SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
The application of systolic priority queues to the sequential stack decoding algorithm is discussed in a review of the work of K. Yao and C. Y. Chang. Using a systolic array architecture, one can significantly improve the performance of such algorithms at high signal-to-noise ratios.
The end-to-end performance of a program implementing IEEE Std 802.2 logical link control protocol, which provides virtual circuit and datagram service and which constitutes the top sublayer of the data link layer of the reference model for Local Area Networks is studied. The measurements of relative execution times of various functions required in transferring data, over virtual circuits or as datagrams, showed that most of the program execution time is spent in a few relatively low-level functions. One of these functions performs block movement of data in memory, and two other functions provide access to various queues. Based on this result, two alternative versions of the program which move data efficiently were written and measured. In this paper the results of the study are reported and their impact on designing hardware and software systems for a network interface are discussed.
The interdependency of nodes and multicomputer interconnection networks is examined using simple calculations based on the asymptotic properties of queueing networks. Methods are described for choosing interconnection networks that fit individual classes of applications. It is also shown how analytic models can be extended to benchmark existing interconnection networks.
The Fiber Distributed Data Interface (FDDI) is an imerging ANSI and ISO standard for a 100 megabit per second fiber optic token ring. The performance of the FDDI media access control protocol is analyzed using a simulation developed at NASA Ames. Both analyses using standard measures of performance (including average delay for asynchronous traffic, channel utilization, and transmission queue length) and analyses of characteristics of ring behavior which can be attributed to constraints imposed by the timed token protocol on token holding time (including bounded token rotation time, support for synchronous traffic, and fairness of channel access for nodes transmitting asynchronous traffic) are included.
The embedded systems running real-time applications, for which Ada was designed, require their own mechanisms for the management of dynamically allocated storage. There is a need for packages which manage their own internalo structures to control their deallocation as well, due to the performance implications of garbage collection by the KAPSE. This places a requirement upon the design of generic packages which manage generically structured private types built-up from application-defined input types. These kinds of generic packages should figure greatly in the development of lower-level software such as operating systems, schedulers, controllers, and device driver; and will manage structures such as queues, stacks, link-lists, files, and binary multary (hierarchical) trees. Controlled to prevent inadvertent de-designation of dynamic elements, which is implicit in the assignment operation A study was made of the use of limited private type, in solving the problems of controlling the accumulation of anonymous, detached objects in running systems. The use of deallocator prodecures for run-down of application-defined input types during deallocation operations during satellites.
SIMD computers with local indirect addressing allow programs to have queues and buffers, making certain kinds of problems much more efficient. Examined here are a class of problems characterized by computations on data points where the computation is identical, but the convergence rate is data dependent. Normally, in this situation, the algorithm time is governed by the maximum number of iterations required by each point. Using indirect addressing allows a processor to proceed to the next data point when it is done, reducing the overall number of iterations required to approach the mean convergence rate when a sufficiently large problem set is solved. Load balancing techniques can be applied for additional performance improvement. Simulations of this technique applied to solving Mandelbrot Sets indicate significant performance gains.
A new multiprocessor data acquisition system was developed for the existing Airborne Oceanographic Lidar (AOL). This implementation simultaneously utilizes five single board 68010 microcomputers, the UNIX system V operating system, and the real time executive VRTX. The original data acquisition system was implemented on a Hewlett Packard HP 21-MX 16 bit minicomputer using a multi-tasking real time operating system and a mixture of assembly and FORTRAN languages. The present collection of data sources produce data at widely varied rates and require varied amounts of burdensome real time processing and formatting. It was decided to replace the aging HP 21-MX minicomputer with a multiprocessor system. A new and flexible recording format was devised and implemented to accommodate the constantly changing sensor configuration. A central feature of this data system is the minimization of non-remote sensing bus traffic. Therefore, it is highly desirable that each micro be capable of functioning as much as possible on-card or via private peripherals. The bus is used primarily for the transfer of remote sensing data to or from the buffer queue.
A decentralized dynamic load-sharing (LS) method based on state-change broadcasts is proposed for a distributed real-time system. Whenever the state of a node changes from underloaded to fully loaded and vice versa, the node broadcasts this change to a set of nodes, called a buddy set, in the system. The performance of the method is evaluated with both analytic modeling and simulation. It is modeled first by an embedded Markov chain for which numerical solutions are derived. The model solutions are then used to calculate the distribution of queue lengths at the nodes and the probability of meeting task deadlines. The analytical results show that buddy sets of 10 nodes outperform those of less than 10 nodes, and the incremental benefit gained from increasing the buddy set size beyond 15 nodes is insignificant. These and other analytical results are verified by simulation. The proposed LS method is shown to meet task deadlines with a very high probability.
Recurrent loss of sensor data in integrated control systems of an advanced aircraft may occur under different operating conditions that include detected frame errors and queue saturation in computer networks, and bad data suppression in signal processing. This paper presents an extension of the concept of observability based on a set of randomly selected nonconsecutive outputs in finite-dimensional, linear, time-invariant systems. Conditions for testing extended observability have been established.
Emergency escape system for aircraft and aerospace vehicles ejects up to seven crewmembers, one by one, within 120 s. Intended for emergencies in which disabled craft still in stable flight at no more than 220 kn (113 m/s) equivalent airspeed and sinking no faster than 110 ft/s (33.5 m/s) at altitudes up to 50,000 ft (15.2 km). Ejection rockets load themselves from magazine after each crewmember ejected. Jumpmaster queues other crewmembers and helps them position themselves on egress ramp. Rockets pull crewmembers clear of aircraft structure. Provides orderly, controlled exit and avoids ditching at sea or landing in rough terrain.
Recently two standards for Metropolitan Area Networks (MANs), Fiber Distributed Data Interface (FDDI) and Distributed Queue Dual Bus (DQDB), have emerged as the primary competitors for the MAN arena. Great interest exists in building higher speed networks which support large numbers of node and greater distance, and it is not clear what types of protocols are needed for this type of environment. There is some question as to whether or not these MAN standards can be extended to such environments. The extensibility of FDDI to the Gbps range and a long distance environment is investigated. Specification parameters which affect performance are shown and a measure is provided for predicting utilization of FDDI. A comparison of FDDI at 100 Mbps and 1 Gbps is presented. Some specific problems with FDDI are addressed and modifications which improve the viability of FDDI in such high speed networks are investigated.
Most lower speed (approx. 10 Mbps) local area networks use adaptive or random access protocols like Ethernet. Others at higher speed use demand assignment like token or slotted rings. These include Cambridge ring and electronic token ring systems. Fairness issues in representatives of such protocols are discussed. In particular, Fiber Distributed Data Interface (FDDI) was selected as a demand access protocol using tokens, Carrier Sensed Multiple Access/Ring Network (CSMA/RN) a random access protocol, and Distributed Queue Dual Bus (DQDB) a demand access protocol using reservations. Fairness at the media access level was the focus, i.e., attaining access or being excessively delayed when a message is queued to be sent as a function of network location. Within that framework, the essential fairness of FDDI was observed along with severe fairness problems in DQDB and some problems for CSMA/RN. Several modifications were investigated and their ameliorative effect is shown. Finally, a unified presentation which allows comparisons of the three protocols' fairness when normalized to their capacity is given.
The intent of the proposed effort is the examination of the impact of the elements of parallel architectures on the performance realized in a parallel computation. To this end, three major projects are developed: a language for the expression of high level parallelism, a statistical technique for the synthesis of multicomputer interconnection networks based upon performance prediction, and a queueing model for the analysis of shared memory hierarchies.
Lately, the growing demand on the Internet has prompted the need for more effective congestion control policies. Currently No Gateway Policy is used to relieve and signal congestion, which leads to unfair service to the individual users and a degradation of overall network performance. Network simulation was used to illustrate the character of Internet congestion and its causes. A newly proposed gateway congestion control policy, called Random Drop, was considered as a promising solution to the pressing problem. Random Drop relieves resource congestion upon buffer overflow by choosing a random packet from the service queue to be dropped. The random choice should result in a drop distribution proportional to the bandwidth distribution among all contending TCP connections, thus applying the necessary fairness. Nonetheless, the simulation experiments demonstrate several shortcomings with this policy. Because Random Drop is a congestion control policy, which is not applied until congestion has already occurred, it usually results in a high drop rate that hurts too many connections including well-behaved ones. Even though the number of packets dropped is different from one connection to another depending on the buffer utilization upon overflow, the TCP recovery overhead is high enough to neutralize these differences, causing unfair congestion penalties. Besides, the drop distribution itself is an inaccurate representation of the average bandwidth distribution, missing much important information about the bandwidth utilization between buffer overflow events. A modification of Random Drop to do congestion avoidance by applying the policy early was also proposed. Early Random Drop has the advantage of avoiding the high drop rate of buffer overflow. The early application of the policy removes the pressure of congestion relief and allows more accurate signaling of congestion. To be used effectively, algorithms for the dynamic adjustment of the parameters of Early Random Drop to suite the current network load must still be developed.
Some technologies developed for system level modeling and analysis of algorithms/architectures using an architecture design and development system are reviewed. Modeling and analysis is described with attention given to modeling constraints and analysis using constrained software graphs. An example is presented of an ADAS graph and its associated attributes, such as firing delay, token consume rate, token produce rate, firing threshold, firing condition, arc queue lengths, associated C or Ada functional model, and stochastic behavior.
An artificial intelligence design and qualitative modeling tool is disclosed for creating computer models and simulating continuous activities, functions, and/or behavior using developed discrete event techniques. Conveniently, the tool is organized in four modules: library design module, model construction module, simulation module, and experimentation and analysis. The library design module supports the building of library knowledge including component classes and elements pertinent to a particular domain of continuous activities, functions, and behavior being modeled. The continuous behavior is defined discretely with respect to invocation statements, effect statements, and time delays. The functionality of the components is defined in terms of variable cluster instances, independent processes, and modes, further defined in terms of mode transition processes and mode dependent processes. Model construction utilizes the hierarchy of libraries and connects them with appropriate relations. The simulation executes a specialized initialization routine and executes events in a manner that includes selective inherency of characteristics through a time and event schema until the event queue in the simulator is emptied. The experimentation and analysis module supports analysis through the generation of appropriate log files and graphics developments and includes the ability of log file comparisons.
This invention relates to a resource allocation in computer systems, and more particularly, to a method and associated apparatus for shortening response time and improving efficiency of a heterogeneous distributed networked computer system by reallocating the jobs queued up for busy nodes to idle, or less-busy nodes. In accordance with the algorithm (SIDA for short), the load-sharing is initiated by the server device in a manner such that extra overhead in not imposed on the system during heavily-loaded conditions. The algorithm employed in the present invention uses a dual-mode, server-initiated approach. Jobs are transferred from heavily burdened nodes (i.e., over a high threshold limit) to low burdened nodes at the initiation of the receiving node when: (1) a job finishes at a node which is burdened below a pre-established threshold level, or (2) a node is idle for a period of time as established by a wakeup timer at the node. The invention uses a combination of the local queue length and the local service rate ratio at each node as the workload indicator.
Communicating finite state machines (CFSM's) with FIFO (first in, first out) queues are used to model a protocol converter. A protocol conversion algorithm is developed and presented for the CSFM model of the protocols A and B. A converter H for protocols A = (A0, A1) and B = (B0, B1) is viewed as a black box such that H is between sender A0 and receiver B1. This gives a resulting protocol X = (A0, H, B1). The conversion algorithm requires a specification of the message relationships between the messages of protocols A and B. It is assumed that protocols A and B have the required progress properties. The algorithm includes a search for related messages from the two protocols in an FIFO from a composite space formed by a Cartesian cross-product of state spaces A1 and B0. The search produces finite-length traces which are combined to form a state machine H, which is examined for freedom from unspecified receptions, deadlocks, and livelocks. A protocol conversion example demonstrates the applicability of the algorithm.