TreadMarks is a distributed shared memory (DSM) system for standard Unix systems such as SunOS and Ultrix. This paper presents a performance evaluation of TreadMarks running on Ultrix using DECstation-5000/240's that are connected by a 100-Mbps switch-based ATM LAN and a 10-Mbps Ethernet. Our objective is to determine the efficiency of a user-level DSM implementation on commercially available workstations and operating systems. We achieved good speedups on the 8-processor ATM network for Jacobi (7.4), TSP (7.2), Quicksort (6.3), and ILINK (5.7). For a slightly modified version of Water from the SPLASH benchmark suite, we achieved only moderate speedups (4.0) due to the high communication and synchronization rate. Speedups decline on the 10-Mbps Ethernet (5.5 for Jacobi, 6.5 for TSP, 4.2 for Quicksort, 5.1 for ILINK, and 2.1 for Water), reflecting the bandwidth limitations of the Ethernet. These results support the contention that, with suitable networking technology, DSM is a...

We evaluate the effect of processor speed, network characteristics, and software overhead on the performance of release-consistent software distributed shared memory. We examine five different protocols for implementing release consistency: eager update, eager invalidate, lazy update, lazy invalidate, and a new protocol called lazy hybrid. This lazy hybrid protocol combines the benefits of both lazy update and lazy invalidate. Our simulations indicate that with the processors and networks that are becoming available, coarse-grained applications such as Jacobi and TSP perform well, more or less independent of the protocol used. Medium-grained applications, such as Water, can achieve good performance, but the choice of protocol is critical. For sixteen processors, the best protocol, lazy hybrid, performed more than three times better than the worst, the eager update. Fine-grained applications such as Cholesky achieve little speedup regardless of the protocol used because of the frequency of synchronization operations and the high latency involved. While the use of relaxed memory models, lazy implementations, and multiple-writer protocols has reduced the impact of false sharing, synchronization latency remains a serious problem for software distributed shared memory systems. These results suggest that future work on software DSMs should concentrate on reducing the amount ofsynchronization or its effect.

In the mobile wireless computing environment of the future a large number of users equipped with low powered palmtop machines will query databases over the wireless communication channels. Palmtop based units will often be disconnected for prolonged periods of time due to the battery power saving measures; palmtops will also frequently relocate between different cells and connect to different data servers at different times. Caching of frequently accessed data items will be an important technique that will reduce contention on the narrow bandwidth wireless channel. However, cache invalidation strategies will be severely affected by the disconnection and mobility of the clients. The server may no longer know which clients are currently residing under its cell and which of them are currently on. We propose a taxonomy of different cache invalidation strategies and study the impact of client's disconnection times on their performance. We study ways to further improve the efficiency of the ...

We present a unified approach to locality optimization that employs both data and control transformations. Data transformations include changing the array layout in memory. Control transformations involve changing the execution order of programs. We have developed new techniques for compiler optimizations for distributed shared-memory machines, although the same techniques can be used for sequential machines with a memory hierarchy. Our compiler optimizations are based on an algebraic representation of data mappings and a new data locality model. We present a pure data transformation algorithm and an algorithm unifying data and control transformations. While there has been much work on control transformations, the opportunities for data transformations have been largely neglected. In fact, data transformations have the advantage of being applicable to programs that cannot be optimized with control transformations. The unified algorithm, which performs data and control transformations s...

Abstract not found

Massively parallel computers (MPC) are characterized by the distribution of memory among an ensemble of nodes. Since memory is physically distributed, MPC nodes communicate by sending data through a network. In order to program an MPC, the user may directly invoke low-level message passing primitives, may use a higher-level communications library, or may write the program in a data parallel language and rely on the compiler to translate language constructs into communication operations. Whichever method is used, the performance of communication operations directly affects the total computation time of the parallel application. Communication operations may be either point-to-point, which involves a single source and a single destination, or collective, in which more than two processes participate. This paper discusses the design of collective communication operations for current systems that use the wormhole routing switching strategy, in which messages are divided into small pieces and...

Distributed shared memory (DSM) is a software abstraction of shared memory on a distributed memory machine. One of the key problems in building an e cient DSM system is to reduce the amount ofcommunication needed to keep the distributed memories consistent. In this paper we presentfour techniques for doing so: (1) software release consistency � (2) multiple consistency protocols � (3) write-shared protocols � and (4) an update-with-timeout mechanism. These techniques have been implemented in the Munin DSM system. We compare the performance of seven application programs on Munin, rst to their performance when implemented using message passing and then to their performance when running on a conventional DSM system that does not embody the above techniques. On a 16-processor cluster of workstations, Munin's performance is within 5 % of message passing for four out of the seven applications. For the other three, performance is within 29 % to 33%. Detailed analysis of two of these three applications indicates that the addition of a function shipping capability would bring their performance within 7 % of the message passing performance. Compared to a conventional DSM system, Munin achieves performance improvements ranging from a few to several hundred percent, depending on the application.

Lately there has been increasing interest in the use of data dissemination as a means for delivering data from servers to clients in both wired and wireless environments. Using data dissemination, the transfer of data is initiated by servers, resulting in a reversal of the traditional relationship between clients and servers. In previous papers, we have proposed Broadcast Disks as a model for structuring the repetitive transmission of data in a broadcast medium. Broadcast Disks are intended for use in environments where, for either physical or application-dependent reasons, there is asymmetry in the communication capacity between clients and servers. Examples of such environments include wireless networks with mobile clients, cable and direct satellite broadcast, and information dispersal applications. Our initial studies of Broadcast Disks focused on the performance of the mechanism when the data being broadcast did not change. In this paper, we extend those results to incorporate the...

A distributed shared memory (DSM) system allows shared memory parallel programs to be executed on distributed memory multiprocessors. The challenge in building a DSM system is to achieve good performance over a wide range of shared memory programs without requiring extensive modifications to the source code. The performance challenge translates into reducing the amount of communication performed by the DSM system to that performed by an equivalent message passing program. This thesis describes four novel techniques for reducing the communication overhead of DSM, including: (i) the use of software release consistency, (ii) support for multiple consistency protocols, (iii) a multiple writer protocol, and (iv) an update timeout mechanism. Release consistency allows modifications of shared data to be handled via a delayed update queue, which masks network latencies. Providing multiple cons...

ing with credit is permitted. To copy otherwise, to republish, to post on servers, to redistribute to lists, or to use any component of this work in other works, requires prior specific permission and/or a fee. Permissions may be requested from Publications Dept, ACM Inc., 1515 Broadway, New York, NY 10036 USA, fax +1 (212) 869-0481, or permissions@acm.org. 2 \Delta M. J. Franklin et al. 1. INTRODUCTION 1.1 Client-Server Database System Architectures Advances in distributed computing and object-orientation have combined to bring about the development of a new class of database systems. These systems employ a client-server computing model to provide both responsiveness to users and support for complex, shared data in a distributed environment. Current relational DBMS products are based on a query-shipping approach in which most query processing is performed at servers; clients are primarily used to manage the user interface. In contrast, object-oriented database systems (OODBMS), whi...