The Metaflow architecture

The Metaflow architecture, a unified approach to maximizing the performance of superscalar microprocessors, is introduced. The Metaflow architecture exploits inherent instruction-level parallelism in conventional sequential programs by hardware means, without relying on optimizing compilers. It is based on a unified structure, the DRIS (deferred-scheduling, register-renaming instruction shelf), that manages out-of-order execution and most of the attendant problems. Coupling the DRIS with a speculative-execution mechanism that avoids conditional branch stalls results in performance limited only be inherent instruction-level parallelism and available execution resources. Although presented in the context of superscalar machines, the technique is equally applicable to a superpipelined implementation. Lightning, the first implementation of the Metaflow architecture, which executes the Sparc RISC instruction set is described     

Hearing the horror: A comment on the final report of the APA Task Force on the Victims of Crime and Violence.

Comments that a critical element in the final report of the American Psychological Association (APA) Task Force on the Victims of Crime and Violence may be lost simply because of the enormity and complexity of the issues involved. The real nature of the victim's emotional experience is often not directly addressed by researchers or service providers in the mental health community. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The glass fibre-polymer interface: II—Work of fracture and shear stresses

Pull-out experiments have been carried out on single production fibres under carefully controlled conditions. Four parameters were determined. The interfacial yield stresses, of about 9–14 MPa, were very much smaller than the shear strengths of the bulk polymers in the case of an epoxy, whether post-cured or not, and a non-post-cured polyester. Values for the work of fracture of the interface varied from 140 to 300 Jm^?2, and again were less than those of the polymer. Interface failure sometimes took place in the epoxy rather than at the fibre surface, whereas with the polyester it always took place at the fibre surface. After interface failure, pull-out was governed by friction, with maximum shear stresses of 7–10 MPa for polyester, and 21–34 MPa for epoxy, the higher values being obtained for the post-cured resins. Average frictional shear stresses were sometimes less than a half of the maximum shear stress, indicating that the fibre Poisson's shrinkage was playing an important role in the pull-out process. A silicone release agent reduced the frictional shear stresses to 2·5 MPa, with both resins.     

FMR and EXAFS modeling of heat-treated Fe-rich and Co-rich TM-M thin films

Ion-beam sputter-deposited alloy films of Co/sub 74/Fe/sub 6/B/sub 15/Si/sub 5/ and Fe/sub 75/Ni/sub 5/B/sub 15/Si/sub 5/ were examined for their magnetic and structural properties. Films were characterized by ferromagnetic resonance, vibrating sample magnetometry, and extended X-ray absorption fine structure (EXAFS) analysis. Using atomic parameters deduced from EXAFS modeling and fitting procedures, magnetic properties were calculated with no adjustable parameters. Correlation between perpendicular FMR measurements and EXAFS first-shell modeling suggests a low-temperature formation of cobalt-borides in the Co/sub 74/Fe/sub 6/B/sub 15/Si/sub 5/ alloy. Annealed Fe/sub 75/Ni/sub 5/B/sub 15/Si/sub 5/ samples did not display evidence of structural and/or magnetic instabilities until the onset of long-range crystallization near T/sub ann/=400 degrees C.<>     

Study of the nutrient distribution in root tips of the tropical forage Brachiaria

A Brachiaria breeding project is being conducted at CIAT, Colombia to combine acid soil adaptation of B. decumbens with other favourable traits of Brachiaria species that are less adapted to acid soils. Micro-PIXE was applied to investigate nutrient uptake and distribution in root tips of different species grown in hydroponic culture under control and simulated acid soil stress conditions. Different sample measurement approaches were evaluated, including: (1) linear scans with single point measurements along the root axis; (2) mapping of whole root tips; and (3) mapping of root cross sections. Different tissue types could be distinguished on the base of differences in nutrient concentrations and/or Al stress. Al, if supplied under nutrient stress conditions, increased P accumulation in the central vascular tissue of the meristematic and elongation zone of B. decumbens and B. brizantha. Furthermore, a negative correlation was found between Al and Cl accumulation in the root cap of B. decumbens.     

Polynomial-complexity deadlock avoidance policies for sequentialresource allocation systems

The development of efficient deadlock avoidance policies (DAPs) for sequential resource allocation systems (RASs) is a problem of increasing interest in the scientific community, largely because of its relevance to the design of large-scale flexibly automated manufacturing systems. Much of the work on this problem existing in the literature is focused on the so-called single-unit RAS model, which is the simplest model in the considered class of RASs. Furthermore, due to a well-established result stating that, even for single-unit RASs, the computation of the maximally permissive DAP is intractable (NP-hard), many researchers (including our group) have focused on obtaining good suboptimal policies which are computationally tractable (scalable) and provably correct. In the first part of the paper, it is shown, however, that for a large subset (in fact, a majority) of single-unit RASs, the optimal DAP can be obtained in real-time with a computational cost which is a polynomial function of the system size (i.e., the number of resource types and the distinct route stages of the processes running through the system). The implications of this result for the entire class of single-unit RASs are also explored. With a result on the design of optimal DAPs for single-unit RASs, the second part of the paper concentrates on the development of scalable and provably correct DAPs for the more general case of conjunctive RASs     

Infinite-dimensional convex optimization in optimal and robustcontrol theory

Many engineering problems can be shown to be equivalent to solving semidefinite programs (SPs), i.e., convex optimization problems involving linear matrix inequalities (LMIs). Powerful computation tools are available for such problems in the finite-dimensional case. However, the problems arising in optimal and robust control theory are often infinite dimensional, and so adequate computation tools are not available. The key to tackling such problems with finite computation tools is to have a primal-dual formulation of the problem without duality gap. In this paper we study infinite-dimensional SPs and present a lifting technique to recast SPs as parameterized linear programs (LPs). This enables the wealth of theoretical tools available for infinite-dimensional LPs to be extended to infinite-dimensional SPs. In particular, we develop some new sufficient conditions for the lack of a duality gap for infinite-dimensional SPs and give an exact characterization of the primal and dual problems for these cases. Both primal and dual problems are formed as infinite-dimensional SP problems, with finite truncations to each giving upper and lower bounds, respectively, on the exact solution to the infinite-dimensional problem. Thus, these results can form the basis of practical computation schemes for infinite-dimensional problems, which require only finite-dimensional computation tools. To illustrate the power of these tools we apply the results to two previously unsolved optimization problems, namely minimizing the l₁ norm of a closed-loop system subject to bounds on the frequency response magnitude at a finite number of points and/or bounds on the H₂ norm     

New advances on a posteriori error on constitutive relation in f.e. analysis

This paper deals with error estimators based on residuals on the constitutive relation which have been developed for the past 20 years at Cachan. Especially in the case of elasticity, these error estimators can become poor in situations where the material and the mesh are strongly anisotropic. The crucial point herein is the construction of equilibrated stress fields from the computed finite element solution. Therefore, in this paper, the approach and in particular this last point are re-examined. Several important modifications are introduced in the concepts and basic techniques. Hence, a new generation of error estimators which seem to be extremely robust upon initial applications has been generated.