Asynchronous grid computation for American options derivatives

Parallel asynchronous iterative algorithms exhibit features that are extremely well-suited for Grid computing, such as lack of synchronization points. Unfortunately, they also suffer from slow convergence rates. In this paper we propose using asynchronous methods as a coarse-grained preconditioner in a flexible iterative method, where the preconditioner is allowed to change in each iteration step. A full implementation of the algorithm is presented using Grid middleware that allows for both synchronous and asynchronous communication. Advantages and disadvantages of the approach are discussed. Numerical experiments on heterogeneous computing hardware demonstrate the effectiveness of the proposed algorithm on Grid computers, with application to large 2D and 3D bubbly flow problems.

In this paper, we will discuss a multi-camera tracking system, where we place a stress on a highway through vehicle plate recognition. Generally, recognizing a vehicle plate for a toll-gate system or parking system is easier than recognizing a car plate for the highway system. There are many cameras installed on the highway to capture images and every camera has different angles of images. As a result, the images are captured in varied imaging conditions and not focusing on the vehicle itself. Therefore, we need a system that is able to recognize the object first. However, such a system consumes a large amount of time to complete the whole process. To overcome this drawback, we installed this process with grid computing as a solution and a future view of a multi-camera tracking system. We construct a multi-camera tracking system that consists of many cameras, a grid computer system, a data base and a network. Each camera provides a view of some limited partial space out of the vast universe. These partial views obtained by plural cameras re-build the spatial universe in the system. The grid computer system provides with the car plate recognition system. The data base provides the linked information obtained through many cameras and car plate recognition system. The network connects all grid computer subsystems with the data base system.

Distributed computing over large networks often suffers poor performances due to architecture heterogeneity and synchronization delays. This is the case of classical computing libraries which are dedicated to parallel machines or clusters. To achieve a better efficiency on multisites heterogeneous networks, one can use asynchronous algorithms which are less sensible to communication delays and loss of messages. Implementing such algorithms with classical MPI versions is not the best choice. We propose Jace, a Java environment dedicated to distributed asynchronous computations, and more especially to asynchronous iterations-asynchronous communications algorithms. It contains all facilities to build a parallel virtual machine and to implement computing tasks in a message passing style. Communications have a special semantic adapted to asynchronism. First tests on a simple Jacobi algorithm clearly show the benefits of our environment to compute on a multisite heterogeneous network, that is, the grid.

Large-scale neutron facilities such as the Spallation Neutron Source (SNS) located at Oak Ridge National Laboratory need easy-to-use access to Department of Energy Leadership Computing Facilities and experiment repository data. The Orbiter thick- and thin-client and its supporting Service Oriented Architecture (SOA) based services (available at https://orbiter.sns.gov) consist of standards-based components that are reusable and extensible for accessing high performance computing, data and computational grid infrastructure, and cluster-based resources easily from a user configurable interface. The primary Orbiter system goals consist of (1) developing infrastructure for the creation and automation of virtual instrumentation experiment optimization, (2) developing user interfaces for thin- and thick-client access, (3) provide a prototype incorporating major instrument simulation packages, and (4) facilitate neutron science community access and collaboration. The secure Orbiter SOA authentication and authorization is achieved through the developed Virtual File System (VFS) services, which use Role-Based Access Control (RBAC) for data repository file access, thin-and thick-client functionality and application access, and computational job workflow management. The VFS Relational Database Management System (RDMS) consists of approximately 45 database tables describing 498 user accounts with 495 groups over 432,000 directories with 904,077 repository files. Over 59 million NeXus file metadata records are associated to the 12,800 unique NeXus file field/class names generated from the 52,824 repository NeXus files. Services that enable (a) summary dashboards of data repository status with Quality of Service (QoS) metrics, (b) data repository NeXus file field/class name full text search capabilities within a Google like interface, (c) fully functional RBAC browser for the read-only data repository and shared areas, (d) user/group defined and shared metadata for data repository files, (e) user, group, repository, and web 2.0 based global positioning with additional service capabilities are currently available. The SNS based Orbiter SOA integration progress with the Distributed Data Analysis for Neutron Scattering Experiments (DANSE) software development project is summarized with an emphasis on DANSE Central Services and the Virtual Neutron Facility (VNF). Additionally, the DANSE utilization of the Orbiter SOA authentication, authorization, and data transfer services best practice implementations are presented.

Fast operator splitting methods for obstacle problems

We present a distributed asynchronous algorithm for solving two-stage stochastic mixed-integer programs (SMIP) using scenario decomposition, aimed at industrial-scale instances of the stochastic unit commitment (SUC) problem. The algorithm is motivated by large differences in run times observed among scenario subproblems of SUC instances, which can result in inefficient use of distributed computing resources by synchronous parallel algorithms. Our algorithm performs dual iterations asynchronously using a block-coordinate subgradient descent method which allows performing block-coordinate updates using delayed information, while candidate primal solutions are recovered from the solutions of scenario subproblems using heuristics. We present a high performance computing implementation of the asynchronous algorithm, detailing the operations performed by each parallel process and the communication mechanisms among them. We conduct numerical experiments using SUC instances of the Western Electricity Coordinating Council system with up to 1000 scenarios and of the Central Western European system with up to 120 scenarios. We also conduct numerical experiments on generic SMIP instances from the SIPLIB library (DCAP and SSLP). The results demonstrate the general applicability of the proposed algorithm and its ability to solve industrial-scale SUC instances within operationally acceptable time frames. Moreover, we find that an equivalent synchronous parallel algorithm would leave cores idle up to 80.4% of the time on our realistic test instances, an observation which underscores the need for designing asynchronous optimization schemes in order to fully exploit distributed computing on real world applications.

IDR (s) is a family of fast algorithms for iteratively solving large nonsymmetric linear systems. With cluster computing and in particular with Grid computing, the inner product is a bottleneck operation. In this paper, three techniques are investigated for alleviating this bottleneck. First, a recently proposed IDR (s) algorithm that is highly efficient and stable is reformulated in such a way that it has a single global synchronization point per iteration step. Second, the so-called test matrix is chosen so that the work, communication, and storage involving this matrix is minimized in multi-cluster environments. Finally, a methodology is presented for a-priori estimation of the optimal value of s using only problem and machine-based parameters. Numerical experiments applied to a 3D convection–diffusion problem are performed on the DAS-3 Grid computer, demonstrating the effectiveness of our approach. Copyright © 2011 John Wiley & Sons, Ltd.

Grid Computing is a newly emerging technology that enables users to share a large number of computing resources distributed over a network. Due to that the grid computational resources are not storable, the advance reservation of these resources are necessary for users to request resources from multiple scheduling systems at a specific time. In this paper, we use auction-based scheduling method for resource reservation. We propose a variant version of traditional ascending auction for automatic resource reservation and introduce two novel heuristic strategies to guide agents on participating actions. We also compare our bidding strategies with several other different bidding strategies for the computational resource reservation in different scenarios. The results of experiments show that our heuristic bidding strategies outperforms those methods in those cases.

High-throughput proteome annotation refers to the activity of extracting information from all proteins in a particular organism using bioinformatics software on a high performance computing platform such as the grid. The Encyclopedia of Life (EOL) project [1] aims to catalog all proteins in all species for public benefits using an Integrative Genome Annotation Pipeline [2] (iGAP). The intrinsic complexity of the pipeline makes iGAP an ideal life sciences application to drive grid software development. It is a flagship application for the TeraGrid project [3]. The deployment of iGAP on the grid using grid middleware and mediator software has been described previously [4]. The heterogeneous and distributed computing environment on the grid requires an interactive user interface where jobs may be submitted and monitored. Here we describe our international collaborative effort in creating a grid portal solution for grid computing in life sciences under the auspices of PRAGMA [5]. Specifically, the development of GridMonitor for interactive monitor of iGAP workflow, and the use of a GridSpeed [6] generated iGAP application portal are described. The portal solution was part of the EOL demonstration at Supercomputing 2003 (SC'03) [7], where resources from 6 institutions on 5 continents are utilized to annotate more than 36,000 proteins from various species. It is a testimony to the necessity and expediency for international collaboration in an increasingly global grid computational environment to advance life sciences research.

Scheduling problems arise in many applications in process industries. However, despite various efforts to develop efficient scheduling methods, current approaches cannot be used to solve instances of industrial importance in reasonable time frames. The goal of this paper is the development of a dynamic decomposition framework that exploits the structure of the problem and is well suited for grid computing. The problem we study is the simultaneous batching and scheduling of multistage batch processes for which the binary decision variables are batch selection, batch-unit assignment, and batch sequencing on units. We present methods to decompose the original problem into a number of subproblems in a dynamic fashion. First, we discuss the generation of subproblems based on fixing the batch-selection variables. Second, we generate subproblems by fixing the batch-unit assignment variables in a bottlenecking stage. Third, we generate subproblems by fixing the last batch in the sequence on each unit of the bottlenecking stage. Furthermore, the second and third methods can be carried out in various combinations. Alternatively, a problem can be decomposed into a number of promising subproblems using an automatic strong branching scheme. Our results show that the proposed method can be used on a grid computer to solve large problems to optimality in a reasonable computational time.

In this work we present Zeus, a distributed timed model checker that evolves from the TCTL model checker Kronos [13] and that currently can handle backwards computation of reachability properties [2] over timed automata [3].Zeus was developed following a software architecture-centric approach. Its conceptual architecture was conceived to be sufficiently modular to house several features such as a priori graph partitioning, synchronous and asynchronous computation, communication piggybacking, delayed messaging, and dead-time utilization.Surprisingly enough, early experiments pinpointed the difficulties of getting speedups using asynchronous versions and showed interesting results on the synchronous counterpart, although being intuitively less attractive.

This paper deals with the numerical solution of financial applications, more specifically the computation of American and European options derivatives modeled by boundary value problems. In such applications we have to solve large-scale algebraic linear systems. We concentrate on synchronous and asynchronous parallel iterative algorithms carried out on Grid’5000, by using an experimental peer-to-peer platform. The properties of the operators arising in the discretized problem ensure the convergence of the parallel iterative synchronous and asynchronous algorithms. Different detection convergence algorithms are tested for asynchronous iterations. Computational experiments performed on distributed architectures are presented and analyzed.

The shape and size of a satellite adapter ring are optimized in this paper using particle swarm optimization and an in-house finite element program. For a realistic high-fidelity modeling of the adapter ring, a commercial preprocessor is used. However, optimization of a high-fidelity model inevitably involves longer computation time; therefore, parallelization is essential to shorten the total elapsed time. Furthermore, fitness evaluation time by the finite element simulation differs from case to case, which unavoidably causes idling of some of parallel computing resources. To overcome the inefficiency induced by the irregularities of individual fitness evaluation, an asynchronous parallel swarm algorithm is developed and applied to the structural optimization of the adapter ring with 19 design variables. The adapter ring’s total mass is reduced to 33.4 kg from 35.9 kg within 202 min. The asynchronous version also performs almost twice better compared with the synchronous one. The methodology proposed in this paper offers an attractive advantage for complex structural design, both in aspect of computational time and global search.

In this paper we are interested in studying the development of parallel algorithms to solve nonlinear wave equations. Both synchronous and asynchronous algorithms contexts are considered. The solver is based on the multisplitting Newton method that provides a coarse-grained scheme. Experiments are carried out in both homogeneous and heterogeneous grid environments. According to the configuration environment, the behaviors of parallel synchronous and asynchronous algorithms are analyzed. Experiments allow us to draw some conclusions about the use of parallel iterative algorithms in grid computing environment.

A new branch-and-Benders-cut algorithm for the time-dependent vehicle routing problem