Dynamic partitioning of loop iterations on heterogeneous PC clusters

Loop partitioning on parallel and distributed systems has been a critical problem. Furthermore, it becomes more difficult to deal with on the emerging heterogeneous PC cluster environments. In the past, some loop self-scheduling schemes have been proposed to be applicable to heterogeneous cluster environments. In this paper, we propose a performance-based approach, which partitions loop iterations according to the performance ratio of cluster nodes. To verify the proposed approach, a heterogeneous cluster is built, and three types of application programs are implemented to be executed in this testbed. Experimental results show that the proposed approach performs better than traditional schemes.

Power optimization for dynamic configuration in heterogeneous web server clusters

To reduce the environmental impact, it is essential to make data centers green, by turning off servers and tuning their speeds for the instantaneous load offered, that is, determining the dynamic configuration in web server clusters. We model the problem of selecting the servers that will be on and finding their speeds through mixed integer programming; we also show how to combine such solutions with control theory. For proof of concept, we implemented this dynamic configuration scheme in a web server cluster running Linux, with soft real-time requirements and QoS control, in order to guarantee both energy-efficiency and good user experience. In this paper, we show the performance of our scheme compared to other schemes, a comparison of a centralized and a distributed approach for QoS control, and a comparison of schemes for choosing speeds of servers.     

A two-phase scheduling strategy for real-time applications with security requirements on heterogeneous clusters

Nowadays, increasing attention has been directed towards the issue of security service for real-time applications with security requirements on clusters. However, the study of integrating security demands of real-time applications into scheduling is rare. In this paper, we propose a novel two-phase scheduling strategy TPSS which takes timing constraints and security needs into consideration for security-critical real-time applications on heterogeneous clusters. In the first-phase, a novel algorithm DSRF is proposed to schedule real-time tasks. When the system is in heavy burden, DSRF is able to degrade the security levels of new tasks and tasks waiting in local queues so as to enhance guarantee ratio. On the contrary, when the system is in light burden, DSRF is capable of employing slack time to improve the security quality of new tasks and adequately utilize the system resource. The minimal security level can guarantee the system security, and higher security level is able to make the system more secure. In the second-phase, a new algorithm FMSL is proposed to minimize the difference of security levels of accepted tasks and further improve the security levels of accepted tasks on the whole, which degrades the probability of the applications being attacked. We compare TPSS, DSRF, SAEDF and RF by extensive simulations. The experimental results indicate that TPSS significantly improves the flexibility of scheduling and outperforms other algorithms.     

Integer linear programming optimization of joint RRM policies for heterogeneous wireless systems

Wireless systems will be characterized by the coexistence of heterogeneous Radio Access Technologies (RATs) with different, but also complementary, performance and technical characteristics. These heterogeneous wireless networks will provide network operators the possibility to efficiently and coordinately use the heterogeneous radio resources, for which novel Joint Radio Resource Management (JRRM) policies need to be designed. In this context, this work proposes and evaluates a JRRM policy that simultaneously determines for each user an adequate combination of RAT and number of radio resources within such RAT to guarantee the user/service QoS requirements, and efficiently distribute the radio resources considering a user fairness approach aimed at maximizing the system capacity. To this aim, the JRRM algorithm, which takes into account the discrete nature of radio resources, is based on integer linear programming optimization mechanisms.     

On optimization of finite-difference time-domain (FDTD) computation on heterogeneous and GPU clusters

A model for the computational cost of the finite-difference time-domain (FDTD) method irrespective of implementation details or the application domain is given. The model is used to formalize the problem of optimal distribution of computational load to an arbitrary set of resources across a heterogeneous cluster. We show that the problem can be formulated as a minimax optimization problem and derive analytic lower bounds for the computational cost. The work provides insight into optimal design of FDTD parallel software. Our formulation of the load distribution problem takes simultaneously into account the computational and communication costs. We demonstrate that significant performance gains, as much as 75%, can be achieved by proper load distribution.     

A flexible Patch-based lattice Boltzmann parallelization approach for heterogeneous GPU-CPU clusters

Sustaining a large fraction of single GPU performance in parallel computations is considered to be the major problem of GPU-based clusters. We address this issue in the context of a lattice Boltzmann flow solver that is integrated in the WaLBerla software framework. Our multi-GPU implementation uses a block-structured MPI parallelization and is suitable for load balancing and heterogeneous computations on CPUs and GPUs. The overhead required for multi-GPU simulations is discussed in detail. It is demonstrated that a large fraction of the kernel performance can be sustained for weak scaling on InfiniBand clusters, leading to excellent parallel efficiency. However, in strong scaling scenarios using multiple GPUs is much less efficient than running CPU-only simulations on IBM BG/P and x86-based clusters. Hence, a cost analysis must determine the best course of action for a particular simulation task and hardware configuration. Finally we present weak scaling results of heterogeneous simulations conducted on CPUs and GPUs simultaneously, using clusters equipped with varying node configurations.     

A mixture of generalized latent variable models for mixed mode and heterogeneous data

In the behavioral, biomedical, and social-psychological sciences, mixed data types such as continuous, ordinal, count, and nominal are common. Subpopulations also often exist and contribute to heterogeneity in the data. In this paper, we propose a mixture of generalized latent variable models (GLVMs) to handle mixed types of heterogeneous data. Different link functions are specified to model data of multiple types. A Bayesian approach, together with the Markov chain Monte Carlo (MCMC) method, is used to conduct the analysis. A modified DIC is used for model selection of mixture components in the GLVMs. A simulation study shows that our proposed methodology performs satisfactorily. An application of mixture GLVM to a data set from the National Longitudinal Surveys of Youth (NLSY) is presented.     

A multistart adaptive memory-based tabu search algorithm for the heterogeneous fixed fleet open vehicle routing problem

This paper addressed the heterogeneous fixed fleet open vehicle routing problem (HFFOVRP), in which the demands of customers are fulfilled by a fleet of fixed number of vehicles with various capacities and related costs. Moreover, the vehicles start at the depot and terminate at one of the customers. This problem is an important variant of the classical vehicle routing problem and can cover more practical situations in transportation and logistics. We propose a multistart adaptive memory programming metaheuristic with modified tabu search algorithm to solve this new vehicle routing problem. The algorithmic efficiency and effectiveness are experimentally evaluated on a set of generated instances.     

Power-aware data retrieval protocols for indexed broadcast parallel channels

In pervasive and mobile computing environments, “timely and reliable” access to public data requires methods that allow quick, efficient, and low-power access to information to overcome technological limitations of wireless communication and access devices. The literature suggests broadcasting (one-way communication) as an effective way to disseminate the public data to mobile devices. Within the scope of broadcasting, the response time and energy consumption of retrieval methods have been used as the performance metrics for measuring the effectiveness of different access methods. The hardware and architecture of the mobile units offer different operational modes that consume different energy levels. Along with these architectural and hardware enhancements, techniques such as indexing, broadcasting along parallel channels, and efficient allocation and retrieval protocols can be used to minimize power consumption and access latency.In general, the retrieval methods attempt to determine the optimal access pattern for retrieving the requested data objects on parallel broadcast channels. The employment of heuristics provides a methodology for such ideal path planning solutions. Using informative heuristics and intelligent searches of an access forest can provide a prioritized cost evaluation of access patterns for requested data objects and, hence, an optimal path for the access of requested data on broadcast air channels.This paper examines two scheduling methods that along with a set of heuristics generate and facilitate the access patterns for retrieving data objects in the presence of conflicts in an indexed parallel broadcast channel environment. A simulation of the proposed schemes is presented for analyzing the relationship between response time and power consumption.     

动态格点搜索的改进算法用于团簇结构快速优化

结合高效的动态格点搜索(DLS)算法与扰动操作(Perturbation Operation)提出一种新的改进方法(DLS-PO),用于确定团簇的最低能量结构。针对一个特定构型,DLS算法总能给出其对应搜索空间的最规则结构。然而,一次失败的DLS优化将消耗大量的运算资源。为此,采取原子移动和结构旋转的扰动操作成功地改变了构型,再结合后续的DLS操作,提高了优化效率。将该算法用于原子数高达309的Lennard-Jones团簇及100原子NP-B函数铝团簇的结构优化。优化结果显示相比于DLS算法,DLS-PO算法更为高效。     

A generic energy optimization framework for heterogeneous platforms using scaling models

Mobile platforms are becoming highly heterogeneous by combining a powerful multiprocessor system-on-a-chip (MpSoC) with numerous other resources, including display, memory, power management IC, battery and wireless modems into a compact package. Furthermore, the MpSoC itself is a heterogeneous resource that integrates many processing elements such as CPU cores, GPU, video, image, and audio processors. Platform energy consumption and responsiveness are two major considerations for mobile systems, since they determine the battery life and user satisfaction, respectively. As a result, energy minimization approaches targeting mobile computing need to consider the platform at various levels of granularity. In this paper, we first present power consumption, response time, and energy consumption models for mobile platforms. Using these models, we optimize the energy consumption of baseline platforms under power, response time, and thermal constraints with and without introducing new resources. Finally, we validate the proposed framework through experiments on Qualcomm’s Snapdragon 800 Mobile Development Platforms.     

A level-set based variational method for design and optimization of heterogeneous objects

A heterogeneous object is referred to as a solid object made of different constituent materials. The object is of a finite collection of regions of a set of prescribed material classes of continuously varying material properties. These properties have a discontinuous change across the interface of the material regions. In this paper, we propose a level-set based variational approach for the design of this class of heterogeneous objects. Central to the approach is a variational framework for a well-posed formulation of the design problem. In particular, we adapt the Mumford-Shah model which specifies that any point of the object belongs to either of two types: inside a material region of a well-defined gradient or on the boundary edges and surfaces of discontinuities. Furthermore, the set of discontinuities is represented implicitly, using a multi-phase level set model. This level-set based variational approach yields a computational system of coupled geometric evolution and diffusion partial differential equations. Promising features of the proposed method include strong regularity in the problem formulation and inherent capabilities of geometric and material modeling, yielding a common framework for optimization of the heterogeneous objects that incorporates dimension, shape, topology, and material properties. The proposed method is illustrated with several 2D examples of optimal design of multi-material structures and materials.     

Accelerating Benders stochastic decomposition for the optimization under uncertainty of the petroleum product supply chain

This paper addresses the solution of a two-stage stochastic programming model for an investment planning problem applied to the petroleum products supply chain. In this context, we present the development of acceleration techniques for the stochastic Benders decomposition that aim to strengthen the cuts generated, as well as to improve the quality of the solutions obtained during the execution of the algorithm. Computational experiments are presented for assessing the efficiency of the proposed framework. We compare the performance of the proposed algorithm with two other acceleration techniques. Results suggest that the proposed approach is able to efficiently solve the problem under consideration, achieving better performance in terms of computational times when compared to other two techniques.     

MobileFBP: Designing portable reconfigurable applications for heterogeneous systems

Power-efficiency has been a key issue for today’s application and system design, ranging from embedded systems to data centers. While application-specific designs and optimizations may improve the power efficiency, it requires significant efforts to co-design the hardware and software, which are difficult to re-use. On the hardware front, the trend of heterogeneous computing enables custom designs for specific applications by integrating different types of processors and reconfigurable hardware to handle compute-intensive tasks. However, what is still missing is an elegant application framework, i.e., a programming environment and a runtime system, to develop portable applications which can offload tasks or be reconfigured dynamically to run on a variety of systems efficiently.Our ongoing work, MobileFBP, provides an application framework which aims to support heterogeneous and reconfigurable systems. Using the framework, the developers build portable applications with a dataflow programming paradigm, and the MobileFBP runtime system dynamically schedules the task components to run on available computing resources locally or remotely based on the application profiles. We hope that this ability produces high-level portable applications and reduces the efforts and skills needed for the developers to optimize their applications on a range of systems. This paper describes this work and presents our preliminary results.     

A two-stage stochastic programming model for transportation network protection

Network protection against natural and human-caused hazards has become a topical research theme in engineering and social sciences. This paper focuses on the problem of allocating limited retrofit resources over multiple highway bridges to improve the resilience and robustness of the entire transportation system in question. The main modeling challenges in network retrofit problems are to capture the interdependencies among individual transportation facilities and to cope with the extremely high uncertainty in the decision environment. In this paper, we model the network retrofit problem as a two-stage stochastic programming problem that optimizes a mean-risk objective of the system loss. This formulation hedges well against uncertainty, but also imposes computational challenges due to involvement of integer decision variables and increased dimension of the problem. An efficient algorithm is developed, via extending the well-known L-shaped method using generalized benders decomposition, to efficiently handle the binary integer variables in the first stage and the nonlinear recourse in the second stage of the model formulation. The proposed modeling and solution methods are general and can be applied to other network design problems as well.     

Total allowable catch for managing squat lobster fishery using stochastic nonlinear programming

The authors’ work on lobster fishery in Chile is summarized in this paper. The paper presents the formulation and algorithmic resolution of a two-stage stochastic nonlinear programming model with recourse. The proposed model considers a long-term planning horizon and specifically allows an optimal total allowable catch quota to be obtained for the first planning period. This model takes into account biomass dynamics, the conditions guaranteeing sustained species management and uncertain parameters such as growth rate and species carrying capacity. These parameters are explicitly incorporated via a discrete random variable (scenarios). The proposed model is solved by Lagrangian decomposition using the algebraic modeling software AMPL, in combination with the solver MINOS to solve the nonlinear models resulting from the scenario decomposition. The article also presents the results obtained with this methodology and the conclusions drawn from the work.     

A novel discrete particle swarm optimization algorithm for meta-task assignment in heterogeneous computing systems

Optimal assignment of a meta-task in heterogeneous computing systems is NP-complete in the general case. Therefore, heuristic approaches must be employed to find good solutions within a reasonable time. We propose a novel discrete particle swarm optimization (DPSO) algorithm for this problem. Firstly, to make particle swarm optimization algorithm more suitable for solving task assignment problems, particles are represented as integer vectors and a new position update method is developed based on discrete domain. Secondly, an effective variable neighborhood descent algorithm is applied to emphasize exploitation. In addition, migration mechanism is introduced with the hope to escape from possible local optimum and to balance the exploration and exploitation. Computational simulations and comparisons based on a set of benchmark instances indicate that the proposed DPSO algorithm is a viable approach for the task assignment problem.     

A hybrid Branch-and-Bound and evolutionary approach for allocating strings of applications to heterogeneous distributed computing systems

Providing efficient workload management is an important issue for a large-scale heterogeneous distributed computing environment where a set of periodic applications is executed. The considered shipboard distributed system is expected to operate in an environment where the input workload is likely to change unpredictably, possibly invalidating a resource allocation that was based on the initial workload estimate. The tasks consist of multiple strings, each made up of an ordered sequence of applications. There is a quality of service (QoS) minimum throughput constraint that must be satisfied for each application in a string, and a maximum utilization constraint that must be satisfied on each of the hardware resources in the system. The challenge, therefore, is to efficiently and robustly manage both computation and communication resources in this unpredictable environment to achieve high performance while satisfying the imposed constraints. This work addresses the problem of finding a robust initial allocation of resources to strings of applications that is able to absorb some level of unknown input workload increase without rescheduling. The proposed hybrid two-stage method of finding a near-optimal allocation of resources incorporates two specially designed mapping techniques: (1) the Permutation Space Genitor-Based heuristic, and (2) the follow-up Branch-and-Bound heuristic based on an Integer Linear Programming (ILP) problem formulation. The performance of the proposed resource allocation method is evaluated under different simulation scenarios and compared to an iteratively computed upper bound.     

Computer-based interface for an integrated solid waste management optimization model

Planning a regional waste management strategy is a critical step that, if not properly addressed, will lead to an inefficient integrated solid waste management (ISWM) system. Regional planning affects the design, implementation, and efficiency of the overall ISWM scheme. Consequently, decision-makers must look for optimized regional waste management planning to achieve a successful strategy. The optimization of an ISWM strategy for an area requires the knowledge of available solid waste management alternatives and technologies, economic and environmental costs associated with these alternatives, and their applicability to the specific area. Decision-makers often have to rely on optimization models to examine the impacts of mass balance, capacity limitations, operation, and site availability as well as to analyze different alternative options in the selection of a cost effective, environmentally sound waste management alternative. In this context, the complexity associated with the formulation of optimization models may hinder its use, and consequently, user friendliness is a major concern. This paper presents an interface that was developed to address this concern, that is to formulate the matrices associated with an integrated waste management optimization model.