Scenario-oriented design for single-chip heterogeneous multiprocessors

Single-chip heterogeneous multiprocessors (SCHMs) are arising to meet the computational demands of portable and handheld devices. These computing systems are not fully custom designs traditionally targeted by the design automation community, general-purpose designs traditionally targeted by the computer architecture community, nor pure embedded designs traditionally targeted by the real-time community. An entirely new design philosophy will be needed for this hybrid class of computing. The programming of the device will be drawn from a narrower set of applications with execution that persists in the system over a longer period of time than for general-purpose programming. However, the devices will still be programmable, not only at the level of the individual processing element, but across multiple processing elements and even the entire chip. The design of other programmable single chip computers has enjoyed an era where the design tradeoffs could be captured in simulators such as SimpleScalar and performance could be evaluated to the SPEC benchmarks. Motivated by this, we describe new benchmark-based design strategies for SCHMs which we refer to as scenario-oriented design. We include an example and results.     

Description of Structural Damage Caused by the Terrorist Attack on the Pentagon

On September 11, 2001, an airliner was intentionally crashed into the Pentagon. It struck at the first elevated slab on the west wall, and slid approximately 310?ft (94.5?m) diagonally into the building. The force of the collision demolished numerous columns and the fa?ade of the exterior wall, and induced damage to first-floor columns and the first elevated slab over an area approximately 90?ft (27.4?m) wide and 310?ft (94.5?m) long. None of the building collapsed immediately. The portion that remained standing, even after an intense fire, sustained substantial damage at the first-floor level.     

Reliability analysis of nuclear containment without metallic liners against jet aircraft crash

The present study presents a methodology for detailed reliability analysis of nuclear containment without metallic liners against aircraft crash. For this purpose, a nonlinear limit state function has been derived using violation of tolerable crack width as failure criterion. This criterion has been considered as failure criterion because radioactive radiations may come out if size of crack becomes more than the tolerable crack width. The derived limit state uses the response of containment that has been obtained from a detailed dynamic analysis of nuclear containment under an impact of a large size Boeing jet aircraft. Using this response in conjunction with limit state function, the reliabilities and probabilities of failures are obtained at a number of vulnerable locations employing an efficient first-order reliability method (FORM). These values of reliability and probability of failure at various vulnerable locations are then used for the estimation of conditional and annual reliabilities of nuclear containment as a function of its location from the airport. To study the influence of the various random variables on containment reliability the sensitivity analysis has been performed. Some parametric studies have also been included to obtain the results of field and academic interest.     

Self-Deception and Emotional Coherence

This paper proposes that self-deception results from the emotional coherence of beliefs with subjective goals. We apply the HOTCO computational model of emotional coherence to simulate a rich case of self-deception from Hawthorne's The Scarlet Letter.We argue that this model is more psychologically realistic than other available accounts of self-deception, and discuss related issues such as wishful thinking, intention, and the division of the self.     

Post-pass partitioning of signal processing programs

Symmetric multiprocessor systems are increasingly common, not only as high-throughput servers, but as a vehicle for executing a single application in parallel in order to reduce its execution latency. This article presents Pedigree, a compilation tool that employs a new partitioning heuristic based on the program dependence graph (PDG). Pedigree creates overlapping, potentially interdependent threads, each executing on a subset of the SMP processors that matches the thread’s available parallelism. A unified framework is used to build threads from procedures, loop nests, loop iterations, and smaller constructs. Pedigree does not require any parallel language support; it is post-compilation tool that reads in object code. The SDIO Signal and Data Processing Benchmark Suite has been selected as an example of real-time, latency-sensitive code. Its coarse-grained data flow parallelism is naturally exploited by Pedigree to achieve speedups of 1.63×/2.13× (mean/max) and 1.71×/2.41× on two and four processors, respectively. There is roughly a 20% improvement over existing techniques that exploit only data parallelism. By exploiting the unidirectional flow of data for coarse-grained pipelining, the synchronization overhead is typically limited to less than 6% for synchronization latency of 100 cycles, and less than 2% for 10 cycles. This research was supported by ONR contract numbers N00014-91-J-1518 and N00014-96-1-0347. We would like to thank the Pittsburgh Supercomputing Center for use of their Alpha systems.     

A framework for determining design correctness

Quality is one of the main concerns in today's systems and software development and use. One important instrument in verification is the use of formal methods, which means that requirements and designs are analyzed formally to determine their relationships. Furthermore, since professional software design is to an increasing extent a distributed process, the issue of integrating different systems to an entity is of great importance in modern system development and design. Various candidates for formalizing system development and integration have prevailed, but very often, particularly for dynamic conflict detection, these introduce non-standard objects and formalisms, leading to severe confusion, both regarding the semantics and the computability. In contrast to such, we introduce a framework for defining requirement fulfillment by designs, detecting conflicts of various kinds as well as integration of heterogeneous schemata. The framework introduced transcends ordinary logical consequence, as it takes into account static and dynamic aspects of design consistency and, in particular, the specific features of the state space of a specification. Another feature of the approach is that it provides a unifying framework for design conflict analysis and schema integration.     

Election security: Perception and reality

Voters' trust in elections comes from a combination of the mechanisms and procedures we use to record and tally votes, and from confidence in election officials' competence and honesty. Electronic voting systems pose considerable risks to both the perception and reality of trustworthy elections.     

Category Learning in Rhesus Monkeys: A Study of the Shepard, Hovland, and Jenkins (1961) Tasks.

In influential research, R. N. Shepard, C. I. Hovland, and H. M. Jenkins (1961) surveyed humans' categorization abilities using tasks based in rules, exclusive-or (XOR) relations, and exemplar memorization. Humans' performance was poorly predicted by cue-conditioning or stimulus-generalization theories, causing Shepard et al. to describe it in terms of hypothesis selection and rule application that were possibly supported by verbal mediation. The authors of the current article surveyed monkeys' categorization abilities similarly. Monkeys, like humans, found category tasks with a single relevant dimension the easiest and perceptually chaotic tasks requiring exemplar memorization the most difficult. Monkeys, unlike humans, found tasks based in XOR relations very difficult. The authors discuss the character and basis of the species difference in categorization and consider whether monkeys are the generalization-based cognitive system that humans are not. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Audience-induced inhibition of overt practice during learning.

Three experiments with 204 undergraduates examined the hypothesis that an audience can inhibit overt practice and thereby impair learning of unfamiliar words and enhance learning of familiar words. This hypothesis was derived from an analysis of motoric and symbolic mediation during learning. In comparison with learning while alone, the results show that the audience inhibited overt practice of unfamiliar and familiar words and that reduced practice was detrimental to learning unfamiliar words. Inhibition of overt practice with an audience enhanced learning of familiar words in only 1 of the experiments. Instructions to practice overtly reduced the audience-inhibition effect in learning unfamiliar words. The studies are discussed in the context of drive-theory explanations for social facilitation effects in learning. (20 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)