Diagnosing rediscovered software problems using symptoms

This paper presents an approach to automatically diagnosing rediscovered software failures using symptoms, in environments in which many users run the same procedural software system. The approach is based on the observation that the great majority of field software failures are rediscoveries of previously reported problems and that failures caused by the same defect often share common symptoms. Based on actual data, the paper develops a small software failure fingerprint, which consists of the procedure call trace, problem detection location, and the identification of the executing software. The paper demonstrates that over 60 percent of rediscoveries can be automatically diagnosed based on fingerprints; less than 10 percent of defects are misdiagnosed. The paper also discusses a pilot that implements the approach. Using the approach not only saves service resources by eliminating repeated data collection for and diagnosis of reoccurring problems, but it can also improve service response time for rediscoveries     

Parallel programming for multimedia applications

Computing capabilities are continuing to increase with the availability of multi core and many core processors. The wide availability of multi core processors has made parallel programming possible for end user applications running on desktops, workstations, and mobile devices. While parallel hardware has become common, software that exploits parallel capabilities is just beginning to take hold. Multimedia applications, with their data parallel nature and large computing requirements will benefit significantly from parallel programming. In this paper an overview of parallel programming is presented and languages and tools for parallel programming such as OpenMP and CUDA are introduced within the scope of multimedia applications.     

Eddy current probe sensitivity as a function of coil construction parameters

We report the results of the first phase of a study designed to quantify the relationship between eddy current coil construction and the performance of these coils used in nondestructive evaluation (NDE) inspections. The ferrite core coils wound for this study are small but typical of the sizes commonly used in commercially manufactured eddy current probes. Coil diameters range from 1 mm to 7 mm with lengths from 0.5 mm to 4 mm. Seven parameters were studied and included ferrite diameter, ferrite permeability, coil aspect ratio, number of turns, distance of the windings from the inspection end of the ferrite, wire gauge, and length of the ferrite beyond the end of the windings. Additionally, the coil set was designed to provide some indication of the repeatability of identical constructions, what we have called winding inhomogeneity. The coils were incorporated into surface probes for scanning defects in flat plate specimens. The measure of sensitivity was the change of probe impedance (Z) as the probe was scanned from an unflawed area to the flawed area of the test specimen. Measurements were also made of the component of Z perpendicular to the liftoff vector.The data reported here were produced from a set of 27 probes scanned over a single defect. The defect was an electrical-discharge-machined (EDM) notch in a 19 mm thick 7075-T6 aluminum alloy specimen. The part-circular EDM notch was 9 mm long and 3 mm deep and 0.1 mm wide.Analysis of the data shows that the number of turns, the winding distance, the coil aspect ratio, and the backside ferrite length all affect the coil sensitivity. Winding inhomogeneity is significant for coils having many winding layers and can be considerably larger than the contribution made by variations in some of the construction factors. Wire gauge, ferrite diameter, and permeability showed no significant effects on our measure of sensitivity in this study.     

Electron transport in highly compensated,plastically bent,n-type InSb in the temperature range 4.2–300 K

Measurements of the Hall coefficient, dc electrical conductivity, and magnetoresistance have been made on two highly compensated, plastically bent,n-type InSb samples from liquid helium to room temperature. The number and Hall mobility of charge carriers and the electrical conductivity are greatly affected by plastic bending. The mobility decreases appreciably and the number of charge carriers increases in both the deformed samples. This increase of effective charge carriers can be attributed to the introduction of effective donor centers due to plastic bending. The electrical conductivity in one of the deformed samples increases between the temperature ranges 4.2–15 K and 125–190 K compared to that of the undeformed state of the sample. This unusual increase in is attributed to the large increase inn value. The magnetoresistance at 4.2 K is due to impurity-band conduction and is found to be positive. It shows approximately a linear variation with magnetic field in both the deformed samples. The observed behavior of the magnetoresistance at 300 K is consistent with the behavior expected for free electrons. The observed / at 77.4 K is found to be less than that at 300 K and is explained in terms of the Hall mobility values at these two temperatures.     

Efficient asynchronous executions of AMR computations and visualization on a GPU system

Adaptive Mesh Refinement is a method which dynamically varies the spatio-temporal resolution of localized mesh regions in numerical simulations, based on the strength of the solution features. In-situ visualization plays an important role for analyzing the time evolving characteristics of the domain structures. Continuous visualization of the output data for various timesteps results in a better study of the underlying domain and the model used for simulating the domain. In this paper, we develop strategies for continuous online visualization of time evolving data for AMR applications executed on GPUs. We reorder the meshes for computations on the GPU based on the users input related to the subdomain that he wants to visualize. This makes the data available for visualization at a faster rate. We then perform asynchronous executions of the visualization steps and fix-up operations on the CPUs while the GPU advances the solution. By performing experiments on Tesla S1070 and Fermi C2070 clusters, we found that our strategies result in 60% improvement in response time and 16% improvement in the rate of visualization of frames over the existing strategy of performing fix-ups and visualization at the end of the timesteps.     

Simulating perfect channels with probabilistic lossy channels

We consider the problem of deciding whether an infinite-state system (expressed as a Markov chain) satisfies a correctness property with probability 1. This problem is, of course, undecidable for general infinite-state systems. We focus our attention on the model of probabilistic lossy channel systems consisting of finite-state processes that communicate over unbounded lossy FIFO channels. Abdulla and Jonsson have shown that safety properties are decidable while progress properties are undecidable for non-probabilistic lossy channel systems. Under assumptions of “sufficiently high” probability of loss, Baier and Engelen have shown how to check whether a property holds of probabilistic lossy channel system with probability 1. In this paper, we consider a model of probabilistic lossy channel systems, where messages can be lost only during send transitions. In contrast to the model of Baier and Engelen, once a message is successfully sent to channel, it can only be removed through a transition which receives the message. We show that checking whether safety properties hold with probability 1 is undecidable for this model. Our proof depends upon simulating a perfect channel, with a high degree of confidence, using lossy channels.     

Networking and communication challenges for post-exascale systems

With the significant advancement in emerging processor, memory, and networking technologies, exascale systems will become available in the next few years (2020–2022). As the exascale systems begin to be deployed and used, there will be a continuous demand to run next-generation applications with finer granularity, finer time-steps, and increased data sizes. Based on historical trends, next-generation applications will require postexascale systems during 2025–2035. In this study, we focus on the networking and communication challenges for post-exascale systems. Firstly, we present an envisioned architecture for post-exascale systems. Secondly, the challenges are summarized from different perspectives: heterogeneous networking technologies, high-performance communication and synchronization protocols, integrated support with accelerators and field-programmable gate arrays, fault-tolerance and quality-of-service support, energy-aware communication schemes and protocols, softwaredefined networking, and scalable communication protocols with heterogeneous memory and storage. Thirdly, we present the challenges in designing efficient programming model support for high-performance computing, big data, and deep learning on these systems. Finally, we emphasize the critical need for co-designing runtime with upper layers on these systems to achieve the maximum performance and scalability.