Showing papers on "Scalability published in 2004"

A survey of peer-to-peer content distribution technologies

Abstract: Distributed computer architectures labeled "peer-to-peer" are designed for the sharing of computer resources (content, storage, CPU cycles) by direct exchange, rather than requiring the intermediation or support of a centralized server or authority. Peer-to-peer architectures are characterized by their ability to adapt to failures and accommodate transient populations of nodes while maintaining acceptable connectivity and performance.Content distribution is an important peer-to-peer application on the Internet that has received considerable research attention. Content distribution applications typically allow personal computers to function in a coordinated manner as a distributed storage medium by contributing, searching, and obtaining digital content.In this survey, we propose a framework for analyzing peer-to-peer content distribution technologies. Our approach focuses on nonfunctional characteristics such as security, scalability, performance, fairness, and resource management potential, and examines the way in which these characteristics are reflected in---and affected by---the architectural design decisions adopted by current peer-to-peer systems.We study current peer-to-peer systems and infrastructure technologies in terms of their distributed object location and routing mechanisms, their approach to content replication, caching and migration, their support for encryption, access control, authentication and identity, anonymity, deniability, accountability and reputation, and their use of resource trading and management schemes.

Modeling and performance analysis of BitTorrent-like peer-to-peer networks

Abstract: In this paper, we develop simple models to study the performance of BitTorrent, a second generation peer-to-peer (P2P) application. We first present a simple fluid model and study the scalability, performance and efficiency of such a file-sharing mechanism. We then consider the built-in incentive mechanism of BitTorrent and study its effect on network performance. We also provide numerical results based on both simulations and real traces obtained from the Internet.

Simulating the power consumption of large-scale sensor network applications

Abstract: Developing sensor network applications demands a new set of tools to aid programmers. A number of simulation environments have been developed that provide varying degrees of scalability, realism, and detail for understanding the behavior of sensor networks. To date, however, none of these tools have addressed one of the most important aspects of sensor application design: that of power consumption. While simple approximations of overall power usage can be derived from estimates of node duty cycle and communication rates, these techniques often fail to capture the detailed, low-level energy requirements of the CPU, radio, sensors, and other peripherals.In this paper, we present, a scalable simulation environment for wireless sensor networks that provides an accurate, per-node estimate of power consumption. PowerTOSSIM is an extension to TOSSIM, an event-driven simulation environment for TinyOS applications. In PowerTOSSIM, TinyOS components corresponding to specific hardware peripherals (such as the radio, EEPROM, LEDs, and so forth) are instrumented to obtain a trace of each device's activity during the simulation runPowerTOSSIM employs a novel code-transformation technique to estimate the number of CPU cycles executed by each node, eliminating the need for expensive instruction-level simulation of sensor nodes. PowerTOSSIM includes a detailed model of hardware energy consumption based on the Mica2 sensor node platform. Through instrumentation of actual sensor nodes, we demonstrate that PowerTOSSIM provides accurate estimation of power consumption for a range of applications and scales to support very large simulations.

Mercury: supporting scalable multi-attribute range queries

Abstract: This paper presents the design of Mercury, a scalable protocol for supporting multi-attribute range-based searches. Mercury differs from previous range-based query systems in that it supports multiple attributes as well as performs explicit load balancing. To guarantee efficient routing and load balancing, Mercury uses novel light-weight sampling mechanisms for uniformly sampling random nodes in a highly dynamic overlay network. Our evaluation shows that Mercury is able to achieve its goals of logarithmic-hop routing and near-uniform load balancing.We also show that Mercury can be used to solve a key problem for an important class of distributed applications: distributed state maintenance for distributed games. We show that the Mercury-based solution is easy to use, and that it reduces the game's messaging overheard significantly compared to a naive approach.

Approximate aggregation techniques for sensor databases

Abstract: In the emerging area of sensor-based systems, a significant challenge is to develop scalable, fault-tolerant methods to extract useful information from the data the sensors collect. An approach to this data management problem is the use of sensor database systems, exemplified by TinyDB and Cougar, which allow users to perform aggregation queries such as MIN, COUNT and AVG on a sensor network. Due to power and range constraints, centralized approaches are generally impractical, so most systems use in-network aggregation to reduce network traffic. However, these aggregation strategies become bandwidth-intensive when combined with the fault-tolerant, multipath routing methods often used in these environments. For example, duplicate-sensitive aggregates such as SUM cannot be computed exactly using substantially less bandwidth than explicit enumeration. To avoid this expense, we investigate the use of approximate in-network aggregation using small sketches. Our contributions are as follows: 1) we generalize well known duplicate-insensitive sketches for approximating COUNT to handle SUM, 2) we present and analyze methods for using sketches to produce accurate results with low communication and computation overhead, and 3) we present an extensive experimental validation of our methods.

UbiCrawler: a scalable fully distributed web crawler

Abstract: We report our experience in implementing UbiCrawler, a scalable distributed Web crawler, using the Java programming language. The main features of UbiCrawler are platform independence, linear scalability, graceful degradation in the presence of faults, a very effective assignment function (based on consistent hashing) for partitioning the domain to crawl, and more in general the complete decentralization of every task. The necessity of handling very large sets of data has highlighted some limitations of the Java APIs, which prompted the authors to partially reimplement them.

Constrained coverage for mobile sensor networks

Abstract: We consider the problem of self-deployment of a mobile sensor network. We are interested in a deployment strategy that maximizes the area coverage of the network with the constraint that each of the nodes has at least K neighbors, where K is a user-specified parameter. We propose an algorithm based on artificial potential fields which is distributed, scalable and does not require a prior map of the environment. Simulations establish that the resulting networks have the required degree with a high probability, are well connected and achieve good coverage. We present analytical results for the coverage achievable by uniform random and symmetrically tiled network configurations and use these to evaluate the performance of our algorithm.

Constrained Coverage for Mobile Sensor Networks

Abstract: We consider the problem of self-deployment of a mobile sensor network. We are interested in a deployment strategy that maximizes the area coverage of the network with the constraint that each of the nodes has at least K neighbors, where K is a user-specified parameter. We propose an algorithm based on artificial potential fields which is distributed, scalable and does not require a prior map of the environment. Simulations establish that the resulting networks have the required degree with a high probability, are well connected and achieve good coverage. We present analytical results for the coverage achievable by uniform random and symmetrically tiled network configurations and use these to evaluate the performance of our algorithm.

Medians and beyond: new aggregation techniques for sensor networks

Abstract: Wireless sensor networks offer the potential to span and monitor large geographical areas inexpensively. Sensors, however, have significant power constraint (battery life), making communication very expensive. Another important issue in the context of sensor-based information systems is that individual sensor readings are inherently unreliable. In order to address these two aspects, sensor database systems like TinyDB and Cougar enable in-network data aggregation to reduce the communication cost and improve reliability. The existing data aggregation techniques, however, are limited to relatively simple types of queries such as SUM, COUNT, AVG, and MIN/MAX. In this paper we propose a data aggregation scheme that significantly extends the class of queries that can be answered using sensor networks. These queries include (approximate) quantiles, such as the median, the most frequent data values, such as the consensus value, a histogram of the data distribution, as well as range queries. In our scheme, each sensor aggregates the data it has received from other sensors into a fixed (user specified) size message. We provide strict theoretical guarantees on the approximation quality of the queries in terms of the message size. We evaluate the performance of our aggregation scheme by simulation and demonstrate its accuracy, scalability and low resource utilization for highly variable input data sets.

Medians and Beyond: New Aggregation Techniques for Sensor Networks

Abstract: Wireless sensor networks offer the potential to span and monitor large geographical areas inexpensively. Sensors, however, have significant power constraint (battery life), making communication very expensive. Another important issue in the context of sensor-based information systems is that individual sensor readings are inherently unreliable. In order to address these two aspects, sensor database systems like TinyDB and Cougar enable in-network data aggregation to reduce the communication cost and improve reliability. The existing data aggregation techniques, however, are limited to relatively simple types of queries such as SUM, COUNT, AVG, and MIN/MAX. In this paper we propose a data aggregation scheme that significantly extends the class of queries that can be answered using sensor networks. These queries include (approximate) quantiles, such as the median, the most frequent data values, such as the consensus value, a histogram of the data distribution, as well as range queries. In our scheme, each sensor aggregates the data it has received from other sensors into a fixed (user specified) size message. We provide strict theoretical guarantees on the approximation quality of the queries in terms of the message size. We evaluate the performance of our aggregation scheme by simulation and demonstrate its accuracy, scalability and low resource utilization for highly variable input data sets.

Integrating vertical and horizontal partitioning into automated physical database design

Abstract: In addition to indexes and materialized views, horizontal and vertical partitioning are important aspects of physical design in a relational database system that significantly impact performance. Horizontal partitioning also provides manageability; database administrators often require indexes and their underlying tables partitioned identically so as to make common operations such as backup/restore easier. While partitioning is important, incorporating partitioning makes the problem of automating physical design much harder since: (a) The choices of partitioning can strongly interact with choices of indexes and materialized views. (b) A large new space of physical design alternatives must be considered. (c) Manageability requirements impose a new constraint on the problem. In this paper, we present novel techniques for designing a scalable solution to this integrated physical design problem that takes both performance and manageability into account. We have implemented our techniques and evaluated it on Microsoft SQL Server. Our experiments highlight: (a) the importance of taking an integrated approach to automated physical design and (b) the scalability of our techniques.

Xpipes: a network-on-chip architecture for gigascale systems-on-chip

Abstract: The growing complexity of embedded multiprocessor architectures for digital media processing will soon require highly scalable communication infrastructures. Packet switched networks-on-chip (NoC) have been proposed to support the trend for systems-on-chip integration. In this paper, an advanced NoC architecture, called Xpipes, targeting high performance and reliable communication for on-chip multi-processors is introduced. It consists of a library of soft macros (switches, network interfaces and links) that are design-time composable and tunable so that domain-specific heterogeneous architectures can be instantiated and synthesized. Links can be pipelined with a flexible number of stages to decouple link throughput from its length and to get arbitrary topologies. Moreover, a tool called XpipesCompiler, which automatically instantiates a customized NoC from the library of soft network components, is used in this paper to test the Xpipes-based synthesis flow for domain-specific communication architectures.

Multilevel μTESLA: Broadcast authentication for distributed sensor networks

Abstract: Broadcast authentication is a fundamental security service in distributed sensor networks. This paper presents the development of a scalable broadcast authentication scheme named multilevel μTESLA based on μTESLA, a broadcast authentication protocol whose scalability is limited by its unicast-based initial parameter distribution. Multilevel μTESLA satisfies several nice properties, including low overhead, tolerance of message loss, scalability to large networks, and resistance to replay attacks as well as denial-of-service attacks. This paper also presents the experimental results obtained through simulation, which demonstrate the performance of the proposed scheme under severe denial-of-service attacks and poor channel quality.

The Panasas ActiveScale Storage Cluster: Delivering Scalable High Bandwidth Storage

Abstract: Fundamental advances in high-level storage architectures and low-level storage-device interfaces greatly improve the performance and scalability of storage systems. Specifically, the decoupling of storage control (i.e., file system policy) from datapath operations (i.e., read, write) allows client applications to leverage the readily available bandwidth of storage devices while continuing to rely on the rich semantics of today’s file systems. Further, the evolution of storage interfaces from block-based devices with no protection to object-based devices with per-command access control enables storage to become secure, first-class IP-based network citizens. This paper examines how the Panasas ActiveScale Storage Cluster leverages distributed storage and object-based devices to achieve linear scalability of storage bandwidth. Specifically, we focus on implementation issues with our Object-based Storage Device, aggregation algorithms across the collection of OSDs, and the close coupling of networking and storage to achieve scalability.

PIC: practical Internet coordinates for distance estimation

Abstract: We introduce PIC, a practical coordinate-based mechanism to estimate Internet network distance (i.e., round-trip delay or network hops). Network distance estimation is important in many applications; for example, network-aware overlay construction and server selection. There are several proposals for distance estimation in the Internet but they all suffer from problems that limit their benefit. Most rely on a small set of infrastructure nodes that are a single point of failure and limit scalability. Others use sets of peers to compute coordinates but these coordinates can be arbitrarily wrong if one of these peers is malicious. While it may be reasonable to secure a small set of infrastructure nodes, it is unreasonable to secure all peers. PIC addresses these problems: it does not rely on infrastructure nodes and it can compute accurate coordinates even when some peers are malicious. We present PIC's design, experimental evaluation, and an application to network-aware overlay construction and maintenance.

Apparatus, method and system for aggregrating computing resources

Abstract: A system for executing applications designed to run on a single SMP computer on an easily scalable network of computers, while providing each application with computing resources, including processing power, memory and others that exceed the resources available on any single computer. A server agent program, a grid switch apparatus and a grid controller apparatus are included. Methods for creating processes and resources, and for accessing resources transparently across multiple servers are also provided.

Scalable pattern matching for high speed networks

Abstract: In this paper, we present a scalable FPGA design methodology for searching network packet payloads for a large number of patterns, including complex regular expressions. The efficiency of the technique enables a current-generation FPGA device to support pattern-matching at network rates from 1 Gbps to 100 Gbps and beyond. It offers flexible trade-offs between character capacity, throughput, and data bus width and rate. This allows the approach to be used in a wide range of devices from low-end home network appliances to high-end backbone routers. Suitable network applications for the FPGA pattern-matcher include firewalls, network intrusion detection, email virus scanning, and junk-email identification. In this work, we use a standard set of patterns from an intrusion detection system to demonstrate the performance and scalability of our design with a real-world application.

A scalable distributed information management system

Abstract: We present a Scalable Distributed Information Management System (SDIMS) that aggregates information about large-scale networked systems and that can serve as a basic building block for a broad range of large-scale distributed applications by providing detailed views of nearby information and summary views of global information. To serve as a basic building block, a SDIMS should have four properties: scalability to many nodes and attributes, flexibility to accommodate a broad range of applications, administrative isolation for security and availability, and robustness to node and network failures. We design, implement and evaluate a SDIMS that (1) leverages Distributed Hash Tables (DHT) to create scalable aggregation trees, (2) provides flexibility through a simple API that lets applications control propagation of reads and writes, (3) provides administrative isolation through simple extensions to current DHT algorithms, and (4) achieves robustness to node and network reconfigurations through lazy reaggregation, on-demand reaggregation, and tunable spatial replication. Through extensive simulations and micro-benchmark experiments, we observe that our system is an order of magnitude more scalable than existing approaches, achieves isolation properties at the cost of modestly increased read latency in comparison to flat DHTs, and gracefully handles failures.

Topical web crawlers: Evaluating adaptive algorithms

Abstract: Topical crawlers are increasingly seen as a way to address the scalability limitations of universal search engines, by distributing the crawling process across users, queries, or even client computers. The context available to such crawlers can guide the navigation of links with the goal of efficiently locating highly relevant target pages. We developed a framework to fairly evaluate topical crawling algorithms under a number of performance metrics. Such a framework is employed here to evaluate different algorithms that have proven highly competitive among those proposed in the literature and in our own previous research. In particular we focus on the tradeoff between exploration and exploitation of the cues available to a crawler, and on adaptive crawlers that use machine learning techniques to guide their search. We find that the best performance is achieved by a novel combination of explorative and exploitative bias, and introduce an evolutionary crawler that surpasses the performance of the best nonadaptive crawler after sufficiently long crawls. We also analyze the computational complexity of the various crawlers and discuss how performance and complexity scale with available resources. Evolutionary crawlers achieve high efficiency and scalability by distributing the work across concurrent agents, resulting in the best performance/cost ratio.

Method and apparatus for providing virtual computing services

Abstract: A level of abstraction is created between a set of physical processors and a set of virtual multiprocessors to form a virtualized data center. This virtualized data center comprises a set of virtual, isolated systems separated by a boundary referred as a partition. Each of these systems appears as a unique, independent virtual multiprocessor computer capable of running a traditional operating system and its applications. In one embodiment, the system implements this multi-layered abstraction via a group of microkernels, each of which communicates with one or more peer microkemel over a high-speed, low-latency interconnect and forms a distributed virtual machine monitor. Functionally, a virtual data center is provided, including the ability to take a collection of servers and execute a collection of business applications over a compute fabric comprising commodity processors coupled by an interconnect. Processor, memory and I/O are virtualized across this fabric, providing a single system, scalability and manageability. According to one embodiment, this virtualization is transparent to the application, and therefore, applications may be scaled to increasing resource demands without modifying the application.

Decentralized orchestration of composite web services

Abstract: Web services make information and software available programmatically via the Internet and may be used as building blocks for applications. A composite web service is one that is built using multiple component web services and is typically specified using a language such as BPEL4WS or WSIPL. Once its specification has been developed, the composite service may be orchestrated either in a centralized or in a decentralized fashion. Decentralized orchestration offers performance improvements in terms of increased throughput and scalability and lower response time. However, decentralized orchestration also brings additional complexity to the system in terms of error recovery and fault handling. Further, incorrect design of a decentralized system can lead to potential deadlock or non-optimal usage of system resources. This paper investigates build time and runtime issues related to decentralized orchestration of composite web services. We support our design decisions with performance results obtained on a decentralized setup using BPEL4WS to describe the composite web services and BPWS4J as the underlying runtime environment to orchestrate them.

Database Tuning Advisor for Microsoft SQL Server 2005

Abstract: Publisher Summary This chapter provides an overview of Database Tuning Advisor's (DTA's) novel functionality, the rationale for its architecture, and demonstrates DTA's quality and scalability on large customer workloads The DTA is part of Microsoft SQL Server 2005 It is an automated physical database design tool that significantly advances the state-of-the-art in several ways First, the DTA is capable of providing an integrated physical design recommendation for horizontal partitioning, indexes, and materialized views Second, unlike today's physical design tools that focus solely on performance, the DTA also supports the capability for a database administrator (DBA) to specify manageability requirements while optimizing for performance Third, the DTA is able to scale to large databases and workloads using several novel techniques including: workload compression, reduced statistics creation, and exploiting test server to reduce load on production server Finally, the DTA greatly enhances scriptability and customization through the use of a public XML schema for input and output

Ganymed: scalable replication for transactional web applications

Abstract: Data grids, large scale web applications generating dynamic content and database service providing pose significant scalability challenges to database engines. Replication is the most common solution but it involves difficult trade-offs. The most difficult one is the choice between scalability and consistency. Commercial systems give up consistency. Research solutions typically either offer a compromise (limited scalability in exchange for consistency) or impose limitations on the data schema and the workload. In this paper we introduce Ganymed, a database replication middleware intended to provide scalability without sacrificing consistency and avoiding the limitations of existing approaches. The main idea is to use a novel transaction scheduling algorithm that separates update and read-only transactions. Transactions can be submitted to Ganymed through a special JDBC driver. Ganymed then routes updates to a main server and queries to a potentially unlimited number of read-only copies. The system guarantees that all transactions see a consistent data state (snapshot isolation). In the paper we describe the scheduling algorithm, the architecture of Ganymed, and present an extensive performance evaluation that proves the potential of the system.

A Peer-to-Peer Approach to Web Service Discovery

Abstract: Web Services are emerging as a dominant paradigm for constructing and composing distributed business applications and enabling enterprise-wide interoperability. A critical factor to the overall utility of Web Services is a scalable, flexible and robust discovery mechanism. This paper presents a Peer-to-Peer (P2P) indexing system and associated P2P storage that supports large-scale, decentralized, real-time search capabilities. The presented system supports complex queries containing partial keywords and wildcards. Furthermore, it guarantees that all existing data elements matching a query will be found with bounded costs in terms of number of messages and number of nodes involved. The key innovation is a dimension reducing indexing scheme that effectively maps the multidimensional information space to physical peers. The design and an experimental evaluation of the system are presented.

System and method for securing energy management systems

Abstract: A power management architecture for an electrical power distribution system, or portion thereof, is disclosed The architecture includes multiple intelligent electronic devices (“IED's”) distributed throughout the power distribution system to manage the flow and consumption of power from the system The IED's are linked via a network to back-end servers Power management application software and/or hardware components operate on the IED's and the back-end servers and inter-operate via the network to implement a power management application The architecture provides a scalable and cost effective framework of hardware and software upon which such power management applications can operate to manage the distribution and consumption of electrical power by one or more utilities/suppliers and/or customers which provide and utilize the power distribution system Security mechanisms are further provided which protect and otherwise ensure the authenticity of communications

Dynamic Metadata Management for Petabyte-Scale File Systems

Abstract: In petabyte-scale distributed file systems that decouple read and write from metadata operations, behavior of the metadata server cluster will be critical to overall system performance and scalability. We present a dynamic subtree partitioning and adaptive metadata management system designed to efficiently manage hierarchical metadata workloads that evolve over time. We examine the relative merits of our approach in the context of traditional workload partitioning strategies, and demonstrate the performance, scalability and adaptability advantages in a simulation environment.

FAB: building distributed enterprise disk arrays from commodity components

Abstract: This paper describes the design, implementation, and evaluation of a Federated Array of Bricks (FAB), a distributed disk array that provides the reliability of traditional enterprise arrays with lower cost and better scalability. FAB is built from a collection of bricks, small storage appliances containing commodity disks, CPU, NVRAM, and network interface cards. FAB deploys a new majority-voting-based algorithm to replicate or erasure-code logical blocks across bricks and a reconfiguration algorithm to move data in the background when bricks are added or decommissioned. We argue that voting is practical and necessary for reliable, high-throughput storage systems such as FAB. We have implemented a FAB prototype on a 22-node Linux cluster. This prototype sustains 85MB/second of throughput for a database workload, and 270MB/second for a bulk-read workload. In addition, it can outperform traditional master-slave replication through performance decoupling and can handle brick failures and recoveries smoothly without disturbing client requests.

Authenticating query results in edge computing

Abstract: Edge computing pushes application logic and the underlying data to the edge of the network, with the aim of improving availability and scalability. As the edge servers are not necessarily secure, there must be provisions for validating their outputs. This paper proposes a mechanism that creates a verification object (VO) for checking the integrity of each query result produced by an edge server - that values in the result tuples are not tampered with, and that no spurious tuples are introduced. The primary advantages of our proposed mechanism are that the VO is independent of the database size, and that relational operations can still be fulfilled by the edge servers. These advantages reduce transmission load and processing at the clients. We also show how insert and delete transactions can be supported.

A General Model for Authenticated Data Structures

Abstract: Query answers from on-line databases can easily be corrupted by hackers or malicious database publishers. Thus it is important to provide mechanisms which allow clients to trust the results from on-line queries. Authentic publication allows untrusted publishers to answer securely queries from clients on behalf of trusted off-line data owners. Publishers validate answers using hard-to-forge verification objects VOs), which clients can check efficiently. This approach provides greater scalability, by making it easy to add more publishers, and better security, since on-line publishers do not need to be trusted.To make authentic publication attractive, it is important for the VOs to be small, efficient to compute, and efficient to verify. This has lead researchers to develop independently several different schemes for efficient VO computation based on specific data structures. Our goal is to develop a unifying framework for these disparate results, leading to a generalized security result. In this paper we characterize a broad class of data structures which we call Search DAGs, and we develop a generalized algorithm for the construction of VOs for Search DAGs. We prove that the VOs thus constructed are secure, and that they are efficient to compute and verify. We demonstrate how this approach easily captures existing work on simple structures such as binary trees, multi-dimensional range trees, tries, and skip lists. Once these are shown to be Search DAGs, the requisite security and efficiency results immediately follow from our general theorems. Going further, we also use Search DAGs to produce and prove the security of authenticated versions of two complex data models for efficient multi-dimensional range searches. This allows efficient VOs to be computed (size O(log N + T)) for typical one- and two-dimensional range queries, where the query answer is of size T and the database is of size N. We also show I/O-efficient schemes to construct the VOs. For a system with disk blocks of size B, we answer one-dimensional and three-sided range queries and compute the VOs with O(logB N + T/B) I/O operations using linear size data structures.

A new hierarchical parallelization scheme: Generalized distributed data interface (GDDI), and an application to the fragment molecular orbital method (FMO)

Abstract: A two-level hierarchical scheme, generalized distributed data interface (GDDI), implemented into GAMESS is presented. Parallelization is accomplished first at the upper level by assigning computational tasks to groups. Then each group does parallelization at the lower level, by dividing its task into smaller work loads. The types of computations that can be used with this scheme are limited to those for which nearly independent tasks and subtasks can be assigned. Typical examples implemented, tested, and analyzed in this work are numeric derivatives and the fragment molecular orbital method (FMO) that is used to compute large molecules quantum mechanically by dividing them into fragments. Numeric derivatives can be used for algorithms based on them, such as geometry optimizations, saddle-point searches, frequency analyses, etc. This new hierarchical scheme is found to be a flexible tool easily utilizing network topology and delivering excellent performance even on slow networks. In one of the typical tests, on 16 nodes the scalability of GDDI is 1.7 times better than that of the standard parallelization scheme DDI and on 128 nodes GDDI is 93 times faster than DDI (on a multihub Fast Ethernet network). FMO delivered scalability of 80-90% on 128 nodes, depending on the molecular system (water clusters and a protein). A numerical gradient calculation for a water cluster achieved a scalability of 70% on 128 nodes. It is expected that GDDI will become a preferred tool on massively parallel computers for appropriate computational tasks.