On the Integrity of Lightweight Checkpoints

Long error detection latency, the time elapsed from the occurrence of an error caused by a bug to its manifestation as an observable failure, severely limits the effectiveness of existing post-silicon validation and debug techniques. Traditional post-silicon validation tests can incur very long error detection latencies of millions or even billions of clock cycles. An earlier technique called Quick Error Detection (QED) shortens error detection latencies to only few hundred (or thousand) clock cycles. However, software-only QED (i.e., QED implemented entirely in software) can result in significantly increased post-silicon validation test runtimes. We present a new technique called Fast QED that overcomes this drawback of software-only QED, while preserving the error detection latency and bug coverage benefits of software-only QED. Simulation results using an OpenSPARC T2-like multi-core SoC and bugs abstracted from multiple commercial multi-core SoCs demonstrate: 1. Fast QED achieves 4 orders of magnitude improvement in test runtime as compared to software-only QED, with only 0.4% increase in chip area; 2. Fast QED improves error detection latencies by up to 5 orders of magnitude compared to non-QED tests, and also achieves improved error detection latencies compared to software-only QED; and, 3. Fast QED improves bug coverage by up to 2-fold compared to non-QED tests (similar to software-only QED).

Dynamic thread duplication is a known redundancy technique for multi-cores. Recent research applied this concept to hybrid multi-cores for error detection and introduced thread shadowing that runs hardware threads in the reconfigurable cores and compares their outputs for deviation at configurable signature levels. Previously published work evaluated this concept in terms of performance, error detection latency and resource consumption. In this paper we report on the error detection capabilities of thread shadowing by presenting an extensive fault injection campaign. We employ the Xilinx Soft Error Mitigation Controller for fault injection and the Xilinx Essential Bit facility to limit the fault injections to relevant bits in the configuration bitstream. Our findings from fault injection experiments with a sorting benchmark are threefold: First, up to 98% of all errors are detected by the operating system of the hybrid multi-core supported by thread shadowing. Second, thread shadowing's signature levels provide a useful trade-off between detected errors and effort needed, with around 5% of all errors detected in calls to operating system functions and around 52% of errors detected in memory accesses of the hardware thread. Third, essential bit testing is effective and cuts down the amount of bits to be tested by a factor of 14.48 compared to the total amount of bits available in the configuration address space.

Local triple modular redundancy (LTMR) is often the first choice to harden a flash-based FPGA application against soft errors in space. Unfortunately, LTMR leads to at least 300% area overhead. We propose a parity-based error detection approach, to use the limited resources of space-proven flash-based FPGAs more area-efficiently; this method can be the key for fitting the application onto the FPGA. A drawback of parity-based hardening is the significant impact on the critical path. To alleviate this error detection latency, pipeline structures in the design can be utilized. According to our results, this eliminates from 22% to 65% of the critical path overhead of the unpipelined error detection. Compared with LTMR, the new approach increases the critical path overhead of LTMR by a factor varying from 2 to 7.

This paper presents the prototype of an automatic and model-independent fault injection tool, to use on an IBM-PC (or compatible) platform. The tool has been built around a commercial VHDL simulator. With this tool, both transient and permanent faults, of a wide range of types, can be injected into medium-complexity models. Another remarkable aspect of the tool is the fact that it is able to analyse the results obtained from the injection campaigns, in order to study the error syndrome of the system model and/or validate its fault-tolerance mechanisms. Some results of a fault injection campaign carried out to validate the dependability of a fault tolerant microcomputer system are shown. We have analysed the pathology of the propagated errors, measured their latencies, and calculated both error detection and recovery latencies and coverages.

High-performance computing (HPC) systems are growing more powerful by utilizing more components. As the system mean time before failure correspondingly drops, applications must checkpoint frequently to make progress. However, at scale, the cost of checkpointing becomes prohibitive. A solution to this problem is multilevel checkpointing, which employs multiple types of checkpoints in a single run. Lightweight checkpoints can handle the most common failure modes, while more expensive checkpoints can handle severe failures. We designed a multilevel checkpointing library, the Scalable Checkpoint/Restart (SCR) library, that writes lightweight checkpoints to node-local storage in addition to the parallel file system. We present probabilistic Markov models of SC’s performance. We show that on future large-scale systems, SCR can lead to a gain in machine efficiency of up to 35%, and reduce the load on the parallel file system by a factor of two. Additionally, we predict that checkpoint scavenging, or only writing checkpoints to the parallel file system on application termination, can reduce the load on the parallel file system by 20× on today’s systems and still maintain high application efficiency.

How to improve employees' satisfaction in the remote office mode while working together has become a challenge for enterprises to deal with the new office management mode. The concept of service design touch point is introduced into the remote office management system to improve employees' office experience and help enterprises complete the remote office service design. From the perspective of virtuous circle, the cost of failure analysis and preventive measures for service design touch point in the process of service design is lower than that of dealing with failure after service failure. Therefore, this paper made a risk assessment on the failure mode of service design touch point loss analysis method based on the triangular fuzzy number evaluation method. In the failure risk assessment, the fuzzy failure mode and effect analysis theory and the failure mode of service design touch point are analyzed first, and the expert scoring method is used to evaluate and determine the fuzzy level of severity, occurrence and detection of each failure mode; Then, aiming at the ability difference of different experts in evaluating different objects, the expert importance matrix, which is based on attribute difference, is determined; On this basis, the risk priority value of each failure mode is analyzed and determined by fuzzy calculation method. The risk evaluation ranking results of touch point failure modes are obtained according to the risk priority value. Finally, taking the failure analysis of Y company's remote collaborative office service as an example, the feasibility of the method is verified by the case of protection during COVID-19.

A Link slab of continuous bridge deck over its adjacent span of simply supported precast girders is desirable for smooth riding due to jointless construction. Since end movements of the girders have become restraints of the slab associated with some other actions, the movements of typical highway girders of I, T, U and Box sections with different span length and their construction sequences have been investigated. The interaction behavior of end restraints; axial, rotational and translational with mid-span loading, will be determined in the study. The finite element method of the microplane model (MASA) will be a tool for the structural analyses of crack patterns, crack width, modes of failure and structural responses of each action with different details and thickness-to-span ratios. Full-scale experimental investigation of 3 specimens of different reinforcing details of hinge, semi-continuity and full continuity with mid-span loading has been conducted to verify the results of the analyses. Monitoring of actual behaviors of real structures has also been done for comparison of some essential behaviors. End movements of typical girders have shown to be less significant on the cross-section and its construction sequences. Span length has played a major role on axial deformation and the rotation, as the translation is influenced by vertical stiffness of the support. Long-term effects due to creep, shrinkage and relaxation have shown indication of the extreme cases of 20% increase. The interaction behaviors for axial deformation and end rotation due to end movements of the girders have shown some influences of support conditions. However, the effects of the support level (x/H) in roller support (R-R) and centroid of girders (Cb/H) in hinged support (H-H) is less significant. For elastomeric bearing support, axial deformation is controlled by the number of spans and girder span length and show that rotation is less influenced by the relative stiffness of girders and link slabs of more than 10 and the location of the link slab in the structural system. Translation is subjected to shear and moment to be controlled by vertical stiffness, the slab thickness and its length. To design a link slab, span length and the number of girder spans are required for interaction of restraints to determine forces and displacement of the extreme cases. Then design for strengths can be carried out by means of tension, flexure, and shear while design for serviceability would be governed by stiffness of elastomeric bearing and crack distribution as per reinforcing details. Design example has illustrated the concept and procedure of the real practice.

In this paper we discuss our experience with the design, development and deployment of MneMojno Semantic Web Service and Mobile Application. MneMojno makes use of Semantic Web Technologies to create a Web service and a mobile application for rating and providing detail information about food products. This paper introduces the main components of the system: a framework to capture information about food products from various sources, a semantic web service and a framework to visualize and analyze usage statistics. Finally, we discuss challenges and problems we faced during the development and present our conclusions and future directions for exploration in terms of developing MneMojno further.

This paper introduces service failure management on internet shopping environment. The purpose of this study is to find and improve service failure modes at the time of customer's complaint thereby reducing that. To achieve this purpose, this study combines the Service Blueprint which describes the online shopping process and FMEA which finds each encounter of service failures and proposes how to recover them. First of all this study generates internet shopping process using Service Blueprint then matches customer's purchase decision making process and company's service provide process. After this process customer complaint types in real purchasing process are fell in according to their occurrence and more frequently occurred complaint is more risky. Finally 6 Risk Priority Numbers(unfair exchange/return policies, slow response/poor customer service support, purchase arrived later than promised/deliverly service dissatisfaction, dissatisfaction short period to take back/exchange/cancels order, A/S or handle defective item) are extracted and suggest their improvement.

Based on experiences in teaching Service Design in a blended learning context, we developed an electronic learning environment (ELE) including features that turned out to be suitable for learners from different cultures. We used this ELE in blended learning courses on Service Design in Universities in Italy and in China. Students were guided through collaborative learning and mutual teaching. Students were supported by the teacher with the help of didactic technologies in a learning process that merged theoretical understanding with design for real life applications in their culture. The course was structured with the help of concept maps. The approach of the teaching was based on constructivism. In both student groups, our intended improvements seem to be acknowledged by the students’ opinions.

A unified method for the design of telecommunication services

The Web enters a new era where contents are to take the back seat and services will take the driver seat to form a service-oriented Web. This paper presents a service-oriented user interface design for the next generation Web. The design leverages the advances of semantic Web and service composition technologies to provide an intelligent and generic user interface to query, compose and execute Web services for a variety of user tasks. First, a simple cost model is developed for estimating the development and learning overheads of Web service interfaces for service-oriented applications as the motivation of this work. Then, the authors present the design of the service-oriented browser and discuss the enabling technologies. A prototype system is developed using existing technologies and standards as a proof of concept.

Mobile agents seem an interesting solution for the design and deployment of Web services and applications in the Internet scenario. However, mobility complicates the design of applications and calls for new approaches to facilitate the specification and control of the mobility behaviour without any impact on agent implementation. The paper advocates a policy-based model to specify mobility strategies separately from the agent code and presents a policy controlled mobile agents framework. This approach permits to adapt agent applications to the evolving conditions of the execution environment. The paper also presents a case study to validate our policy-based solution to agent mobility.

Design and Simulation of the Timed Triggered Protocol (TTP) Using Agents

Economic optimization and sensitivity analysis of photovoltaic system in residential buildings