翻訳と辞書 |
Automatic parallelization tool : ウィキペディア英語版 | Automatic parallelization tool
For several years parallel hardware was only available for distributed computing but recently it is becoming available for the low end computers as well. Hence it has become inevitable for software programmers to start writing parallel applications. It is quite natural for programmers to think sequentially and hence they are less acquainted with writing multi-threaded or parallel processing applications. Parallel programming requires handling various issues such as synchronization and deadlock avoidance. Programmers require added expertise for writing such applications apart from their expertise in the application domain. Hence programmers prefer to write sequential code and most of the popular programming languages support it. This allows them to concentrate more on the application. Therefore there is a need to convert such sequential applications to parallel applications with the help of automated tools. The need is also non-trivial because large amount of legacy code written over the past few decades needs to be reused and parallelized. ==Need for automatic parallelization==
Past techniques provided solutions for languages like FORTRAN and C; however, these are not enough. These techniques dealt with parallelization sections with specific system in mind like loop or particular section of code. Identifying opportunities for parallelization is a critical step while generating multithreaded application. This need to parallelize applications is partially addressed by tools that analyze code to exploit parallelism. These tools use either compile time techniques or run-time techniques. These techniques are built-in in some parallelizing compilers but user needs to identify parallelize code and mark the code with special language constructs. The compiler identifies these language constructs and analyzes the marked code for parallelization. Some tools parallelize only special form of code like loops. Hence a fully automatic tool for converting sequential code to parallel code is required.〔“Increasing Parallelism on Multicore Processors Using Induced Parallelism”, by Vinay G. Vaidya, PushpRaj Agrawal, Aditi Athavale, Anish Sane, Sudhakar Sah and Priti Ranadive〕
抄文引用元・出典: フリー百科事典『 ウィキペディア(Wikipedia)』 ■ウィキペディアで「Automatic parallelization tool」の詳細全文を読む
スポンサード リンク
翻訳と辞書 : 翻訳のためのインターネットリソース |
Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.
|
|