Abstract: This book constitutes the joint refereed post-proceedings of 20 workshops, one panel session, and one poster session held during the 13th European Conference on Object-Oriented Programming, ECOOP'99, in Lisbon, Portugal in June 1999. The volume presents overviews of the 20 workshops as well as more than 200 individual short presentations by the contributing authors in a coherent and systematic way. The wealth of up-to-date information provided spans the whole spectrum of object technology, from theoretical and foundational issues to applications in various domains.

Abstract: Aliasing in Object-Oriented Systems.

Abstract: This paper describes the design of a common message passing layer for implementing both MPI and PVM over the SCI interconnect in a workstation or PC cluster. The design is focused at obtaining low latency. The message layer encapsulates all necessary knowledge of the underlying interconnect and operating system. Yet, we claim that it can be used to implement such different message passing libraries as MPI and PVM without sacrificing efficiency. Initial results obtained from using the message layer in SCI clusters are presented.

Abstract: This short paper presents a system offering parallel persistent and polymorphic sets of objects, on the level of an existing general purpose object-oriented programming language, like Modula-3 and JAVA. The user of such a system gets distribution and persistence in the same natural way, as users of traditional systems get volatile arrays of numbers of objects. In addition, advantages are taken from sophisticated optimization techniques.

Abstract: Even the more or less "canonical'', lower-level architecture of information systems needs to be revisited from time to time. Notions like persistence and transactions belong traditionally to the area of database management systems. There are, however, many applications, such as CAD, VLSI design or simulation, which need persistence and could take advantage of transactions, but require especially fast implementations not provided by DBMS. In this paper we are describing a low-level transaction concept used to implement our parallel main memory object store (PPOST), to provide main memory access times combined with the safety and convenience of transactions.

Abstract: Low latencies for small messages are an important factor of efficient fine-grained parallel computation. The Active Messages concept provides this minimal overhead by eliminating certain parts of the critical path of sending and receiving messages, that is the context switch into the operating system kernel when using user-mode I/O, and multiple buffering in the network layer. Hardware-supported distributed shared memory (DSM) architectures exhibit various properties that make them particularly useful for an implementation of the aforementioned messaging mechanisms. This paper thus describes the concept, implementation, and the performance of a DSM-based Active Messages layer.

Abstract: To enable the efficient utilization of clusters of workstations it is crucial to develop a stable and rich software infrastructure. The ESPRIT Project SISCI will provide two widely used message-passing interfaces, MPI and PVM, as well as a POSIX compliant, distributed thread package (Pthreads) on multiple SCI-based clusters. This paper features motivation and background on this projects as well as details of the two core components: the common messaging layer and the Pthreads package.

Abstract: Active Messages haben sich als effizientes Kommunikationsverfahren insbesondere auf Kommunikationstechnologien durchgesetzt, die einen direkten Zugriff des Benutzers ohne Intervention des Betriebssystems zulassen. Als Nachteil der leichtgewichtigen Kommunikation erwiesen sich jedoch die nicht ausreichenden Schutzmechanismen, vor allem bei der Verwendung mehrerer Prozesse, die sich gleichzeitig einer Active-Message-Bibliothek bedienen. Die Spezifikation 2.0 der Berkeley-Active-Messages unternimmt nun den Versuch, f¨ur das bekannte und schnelle Kommunikationsverfahren Schutzabstraktionen vorzusehen. Im Rahmen dieser Arbeit wird die Implementation eines solchen Active-Message-Layers der Version 2.0 auf einem Cluster von SCI-gekoppelten Arbeitsplatzrechnern beschrieben. Wir k¨onnen zeigen, daß die zus¨atzlichen Schutzmechanismen nur wenig Einfluß auf die Leistung haben und somit der Vorteil der Active Messages, die leichtgewichtige, feingranulare Kommunikation, erhalten bleibt.

Abstract: Active Messages haben sich als effizientes Kommunikationsverfahren insbesondere auf Kommunikationstechnologien durchgesetzt, die einen direkten Zugriff des Benutzers ohne Intervention des Betriebssystems zulassen. Als Nachteil der leichtgewichtigen Kommunikation erwiesen sich jedoch die nicht ausreichenden Schutzmechanismen, vor allem bei der Verwendung mehrerer Prozesse, die sich gleichzeitig einer Active-Message- Bibliothek bedienen. Die Spezifikation 2.0 der Berkeley-Active-Messages unternimmt nun den Versuch, für das bekannte und schnelle Kommunikationsverfahren Schutzabstraktionen vorzusehen. Im Rahmen dieser Arbeit wird die Implementation eines solchen Active- Message-Layers der Version 2.0 auf einem Cluster von SCI-gekoppelten Arbeitsplatzrechnern beschreiben. Wir können zeigen, daß die zusätzlichen Schutzmechanismen nur wenig Einfluß auf die Leistung haben und somit der Vorteil der Active Messages, die leichtgewichtige, feingranulare Kommunikation, erhalten bleibt.

Abstract: Choosing the "First Computer Language" is still a crucial issue. While the debate is quite often conducted on the language level, the arguments for making the choice are rather of much deeper methodological, didactical, and non-technical nature. Here, we describe the decision process that lead us to choose Modula-3 as the first language to be taught to informatics students at the Universität Klagenfurt and report on the experience gained.

Abstract: An extension of a general-purpose programming language (gpPL) is presented. It enables parallelism, persistence and query optimization based on sets. The authors demonstrate that in gpPLs the primitive "set" can be generalised for the needs of database and expert system applications. Side-effect free declarative queries, based on set expressions, can be optimized and executed in parallel. Individual optimization and parallelization are integral parts of the language system and compiler. Very different combinations of persistent or volatile, and parallel or sequential, and optimized or non-optimized implementations are possible. This is eased by the fact that a great part of the implementation is located outside the compiler with the help of predefined interfaces. Different algebras, optimizers or algorithms can be considered. The same program can be executed without modification in various systems or platforms.

Abstract: An approach to accelerate distributed, object-oriented simulations is presented in this paper. It is based on the assumption that a higher acceleration can be achieved in an easier way, if the problem is alread tackled early at the modeling stage [STOP 95]. The user adds hints about the communication behavior and frequencies of object classes to the simulation model. Based on this information, an object graph is generated and distributed to a selected number of partitions. The distribution phase is fully automatic. As a result a distribution of the problem nearby the communication optimum is generated. In the next phase the distributed simulation program (code) is generated. In a final step the user only has to code the methods of the object classes and run the simulation. The major advantage of this approach is that the user is freed from the difficult task of finding a good distribution for the problem to be simulated, which is an important factor for the overall performance of the simulation. Another advantage is the possibility to vary model information (hints) about the communication, and get a new (quasi optimal) version of the simulation automatically generated.

Abstract: A hint-based, distributed, discrete, object-oriented simulation system is described. In course of the design phase of the simulation model, explicit hints can be provided concerning dependencies and information flow inside the model. The process of parallelization consists of two major steps. In the first step, the abstract model, enriched with user-supplied hints is mapped onto an arbitrary number of active units. In the second step, the active units are mapped onto a given number of physical nodes, characterized by their processing capacity and by the communication latency between them. The distribution scheme may be dynamic, i.e. simulation objects can change their location in course of the simulation, in order to get better performance. Klaus.Leopold 05.04.2001.

Abstract: Parallel and persistent object sets are suggested to be incorporated into general-purpose programming languages. Two alternative implementations are presented. The actual form of the proposal is an extension of Modula-3.

Abstract: Our work explores the practical relevance of Randomized Shared Memory (RSM), a theoretical concept that has been proven to enable an (asymptotically) optimally efficient implementation of scalable and universal shared memory in a distributed-memory parallel system. RSM (address hashing) pseudo-randomly distributes global memory addresses throughout the nodes' local memories. High memory access latencies are masked through massive parallelism. This paper introduces the basic principles and properties of RSM and analyzes its practical efficiency in terms of constant factors through simulation studies, assuming a state-of-the-art parallel architecture. Bottlenecks in the architecture are pointed out, and improvements are being made and their effects assessed quantitatively. The results show that RSM efficiency is encouragingly high, even in a non-optimized architecture. We propose architectural features to support RSM and conclude that RSM may indeed be a feasible shared-memory implementation in future massively parallel computers.

Abstract: This paper analyzes the efficiency of Randomized Shared Memory (RSM) in terms of constant factors. RSM or memory hashing, that is, pseudorandom distribution of global memory addresses throughout local memories in a distributed-memory parallel system, has been proven to enable an (asymptotically) optimally efficient implementation of scalable and universal shared memory. High memory access latencies are hidden through massive parallelism. Our work examines the practical relevance and feasibility of this potentially significant theoretical result. After an introduction of the background, principles, and desirable properties of RSM and an outline of the approach to determine RSM efficiency, the major results of our simulations are presented. The results show that RSM efficiency is encouragingly high (up to 20% efficiency of idealized shared memory), even in an architecture modelled on the basis of state-of-the-art technology. Performance-limiting factors are identified from the results and architectural features to increase efficiency are proposed, most notably extremely fast process switching and a combining network. Several novel machine designs document the increased interest in RSM and hardware support.