Trade-offs In Scheduling Research Articles

Attacking the one-out-of-m multicore problem by combining hardware management with mixed-criticality provisioning

The multicore revolution is having limited impact in safety-critical application domains. A key reason is the "one-out-of-m" problem: when validating real-time constraints on an m-core platform, excessive analysis pessimism can effectively negate the processing capacity of the additional $$m-1$$m-1 cores so that only "one core's worth" of capacity is utilized even though m cores are available. Two approaches have been investigated previously to address this problem: mixed-criticality allocation techniques, which provision less-critical software components less pessimistically, and hardware-management techniques, which make the underlying platform itself more predictable. A better way forward may be to combine both approaches, but to show this, fundamentally new criticality-cognizant hardware-management tradeoffs must be explored. Such tradeoffs are investigated herein in the context of a new variant of a mixed-criticality framework, called $$\textsf {MC}^\textsf {2} $$MC2, that supports configurable criticality-based hardware management. This framework allows specific DRAM memory banks and areas of the last-level cache (LLC) to be allocated to certain groups of tasks. A linear-programming-based optimization framework is presented for sizing such LLC areas, subject to conditions for ensuring $$\textsf {MC}^\textsf {2} $$MC2 schedulability. The effectiveness of the overall framework in resolving hardware-management and scheduling tradeoffs is investigated in the context of a large-scale overhead-aware schedulability study. This study was guided by extensive trace data obtained by executing benchmark programs on the new variant of $$\textsf {MC}^\textsf {2} $$MC2 presented herein. This study shows that mixed-criticality allocation and hardware-management techniques can be much more effective when applied together instead of alone.

Scheduling decision styles on leisure and social activities

This paper investigates scheduling decisions associated with different types of leisure and social activities. Correlations among decisions and self-selection biases are explicitly investigated by using a sample selection model with a bivariate probit selection rule. A dataset collected in the first wave of a recent activity-travel scheduling panel survey carried out in Valencia (Spain) was used for empirical investigation. Significant differences are revealed in the empirical models for leisure and social activities in planning decisions, including different effects of temporal, companionship and demographic factors. The findings of the empirical model have important implications to travel behavior and activity-travel scheduling model developments. These results confirm the existence of different mechanisms underlying the activity-travel decision processes when leisure and social activities are of concerns. Results provide significant insights into enhancing the performances of an activity scheduling model by capturing accurate activity-travel scheduling tradeoffs in flexible activity types e.g. leisure and social activities.

Energy-Aware Scheduling of Distributed Systems

Scheduling of tasks on a multi-machine system to reduce the makespan, while satisfying the precedence constraints between the tasks, is known to be an NP-hard problem. We propose a new formulation and show that energy-aware scheduling is a generalization of the minimum makespan scheduling problem. Taking the system graph and program graph as inputs, we propose three different algorithms for energy-aware scheduling, each of them having its own strengths and limitations. The first is a genetic algorithm (Plain GA) that searches for an energy reducing schedule. The second (CA+GA) uses cellular automata (CA) to generate low energy schedules, while using a genetic algorithm (GA) to find good rules for the CA. The third (EAH) is a heuristic which gives preference to high-efficiency machines in allocation. We have tested our algorithms on well-known program graphs and compared our results with other state-of-the-art scheduling algorithms, which confirms the efficacy of our approach. Our work also gives insight into the time-energy trade-offs in scheduling.

Efficiency and Fairness Trade-Offs in SC-FDMA Schedulers

In this paper, we address the uplink resource scheduling problem in single carrier frequency-domain multiple access systems. In particular, we focus on the efficiency and fairness trade-offs in scheduling and resource allocation for wireless cellular networks. We present an efficient implementation method that translates these scheduling problems into set partitioning problems that are well-studied in the literature. Then, we discuss a family of utility functions that enable us to investigate the performance of different frequency domain schedulers such as the sum-rate maximization, proportional fair, and max-min fair schedulers. We use the price of fairness as a metric to analytically quantify these trade-offs. Based on the intuition that fairness of resource allocation in cellular radio networks corresponds to the prioritization of cell-edge user rates, we demonstrate that the proportional fair scheduler significantly improves fairness among users, and increases the rates offered to the cell-edge and median users when compared to the sum-rate maximization scheduler. This comes at the cost of reducing the cell-center user rates and the aggregate user rate. We present the steps on how to take into account the practical implementation constraints, in particular, those related with the discrete Fourier transform implementation, in the problem formulation. Simulation results that illustrate these trade-offs are also presented. We conclude that this type of analysis can provide guidelines for the network operators to control the efficiency and fairness trade-off as the data traffic grows.

Effects of Schedule Pressure on Construction Performance

Accelerating a project can be rewarding. The consequences, however, can be troublesome if productivity and quality are sacrificed for the sake of remaining ahead of schedule, such that the actual schedule benefits are often barely worth the effort. The tradeoffs and paths of schedule pressure—and its causes and effects—are often overlooked when schedule decisions are being made. This paper analyzes the effects that schedule pressure has on construction performance, and focuses on tradeoffs in scheduling. A research framework has been developed using a causal diagram to illustrate the cause-and-effect analysis of schedule pressure. An empirical investigation has been performed by using survey data collected from 102 construction practitioners working in 38 construction sites in Singapore. The results of this survey data analysis indicate that advantages of increasing the pace of work—by working under schedule pressure—can be offset by losses in productivity and quality. The negative effects of schedule pressure arise mainly by working out of sequence, generating work defects, cutting corners, and losing the motivation to work. The adverse effects of schedule pressure can be minimized by scheduling construction activities realistically and planning them proactively, motivating workers, and by establishing an effective project coordination and communication mechanism.

Engineering Ethics: Balancing Cost, Schedule, and Risk--Lessons Learned from the Space Shuttle (review)

Reviewed by: Engineering Ethics: Balancing Cost, Schedule, and Risk—Lessons Learned from the Space Shuttle * Michael S. Pritchard (bio) Engineering Ethics: Balancing Cost, Schedule, and Risk—Lessons Learned from the Space Shuttle. By Rosa Lynn B. Pinkus et al. Cambridge and New York: Cambridge University Press, 1997. Pp. xviii+379; figures, appendixes, notes, bibliography, index. $70.00 (hardcover); $27.95 (paper). This book approaches engineering ethics from the perspective of practicing engineers. It does so by documenting the historical development of the main engines of the space shuttle from 1969 to the fateful Challenger explosion of 1986. Although the book might be viewed as presenting historical documentation of the various factors that ultimately resulted in the Challenger disaster, it would be a mistake to see this as its basic aim. Rather, the goal is to demonstrate a methodological approach to the more general subject of engineering ethics. The book advocates an interdisciplinary approach that pays very careful attention to the historical, political, organizational, and technical dimensions of particular engineering contexts that call for ethical reflection and decision making. In arguing for this approach the authors take full advantage of the material available on the development of NASA’s space shuttle program. This enables them to present a detailed account of the role of engineers in a very large, complicated project over a long period of time. In addition to its wealth of historical and technical information, the book presents a series of five case studies based on this information. Only the last of these cases discusses the Challenger disaster. Written as a practical book, Engineering Ethics is intended for engineers, managers, professional ethicists, and students. It focuses on the everyday decisions engineers and managers make as they design, test, and put technologies into operation. The authors characterize engineering as a heuristic skill practiced before “all the facts are in”—estimating risks, balancing budgets and deadlines—rather than an applied science. Just as the authors do not regard engineering simply as the practical application of scientific theory, they do not regard engineering ethics simply as the practical application of philosophical ethics. Here the authors take a lesson from the casuistic approach to medical ethics that begins with cases and brings in abstract moral principles and theories only if careful [End Page 164] analysis of the details of a given case seem to call for this. Thus, taking their cue from Abert Jonsen and Stephen Toulmin’s Abuse of Casuistry (Berkeley: University of California Press, 1988), they embrace the bottom-up rather than top-down approach. This does not mean that they eschew ethical principles. The authors offer three framing principles, each of which they claim is grounded in engineering practice rather than abstract ethical theory. The first is a principle of competence, requiring the application of engineering expertise to the problems at hand. The second is a principle of responsibility, emphasizing the responsibility to communicate knowledge effectively, making best use of information acquired through engineering expertise. The third is what the authors call “Cicero’s Creed II,” which expresses a commitment to reduce risk and failure and to promote public safety. Each of these principles can be applied at both individual and organizational levels. The authors adapt Herbert A. Simon’s theory of organizational behavior to their historical account of the development of the space shuttle main engine. For Simon, organizations have a kind of collective rationality based on their hierarchical structure, with each level being an end relative to those below it and a means relative to levels above it. In evaluating organizational operations, Simon’s key notion is “satisficing” rather than “maximizing” values; feasibility, not optimization, is the appropriate goal in complex organizational hierarchies. This notion is then used to assess how well cost, schedule, and risk trade-offs fared in the development of the space shuttle main engine. The first several chapters develop the authors’ methodological assumptions in great detail. Part 2 of the book (chapters 5–13) presents technical and political background as well as the five case studies. These cases discuss “all up” vs. component testing; cost, risk, and schedule trade-offs; the dissenting voice of engineer A. O. Tischler, who was critical of many of...

Design considerations for a general-purpose microprocessor

The authors examine the performance, cost, and schedule tradeoffs made for the NS 32532, a 32-bit general-purpose microprocessor. Among its features are a 30-MHz clock frequency, three on-chip caches, a four-stage pipeline, and dedicated mechanisms for multiprocessing support. The authors describe the design constraints set by the VLSI processing and packaging technologies. They address the issue of market requirements by examining the software and hardware considerations for the microprocessor's target applications. After describing the functional partitioning choices, including the means for supporting a memory hierarchy and floating-point operations, they present the NS32532's microarchitecture. They then examine the microprocessor's system interface, the memory reference transactions, and the instruction-flow and data-flow monitoring mechanisms. Finally, the authors present an overview of the methodology adopted to accomplish the design within a strict schedule while achieving full functionality and meeting cost and performance goals. >