Understanding the Behavior and Performance of Non-blocking Communications in MPI
نویسندگان
چکیده
The behavior and performance of MPI non-blocking message passing operations are sensitive to implementation specifics as they are heavily dependant on available system level buffers. In this paper we investigate the behavior of non-blocking communication primitives provided by popular MPI implementations and propose strategies for these primitives than can reduce processor synchronization overheads. We also demonstrate the improvements in the performance of a parallel Structured Adaptive Mesh Refinement (SAMR) application using these strategies.
منابع مشابه
Performance Comparison between Blocking and Non-Blocking Communications for a Three-Dimensional Poisson Problem
The system of linear equations obtained by finite difference discretization of the three-dimensional Poisson problem is solved by a matrix-free parallel implementation of the Jacobi method. After checking the convergence of our implementation, we compare the speed of using blocking MPI_Ssend/MPI_Recv and non-blocking MPI_Isend/MPI_Irecv communications. The comparisons indicate that the non-bloc...
متن کاملA Comparative Study of the MPI Communication Primitives on a Cluster
MPI (Message Passing Interface) has become the de facto standard for implementing parallel programs on distributed systems. In MPI, the two basic communication primitives are pointto-point communication and broadcast respectively. In this paper, we evaluate and compare the performance of broadcast with point-to-point communication (both blocking and non-blocking) of the MPI-1 standard library o...
متن کاملPerformance Simulation of Non-blocking Communication in Message-Passing Applications
In our previous work [1], we introduced performance simulation as an instrument to verify hypotheses on causality between locally and spatially distant performance phenomena without altering the application itself. This is accomplished by modifying mpi event traces and using them to simulate hypothetical message-passing behavior. Here, we present enhancements to our approach, which was previous...
متن کاملArchitecture Specific Communication Optimizations for Structured Adaptive Mesh-refinement Applications
OF THE THESIS Architecture Specific Communication Optimizations for Structured Adaptive Mesh-Refinement Applications by Taher Saif Thesis Director: Professor Manish Parashar Dynamic Structured Adaptive Mesh Refinement (SAMR) techniques for solving partial differential equations provide a means for concentrating computational effort to appropriate regions in the computational domain. Parallel im...
متن کاملA Case for Standard Non-blocking Collective Operations
In this paper we make the case for adding standard nonblocking collective operations to the MPI standard. The non-blocking point-to-point and blocking collective operations currently defined by MPI provide important performance and abstraction benefits. To allow these benefits to be simultaneously realized, we present an application programming interface for non-blocking collective operations i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004