The Real-Time Message Passing Interface (MPI/RT) is a communication layer middleware standard that is aimed at providing guaranteed Quality of Service for data transfers on high performance networks. It poses “middleout” requirements both on applications and on the operating system. In this paper, we consider the “middledown” issues by modifying a POSIX compliant operating system in order to su...

High-end computing is universally recognized to be a strategic tool for leadership in science and technology. A significant portion of high-end computing is conducted on clusters running the Message Passing Interface (MPI) library. MPI has become the de facto standard in high performance computing (HPC). Our research addresses the need to avoid bugs in MPI programs through a combination of tech...

The lack of a portable parallel I/O interface limits the development of scientiic applications. MPI-IO is the rst widespread attempt to alleviate this problem. Its eecient implementation requires the developer to face and solve several software design and interface issues. Our paper outlines strategies, which may be helpful in this task. Although originally targeted for the NEC Cenju-3, our con...

Many common implementations of Message Passing Interface (MPI) implement collective operations over point-to-point operations. This work examines IP multicast as a framework for collective operations. IP multicast is not reliable. If a receiver is not ready when a message is sent via IP multicast, the message is lost. Two techniques for ensuring that a message is not lost due to a slow receivin...

With the advent of high-speed LANs and rapid development of PC technologies, the communication software evolution has lagged behind. Traditional communication protocol stacks fail to deliver much of the performance of physical network to user applications. So efficient communication protocols are needed to take full advantage of the high performance of underlying interconnection networks. This ...

This paper presents the StarT X PCI card a net work interface unit for the Arctic Switch Fabric StarT X provides a user level hardware interface for message passing on a cluster of PCI equipped host platforms StarT X supports three message passing mechanisms that are tuned for di erent granularities of communication On a SUN E with StarT X a processor can send and receive a byte message in less...

ADAPTOR is a public domain High Performance Fortran compilation system that provides the comfortable data parallel programming paradigm on parallel machines with distributed memory. Therefore, the data parallel programs with their global view of data are translated to programs that work on the local parts of the distributed data and exchange the other needed data via message passing. This paper...

High-Performance Computing (HPC) research, from hardware and software to the end applications, provides remarkable computing power help scientists solve complex problems in science, engineering, or even daily business. Over last decades, Message Passing Interface (MPI) libraries have been powering numerous scientific such as weather forecasting, earthquake simulations, physic, chemical conduct ...

This paper shows how functional programming techniques have been successfully applied to relieve a performance bottleneck in an MPI collective communication operation. A functional speciication for the improved operation is given, and an eecient version implementable in an imperative language is derived and proved correct. Experimental results on an IBM SP2 distributed{memory machine connrm the...

The Message Passing Interface (MPI) is the de facto standard for writing parallel scientific applications in the message passing programming paradigm. Implementations of MPI were not designed to interoperate, thereby limiting the environments in which parallel jobs could be run. We briefly describe a set of protocols, designed by a steering committee of current implementors of MPI, that enable ...