Engineering topics

Iyer, Ravi K.

Publications and source records attributed to Iyer, Ravi K..

6 records

NASA NTRS1991

Modeling and measuring multiprogramming and system overheads on a shared-memory multiprocessor - Case study

The present discussion of methods for quantifying multiprogramming (MP) overhead on a computer system illustrates two such techniques, respectively for quantifying MP overheads' lower bound and determining the MP overload of real workloads, in light of the percentage of parallel processing time that is consumed by MP overhead on Alliant multiprocessors. Kernel lock spinning is found to be a major factor in MP overhead, which accounts for more than half of total system overhead. It is noted that parallel environments' MP overhead is not statistically dependent on the number of parallel jobs undergoing multiprogramming.

Dimpsey, Robert T.↗

NASA NTRS1990

MEASURE: An integrated data-analysis and model identification facility

The first phase of the development of MEASURE, an integrated data analysis and model identification facility is described. The facility takes system activity data as input and produces as output representative behavioral models of the system in near real time. In addition a wide range of statistical characteristics of the measured system are also available. The usage of the system is illustrated on data collected via software instrumentation of a network of SUN workstations at the University of Illinois. Initially, statistical clustering is used to identify high density regions of resource-usage in a given environment. The identified regions form the states for building a state-transition model to evaluate system and program performance in real time. The model is then solved to obtain useful parameters such as the response-time distribution and the mean waiting time in each state. A graphical interface which displays the identified models and their characteristics (with real time updates) was also developed. The results provide an understanding of the resource-usage in the system under various workload conditions. This work is targeted for a testbed of UNIX workstations with the initial phase ported to SUN workstations on the NASA, Ames Research Center Advanced Automation Testbed.

Singh, Jaidip↗

NASA NTRS1989

An experimental study of memory fault latency

The difficulty with the measurement of fault latency is due to the lack of observability of the fault occurrence and error generation instants in a production environment. The authors describe an experiment, using data from a VAX 11/780 under real workload, to study fault latency in the memory subsystem accurately. Fault latency distributions are generated for stuck-at-zero (s-a-0) and stuck-at-one (s-a-1) permanent fault models. The results show that the mean fault latency of an s-a-0 fault is nearly five times that of the s-a-1 fault. An analysis of variance is performed to quantify the relative influence of different workload measures on the evaluated latency.

Chillarege, Ram↗

NASA NTRS1988

Space-borne computing for the year 2000 and beyond

The influence and utilization of computers in space science investigations greatly enhances the ability to address difficult and complicated questions about the Universe. Space Science is wholly dependent on computers because the data acquired from instruments on the spacecraft are not only complicated in form but also voluminous. Athough a great deal of attention has been paid to develop efficient and powerful computing systems on-ground, research in the area of spaceborne computing is far from satisfactory. On-board processing of data will be important in future planetary missions where telemetry rates constrain the total amount of data which can be returned and decisions may have to be made in real time. Little thought has been given to a dynamic man-machine interface with regard to scientific real-time interactive control of flight experiments. Careful thinking is therefore essential to define appropriate spaceborne computing requirements for the future. It is imperative that powerful multiprocessing systems for on-board processing be experimentally impleneted and evaluated in selected application missions. The presentation addresses key issues and attempts to define the requirements for such processing with some of NASA's future missions in perspective. The resulting architectural and performance issues and possible developments are also addressed.

Iyer, Ravi K.↗

NASA NTRS1987

Overview of ICLASS research: Reliable and parallel computing

An overview of Illinois Computer Laboratory for Aerospace Systems and Software (ICLASS) Research: Reliable and Parallel Computing is presented. Topics covered include: reliable and fault tolerant computing; fault tolerant multiprocessor architectures; fault tolerant matrix computation; and parallel processing.

Iyer, Ravi K.↗

NASA NTRS1987

A measurement-based performability model for a multiprocessor system

A measurement-based performability model based on real error-data collected on a multiprocessor system is described. Model development from the raw errror-data to the estimation of cumulative reward is described. Both normal and failure behavior of the system are characterized. The measured data show that the holding times in key operational and failure states are not simple exponential and that semi-Markov process is necessary to model the system behavior. A reward function, based on the service rate and the error rate in each state, is then defined in order to estimate the performability of the system and to depict the cost of different failure types and recovery procedures.

Ilsueh, M. C.↗