tailieunhanh - DISTRIBUTED AND PARALLEL SYSTEMSCLUSTER AND GRID COMPUTING 2005 phần 8

Trong thời hạn WebCom-G nhiệm vụ trình tự được thể hiện như một đồ thị đặc [13]. Thực hiện nhiệm vụ được thực hiện bằng cách sử dụng các mô-đun Thực hiện động cơ phù hợp. Hỗ trợ cho các ứng dụng di sản được cung cấp bằng cách biên dịch hoặc dịch mã hiện tại thành một đại diện trung gian được thể hiện như một đồ thị đặc. | 149 2. Program Execution in WebCom-G Figure 1. Annotation and Extraction. Within WebCom-G task sequencing is expressed as a Condensed Graph 13 . Task execution is carried out using appropriate Execution Engine modules. Support for legacy applications is provided by compiling or translating existing code into an intermediate representation expressed as a Condensed Graph. This support is provided by two methodologies called Extraction and Annotation. Extraction Extraction is a process of translating higher level specifications into Condensed Graph representation. This process is suitable for specification languages such as the Globus Resource Specification Language RSL 12 for example. RSL specifies the list of tasks to be executed and their associated configurations. During extraction tasks specified in the RSL will be expressed as nodes in a Condensed Graph. In addition the task sequencing constraints specified in the RSL script are represented as arcs in the resulting Condensed Graph. For extraction this Condensed Graph can be specified as an XML document. WebCom-G can dynamically load and execute Condensed Graphs specified in XML. Condensed Graph applications executed by WebCom-G receive all the benefits of the WebCom-G system including transparent support for fault tolerance load balancing scheduling and security. Hence tasks extracted from RSL scripts also benefit from these WebCom-G features. For example if the 150 DISTRIBUTED AND PARALLEL SYSTEMS Figure 2. The process of generating a Condensed Graph from sequential code. job should fail to execute WebCom-G will reschedule the job for execution at a later time. A different approach has to be adopted for traditional high level languages like C C and Java. These languages are typically not optimised for execution in distributed environments as they normally consist of sequential code. Attempting to parallelise sequential code is not trivial. A Condensed Graphs compiler is used to parallelise sequential .