Management of SPMD based parallel processing on clusters of workstations

Current attempts to manage parallel applications on Clusters of Workstations (COWs) have either generally followed the parallel execution environment approach or been extensions to existing network operating systems, both of which do not provide complete or satisfactory solutions. The efficient and transparent management of parallelism within the COW environment requires enhanced methods of process instantiation, mapping of parallel process to workstations, maintenance of process relationships, process communication facilities, and process coordination mechanisms. The aim of this research is to synthesise, design, develop and experimentally study a system capable of efficiently and transparently managing SPMD parallelism on a COW. This system should both improve the performance of SPMD based parallel programs and relieve the programmer from the involvement into parallelism management in order to allow them to concentrate on application programming. It is also the aim of this research to show that such a system, to achieve these objectives, is best achieved by adding new special services and exploiting the existing services of a client/server and microkernel based distributed operating system. To achieve these goals the research methods of the experimental computer science should be employed. In order to specify the scope of this project, this work investigated the issues related to parallel processing on COWs and surveyed a number of relevant systems including PVM, NOW and MOSIX. It was shown that although the MOSIX system provide a number of good services related to parallelism management, none of the system forms a complete solution. The problems identified with these systems include: instantiation services that are not suited to parallel processing; duplication of services between the parallelism management environment and the operating system; and poor levels of transparency. A high performance and transparent system capable of managing the execution of SPMD parallel applications was synthesised and the specific services of process instantiation, process mapping and process interaction detailed. The process instantiation service designed here provides the capability to instantiate parallel processes using either creation or duplication methods and also supports multiple and group based instantiation which is specifically design for SPMD parallel processing. The process mapping service provides the combination of process allocation and dynamic load balancing to ensure the load of a COW remains balanced not only at the time a parallel program is initialised but also during the execution of the program. The process interaction service guarantees to maintain transparently process relationships, communications and coordination services between parallel processes regardless of their location within the COW. The combination of these services provides an original architecture and organisation of a system that is capable of fully managing the execution of SPMD parallel applications on a COW. A logical design of a parallelism management system was developed derived from the synthesised system and was shown that it should ideally be based on a distributed operating system employing the client server model. The client/server based distributed operating system provides the level of transparency, modularity and flexibility necessary for a complete parallelism management system. The services identified in the synthesised system have been mapped to a set of server processes including: Process Instantiation Server providing advanced multiple and group based process creation and duplication; Process Mapping Server combining load collection, process allocation and dynamic load balancing services; and Process Interaction Server providing transparent interprocess communication and coordination. A Process Migration Server was also identified as vital to support both the instantiation and mapping servers. The RHODOS client/server and microkernel based distributed operating system was selected to carry out research into the detailed design and to be used for the implementation this parallelism management system. RHODOS was enhanced to provide the required servers and resulted in the development of the REX Manager, Global Scheduler and Process Migration Manager to provide the services of process instantiation, mapping and migration, respectively. The process interaction services were already provided within RHODOS and only required some extensions to the existing Process Manager and IPC Managers. Through a variety of experiments it was shown that when this system was used to support the execution of SPMD parallel applications the overall execution times were improved, especially when multiple and group based instantiation services are employed. The RHODOS PMS was also shown to greatly reduce the programming burden experienced by users when writing SPMD parallel applications by providing a small set of powerful primitives specially designed to support parallel processing. The system was also shown to be applicable and has been used in a variety of other research areas such as Distributed Shared Memory, Parallelising Compilers and assisting the port of PVM to the RHODOS system. The RHODOS Parallelism Management System (PMS) provides a unique and creative solution to the problem of transparently and efficiently controlling the execution of SPMD parallel applications on COWs. Combining advanced services such as multiple and group based process creation and duplication; combined process allocation and dynamic load balancing; and complete COW wide transparency produces a totally new system that addresses many of the problems not addressed in other systems.

Grid transaction management and an efficient development kit

Grid transaction management aims at guaranteeing the system consistency in face of various failures in Grid environments. In this paper, we propose a Grid transaction service (GridTS) and design coordination mechanisms for atomic, long-lived and real-time Grid transactions respectively, based on the features of Grid environments. GridTS has the following three advantages. Firstly, it separates the transaction management unit with transaction coordination algorithms so that it can coordinate the above three categories of transactions in a uniform way. Secondly, GridTS can dynamically generate compensating transactions during the long-lived transaction processing. Finally, it provides the programming interfaces similar to traditional distributed transactions. Moreover, we implement a Grid transaction development kit (GridTDK) for application programmers based on our GridTS. We evaluate the feasibility and effectiveness of GridTS by developing an application system using our GridTDK. ©2012 CRL Publishing Ltd.

Online motor control in children with developmental coordination disorder: chronometric analysis of double-step reaching performance

Background
Although there are a number of plausible accounts to explain movement clumsiness in children [or developmental coordination disorder (DCD)], the cause(s) of the disorder remain(s) an issue of debate. One aspect of motor control that is particularly important to the fluid expression of skill is rapid online control (ROC). Data on DCD have been conflicting. While some recent work using double-step reaching suggests no difficulty in online control, others suggest deficits (e.g. based on sequential pointing). To help resolve this debate, we suggest two things: use of recent neuro-computational models as a framework for investigating motor control in DCD, and more rigorous investigation of double-step reaching. Our working assumption here is that ROC is only viable through the seamless integration of predictive (or forward) models of movement and feedback-based mechanisms.

Aim
The aim of this chronometric study was to explore ROC in children with DCD using a double-step reaching paradigm. We predicted slower online adjustments in DCD based on the argument that these children manifest a core difficulty in predictive control.

Methods
Participants were a group of 17 children with DCD and 27 typically developing children aged between 7 and 12 years. Visual targets were presented on a 17-inch LCD touch screen, inclined to an angle of 15° from horizontal. The children were instructed to press each target as it appeared as quickly and accurately as possible. For 80% of the trials, the central target location remained unchanged for the duration of the movement (non-jump trials), while for the remaining 20% of trials, the target jumped at movement onset to one of the two peripheral locations (jump trials). Reaction time (RT), movement time (MT) and reaching errors were recorded.

Results
For both groups, RT did not vary according to trial condition, while children with DCD were slower to initiate movement. Further, the MT of children with DCD was prolonged to a far greater extent on jump trials relative to controls, with a large effect size. As well, children with DCD committed significantly more errors, notably a reduced ability to inhibit central responses on jump trials.

Conclusion
Our findings help reconcile some disparate findings in the literature using similar tasks. The pattern of performance in children with DCD suggests impairment in the ability to make rapid online adjustments that are based on a predictive (or internal) model of the action. These results pave the way for future kinematic investigation.