Load balancing algorithms for an extended hypercube

Reduction of the execution time of a job through equitable distribution of work load among the processors in a distributed system is the goal of load balancing. Performance of static and dynamic load balancing algorithms for the extended hypercube, is discussed. Threshold algorithms are very well-known algorithms for dynamic load balancing in distributed systems. An extension of the threshold algorithm, called the multilevel threshold algorithm, has been proposed. The hierarchical interconnection network of the extended hypercube is suitable for implementing the proposed algorithm. The new algorithm has been implemented on a transputer-based system and the performance of the algorithm for an extended hypercube is compared with those for mesh and binary hypercube networks

A general procedure for modified crack closure integral in 3D problems with cracks

In linear elastic fracture mechanics (LEFM), Irwin's crack closure integral (CCI) is one of the signficant concepts for the estimation of strain energy release rates (SERR) G, in individual as well as mixed-mode configurations. For effective utilization of this concept in conjunction with the finite element method (FEM), Rybicki and Kanninen [Engng Fracture Mech. 9, 931 938 (1977)] have proposed simple and direct estimations of the CCI in terms of nodal forces and displacements in the elements forming the crack tip from a single finite element analysis instead of the conventional two configuration analyses. These modified CCI (MCCI) expressions are basically element dependent. A systematic derivation of these expressions using element stress and displacement distributions is required. In the present work, a general procedure is given for the derivation of MCCI expressions in 3D problems with cracks. Further, a concept of sub-area integration is proposed which facilitates evaluation of SERR at a large number of points along the crack front without refining the finite element mesh. Numerical data are presented for two standard problems, a thick centre-cracked tension specimen and a semi-elliptical surface crack in a thick slab. Estimates for the stress intensity factor based on MCCI expressions corresponding to eight-noded brick elements are obtained and compared with available results in the literature.

Decoupled three-dimensional finite element computation of thermoelastic damping using Zener's approximation

We consider three dimensional finite element computations of thermoelastic damping ratios of arbitrary bodies using Zener's approach. In our small-damping formulation, unlike existing fully coupled formulations, the calculation is split into three smaller parts. Of these, the first sub-calculation involves routine undamped modal analysis using ANSYS. The second sub-calculation takes the mode shape, and solves on the same mesh a periodic heat conduction problem. Finally, the damping coefficient is a volume integral, evaluated elementwise. In the only other decoupled three dimensional computation of thermoelastic damping reported in the literature, the heat conduction problem is solved much less efficiently, using a modal expansion. We provide numerical examples using some beam-like geometries, for which Zener's and similar formulas are valid. Among these we examine tapered beams, including the limiting case of a sharp tip. The latter's higher-mode damping ratios dramatically exceed those of a comparable uniform beam.

Coupled electrostatic-elastic analysis for topology optimization using material interpolation

In this paper, we present a novel analytical formulation for the coupled partial differential equations governing electrostatically actuated constrained elastic structures of inhomogeneous material composition. We also present a computationally efficient numerical framework for solving the coupled equations over a reference domain with a fixed finite-element mesh. This serves two purposes: (i) a series of problems with varying geometries and piece-wise homogeneous and/or inhomogeneous material distribution can be solved with a single pre-processing step, (ii) topology optimization methods can be easily implemented by interpolating the material at each point in the reference domain from a void to a dielectric or a conductor. This is attained by considering the steady-state electrical current conduction equation with a `leaky capacitor' model instead of the usual electrostatic equation. This formulation is amenable for both static and transient problems in the elastic domain coupled with the quasi-electrostatic electric field. The procedure is numerically implemented on the COMSOL Multiphysics (R) platform using the weak variational form of the governing equations. Examples have been presented to show the accuracy and versatility of the scheme. The accuracy of the scheme is validated for the special case of piece-wise homogeneous material in the limit of the leaky-capacitor model approaching the ideal case.

Cracks emanating from pin-loaded lugs

Pin-loaded lugs were analysed in the presence of cracks emanating from circular holes. The analysis presents a unified treatment of interference, push or clearance fit pins. Both metallic (isotropic) and composite (orthotropic) plates were dealt with. The finite element model used special singular six-noded quadrilateral elements at the crack tip. The non-linear load contact behaviour at the pin-hole interface was dealt with by an inverse technique. A modified crack closure integral (MCCI) technique was used to evaluate the strain energy release rates (SERRs) and stress intensity factors (SIFs) at the crack tips. Numerical results are presented showing the non-linear variation of SIF with applied stress, and the influence of the amount of interference or clearance and the interfacial friction on SIF.

A Flat Concurrent Prolog compiler for PARAM

We describe a compiler for the Flat Concurrent Prolog language on a message passing multiprocessor architecture. This compiler permits symbolic and declarative programming in the syntax of Guarded Horn Rules, The implementation has been verified and tested on the 64-node PARAM parallel computer developed by C-DAC (Centre for the Development of Advanced Computing, India), Flat Concurrent Prolog (FCP) is a logic programming language designed for concurrent programming and parallel execution, It is a process oriented language, which embodies dataflow synchronization and guarded-command as its basic control mechanisms. An identical algorithm is executed on every processor in the network, We assume regular network topologies like mesh, ring, etc, Each node has a local memory, The algorithm comprises of two important parts: reduction and communication, The most difficult task is to integrate the solutions of problems that arise in the implementation in a coherent and efficient manner. We have tested the efficacy of the compiler on various benchmark problems of the ICOT project that have been reported in the recent book by Evan Tick, These problems include Quicksort, 8-queens, and Prime Number Generation, The results of the preliminary tests are favourable, We are currently examining issues like indexing and load balancing to further optimize our compiler.

Stiffened composite cylindrical panels�Optimum lay-up for buckling by ranking

Buckling of discretely stiffened composite cylindrical panels made of repeated sublaminate construction is studied using a finite element method. In repeated sublaminate construction, a full laminate is obtained by repeating a basic sublaminate, which has a smaller number of plies. This paper deals with the determination of the optimum lay-up for buckling by ranking of such stiffened (longitudinal and hoop) composite cylindrical panels. For this purpose we use the particularized form of a four-noded, 48 degrees of freedom doubly curved quadrilateral thin shell finite element together with a fully compatible two-noded, 16 degrees of freedom composite stiffener element. The computer program developed has been used, after extensive checking for correctness, to obtain an optimum orientation scheme of the plies in the sublaminate so as to achieve maximum buckling load for a specified thickness of typical stiffened composite cylindrical panels.

Link Conditions for Simplifying Meshes with Embedded Structures

Interactive visualization applications benefit from simplification techniques that generate good-quality coarse meshes from high-resolution meshes that represent the domain. These meshes often contain interesting substructures, called embedded structures, and it is desirable to preserve the topology of the embedded structures during simplification, in addition to preserving the topology of the domain. This paper describes a proof that link conditions, proposed earlier, are sufficient to ensure that edge contractions preserve the topology of the embedded structures and the domain. Excluding two specific configurations, the link conditions are also shown to be necessary for topology preservation. Repeated application of edge contraction on an extended complex produces a coarser representation of the domain and the embedded structures. An extension of the quadric error metric is used to schedule edge contractions, resulting in a good-quality coarse mesh that closely approximates the input domain and the embedded structures.

Large deformation finite element analysis of laminated circular composite plates

A 48 d.o.f., four-noded quadrilateral laminated composite shell finite element is particularised to a sector finite element and is used for the large deformation analysis of circular composite laminated plates. The strain-displacement relationships for the sector element are obtained by reducing those of the quadrilateral shell finite element by substituting proper values for the geometric parameters. Subsequently, the linear and tangent stiffness matrices are formulated using conventional methods. The Newton-Raphson method is employed as the nonlinear solution technique. The computer code developed is validated by solving an isotropic case for which results are available in the literature. The method is then applied to solve problems of cylindrically orthotropic circular plates. Some of the results of cylindrically orthotropic case are compared with those available in the literature. Subsequently, application is made to the case of laminated composite circular plates having different lay-up schemes. The computer code can handle symmetric/unsymmetric lay-up schemes. The large displacement analysis is useful in estimating the damage in composite plates caused by low-velocity impact.

Reverse flotation of silica from Kudremukh iron ore .2. Optimization of flotation process

An experimental programme based on statistical analysis was used for optimizing the reverse Rotation of silica from non-magnetic spiral preconcentrate of Kudremukh iron ore. Flotation of silica with amine and starch as the Rotation reagents was studied to estimate the optimum reagent levels at various mesh of grind. The experiments were first carried out using a two level three factor design. Analysis of the results showed that two parameters namely, the concentration level of the amine collector and the mesh of grind, were significant. Experiments based on an orthogonal design of the hexagonal type were then carried out to determine the effects of these two variables, on recovery and grade of the concentrate. Regression equations have been developed as models. Response contours have been plotted using the 'path of steepest ascent', maximum response has been optimized at 0.27 kg/ton of amine collector, 0.5 kg/ton of starch and mesh of grind of 48.7% passing 300 mesh to give a recovery of 83.43% of Fe in the concentrate containing 66.6% Fe and 2.17% SiO2.

Automatic decomposition of unstructured meshes employing genetic algorithms for parallel FEM computations

Parallel execution of computational mechanics codes requires efficient mesh-partitioning techniques. These mesh-partitioning techniques divide the mesh into specified number of submeshes of approximately the same size and at the same time, minimise the interface nodes of the submeshes. This paper describes a new mesh partitioning technique, employing Genetic Algorithms. The proposed algorithm operates on the deduced graph (dual or nodal graph) of the given finite element mesh rather than directly on the mesh itself. The algorithm works by first constructing a coarse graph approximation using an automatic graph coarsening method. The coarse graph is partitioned and the results are interpolated onto the original graph to initialise an optimisation of the graph partition problem. In practice, hierarchy of (usually more than two) graphs are used to obtain the final graph partition. The proposed partitioning algorithm is applied to graphs derived from unstructured finite element meshes describing practical engineering problems and also several example graphs related to finite element meshes given in the literature. The test results indicate that the proposed GA based graph partitioning algorithm generates high quality partitions and are superior to spectral and multilevel graph partitioning algorithms.

Role of length scales on microwave thawing dynamics in 2D cylinders

Microwave (MW) thawing of 2D frozen cylinders exposed to uniform plane waves from one face, is modeled using the effective heat capacity formulation with the MW power obtained from the electric field equations. Computations are illustrated for tylose (23% methyl cellulose gel) which melts over a range of temperatures giving rise to a mushy zone. Within the mushy region the dielectric properties are functions of the liquid volume fraction. The resulting coupled, time dependent non-linear equations are solved using the Galerkin finite element method with a fixed mesh. Our method efficiently captures the multiple connected thawed domains that arise due to the penetration of MWs in the sample. For a cylinder of diameter D, the two length scales that control the thawing dynamics are D/D-p and D/lambda(m), where D-p and lambda(m) are the penetration depth and wavelength of radiation in the sample respectively. For D/D-p, D/lambda(m) much less than 1 power absorption is uniform and thawing occurs almost simultaneously across the sample (Regime I). For D/D-p much greater than 1 thawing is seen to occur from the incident face, since the power decays exponentially into the sample (Regime III). At intermediate values, 0.2 < D/D-p, D/lambda(m) < 2.0 (Regime II) thawing occurs from the unexposed face at smaller diameters, from both faces at intermediate diameters and from the exposed and central regions at larger diameters. Average power absorption during thawing indicates a monotonic rise in Regime I and a monotonic decrease in Regime III. Local maxima in the average power observed for samples in Regime II are due to internal resonances within the sample. Thawing time increases monotonically with sample diameter and temperature gradients in the sample generally increase from Regime I to Regime III. (C) 2002 Elsevier Science Ltd. All rights reserved.

A System-C based Micro architectural Exploration Framework for Latency, Power and Performance Trade-offs of On-Chip Interconnection

We describe a System-C based framework we are developing, to explore the impact of various architectural and microarchitectural level parameters of the on-chip interconnection network elements on its power and performance. The framework enables one to choose from a variety of architectural options like topology, routing policy, etc., as well as allows experimentation with various microarchitectural options for the individual links like length, wire width, pitch, pipelining, supply voltage and frequency. The framework also supports a flexible traffic generation and communication model. We provide preliminary results of using this framework to study the power, latency and throughput of a 4x4 multi-core processing array using mesh, torus and folded torus, for two different communication patterns of dense and sparse linear algebra. The traffic consists of both Request-Response messages (mimicing cache accesses)and One-Way messages. We find that the average latency can be reduced by increasing the pipeline depth, as it enables higher link frequencies. We also find that there exists an optimum degree of pipelining which minimizes energy-delay product.

Performance Evaluation of Distance-Hop Proportionality on Geometric Graph Models of Dense Sensor Networks

Wireless sensor networks can often be viewed in terms of a uniform deployment of a large number of nodes on a region in Euclidean space, e.g., the unit square. After deployment, the nodes self-organise into a mesh topology. In a dense, homogeneous deployment, a frequently used approximation is to take the hop distance between nodes to be proportional to the Euclidean distance between them. In this paper, we analyse the performance of this approximation. We show that nodes with a certain hop distance from a fixed anchor node lie within a certain annulus with probability approach- ing unity as the number of nodes n → ∞. We take a uniform, i.i.d. deployment of n nodes on a unit square, and consider the geometric graph on these nodes with radius r(n) = c q ln n n . We show that, for a given hop distance h of a node from a fixed anchor on the unit square,the Euclidean distance lies within [(1−ǫ)(h−1)r(n), hr(n)],for ǫ > 0, with probability approaching unity as n → ∞.This result shows that it is more likely to expect a node, with hop distance h from the anchor, to lie within this an- nulus centred at the anchor location, and of width roughly r(n), rather than close to a circle whose radius is exactly proportional to h. We show that if the radius r of the ge- ometric graph is fixed, the convergence of the probability is exponentially fast. Similar results hold for a randomised lattice deployment. We provide simulation results that il- lustrate the theory, and serve to show how large n needs to be for the asymptotics to be useful.

Closed form solutions for element equilibrium and flexibility matrices of eight node rectangular plate bending element using integrated force method

Closed form solutions for equilibrium and flexibility matrices of the Mindlin-Reissner theory based eight-node rectangular plate bending element (MRP8) using integrated Force Method (IFM) are presented in this paper. Though these closed form solutions of equilibrium and flexibility matrices are applicable to plate bending problems with square/rectangular boundaries, they reduce the computational time significantly and give more exact solutions. Presented closed form solutions are validated by solving large number of standard square/rectangular plate bending benchmark problems for deflections and moments and the results are compared with those of similar displacement-based eight-node quadrilateral plate bending elements available in the literature. The results are also compared with the exact solutions.