Peer to peer and grid systems provide attractive middlewares to solve large numerical problems. The development, deployment and execution of applications using those middlewares suffer from the lack of well-adapted advanced tools. There is not any available solution to use the same application on two distinct middlewares. Our article presents the YML Framework which provides supporting tools to design and execute portable parallel applications over large scale peer to peer and grid middlewares. The YML Framework defines a new parallel programming language called YvetteML which is composed of a graph language and a component model. We evaluate the performance of our framework with a simple numerical application using XtremWeb as a middleware.
This paper presents the integration of a multi-level scheduler in the YML architecture. It demonstrates the advantages of this architecture based on a component model and why it is well suited to develop parallel applications for Grids. Then, the multi-level scheduler under development for this framework is presented. 1
Global computing platforms have become popular tools for the resolution of large scale problems. They are often independent without any interoperability between each other. Therefore, clients are now asking for a better availability and scalability. In previous work, we presented the YML framework which was a first attempt to enable the development and deployment of applications on several global computing middleware. However, it suffered from scalability issues and a static approach.In this paper, we highlight recent extensions of YML. We achieve a dynamic federation of computing middleware because YML is now able to manage at the run-time several middleware back-ends. Other improvements such as an OmniRPC back-end, a component binary cache mechanism, a new data management module, and a new data type supported by the YML front-end, yield to a much better scalability. We present the first evaluations of these extensions on a network of workstations and with a typical distributed sort application. Although the results show a significant overhead, they stress the benefits of binary caching and dynamic back-ends federation.
Nowadays, large scale distributed systems gather thousands of nodes with hierarchical memory models. They are heterogeneous, volatile and geographically distributed. The efficient exploitation of such systems requires the conception and adaptation of appropriate numerical methods, the definition of new programming paradigms, new metrics for performance prediction, etc. The modern hybrid numerical methods are well adapted to this kind of systems. This is particularly because of their multi-level parallelism and fault tolerance property. However the programming of these methods for these architectures requires concurrent reuse of sequential and parallel code. But the currently existing numerical libraries aren't able to exploit the multi-level parallelism offered by theses methods. A few linear algebra numerical libraries make use of object oriented approach allowing modularity and extensibility. Nevertheless, those which offer modularity,sequential and parallel code reuse are almost non-existent.In this paper, we analyze the lacks in existing libraries and propose a design based on a component approach and the strict separation between computation operations, data management and communication control of an application. We present then an application of this design using YML scientific workflow environment (http://yml.prism.uvsq.fr/) jointly with the object oriented LAKe (Linear Algebra Kernel) library. Some numerical experiments on GRID5000 platform validate our approach and show its efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.