1,720,976 research outputs found
Fault tolerance for data parallel programs
No full textThe main issues when supporting fault tolerance based on checkpointing and rollback recovery for
High-Performance applications are related to the scalability of the introduced support, the possibility of
analyzing the induced overhead and, in more general terms, the optimization of the trade-off between
failure-free and recovery performances. In this paper we describe our contribution in fault tolerance for
high-level structured parallelism models. We take a different viewpoint w.r.t. existing contributions, by
introducing a methodology to derive interesting properties to support fault tolerance. We show how to
apply this methodology to a general data parallel model, deriving useful properties to introduce a class
of checkpointing protocols. Thanks to this methodology, this class of protocols is not affected by the
described issues. We exemplify two checkpointing protocols and the related rollback recovery techniques.
For each protocol we also derive cost models statically describing the failure-free performance, which can
be used for performance tuning or to target some Quality of Service parameter. To assess the innovation
of the results we analytically and experimentally compare the introduced protocols with two literature
protocols. Results show that while the protocols introduced in this paper permit the definition of cost
models and have a good scalability, the literature protocols do not always have these properties
High-Performance Pervasive Computing
No full textIn the area of next-generation mobile and pervasive grids, this chapter addresses the following issues: 1) mechanisms to express location & context-awareness, 2) uniform mechanisms to express parallel and distributed high-performance and fault-tolerant applications, 3) mechanisms for event management, 4) high-performance component model, 5) cost model, in particular with respect to dynamic establishment and management of inter-layer contracts and QoS control.
The new programming model, called ASSISTANT, integrates in the high-performance environment ASSIST the features of management and context-awareness. The model consists of three layers from top to bottom: i) application structuring by means of high-performance components composition (called, the RED layer), ii) Manager network (BLUE layer), iii) context interface (the GREEN layer).
The Manager construct will allow the application designer to explicitly express adaptivity and context-awareness strategies, by taking into account the information sent by the context interfaces (events, state changes, monitoring of computing and communication resource), and by providing to restructure the application layer from the view point of performance and of functionalities.
The context is defined as a proper layer (GREEN) of the whole computing architecture. It is used to spread information about the environment to be controlled (sensors, actuators, the same computing nodes and communication lines) and about application modules (performance measures)
A cost model for autonomic reconfigurations in high-performance pervasive applications
No full textIn the last years we have seen the diffusion of platforms
including high- performance nodes (e.g. multicores) and
powerful mobile devices (e.g. smartphones) interconnected
by heterogeneous networks. Relevant examples of applications
targeting these kinds of platforms are Emergency Management
and Homeland Protection which provide computing/
communication activities characterized by user-defined
Quality of Service constraints. In this paper we introduce
the ASSISTANT programming model for adaptive parallel
applications. ASSISTANT components are specified in multiple
versions, each one dynamically selected according to an
adaptation strategy aimed to target the required QoS levels.
For these applications a key-issue is a well-defined adaptation
semantics featuring a cost model which describes the
overhead for reconfiguring a component (e.g. when switching
between versions). In this paper we introduce our approach
and we evaluate this cost on a flood management application.
Author Keywords
High-Performance Computing, Adaptivity, Autonomic Computing,
Application Reconfigurations
Next Generation Grids and Wireless Communication Networks: Towards a Novel Integrated Approach
No full textOne of the most promising trends for next generation networks is to consider an integrated approach to the communication infrastructure and the processing layer. In particular, the introduction of broadband and reliable wireless networks allows the interaction of a huge number of devices all creating a single network. On the other hand, the grid paradigm is considered as one of the most promising approach for pervasive and dynamic applications. Aim of this paper is to present a novel integrated approach between grid paradigm and wireless networks by highlighting the main advantages of their cooperation. In particular, it will be shown here how a wireless heterogeneous network can be exploited for implementing a pervasive and dynamic grid (mobile grid) and, on the other hand, a mobile grid allows the optimization of the communication infrastructure. The integrated approach can be an effective method for solving applications, such as emergency management, where a huge amount of data derived from a wireless infrastructure needs to be processed efficiently and adaptively, and the traffic flow in the wide area wireless networks needs to be coordinated and optimized
Adaptivity in Risk and Emergency Management Applications on Pervasive Grids
No full textPervasive Grid computing platforms are com- posed of a variety of fixed and mobile nodes, interconnected through multiple wireless and wired network technologies. Pervasive Grid Applications must adapt themselves to the state of their surrounding environment which includes envi- ronmental data (e.g. collected from sensors) and the state of the used resources (e.g. network or node states). Adaptation is especially important if we consider complex High-Performance Pervasive Grid applications, such as intelligent transportation and emergency management. In this paper we investigate how to define adaptivity for complex Pervasive Grid applications by providing multiple versions of application parallel modules. The versions are defined by exploiting different sequential algorithms and parallelization techniques. We introduce per- formance analysis tools for versions, which allow us to define specific selection policies of the best version to be executed, depending on the context. We show how each version is best suited to be executed on two application scenarios, also by means of experiments. To synthesize the contributions of this paper we introduce the ASSISTANT programming model, for adaptive Pervasive Grid applications
Consistent reconfiguration protocols for adaptive high-performance applications
No full textProgramming models for Pervasive Computing applications
typically include the possibility of specifying software
components according to multiple alternative versions, each
optimized for a certain class of computing and communication
technologies. A main mechanism provided by these programming
models permits to dynamically select one of the alternative
versions for the execution. This reconfiguration activity may be
critical, from a performance point of view, when considering
High-Performance Pervasive Computing applications, especially
if the reconfiguration must be performed in such a way that
the application semantics is respected (i.e. the reconfiguration is
consistent). In this paper we show how to introduce consistent reconfiguration
protocols for the ASSISTANT programming model,
we exemplify two general protocols and we show experimental
results for one of them.
Index Terms—High-Performance Computing, Autonomic
Computing, Reconfiguration Protocols, Pervasive and Mobile
Computin
An approach to Mobile Grid platforms for the development and support of complex ubiquitous applications
No full textSeveral complex and time-critical applications require the existence of novel distributed, heterogeneous and dynamic platforms composed of a variety of fixed and mobile processing nodes and networks. Such platforms, that can be called Pervasive Mobile Grids, aim to merge the features of Pervasive Computing and High-performance Grid Computing onto a new emerging paradigm. In this Chapter we study a methodology for designing high-performance distributed computations, able to exploit the heterogeneity and dynamicity of Pervasive Grids, by expressing Adaptivity and Context Awareness directly at the application level. We describe a programming model approach, and we compare it with other existing research works in the field of Pervasive Mobile Computing, discussing the rationales of the requirements and the features of a novel programming model for the target platforms and applications. In order to exemplify the proposed methodology we introduce our evaluation framework ASSISTANT, and we provide some interesting future directions in this research field
- …
