat-tree DCN with bounded link Oversubscription ratio. First, we present a multi-rate network model to accurately describe the communication environment in a fat-tree DCN. Then, we derive the minimum number of core switches required to achieve bounded link Oversubscription ratio under arbitrary multicast traffic. Finally, we provide a comprehensive comparison on the cost of different approaches to building such a multicast fat-tree DCN.
-
Oversubscription Bounded Multicast Scheduling in Fat-Tree Data Center Networks
Parallel & Distributed Processing (IPDPS), 2013 IEEE 27th International Symposium on, 2013Co-Authors: Zhiyang Guo, Jun Duan, Yuanyuan YangAbstract:Multicast benefits numerous data center applications that require group communication by eliminating sending unnecessary duplicated packets in the network, thus significantly reduces network traffic and improves application throughput. Meanwhile, many data center networks (DCNs) adopt a multi-rooted tree structure called fat-tree, which utilizes rich path multiplicity to deliver high bisection bandwidth. However, currently there is no efficient flow scheduling algorithm for the fat-tree that can route multicast flows appropriately to achieve traffic load balance, thus cannot fully take advantage of this high degree of link parallelism. Besides low bandwidth utilization, unbalanced traffic load distribution also leads to unpredictable network performance and degraded data center agility. In this paper, we study multicast traffic load balance problem in fat-tree DCNs. First, we derive a minimum link Oversubscription upper bound in multicast fat-tree DCNs based on a network model that accurately describes the DCN communication environment. Then, we present Oversubscription Bounded Multicast Scheduling (OBMS), a low-complexity multicast flow scheduling algorithm that guarantees bounded link Oversubscription and efficient network utilization even under the most congested traffic patterns. Finally, we evaluate the performance of OBMS in an event-driven DCN simulator under various types of traffic patterns, and show that OBMS significantly outperforms other load-balance methods in terms of network throughput and evenness of traffic load distribution.
-
IPDPS - Oversubscription Bounded Multicast Scheduling in Fat-Tree Data Center Networks
2013 IEEE 27th International Symposium on Parallel and Distributed Processing, 2013Co-Authors: Zhiyang Guo, Jun Duan, Yuanyuan YangAbstract:Multicast benefits numerous data center applications that require group communication by eliminating sending unnecessary duplicated packets in the network, thus significantly reduces network traffic and improves application throughput. Meanwhile, many data center networks (DCNs) adopt a multi-rooted tree structure called fat-tree, which utilizes rich path multiplicity to deliver high bisection bandwidth. However, currently there is no efficient flow scheduling algorithm for the fat-tree that can route multicast flows appropriately to achieve traffic load balance, thus cannot fully take advantage of this high degree of link parallelism. Besides low bandwidth utilization, unbalanced traffic load distribution also leads to unpredictable network performance and degraded data center agility. In this paper, we study multicast traffic load balance problem in fat-tree DCNs. First, we derive a minimum link Oversubscription upper bound in multicast fat-tree DCNs based on a network model that accurately describes the DCN communication environment. Then, we present Oversubscription Bounded Multicast Scheduling (OBMS), a low-complexity multicast flow scheduling algorithm that guarantees bounded link Oversubscription and efficient network utilization even under the most congested traffic patterns. Finally, we evaluate the performance of OBMS in an event-driven DCN simulator under various types of traffic patterns, and show that OBMS significantly outperforms other load-balance methods in terms of network throughput and evenness of traffic load distribution.
-
INFOCOM - Multicast fat-tree data center networks with bounded link Oversubscription
2013 Proceedings IEEE INFOCOM, 2013Co-Authors: Zhiyang Guo, Yuanyuan YangAbstract:Many data center networks (DCNs) adopt a multirooted tree structure called fat-tree, which has the potential to deliver large bisection bandwidth through rich path multiplicity. However, unbalanced traffic load distribution may prevent efficient utilization of such high degree of parallelism. Meanwhile, high bandwidth multicast communication is critical to many data center services and applications. Hence, in this paper we consider multicast traffic load balance problem in fat-tree DCNs from a novel angle, aiming to find the most cost-effective way to build a multicast fat-tree DCN with bounded link Oversubscription ratio. First, we present a multi-rate network model to accurately describe the communication environment in a fat-tree DCN. Then, we derive the minimum number of core switches required to achieve bounded link Oversubscription ratio under arbitrary multicast traffic. Finally, we provide a comprehensive comparison on the cost of different approaches to building such a multicast fat-tree DCN.
Ken Christensen - One of the best experts on this subject based on the ideXlab platform.
-
The effect of server energy proportionality on data center power Oversubscription
Future Generation Computer Systems, 2020Co-Authors: Sulav Malla, Ken ChristensenAbstract:Abstract Modern data centers improve resource utilization with power Oversubscription. The power hierarchy in a data center is oversubscribed by installing more servers than allowed by the power budget based on server peak power consumption. Power Oversubscription is possible due to the statistically low likelihood of simultaneous peak power operation of multiple servers. As future servers become more energy proportional, the opportunity for greater power Oversubscription increases. The challenge is to quantify the level of Oversubscription that can be attained. In this paper, we quantify the level of Oversubscription possible for a given acceptable probability of power overload for servers characterized by energy proportionality metric and workload distribution. We develop a theoretical framework to characterize and predict the relationship between server energy proportionality and power Oversubscription. We verify our framework through an extensive empirical study using publicly available SPECpower benchmark data for over 500 server models and publicly available Google cluster utilization data. Using our framework, a data center operator can predict the additional power Oversubscription possible when replacing existing servers with a newer model of more energy proportional servers.
-
A Survey on Power Management Techniques for Oversubscription of Multi-Tenant Data Centers
ACM Computing Surveys, 2019Co-Authors: Sulav Malla, Ken ChristensenAbstract:Power management for data centers has been extensively studied in the past 10 years. Most research has focused on owner-operated data centers with less focus on Multi-Tenant Data Centers (MTDC) or colocation data centers. In an MTDC, an operator owns the building and leases out space, power, and cooling to tenants to install their own IT equipment. MTDC’s present new challenges for data center power management due to an inherent lack of coordination between the operator and tenants. In this article, we conduct a comprehensive survey of existing MTDC power management techniques for demand response programs, sustainability, and/or power hierarchy Oversubscription. Power Oversubscription is of particular interest, as it can maximize resource utilization, increase operator profit, and reduce tenant costs. We create a taxonomy to classify and compare key works. Our taxonomy and review differ from existing works in that our emphasis is on safe power Oversubscription, which has been neglected in previous surveys. We propose future research for prediction and control of power overload events in an oversubscribed MTDC.
Masha Sosonkina - One of the best experts on this subject based on the ideXlab platform.
-
Improving efficiency of semi-direct møller-plesset second-order perturbation methods through Oversubscription on multiple nodes.
Journal of computational chemistry, 2019Co-Authors: Ellie L. Fought, Vaibhav Sundriyal, Masha Sosonkina, Theresa L. WindusAbstract:The purpose of this work is to evaluate the efficacy of Oversubscription, at the 1n, 2n, and 3n levels for n physical cores, on semi-direct MP2 methods within NWChem when using two and three Intel nodes. Semi-direct MP2 energy and gradient calculations were performed on chemical systems ranging from 824 to 1626 basis functions using the cc-pVDZ basis set. Wall times for semi-direct MP2 energies were reduced by as much as 36% using two nodes and 44% using three nodes compared to no Oversubscription. Total energy consumed by the CPU and DRAM was also reduced by as much as 12% using two nodes and as much as 20% using three nodes when oversubscribing. MP2 gradient wall times improved by as much as 16% using two nodes and 18% using three nodes compared to execution at the 1n level; however, energy savings were insignificant. Intel performance-counter data show a strong correlation between total wall time saved and less time spent in the idle state, indicating a more efficient use of the processors when oversubscribing. © 2019 Wiley Periodicals, Inc.
-
Saving time and energy with Oversubscription and semi-direct Møller-Plesset second order perturbation methods.
Journal of Computational Chemistry, 2017Co-Authors: Ellie L. Fought, Vaibhav Sundriyal, Masha Sosonkina, Theresa L. WindusAbstract:In this work, the effect of Oversubscription is evaluated, via calling 2n, 3n, or 4n processes for n physical cores, on semi-direct MP2 energy and gradient calculations and RI-MP2 energy calculations with the cc-pVTZ basis using NWChem. Results indicate that on both Intel and AMD platforms, Oversubscription reduces total time to solution on average for semi-direct MP2 energy calculations by 25-45% and reduces total energy consumed by the CPU and DRAM on average by 10-15% on the Intel platform. Semi-direct gradient time to solution is shortened on average by 8-15% and energy consumption is decreased by 5-10%. Linear regression analysis shows a strong correlation between time to solution and total energy consumed. Oversubscribing during RI-MP2 calculations results in performance degradations of 30-50% at the 4n level. © 2017 Wiley Periodicals, Inc.
