Performance Expectations and Guidelines for MPI Derived Datatypes
Performance Expectations and Guidelines for MPI Derived Datatypes
复制标题
DOI：
10.1007/978-3-642-24449-0_18
复制
发表时间：
2011-09
期刊：
影响因子：
--
通讯作者：
W. Gropp;T. Hoefler;R. Thakur;J. Träff
中科院分区：
文献类型：
--
作者：
W. Gropp;T. Hoefler;R. Thakur;J. Träff
MPI的派生数据库提供了一种强大的机制，用于简洁地描述MPI通信中使用的用户数据的任意、非连续布局。本文为派生数据库制定了自洽的性能准则。这样的指导方针使派生数据库的性能预期明确，并建议MPI实现相关的优化。我们还确定了自我一致的指导方针，过于严格的强制执行，因为它们涉及NP-难优化问题。强制执行的自我一致的指导方针向用户保证，某些手动数据类型优化不会导致性能改进，这反过来又有助于根据指导方针执行的MPI实现之间的性能可移植性。我们提出了几个MPI实现的测试结果，这表明他们中的许多人违反了准则。
MPI’s derived datatypes provide a powerful mechanism for concisely describing arbitrary, noncontiguous layouts of user data for use in MPI communication. This paper formulatesself-consistent performance guidelinesfor derived datatypes. Such guidelines make performance expectations for derived datatypes explicit and suggest relevant optimizations to MPI implementers. We also identify self-consistent guidelines that are too strict to enforce, because they entail NP-hard optimization problems. Enforced self-consistent guidelines assure the user that certain manual datatype optimizations cannot lead to performance improvements, which in turn contributes to performance portability between MPI implementations that behave in accordance with the guidelines. We present results of tests with several MPI implementations, which indicate that many of them violate the guidelines.