{"title":"分布式松弛队列在计算机系统远程内存访问模型设计与诊断中的应用","authors":"A. Paznikov, Leti","doi":"10.17223/19988605/50/12","DOIUrl":null,"url":null,"abstract":"реа-лизована стандарте (Message и применяется в семейства (Partitioned Global Remote memory access (RMA) technique is a very attractive way for improving efficiency of high-performance computations (HPC) and simplifying parallel program development. Unlike message-passing, in RMA programs processes communicate by directly accessing each other’s memories. RMA model is implemented in MPI standard and offers Partitioned Global Address Space (PGAS). Many applications have been shown to benefit from RMA communications, where a process directly accesses the memory of another process instead of sending and receiving messages. To the best of knowledge, there are no efficient scalable concurrent data structures designed in RMA model. eliminates bottlenecks, minimizes latency of the operations and provides high scalability of parallel programs.","PeriodicalId":0,"journal":{"name":"","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Distributed relaxed queue in remote memory access model designing and diagnostics of computer systems\",\"authors\":\"A. Paznikov, Leti\",\"doi\":\"10.17223/19988605/50/12\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"реа-лизована стандарте (Message и применяется в семейства (Partitioned Global Remote memory access (RMA) technique is a very attractive way for improving efficiency of high-performance computations (HPC) and simplifying parallel program development. Unlike message-passing, in RMA programs processes communicate by directly accessing each other’s memories. RMA model is implemented in MPI standard and offers Partitioned Global Address Space (PGAS). Many applications have been shown to benefit from RMA communications, where a process directly accesses the memory of another process instead of sending and receiving messages. To the best of knowledge, there are no efficient scalable concurrent data structures designed in RMA model. eliminates bottlenecks, minimizes latency of the operations and provides high scalability of parallel programs.\",\"PeriodicalId\":0,\"journal\":{\"name\":\"\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0,\"publicationDate\":\"2020-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.17223/19988605/50/12\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.17223/19988605/50/12","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Distributed relaxed queue in remote memory access model designing and diagnostics of computer systems
реа-лизована стандарте (Message и применяется в семейства (Partitioned Global Remote memory access (RMA) technique is a very attractive way for improving efficiency of high-performance computations (HPC) and simplifying parallel program development. Unlike message-passing, in RMA programs processes communicate by directly accessing each other’s memories. RMA model is implemented in MPI standard and offers Partitioned Global Address Space (PGAS). Many applications have been shown to benefit from RMA communications, where a process directly accesses the memory of another process instead of sending and receiving messages. To the best of knowledge, there are no efficient scalable concurrent data structures designed in RMA model. eliminates bottlenecks, minimizes latency of the operations and provides high scalability of parallel programs.