MPI Communication in SMP Clusters
نویسنده
چکیده
The recent years have seen a considerable increase in the number of cluster systems. These systems provide a very good performance-cost ratio. However, in order to meet the requirements for ever-increasing computing power of present day applications, several SMP cluster systems have emerged. By deploying two or more processors per workstation can increase the performance of a cluster significantly. The introduction of SMP workstations to a cluster adds a new dimension to the communication between processors. The purpose of this paper is to discuss the impact of SMP workstations in a cluster with respect to the communication. The communication mechanisms are studied and their performances are evaluated. In addition, performance results from a special communication library called MPIT, which is optimized to handle communication operations in SMP clusters, are compared to the traditional communication schemes available for the SMP cluster environments. Key-Words: SMP, Clusters, Communication, MPI, Networks of workstations, message passing, performance evaluation
منابع مشابه
The Florida State University College of Arts
Clusters of Symmetric Multiprocessing (SMP) nodes with multi-core Chip Multiprocessors (CMP), also known as SMP-CMP clusters, are ubiquitous today. Message Passing Interface (MPI) is the de facto standard for developing message passing applications for such clusters. Most modern SMP-CMP clusters support Remote Direct Memory Access (RDMA), which allows for flexible and efficient communication sc...
متن کاملAsynchronous Parallel Programming Model for SMP Clusters
Our study proposes a novel MPI-only parallel programming model with improved performance for SMP clusters. By rescheduling tasks in a typical flat MPI solution, our model forces processors of an SMP node to work in different phases, thereby avoiding unneccessary communication and computation bottlenecks. This study achieves a significant performance improvement with a minimal programming effort...
متن کاملImproving Linpack Performance on SMP Clusters with Asynchronous MPI Programming
This study proposes asynchronous MPI, a simple and effective parallel programming model for SMP clusters, to reimplement the High PerformanceLinpack benchmark. The proposed model forces processors of an SMP node to work in different phases, thereby avoiding unneccessary communication and computation bottlenecks. As a result, we can achieve significant improvements in performance with a minimal ...
متن کاملCommunication Characteristics and Hybrid MPI/OpenMP Parallel Programming on Clusters of Multi-core SMP Nodes
Hybrid MPI/OpenMP and pure MPI on clusters of multicore SMP nodes involve several mismatch problems between the parallel programming models and the hardware architectures. Measurements of communication characteristics between cores on the same socket, on the same SMP node, and between SMP nodes on several platforms (including Cray XT4 and XT5) show that machine topology has a significant impact...
متن کاملSMP-Aware Message Passing Programming
The Message Passing Interface (MPI) is designed as an architecture independent interface for parallel programming in the shared-nothing, message passing paradigm. We briefly summarize basic requirements to a high-quality implementation of MPI for efficient programming of SMP clusters and related architectures, and discuss possible, mild extensions of the topology functionality of MPI, which, wh...
متن کامل