Automatic Scheduling for Parallel Forward Dynamics Computation of Open Kinematic Chains

Biodegrading plumes in groundwater are often typified by relatively reactive zones around the fringes and less reactive zones in the core. A high degree of refinement is required at the fringes if a model is to be of use in improving the conceptual understanding of plumes. Two strategies for dealing with the potentially high computational demands are (i) parallel processing, where the workload is shared between multiple processors, and (ii) locally adaptive remeshing, where a refined area of the grid tracks the moving plume fringes through the domain. The partial differential equation toolbox, UG (Unstructured Grids) offers advanced numerical tools including adaptive remeshing, sparse matrix storage schemes, and multigrid solvers. It embraces many of these features within a parallel processing environment. This paper reports on a recent development of UG to simulate field scale reactive biogeochemistry including Monod kinetics, NAPL dissolution, mineral precipitation/dissolution and ion exchange. The non-linear multicomponent reactive transport system is solved with the fully coupled method. Test cases have been used for verification of the new capability. The paper illustrates an application to a 3D field site. It is demonstrated that both adaptive remeshing and parallel processing can improve efficiency and in turn facilitate the incorporation of a more complex set of species and reactions such that understanding of plume processes is enhanced.

A programming system has been implemented in which annotated Petri nets are used as machine-processable high-evel design representations. The nets can be used to express the parallelism and the dynamic sequential dependencies found in complex software. They can then be interactively fired to facilitate debugging of the design. The nets are processed into a procedure language, called XL/1, to which a variety of transformations are applied in order to produce more efficient programs. These programs are generated for either a serial or a parallel processing environment. Finally, the XL/1 programs may be translated into PL/I or PL/S. The serial processing versions have been compiled and run successfully, but the parallel processing versions have not yet been run in a parallel processing environment.

This paper proposes an architecture for accomplishing transport protocol processing at Gbps rates. The limitations of currently used transport protocols have been analyzed extensively in recent literature. Several benchmark studies have established the achievable throughput of ISO TP4 and TCP to be in the low Mbps range; several new protocols and implementation techniques have been proposed to achieve 100 Mbps and higher throughput rates. We briefly review some of these protocols and establish the need for a radically different approach to meet our objective. An estimate of the aggregate processing power required for Gbps throughput is developed. It is proposed that a cost effective and practical solution to the processing requirements could be based on a multi-processor system. The opportunities for parallel processing in a typical transport protocol are examined. Several alternate parallel processing approaches are examined and arguments are advanced for selecting a favored approach. A corresponding parallel processing architecture is described. Data structures used to preserve packet ordering and techniques for reducing contention in a multi-processing environment are discussed. An implementation methodology for conventional transport protocols (e.g. TP4) is outlined. Some suggestions are made for improving efficiency by making modifications to the protocol that do not compromise functionality. The performance achievable with this modified architecture is analyzed and some suggestions for further work are presented.

Current and future parallel computing model has been suggested for running and solving large-scale application problems such as climate, bio, cryptology, and astronomy, etc. Parallel computing is a form of computation in which many calculations are carried out simultaneously. And we are able to shorten the execution time of the program, as well as can extend the scale of the problem that can be solved. In this paper, we perform the actual cryptographic algorithms through parallel processing and evaluate its efficiency. Length of the key, which is stable criterion of cryptographic algorithm, judged according to the amount of complete enumeration computation. So we present a detailed procedure of DES key search cryptographic algorithms for executing of enumeration computation in parallel processing environment. And then, we did the simulation through applying to clustering system. As a result, we can measure the safety and solidity of cryptographic algorithm.

SummaryPower system monitoring relies on the reliability of state estimation (SE) results. SE plays a dominant role in data debugging if sufficient data is available. Criticality analysis (CA) integrates SE as a module in which measurements—taken one‐by‐one or in groups (tuples) of minimal cardinality—are designated crucial. The combinatorial nature of extensive CA (not restricted to identifying low‐cardinality critical tuples) characterizes its computational complexity and imposes challenging limits to go beyond. In simple terms, these limits are established by the number of measurements to be combined, the cardinality of tuples, and the computing time required to check the criticality condition. This paper proposes an innovative computational solution to expand CA limits found to date in the literature. A framework with multi‐threads designed cleverly on a graphics processing unit (GPU) parallel processing environment is built. The conceived architecture favors evaluating massive measurement combinations of diverse cardinality in extensive CA. Numerical results reveal significant speed‐ups with the proposed approach, contrasting with those reported in research efforts published so far.

Manipulation of terrain data for a real-time display application

An analysis of parallelism for modular process flowsheet calculations is given. The central idea is to examine various algorithms that allow one to decouple and decentralize flowsheet calculations for computation in a multiprocessor environment. Specific algorithms are evaluated which make use of quasi‐Newton updates to converge the flowsheet equations. From the analysis presented and example problems solved, it is clear that parallel processing can be used to enhance the computational speed of modular flowsheet calculations. In particular, various formulations of the simultaneous modular approach are analyzed to show how parallelism may be taken advantage of in flowsheet solutions.

Offset computation for expanding a polyhedral object by an offset radius is a fundamental geometric process frequently used in manufacturing applications. This process combined with the triple-dexel representation solid model has become popular because of its robustness and compatibility with parallel processing using a graphics processing unit (GPU). In parallel geometric processing, conflicts between threads must be avoided. Thus, we propose a novel parallel offsetting algorithm free from conflicts between threads. The triple-dexel model is a combination of x-, y-, and z-axis-aligned dexel models. Each dexel model is defined based on an orthogonal grid given on a coordinate plane. We subdivide the grid into several sub-grids of a fixed size in advance. For each sub-grid, a block of GPU threads is assigned. As each GPU thread always processes different dexel elements from the other threads in this method, no conflict occurs. Our research group has previously presented a parallel offset computation algorithm for a polyhedral solid model that also uses a triple-dexel representation model and a GPU. In the previous algorithm, the surface polygons of the model are classified into several groups in advance. The parallel offset computation of multiple polygon groups is realized by selecting groups of polygon in which the offset processing of the polygons does not affect one another. This selection process is time-consuming. Computational experiments were performed to analyze the performance difference between the current algorithm and our previous algorithm. In our experiments, the current algorithm achieved speedups of 1.4 times to 3.2 times compared to our previous offsetting algorithm.

An efficient parallel algorithm for forward dynamics computation of human figures is proposed. The algorithm is capable of handling any kinematic chains including structure-varying ones. The asymptotic complexity of the algorithm is O(N) in serial computation and O(log N) in parallel computation on O(N) processors for most practical kinematic chains. The idea is to assemble a kinematic chain by adding the joints one by one and compute the constraint forces at the new joints using the principle of virtual work. The parallelism of the algorithm can be adapted for parallel processing systems with any number of processors by simply changing the assembly order. Simulation examples on an 8-node cluster demonstrate the effectiveness of the algorithm.

An Environment for Knowledge Parallel Processing Used in Process Control

Parallel processing of thresholding based on image between-class variance (BCV) is studied in this paper. In parallel processing, a frame of image is divided into M sub-images with the same size. Computation of the normalized probability and moments of image is distributed to each of the PCs. However, the rest of the computation in the BCV-based algorithm is non-parallel in essence. Hence, partial parallel processing structures are proposed in this study. Computer time required for parallel and non-parallel thresholding algorithms is compared on a working platform. Most of computer time is used for computing the image normalized probability. It is effective to distribute such computational efforts to multiple processors to promote the processing speed. Unfortunately, transmission of data among the processors takes dominant computer time. It induces a limitation on the processing speed of the distributed system. Conclusions drawn from this study show that 50% of the computer time the BCV-based algorithm takes can be reduced by using 4 processors in a proposed parallel structure

A variety of techniques and tools exist to parallelize software systems on different parallel architectures (SIMD, MIMD). With the advances in high-speed networks, there has been a dramatic increase in the number of client/server applications. A variety of client/server applications are deployed today, ranging from simple telnet sessions to complex electronic commerce transactions. Industry standard protocols, like Secure Socket Layer (SSL), Secure Electronic Transaction (SET), etc., are in use for ensuring privacy and integrity of data, as well as for authenticating the sender and the receiver during message passing. Consequently, a majority of applications using parallel processing techniques are becoming synchronization-centric, i.e., for every message transfer, the sender and receiver must synchronize. However, more effective techniques and tools are needed to automate the clustering of such synchronization-centric applications to extract parallelism. The authors present a new clustering algorithm to facilitate the parallelization of software systems in a multiprocessor environment. The new clustering algorithm achieves traditional clustering objectives (reduction in parallel execution time, communication cost, etc.). Additionally, our approach: 1) reduces the performance degradation caused by synchronizations, and 2) avoids deadlocks during clustering. The effectiveness of our approach is depicted with the help of simulation results.

Many advanced ground-based solar telescopes improve the spatial resolution of observation images using an adaptive optics (AO) system. As any AO correction remains only partial, it is necessary to use post-processing image reconstruction techniques such as speckle masking or shift-and-add (SAA) to reconstruct a high-spatial-resolution image from atmospherically degraded solar images. In the New Vacuum Solar Telescope (NVST), the spatial resolution in solar images is improved by frame selection and SAA. In order to overcome the burden of massive speckle data processing, we investigate the possibility of using the speckle reconstruction program in a real-time application at the telescope site. The code has been written in the C programming language and optimized for parallel processing in a multi-processor environment. We analyze the scalability of the code to identify possible bottlenecks, and we conclude that the presented code is capable of being run in real-time reconstruction applications at NVST and future large aperture solar telescopes if care is taken that the multi-processor environment has low latencies between the computation nodes.

Purpose: Monte Carlo (MC) simulation is considered the most accurate method for proton therapy dose calculations. To improve its efficiency, we have previously developed a MC proton dose calculation package, gPMC, on a graphics‐processing unit (GPU) platform. This abstract reports our recent progress towards developing a new version gPMC v2.0, which aims at improving its clinical usability and evaluating it using proton therapy treatment plans. Methods: gPMC v2.0 supports loading source particles from a phase space file. Source particles are first placed to different energy bins according to their energies. Simulation is conducted to transport particles in each bin sequentially. This enforces that particles transported at the same time have similar energies and hence similar computational thread lengths, ensuring computational efficiency in parallel processing. Realistic treatment geometry is supported. A multi‐dose‐counter technique is developed, where multiple dose counters are allocated. Each dose deposition event is randomly assigned to one of the counters. This alleviates memory‐writing conflict problem, when multiple threads attempts to deposit dose to the same voxel. The final dose distribution and statistical uncertainty are obtained based on results at those counters. gPMC v2.0 also supports scoring dose‐to‐water. We have tested the new version in head‐and‐neck patient cases. Results: Computation time is ∼5 seconds for a typical patient case, where 2.1 million protons in a phase space file are simulated. It takes additional ∼8 seconds to load the phase space file. The dose distribution agrees well with that from TOPAS/Geant4. Inside a region of interest defined by the 50% iso‐dose line, gamma passing rate is ∼98% (3mm/3%) and ∼95% (2mm/2%) compared with TOPAS/Geant4 Result. The average relative uncertainty is 1.1%. Conclusion: gPMC has achieved accuracy and efficiency well beyond what was previously accomplished. It supports the recalculation of proton therapy treatment plans, making it feasible for routine clinical applications. This work is supported in part by the University of California Lab Fees Research Program and in part by R01 CA140735

Negatively correlated search (NCS) is a latest intelligence algorithm which maintains multiple individual search processes in parallel and models the behavior of individual search processes using probability distributions. In this paper, an improved NCS inspired by particle swarm optimization (PSO) is proposed, namely PSO-NCS. This algorithm introduces the global best solution (gbest) and personal best solution (pbest) from PSO to calculate the Bhattacharyya Distance (BD) of individuals in the population, which greatly reduces the computational time. Experimental results on six 100 dimensional functions and 10 CEC2005 benchmark functions show that the proposed PSO-NCS has outstanding capability in solving the optimization problems and outperforms the conventional NCS and other methods on most of the test functions. The computational time has been greatly shortened, which saves about 65% in average compared to NCS.