Showing papers on "Latency (engineering) published in 1986"

Memory access buffering in multiprocessors

Abstract: In highly-pipelined machines, instructions and data are prefetched and buffered in both the processor and the cache. This is done to reduce the average memory access latency and to take advantage o...

Measurement and Application of Fault Latency

Abstract: The time interval between the occurrence of a fault and the detection of the error caused by the fault is divided by the generation of that error into two parts: fault latency and error latency. Since the moment of error generation is not directly observable, all related works in the literature have dealt with only the sum of fault and error latencies, thereby making the analysis of their separate effects impossible. To remedy this deficiency, we 1) present a new methodology for indirectly measuring fault latency, 2) derive the distribution of fault latency from the methodology, and 3) apply the knowledge of fault latency to the analysis of two important examples.

Alerting effects of naps in patients with narcolepsy.

Abstract: As part of their standard diagnostic evaluation, 45 patients with narcolepsy and 45 patients with other disorders of excessive sleepiness (DOES), primarily obstructive sleep apnea, each underwent one of three nap conditions that involved manipulating time in bed on the 1600 h latency test of the standard multiple sleep latency test (MSLT) and varying the time between the 1600-h latency test and a subsequent fifth latency test. Compared with the mean of tests 1-4, a 15-min nap at 1600 h (condition 1) increased latency to stage 1 sleep on a latency test 15 min later in both groups. However, the increase was greater for patients with narcolepsy than with other DOES. A 30-min nap at 1600 h (condition 2) produced increased latency 15 min later, but the increase was greater for patients with other DOES. While narcoleptic patients showed no change in latency as a function of increased nap duration, the other DOES patients had increased latencies. When tested 30 min after a 15-min nap (condition 3), narcoleptic patients had latencies that did not differ from those of tests 1-4, while the other DOES patients sustained their increased latencies.

Characteristics of analgesias induced by brief or prolonged stress.

Abstract: Some characteristics of the effects of brief and prolonged stress on tail-flick latency are described. The pharmacological profiles of the latency responses to 30 sec and 30 min footshock are strikingly different. Thus, the increase of tail-flick latency after 30 sec shock is unaffected by naloxone and enhanced by drugs which decrease 5HT or DA-dependent transmission, while the increase after 30 min shock is blocked by naloxone and also by the above drugs. The increased tail-flick latency after 30 sec shock only occurs if tail-flick latency is also determined before shock. This finding, together with the attenuation or enhancement of the post-shock response by drugs that similarly affect conditioned avoidance behavior, suggests that the increased latency after brief shock occurs through a mechanism that is related to passive avoidance learning. Finally, a new approach to the investigation of stress-induced analgesia is described in which neurochemical changes during prolonged immobilization stress are repeatedly monitored using cisternal CSF samples taken in parallel with tail-flick latency measurements.

Fault latency in the memory - An experimental study on VAX 11/780

Abstract: Fault latency is the time between the physical occurrence of a fault and its corruption of data, causing an error. The measure of this time is difficult to obtain because the time of occurrence of a fault and the exact moment of generation of an error are not known. This paper describes an experiment to accurately study the fault latency in the memory subsystem. The experiment employs real memory data from a VAX 11/780 at the University of Illinois. Fault latency distributions are generated for s-a-0 and s-a-1 permanent fault models. Results show that the mean fault latency of a s-a-0 fault is nearly 5 times that of the s-a-1 fault. Large variations in fault latency are found for different regions in memory. An analysis of a variance model to quantify the relative influence of various workload measures on the evaluated latency is also given.

Short and long latency reflexes in human muscles following electrical and mechanical stimulation

Abstract: Electromyographic (EMG) recordings were made during slight voluntary contraction or during rest in various human muscles following electrical and mechanical stimulation. The electrical stimuli used in most of these experiments were square wave pulses with the duration of 100 microseconds given at a frequency of 3 Hz on cutaneous and mixed nerves. The mechanical stimuli were constant stretches of the muscle induced by taps of the electromechanical reflex hammer. The aims of the series of studies were to investigate the characteristic features of electrically and mechanically elicited muscular responses, the correspondence between electrically and mechanically elicited responses, the short latency response following muscle afferent stimulation and the modifications of the electrically elicited responses. The electrical stimulation during slight voluntary activity caused short and long latency excitatory phases in averaged and rectified EMG with the onset latencies much shorter than the voluntary reaction time. The responses were considered reflexive. The most constant short and long latency reflexes following electrical stimulation were found in the first dorsal interosseus muscle in the hand and in the extensor digitorum brevis in the foot. The mean onset latency for the short latency reflex was 30.9 +/- 1.7 ms (SD) and for the long latency reflex 50.9 +/- 2.8 ms in the hand muscle. In the foot muscle the mean short latency reflex latency was 54.9 +/- 4.1 ms and the long latency reflex latency was 80.5 +/- 5.5 ms. The onset latencies of the short and long latency reflexes during slight voluntary activity following stretching and following cutaneous nerve stimulation corresponded in the first dorsal interosseus muscle. It was concluded that they are generated at least partly via mutual pathways. The stretches given to the triceps brachii muscle during various head positions, different elbow angles and during the Jendrassik maneuver revealed short latency reflex facititations. The lesser degree of the facilitation was caused by the tonic neck reflex and the Jendrassik maneuver caused the greater degree of the facilitation. The short latency reflex following muscle afferent stimulation (the H-reflex) was elicited in the flexor carpi radialis muscle with a mean latency of 15.4 +/- 0.5 ms. The amplitude of the 50% H-reflex was modified by contracting or by stretching of the muscle. Voluntary contraction increased the 50% H-reflex amplitude about 30% and the passive stretching decreased it to about 80% of the control value. The patients with different central nervous system disorders showed abnormal electrically elicited short and long latency reflexes. The s

The relationship between long latency responses and height.

Abstract: Long latency responses to electrical stimulation of nerve trunks in upper and lower extremities were studied in 83 healthy subjects. The latency differences between the late responses, M2, and the segmental reflexes, M1, on the hand correlated with the height, confirming a transcortical reflex loop. Corresponding to the possible polysynaptic spinal origin of the late reflex response on the lower leg, there was no correlation with height. Therefore, it is not possible to calculate the intraspinal conduction time from long latency reflex examinations.

Fault and Error Latency Under Real Workload - an Experimental Study

Abstract: A practical methodology for the study of fault and error latency is demonstrated under a real workload. This is the first study that measures and quantifies the latency under real workload and fills a major gap in the current understanding of workload-failure relationships. The methodology is based on low level data gathered on a VAX 11/780 during the normal workload conditions of the installation. Fault occurrence is simulated on the data, and the error generation and discovery process is reconstructed to determine latency. The analysis proceeds to combine the low level activity data with high level machine performance data to yield a better understanding of the phenomena. A strong relationship exists between latency and workload and that relationship is quantified. The sampling and reconstruction techniques used are also validated. Error latency in the memory where the operating system resides was studied using data on the physical memory access. Fault latency in the paged section of memory was determined using data from physical memory scans. Error latency in the microcontrol store was studied using data on the microcode access and usage.

Effects of alcohol on P-300's produced by viewing a simulated traffic signal

Abstract: The P-300 event related brain potential was monitored during simula traffic signal tasks for ten subjects who were tested at three levels of mean Blood Alcohol Content (BAC): 0.00%, 0.06%, and 0.13%. A significant increase in latency occurred for the 0.13% BAC level indicating that an increased mental processing time was required to determine if a red or a green light had been presented.