- 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
- 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
- 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
Thread Migration @ Purdue under Prof Rego 1993-99
Thread Migration @ Purdue under Prof Rego 1993-99 The Xthreads Library: Design 1993 Sang Xthreads Implementation, and Applications Thread Migration on Distributed- 1994 Sang Xthreads + migration Memory Multiprocessors Thread Migration on Heterogeneous 1994 Sang Xthreads + generating Systems via Compile-Time Transformations thread’s logical state Multithreading in Distributed-Memory 1994 Sang Systems and Simulation: Design, Implementation, Experiments A System for Multithreading Parallel 1996 Mascarenhas Ariadne Simulation and Computation with Migrant Threads Objects Ariadne: Architecture of a Portable 1996 Mascarenhas Ariadne: design, Threads system supporting Thread Migration implementation, performance Migrant threads on process farms: 1998 Mascarenhas Ariadne: customized features with Parallel programming with Ariadne parallel programming model, examples Arachne: A Portable Threads 1999 Dimitrov Arachne: dynamic stack size, recursive System Supporting Migrant Threads thread functions on Heterogeneous Network Farms Xthreads A user-space threads library on homogeneous machines - At that time, pthread not yet finalized Patterned after the Xinu operating system implemented on nCUBE2, iPSC860, RS6000 distributed-memory multiprocessors (Unix) motivation: lighter overhead (than heavy process) associated with creation, context-switching, interprocess communication, and other routine functions. - purpose: provide a cheap concurrent programming environment supports Si, a simulation system – originally based on Sun Light Weight Process (LWP) library, lacking portability User-level threads (vs kernel-level threads): advantage: requires no intervention from OS kernel, hence more efficient disadvantage: performance loss when invoking a blocking system call or encountering a page fault System memory: code + data + dynamic heap + runtime stack Each thread has own stack and heap stack is preallocated at system init, reducing
文档评论(0)