Gravel: A Communication Library to Fast Path MPI
نویسندگان
چکیده
Remote Direct Memory Access (RDMA) technology allows data to move from the memory of one system into another system’s memory without involving either one’s CPU. This capability enables communication-computation overlapping, which is highly desirable for addressing the costly communication overhead in cluster computing. This paper describes the consumer-initiated and producer-initiated protocols of a companion library for MPI called Gravel. Gravel works in concert with MPI to achieve increased communication-computation overlap by separating the meta-data exchange from the application data exchange, thus allowing different communication protocols to be implemented at the application layer. We demonstrate performance improvements using Gravel for a set of communication patterns commonly found in MPI scientific applications.
منابع مشابه
Design of a VIA Based Communication Protocol for LAM/MPI Suite
The increasing use of System Area Network (SAN) demands efficient communication to benefit of SAN features through a direct access to network resources and avoiding kernel intervention in communication path. Recently, a consortium composed by Microsoft, Compaq and Intel authored a new standard, the Virtual Interface Architecture (VIA), designed to reduce software overhead in data transfers. Thi...
متن کاملThe performance of fast Givens rotations problem implemented with MPI extensions in multicomputers
In this paper, issues related to implementing an MPI version of the fast Givens rotations problem are investigated. We have chosen this algorithm because it has the feature of having no predictable communication pattern. Message Passing Interface (MPI) is an attempt to standardise the communication library for distributed memory computing systems. The message-passing paradigm is attractive beca...
متن کاملPolynomial-time Construction of Optimal Tree-structured Communication Data Layout Descriptions
We show that the problem of constructing tree-structured descriptions of data layouts that are optimal with respect to space or other criteria, from given sequences of displacements, can be solved in polynomial time. The problem is relevant for efficient compiler and library support for communication of non-contiguous data, where tree-structured descriptions with low-degree nodes and small inde...
متن کاملParallel FFT and Quick-Merge Sort on the Reflective Memory Networked Computers and a Cluster of Workstations
This paper is concerned with parallel FFT and Quick-Merge Sort. They are implemented on computers interconnected by VMIC 5579 reflective memory and a cluster of workstations (PCs) interconnected via Fast Ethernet. Message passing interface (MPI) parallel library is used for communication in a cluster of workstations. An improved parallel FFT is also presented to decrease an execution time in th...
متن کاملFlexible Intermediate Library for MPI-2 Support on an SCore Cluster System
A flexible intermediate library named Stampi for MPI-2 support on a heterogeneous computing environment has been implemented on an SCore cluster system. With the help of a flexible communication mechanism of this library, users can execute MPI functions without awareness of underlying communication mechanism. In message transfer of Stampi, a vendor-supplied MPI library and TCP sockets are used ...
متن کامل