this paper describes extensions to VHDL to support system-level behavioral modeling by providing more abstract forms of communication and concurrency than those currently in the language. the report summarizes design ...
详细信息
this paper describes extensions to VHDL to support system-level behavioral modeling by providing more abstract forms of communication and concurrency than those currently in the language. the report summarizes design objectives and issues that must be considered in developing such extensions, and presents definitions of our extensions. the extensions for communication consist of channel types, channel objects, dynamically allocated channels, and message passing statements. the extensions for concurrency consist of process declarations and static and dynamic process instantiation statements. Use of the extensions is illustrated with examples.
A tree-based fault-tolerant multicast algorithm built on top of pipelined circuit switching is presented. the algorithm is provably deadlock-free and livelock-free, requires only a single message startup, and guarante...
详细信息
A tree-based fault-tolerant multicast algorithm built on top of pipelined circuit switching is presented. the algorithm is provably deadlock-free and livelock-free, requires only a single message startup, and guarantees messages are delivered over shortest paths in the fault-free and traffic-free case. simulation results in two-dimensional mesh networks show that the algorithm produces significantly shorter average communication latency than previous fault-tolerant multicast algorithms over a range of network loads and fault conditions.
simulation of large sets of mobile computers or other wireless communication devices is difficult because of the computationally intensive models of wireless channels. Parallel simulation would seem to be applicable h...
详细信息
simulation of large sets of mobile computers or other wireless communication devices is difficult because of the computationally intensive models of wireless channels. Parallel simulation would seem to be applicable here because of the large computation granularity, but the location based communication topology makes conservative methods difficult to implement. this paper considers a novel approach to improving lookahead in conservative parallel simulations by differentiating between data flow paths in the simulation. An experimental study shows that for this application, the technique produces a 70% reduction in null message traffic, with only a 25% increase in null message computation overhead, and a consistent improvement in parallel performance.
the growing complexity in the functionality and system architecture of embeddedsystems has motivated designers to raise the level of abstraction by composing the system with a mix of reusable and system-specific comp...
详细信息
the growing complexity in the functionality and system architecture of embeddedsystems has motivated designers to raise the level of abstraction by composing the system with a mix of reusable and system-specific components. Currently, these components assume specific programming models that make them difficult to compose or retarget. the modal process model addresses the problem of control composition by separating the synchronization semantics from state unification, and by supporting automatic synthesis of control communication onto distributed architectures. By avoiding over-specifying the behavior, the components can be made more composable and the designer can more easily choose the least expensive synchronization semantics for implementing the composition. To help designers evaluate their choice, we propose a method for analyzing the properties of the composed system, including the detection of potential deadlock and livelock situations.
Broadcasting protocols can improve the efficiency of video on demand services by reducing the bandwidth required to transmit videos that are simultaneously watched by many viewers. We present here two broadcasting pro...
详细信息
Broadcasting protocols can improve the efficiency of video on demand services by reducing the bandwidth required to transmit videos that are simultaneously watched by many viewers. We present here two broadcasting protocols that achieve nearly the same low bandwidth as the best extant broadcasting protocol while guaranteeing a lower maximum access time. Our first protocol, cautious harmonic broadcasting, requires somewhat more bandwidththan our second protocol, quasi-harmonic broadcasting, but is also much simpler to implement.
this paper presents a binary feedback flow control scheme which uses the gradient of the system performance function to generate feedback from the network to the data sources. the setting of the single bit congestion ...
详细信息
this paper presents a binary feedback flow control scheme which uses the gradient of the system performance function to generate feedback from the network to the data sources. the setting of the single bit congestion indication communicated back to the users is based upon the sign of the gradient of the system performance function. the proposed scheme uses a simple gradient optimization method and a neural model of the system dynamics to determine the gradient of the performance function. simulation results are presented to compare the performance of the proposed scheme to the conventional queue thresholding approach.
this paper presents a pool of performance models for user applications using IONA's OrbixTalk, a software system that provides a reliable multicast objects message system using UDP-based IP Multicast. the solution...
详细信息
this paper presents a pool of performance models for user applications using IONA's OrbixTalk, a software system that provides a reliable multicast objects message system using UDP-based IP Multicast. the solution presents models for all the levels involved, from the OrbixTalk user program level to the logical level regarding internal proxies using UDP sockets over TCP/IP ports. the OrbixTalk models have been included into the Models' Repository of HELIOS (Hierarchical Evaluation of Large Information Open systems), a CASE tool for predicting the performance of Distributed Information systems.
the effect of the buffer management policies, used at the Internet protocol/asynchronous transfer mode (IP/ATM) gateway, on the end-to-end performance seen by IP traffic when using the ATM available bit rate (ABR) ser...
详细信息
the effect of the buffer management policies, used at the Internet protocol/asynchronous transfer mode (IP/ATM) gateway, on the end-to-end performance seen by IP traffic when using the ATM available bit rate (ABR) service class were examined. the ABR service class uses feedback-based flow control at the ATM layer to dynamically partition bandwidth among active ABR VCs. It is likely that the ABR service will be operated in manner designed to achieve nearly loss free operation in the core of the ATM networks, causing most of the buffering requirements to be pushed to the ingress points of the ATM network.
In this paper, we present the design and implementation of an efficient on-line simulator for wormhole routing networks, which is an important part of the Concordia Parallel systems Simulator (CPSS), a simulator for w...
详细信息
In this paper, we present the design and implementation of an efficient on-line simulator for wormhole routing networks, which is an important part of the Concordia Parallel systems Simulator (CPSS), a simulator for wormhole-routed multicomputers. the ultimate purpose of the CPSS is to provide a parallel programming environment which allows users to study impacts of system and software factors on program performance and to locate performance bottlenecks in parallel programs. Our simulator can accurately simulate a large range of regular topologies that represent the communication structures of most wormhole-routed networks. Users are given the flexibility of changing communication and computation parameters as often as needed without recompilation. It is unique in its integrated parallel simulation of the communication process and the execution of user applications. this makes possible real-time evaluation of network performance in realistic application domains.
Real-time transactions, in addition to preserving consistency of the database as in traditional transactions, have to meet the deadlines. Scheduling real-time transactions in parallel database systems has not received...
详细信息
Real-time transactions, in addition to preserving consistency of the database as in traditional transactions, have to meet the deadlines. Scheduling real-time transactions in parallel database systems has not received much attention. this paper focuses on real-time transaction scheduling in shared-nothing parallel database systems. We evaluate the performance of a new priority-based scheduling policy, in which all scheduling decisions are made locally by each node. In contrast, several other algorithms, proposed for the distributed systems, require communication among the nodes to globally synchronize their local block and abort decisions. Such synchronization can deteriorate performance as real-time transactions will have to meet deadlines. We use miss ratio as the performance metric and show that, in general, the new policy provides a superior performance for the workload and system parameters considered in this study.
暂无评论