Language and Compiler Support for Adaptive Distributed Applications

Adve, Vikram; Lam, Vinh Vi; Ensink, Brian

doi:10.1145/384198.384229

Cited by 20 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If (b) does not hold, then there are two possibilities: (1) the process is not performed along a safe adaptation path or (2) there is an adaptive action taking place in a state that is not globally safe. In the first situation, there must be a configuration on the adaptation path violating dependency relationships, and therefore, the adaptation process is unsafe.…”

Section: (2) Use Proof By Contradiction To Establish (A) → (B)mentioning

confidence: 99%

“…To meet the needs of emerging and future adaptive systems, numerous research efforts in the past several years have addressed ways to construct adaptable software. Examples include support for adaptability in programming languages [2,3,4], frameworks to design context-aware applications [5,6], adaptive middleware platforms that shield applications from external dynamics [7,8], and adaptable and extensible operating systems [9,10,11]. In many cases, adaptations involve not only changes to parameters, but reconfiguration of the software structure itself.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enabling Safe Dynamic Component-Based Software Adaptation

Cheng

Yang

et al. 2005

Architecting Dependable Systems III

View full text Add to dashboard Cite

Abstract. Recomposable software enables a system to change its structure and behavior during execution, in response to a dynamic execution environment. This paper proposes an approach to ensure that such adaptations are safe with respect to system consistency. The proposed method takes into consideration dependency analysis for target components, specifically determining viable sequences of adaptive actions and those states in which an adaptive action may be applied safely. We demonstrate that the technique ensures safe adaptation (insertion, removal, and replacement of components) in response to changing external conditions in a wireless multicast video application.

show abstract

Section: (2) Use Proof By Contradiction To Establish (A) → (B)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enabling Safe Dynamic Component-Based Software Adaptation

Cheng

Yang

et al. 2005

Architecting Dependable Systems III

View full text Add to dashboard Cite

show abstract

“…It has been suggested [43] that static task graphs can be used in a run-time library, and be traversed at run-time. Conversely, the use of static task graphs in run-time libraries for adaptive performance control may be too inefficient [44].…”

Section: Performance Prediction and Controlmentioning

confidence: 99%

Performance control of scientific coupled models in Grid environments

Armstrong

Ford

Gurd

et al. 2005

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYIn recent years, there has been increasing interest in the development of computer simulations of complex biological systems, and of multi-physics and multi-scale physical phenomena. Applications have been developed that involve the coupling together of separate executable models of individual systems, where these models may have been developed in isolation. A lightweight yet general solution is required to problems of linking coupled models, and of handling the incompatibilities between interacting models that arise from their diverse origins and natures. Many such models require high-performance computers to provide acceptable execution times, and there is increasing interest in utilizing Grid technologies. However, Grid applications need the ability to cope with heterogeneous and dynamically changing execution environments, particularly where run-time changes can affect application performance. A general coupling framework (GCF) is described that allows the construction of flexible coupled models. This approach results in a component-based implementation of a coupled model application. A semi-formal presentation of GCF is given. Components under GCF are separately deployable and coupled by simple data flows, making them appropriate structures for dynamic execution platforms such as the Grid. The design and initial implementation of a performance control system (PERCO) is reviewed. PERCO acts by redeploying components, and is thus appropriate for controlling GCF coupled model applications. Redeployment decisions in PERCO require performance prediction capabilities. A proof-of-concept performance prediction algorithm is presented, based on the descriptions of GCF and PERCO. Copyright

show abstract

“…(Figure 1 is the task graph representation of ATR. Task graphs are useful in our future work because they form the basis for adaptive operations in a program control language that we are currently developing [2]. )…”

Section: Task Graph/application Structurementioning

confidence: 99%

“…Simultaneous computation of cell potentials for multiple charge types. 2. Use of optimized library routines for vector-matrix multiply.…”

Section: The Flems Code and The Parallel Fast Multipole Solvermentioning

confidence: 99%

Model-based control of adaptive applications: an overview

Adve

Akinsanmi

Browne

et al. 2002

Proceedings 16th International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

Model-based control utilizes performance models of applications to choose performant system configurations for execution of applications. The performance models used in this research separate specification of the software system from specification of the execution environment so that model-based control can select software configurations for a given execution environment or, conversely, select execution environments for a given software configuration. Some representations, methods, and tools that enable model-based control are briefly described. Application of some of the methods and tools to a stochastic optimization code is briefly sketched. The problems of model-based control of two other applications are defined and described. The relationship between model-based control and other methods for adaptive control is briefly discussed. Model-Based ControlCurrent procedures for selection of system configurations for execution of complex, parallel programs on complex, distributed execution environments are mostly ad hoc. Anecdotal evidence suggests that system configurations obtained from current ad hoc procedures are often sub-optimal. System configuration management is rendered even more difficult when the application is adaptive or when the execution environment changes. Model-based control is a methodology for generating effective system configurations that are based upon predictions obtained from performance models of the application and of its execution environment.Model-based control begins with the well-established but infrequently applied practice of using a performance model of the application and the initial execution environment to determine an effective initial system configuration. Performance models can be assembled manually and the analysis leading to effective configurations can incorporate human intelligence.Adaptive, model-based control adapts system configurations based upon the runtime behavior of the application, changes in execution environment, or both. This control methodology requires us to incorporate measurement, analysis, and modeling into the application structure.It requires automated or semi-automated construction of performance models for application configurations, execution environments, and mapping of applications to resources. Model-based control is domain specific. Automation can occur within application domains and within families of execution environments. This paper reports on progress towards design and implementation of model-based control of a stochastic optimization code and on the initial steps taken toward equipping two other applications, namely a method-of-lines code and a composite materials code, for adaptive modelbased control.The approach and the technology base for adaptive control was established in the POEMS project. POEMS developed methods for automated development of performance models of both applications and execution environments [1]. The original POEMS team, augmented by application developers, is currently extending the technology for compositio...

show abstract

Language and Compiler Support for Adaptive Distributed Applications

Cited by 20 publications

References 15 publications

Enabling Safe Dynamic Component-Based Software Adaptation

Enabling Safe Dynamic Component-Based Software Adaptation

Performance control of scientific coupled models in Grid environments

Model-based control of adaptive applications: an overview

Contact Info

Product

Resources

About