With the advent of the 64bit microprocessor, the virtual address space supported by a workstation will be large enough to permit the use of a single shared address space spanning a network of workstations as the primary abstraction provided by a distributed operating system. In such a system, built upon a software distributed shared memory, the programmer has considerable flexibility when choosing a mech-anism for interprocess communication. This flexibility permits the programmer to make a case-by-case choice between simplicity and performance when both goals are not simultaneously achievable. With the inclusion of mechanisms supporting protection and fault tolerance, we believe that such a system can provide the advantages of conventional message-based distributed operating systems (e.g., multi-ple protection domains, hidden data abstractions, simple client-server interface, and failure isolation), in addition to several other benefits (e.g., easy sharing of complex data structures between processes, transparent replication of server functions, and a uniform interface for all communication). 1

A new model of parallel computation is proposed, CLUMPS (Campbell's Lenient, Unified Model of Parallel Systems). This is composed of an abstract machine with an associated cost model, and aims to be more portable, reflective of costs, expressible and encouraging of more efficient implementations of algorithms than other existing models. It is shown that each basic parallel architecture class can congruently perform each other's computations, but the congruent simulation of each other's communication is not generally possible (where for a simulation to be congruent the simulation costs on the target architecture are asymptotically equivalent to the implementation costs on the native architectures). This is reflected in the CLUMPS abstract machine through its flexibility in terms of program control and memory access. The congruence requirement is relaxed so that though strict congruence may not be achieved according to the above definition, communication costs are reflectively accounted ...

Mether is a Distributed Shared Memory (DSM) that runs on Sun 1 workstations under the SunOS 4.0 operating system. User programs access the Mether address space in a way indistinguishable from other memory. Mether had a number of performance problems which we had also seen on a distributed shared memory called MemNet[2]. In this paper we discuss changes we made to Mether and protocols we developed to use Mether that minimize host load, network load, and latency. An interesting (and unexpected) result was that for one problem we studied the same "best" protocol for Mether is identical to the "best" protocol for MemNet[6]. The changes to Mether involve exposing an inconsistent store to the application and making access to the consistent and inconsistent versions very convenient; providing both demanddriven and data-driven semantics for updating pages; and allowing the user to specify that only a small subset of a page need be transferred. All of these operations are encoded in a few addr...

So much has already been written about everything that you can't nd out anything about it. | James Thurber, Lanterns and Lances (1961) Loosely-coupled distributed systems haveevolved using message passing as the main paradigm for sharing information. Other paradigms used in loosely-coupled distributed systems, such as rpc, are usually implemented on top of an underlying message-passing system. On the other hand, in tightly-coupled architectures, such asmulti-processor machines, the paradigm is usually based on shared memory with its attractively simple programming model. The shared-memory paradigm has recently been extended for use in more loosely-coupled architectures and is known as distributed shared memory (dsm [153, 178,58]) in this context. This chapter discusses some of the issues involved in the design and implementation of such adsm in loosely-coupled distributed systems and brie y discusses related work in other elds. In dsm systems, processes share data transparently across node boundaries � data faulting, location, and movement are handled by thedsm system. Among other things, this allows parallel programs designed to use the shared-memory abstraction to execute without modi cation on a

As an alternative to communication via messages or files, shared memory has the potential to be simpler, faster, and less wasteful of space. Unfortunately, the mechanisms available for sharing in most multi-user operating systems are difficult to use. As a result, shared memory tends to appear primarily in self-contained parallel applications, where library or compiler support can take care of the messy details. We see a tremendous opportunity to extend the advantages of sharing across application boundaries. We believe that these advantages can be realized without introducing major changes to the Unix programming model. In particular, we believe that it is both possible and desirable to incorporate shared memory segments into the hierarchical file system name space. Our approach has two components: First, we use dynamic linking to allow programs to access shared data and code in the same way they access ordinary (private) variables and functions. Second, we unify memory and files in...

Distributed shared memory (DSM) systems provide a shared memory programming paradigm on top of a physically distributed network of computers. The DSM system removes the necessity for programmers to move data explicitly between processors. The principle challenge in the development of an e cient DSM system lies in reducing the amount of communication necessary to maintain coherence to an absolute minimum. This thesis presents Brazos, a DSM system for use in an environment of symmetric multiprocessor (SMP) personal computers that are networked together by industry-standard 100 Mbps FastEthernet. Brazos is distinguished by its use of application-level multithreading, selective multicast, adaptive runtime mechanisms, and a unique performance history mechanism. Through the detailed analysis of twelve scientific programs, we show that Brazos outperforms the current state-of-the-art software DSM system by an average of 83%, and outperforms a version of the same DSM system that has been altered to take advantage of SMP personal computers by an average of 32%. Our results indicate that networks of commodity personal computers using available PC networks and operating systems can perform comparably on a wide variety of scientific applications to more traditional networks of high-end engineering workstations.

File systems that employ caching have been built for many years. However, most work in file systems has been done as part of monolithic operating systems. In this paper we give our experience with building a high-performance distributed file system on Spring, a highly modular operating system where system services such as file systems are provided as user-level servers. The Spring file system described in this paper supports cache coherent file data and attributes. It uses the virtual memory system to provide data caching and uses the operations provided by the virtual memory system to keep the data coherent. The file system uses a unique dynamic caching algorithm that allows per-machine caching file servers to be located when a file object is passed from one machine to another. A per-machine caching file server utilizes the virtual memory system to provide caching of data for read and write operations, and it has a private protocol with the remote file servers to cache file attributes...

This report describes a system called SAM that simplifies the task of programming machines with distributed address spaces by providing a shared name space and dynamic caching of remotely accessed data. SAM makes it possible to utilize the computational power available in networks of workstations and distributed memory machines, while getting the ease of programming associated with a single address space model. The global name space and caching are especially important for complex scientific applications with irregular communication and parallelism. SAM is based on the principle of tying synchronization with data accesses. Precedence constraints are expressed by accesses to single-assignment values, and mutual exclusion constraints are represented by access to data items called accumulators. Programmers easily express the communication and synchronization between processes using these operations; they can also use alternate paradigms that are built with the SAM primitives. Operations f...

We describe an algorithm and implementation of dynamic linking that allows one user process to link a program in another address space without compromising the security of the other address space and without requiring the linking process to enter kernel mode. The same technique can also be used to load program code into an existing address space, e.g., for debugging or other purposes. The implementation makes extensive use of objects in the Spring object-oriented operating system. We have extracted the dynamic linking function from our operating system, and have made it available to user programs as a replaceable library service. In the process, we have taken advantage of features present in a modern, object-oriented operating system to simplify the dynamic linker.

oatatioa ad :ato am//d acbiea. The components ff NIP am: a distributed abared eo ate otiisedram//d object-odeted rora6' : distdbti o oe: the 0dea ff tbe am//d ate. Theater deabea the :eimets /aaed o the Keords: Implicit Parallelism; Neorks oF Workstations; Lazy Task Creation; Distributed Shared Memos.