Search

CAVLC (Context-Adaptive Variable Length Coding) is a high-performance entropy method for video and image compression. It is the most commonly used entropy method in the video standard H.264. In recent years, several hardware accelerators for CAVLC have been designed. In contrast, high-performance software implementations of CAVLC (e.g., GPU-based) are scarce. A high-performance GPU-based implementation of CAVLC is desirable in several scenarios. On the one hand, it can be exploited as the entropy component in GPU-based H.264 encoders, which are a very suitable solution when GPU built-in H.264 hardware encoders lack certain necessary functionality, such as data encryption and information hiding. On the other hand, a GPU-based implementation of CAVLC can be reused in a wide variety of GPU-based compression systems for encoding images and videos in formats other than H.264, such as medical images. This is not possible with hardware implementations of CAVLC, as they are non-separable components of hardware H.264 encoders. In this paper, we present CAVLCU, an efficient implementation of CAVLC on GPU, which is based on four key ideas. First, we use only one kernel to avoid the long latency global memory accesses required to transmit intermediate results among different kernels, and the costly launches and terminations of additional kernels. Second, we apply an efficient synchronization mechanism for thread-blocks (In this paper, to prevent confusion, a block of pixels of a frame will be referred to as simply block and a GPU thread block as thread-block.) that process adjacent frame regions (in horizontal and vertical dimensions) to share results in global memory space. Third, we exploit fully the available global memory bandwidth by using vectorized loads to move directly the quantized transform coefficients to registers. Fourth, we use register tiling to implement the zigzag sorting, thus obtaining high instruction-level parallelism. An exhaustive experimental evaluation showed that our approach is between 2.5x and 5.4x faster than the only state-of-the-art GPUbased implementation of CAVLC., The Journal of Supercomputing, 78 (6), ISSN:0920-8542, ISSN:1573-0484

This paper proposes a new approach for a Parallel implementation of Monte-Carlo method aimed for optimal location and sizing of distributed generators in distribution networks. In this approach, a reduction of the solution space is performed, using heuristic strategies, to improve processing times, power losses and voltage profiles considering the location of distributed generators in electric distribution networks. The mathematical formulation of the problem considers a single-objective function, which is composed by weighting factors associated with active power losses and square voltage error minimization; moreover, classical power flow constraints and distributed generation capabilities are considered as restrictions. A master-slave optimization strategy is used to solve the problem: the master stage corresponds to the proposed parallel Monte-Carlo with space solution reduction, which performs the optimal location of the distributed generators; the slave strategy is in charge of solving the resulting optimal power problem. Classical 33-node and 69node test systems are used to validate the proposed approach via MATLAB/MATPOWER software. For comparison purposes, the loss sensitivity factor (LSF), genetic algorithm (GA) and classical parallel Monte-Carlo (PMC) solutions are also tested. The simulations confirm that the proposed reduction to the space solution for the PMC provides improved results in comparison with the existing approaches. © 2018 IEEE. Universidad Nacional de Colombia, UN Departamento Administrativo de Ciencia, Tecnología e Innovación, COLCIENCIAS Department of Science, Information Technology and Innovation, Queensland Government, DSITI UNAL-ITM-39823/P17211 FINANCIAL SUPPORT This work was supported by the Administrative Department of Science, Technology and Innovation of Colombia (COLCIENCIAS) through the National Scholarship Program, calling contest 727-2015, and the Universidad Nacional de Colombia and the Instituto Tecnológico Metropolitano under the project UNAL-ITM-39823/P17211.

The trend toward HD resolution in most of visual multimedia applications has involved the emergence of a large number of video compression standards such as H.264/AVC (Advanced Video Coding) and HEVC (High Efficiency Video Coding). These standards are characterized by high coding performances in terms of compression ratio and video quality compared to previous standards. However, these performances come with large computational complexities which make it difficult to meet real-time encoding for HD resolution on the most common single-core programmable processors. Moreover, as embedded systems have become increasingly used in various multimedia applications, designing an embedded software solution for the H264/AVC encoder represents another difficult challenge since we have to meet the embedded requirements in terms of hardware resources such as memory and power consumption. The new embedded systems with multicore technology represent an attractive solution to overcome these problems. In this context, this thesis is interested in exploiting the performance of the new generation of Texas Instruments multicore DSPs to design an embedded real-time H264/AVC high definition video encoder. We aim a software solution, characterized by high flexibility that allows setting all parameters (quality, bitrate etc) compared to existing IPs. This software flexibility allows also the system scalability by following the coding enhancements as the migration to the newest HEVC standard. Thus, we present the algorithmic, architectural, and structural optimizations which are applied to improve the encoding speed on a single DSP core before moving to a multicore implementation. Then, we propose parallel implementations of the H264/AVC encoder exploiting the multicore architecture of our platform and the potential parallelism in the encoding chain in order to meet real-time constraints while ensuring a good performance in terms of bitrate and video quality. We also explore the problem of resources allocation (computing resources, storage resources, communication resources) with hard execution time constraints. Finally, this thesis opens the way towards the implementation of the new HEVC video coding standard on two embedded systems in order to prepare a software solution for future research; La migration vers la résolution HD de la plupart des applications multimédias visuelles a nécessité la création de nouveaux standards de compression vidéo tels que le H264/AVC (Advanced Video Coding) et le HEVC (High Efficiency Video Coding). Ces standards sont caractérisés par des hautes performances de codage en termes de taux de compression et qualité vidéo par rapport aux normes précédentes. Cependant, ces performances entraînent de grandes complexités de calcul ce qui rend difficile d'assurer un encodage en temps réel pour la résolution HD sur des processeurs monocœurs programmables qui sont les plus répandus. De plus, comme actuellement les systèmes embarqués sont de plus en plus utilisés dans diverses applications multimédias, concevoir une solution logicielle embarquée pour l'encodeur H264/AVC constitue ainsi un défit très difficile puisqu'il faut répondre aux exigences de l'embarqué au niveau des ressources matérielles comme la mémoire et de la consommation d'énergie. Les récents systèmes embarqués dotés de la technologie multicœur représentent une solution attractive pour surmonter ces problèmes. Dans ce contexte, cette thèse s'intéresse à exploiter la performance de la nouvelle génération de DSP multicœurs de Texas Instruments pour concevoir un encodeur H264/AVC embarqué de résolution HD fonctionnant en temps réel. Nous visons une solution logicielle, caractérisée par une forte flexibilité, par rapport aux IPs existants, qui permet de tout paramétrer (qualité, débit etc). Cette flexibilité logicielle permet aussi l'évolutivité de système en suivant les améliorations de codage comme la migration vers la nouvelle norme HEVC, partiellement abordée dans cette thèse. Nous présentons ainsi les diverses optimisations appliquées que ce soient algorithmiques, architecturales et structurelles afin d'améliorer la vitesse d'encodage sur un seul cœur DSP avant de passer à une implémentation multicœur. Ensuite, nous proposons des implémentations parallèles de l'encodeur H264/AVC sur différentes unités de calcul en exploitant le parallélisme potentiel au sein de la chaîne d'encodage afin de satisfaire la contrainte de temps réel tout en assurant une bonne performance de codage en termes de qualité vidéo et débit binaire. Nous étudions également le problème d'allocation des ressources (ressources de calcul, ressources mémoire, ressources de communication) avec de fortes contraintes temporelles d'exécution. Finalement, cette thèse ouvre la voie vers l'implémentation de la nouvelle norme de codage vidéo HEVC sur deux systèmes embarqués monocœurs dans le but de préparer une solution logicielle embarquée pour les futurs travaux de recherche

With two large deformable mirrors with a total of more than 7000 actuators that need to be driven from the measurements of six 60x60 LGS WFSs (total 1.23Mpixels) at 800Hz with a latency of less than one frame, NFIRAOS presents an interesting real-time computing challenge. This paper reports on a recent trade study to evaluate which current technology could meet this challenge, with the plan to select a baseline architecture by the beginning of NFIRAOS construction in 2014. We have evaluated a number of architectures, ranging from very specialized layouts with custom boards to more generic architectures made from commercial off-the-shelf units (CPUs with or without accelerator boards). For each architecture, we have found the most suitable algorithm, mapped it onto the hardware and evaluated the performance through benchmarking whenever possible. We have evaluated a large number of criteria, including cost, power consumption, reliability and flexibility, and proceeded with scoring each architecture based on these criteria. We have found that, with today's technology, the NFIRAOS requirements are well within reach of off-the-shelf commercial hardware running a parallel implementation of the straightforward matrix-vector multiply (MVM) algorithm for wave-front reconstruction. Even accelerators such as GPUs and Xeon Phis are no longer necessary. Indeed, we have found that the entire NFIRAOS RTC can be handled by seven 2U high-end PC-servers using 10GbE connectivity. Accelerators are only required for the off-line process of updating the matrix control matrix every ∼10s, as observing conditions change., Adaptive Optics Systems IV, June 22-27, 2014, Series: Proceedings of SPIE; no. 9148

Accurate electromagnetic modeling of complicated optical structures poses several challenges. Optical metamaterial and plasmonic structures are composed of multiple coexisting dielectric and/or conducting parts. Such composite structures may possess diverse values of conductivities and dielectric constants, including negative permittivity and permeability. Further challenges are the large sizes of the structures with respect to wavelength and the complexities of the geometries. In order to overcome these challenges and to achieve rigorous and efficient electromagnetic modeling of three-dimensional optical composite structures, we have developed a parallel implementation of the multilevel fast multipole algorithm (MLFMA). Precise formulation of composite structures is achieved with the so-called "electric and magnetic current combined-field integral equation." Surface integral equations are carefully discretized with piecewise linear basis functions, and the ensuing dense matrix equations are solved iteratively with parallel MLFMA. The hierarchical strategy is used for the efficient parallelization of MLFMA on distributed-memory architectures. In this paper, fast and accurate solutions of large-scale canonical and complicated real-life problems, such as optical metamaterials, discretized with tens of millions of unknowns are presented in order to demonstrate the capabilities of the proposed electromagnetic solver. (C) 2013 Optical Society of America

Conference Name: 2012 IEEE International Symposium on Antennas and Propagation Date of Conference: 8-14 July 2012 We present a parallel implementation of the multilevel fast multipole algorithm (MLFMA) for fast and accurate solutions of large-scale electromagnetics problems involving composite objects with dielectric and metallic parts. Problems are formulated with the electric and magnetic current combined-field integral equation (JMCFIE) and solved iteratively with MLFMA on distributed-memory architectures. Numerical examples involving canonical and complicated objects, such as optical metamaterials, are presented to demonstrate the accuracy and efficiency of the implementation. © 2012 IEEE.

Date of Conference: 11-15 April 2011 We investigate error sources and their effects on the accuracy of solutions of extremely large electromagnetics problems with parallel implementations of the multilevel fast multipole algorithm (MLFMA). Accuracy parameters and their effects on the accuracy of MLFMA solutions are studied for large-scale problems discretized with hundreds of millions of unknowns. We show that some error sources are more dominant and should be suppressed for more accurate solutions; identifying less-effective error sources may allow us to derive more efficient implementations. Based on our analysis, we determine a set of benchmark problems that can be used to compare the accuracy of solvers for large-scale computations. A benchmarking tool is provided at www.cem.bilkent.edu.tr/ benchmark.

Lattice Boltzmann method (LBM) is employed to investigate natural convection inside porous medium enclosures at high Rayleigh numbers. Volume averaged porous medium model is coupled with the lattice Boltzmann formulation of the momentum and energy equations for fluid flow. A parallel implementation of the single relaxation time LBM is used, which allows the porous medium modified Rayleigh number Ra m to be as high as 10 8. Heat transfer results in the form of the enclosure averaged Nusselt number Nu are obtained for higher modified Rayleigh numbers 10 4 ? Ra m ? 10 8. The Nu values are compared with values in the absence of the form drag term. The form drag due to the porous medium is found to influence Nu considerably. The effect of the form drag on Nu is studied by using a form drag modified Rayleigh number Ra C (extended from Ra m). Utilizing the results for Nu in the high Ra m range, a correlation is proposed between Nu and Ra C for Darcy numbers 10 -6 ? Da ? 10 -2, encompassing the non-Darcy flow regime. � 2011 American Society of Mechanical Engineers.

Date of Conference: 11-17 July 2010 Large-scale electromagnetics problems can be solved efficiently with the multilevel fast multipole algorithm (MLFMA) [1], which reduces the complexity of matrix-vector multiplications required by iterative solvers from O(N 2) to O(N logN). Parallelization of MLFMA on distributed-memory architectures enables fast and accurate solutions of radiation and scattering problems discretized with millions of unknowns using limited computational resources. Recently, we developed a hierarchical partitioning strategy [2], which provides an efficient parallelization of MLFMA, allowing for the solution of very large problems involving hundreds of millions of unknowns. In this strategy, both clusters (sub-domains) of the multilevel tree structure and their samples are partitioned among processors, which leads to improved load-balancing. We also show that communications between processors are reduced and the communication time is shortened, compared to previous parallelization strategies in the literature. On the other hand, improved partitioning of the tree structure complicates the arrangement of communications between processors. In this paper, we discuss communications in detail when MLFMA is parallelized using the hierarchical partitioning strategy. We present well-organized arrangements of communications in order to maximize the efficiency offered by the improved partitioning. We demonstrate the effectiveness of the resulting parallel implementation on a very large scattering problem involving a conducting sphere discretized with 375 million unknowns. ©2010 IEEE.

Multi-objective Evolutionary Algorithms (MOEAs) have features that can be exploited to harness the processing power offered by modern multi-core CPUs. Modern programming languages offer the ability to use threads and processes in order to achieve parallelism that is inherent in multi-core CPUs. In this paper we present our Parallel implementation of a MOEA algorithm and its application to the de novo drug design problem. The results indicate that using multiple processes that execute independent tasks of a MOEA, can reduce significantly the execution time required and maintain comparable solution quality thereby achieving improved performance. ©2009 IEEE. Conference code: 79527 Cited By :2

Date of Conference: 14-18 Sept. 2009 Conference name: 2009 International Conference on Electromagnetics in Advanced Applications, ICEAA '09 We present fast and accurate solutions of large-scale scattering problems using a parallel implementation of the multilevel fast multipole algorithm (MLFMA). By employing a hierarchical partitioning strategy, MLFMA can be parallelized efficiently on distributed-memory architectures. This way, it becomes possible to solve very large problems discretized with hundreds of millions of unknowns. Effectiveness of the developed simulation environment is demonstrated on various scattering problems involving canonical and complicated objects. © 2009 IEEE.

Date of Conference: 30-31 Aug. 2007 Conference name: 2007 Computational Electromagnetics Workshop We present the solution of multilayer metamaterial (MM) structures containing large numbers of unit cells, such as split-ring resonators. Integral-equation formulations of scattering problems are solved iteratively by employing a parallel implementation of the multilevel fast multipole algorithm. Due to ill-conditioned nature of the problems, advanced preconditioning techniques are used to obtain rapid convergence in the iterative solutions. By constructing a sophisticated simulation environment, we accurately and efficiently investigate large and complicated MM structures. © 2007 IEEE.

Date of Conference: 11-16 Nov. 2007 Conference name: The Second European Conference on Antennas and Propagation, EuCAP 2007 We consider effective preconditioning schemes for the iterative solution of integral-equation methods. For parallel implementations, the sparse approximate inverse or the iterative solution of the near-field system enables fast convergence up to certain problem sizes. However, for very large problems, the near-field matrix itself becomes too crude approximation to the dense system matrix and preconditioners generated from the near-field interactions cannot be effective. Therefore, we propose an approximation strategy to the multilevel fast multipole algorithm (MLFMA) to be used as a preconditioner. Our numerical experiments reveal that this scheme significantly outperforms other preconditioners. With the combined effort of effective preconditioners and an efficiently parallelized MLFMA, we are able to solve targets with tens of millions of unknowns in a few hours.

Date of Conference: 14-16 September 2005 Conference Name: 5th International Workshop on Multi-Carrier Spread-Spectrum, MC-SS 2005 In this paper, based on a sequential Monte Carlo method, a computationally efficient algorithm is presented for estimating the residual phase noise, blindly, generated at the output the phase tracking loop employed in OFDM systems. The basic idea is to treat the transmitted symbols as "missing data" and draw samples sequentially of them based on the observed signal samples up to time t. This way, the Bayesian estimates of the phase noise is obtained through these samples, sequentially drawn, together with their importance weights. The proposed receiver structure is seen to be ideally suited for high-speed parallel implementation using VLSI technology.

In this paper, a computationally efficient algorithm is presented for tracing phase noise with linear drift and blind data detection jointly, based on a sequential Monte Carlo(SMC) method. Tracing of phase noise is achieved by Kalman filter and the nonlinearity of the observation process is taken care of by unscented filter rather that using extended Kalman technique. On the other hand,SMC method treats the transmitted symbols as "missing data" and draw samples sequentially of them based on the observed signal samples up to time t. This way, the Bayesian estimates of the phase noise and the incoming data are obtained through these samples, sequentially drawn, together with their importance weights. The proposed receiver structure is seen to be ideally suited for high-speed parallel implementation using VLSI technology. ISL Altran,Galileo Avionics,Selex Sistemi Intergrati,STMicroelectronics,University of Pisa

In this paper, a computationally efficient algorithm is presented for blind phase noise estimation and data detection jointly, based on a sequential Monte Carlo method. The basic idea is to treat the transmitted symbols as " missing data" and draw samples sequentially of them based on the observed signal samples up to time t. This way, the Bayesian estimates of the phase noise and the incoming data are obtained through these samples, sequentially drawn, together with their importance weights. The proposed receiver structure is seen to be ideally suited for high-speed parallel implementation using VLSI technology. Publisher's Version

We address the issue of using parallel implementations as a mean for efficient experimenting and fine tuning of parameters for metaheuristics --a very difficult and especially time consuming process. This is particularly of great impact to the metaheuristics, at least for two reasons: (a) measuring the performance of a metaheuristic implementation requires testing on a large set of instances and on real world instances usually of big and very big size-- a considerable amount of time is needed to accomplish it; (b) the finding of right values for the search parameters of the metaheuristic is almost indispensable for the success of the metaheuristic implementation. Due to this, considerable efforts have been done by researchers and practitioners to provide, on the one hand, a methodology and rigorous basis for experimental evaluation of heuristics (e.g. Rardin and Uzsoy 2001, Barr et al. 1995) and, on the other, to find efficient approaches for fine tuning of parameters such as developing specific software (e.g. Adenso-Diaz and Laguna 2002), use of experimental design (e.g. Coy et al. 2000) and self-adaptive procedures (e.g. Kivijarvi et al.2003). In this paper we show that parallel implementations of metaheuristics based on simple parallel models are efficient tools for both experimenting and fine tuning of parameters. Our proposal is based on two parallel models: the Independent Runs (IR) and the Independent Runs with Autonomous Strategies (IRAS). To illustrate our proposal, we implement the Tabu Search for the 0-1 Multidimensional Knapsack Problem in both models. We use the two implementations for experimenting and fine tuning of parameters obtaining high quality solutions as compared with best known up-to-date results for the problem.

The processing of seismic data, for the imaging of the earth's subsurface, is pushing current computational possibilities to the limit. In this paper results are presented obtained by optimisation and parallelisation of two innovative seismic algorithms with the use of PVM and FORGE. It shows that where the algorithm is CPU bound, a very significant speedup can be acquired, whereas IO-bound algorithms cannot take advantage of the parallel implementation. This leads to two distinct approaches for optimisation. © Springer-Verlag Berlin Heidelberg 1996.

The processing of seismic data, for the imaging of the earth's subsurface, is pushing current computational possibilities to the limit. In this paper results are presented obtained by optimisation and parallelisation of two innovative seismic algorithms with the use of PVM and FORGE. It shows that where the algorithm is CPU bound, a very significant speedup can be acquired, whereas IO-bound algorithms cannot take advantage of the parallel implementation. This leads to two distinct approaches for optimisation. © Springer-Verlag Berlin Heidelberg 1996.

At the Physics and Electronics Laboratory TNO much research is done in the field of computational electromagnetics (CEM). One of the tools in this field is the Finite Difference Time Domain method (FDTD), a method that has been implemented in a program in order to be able to compute electromagnetic scattering by complex objects. In this paper a parallel implementation of the FDTD code is presented. The implementation is used to investigate the efficiency of the code and to investigate the usefulness of such a parallel implementation, especially with respect to increase in problem size and speed up when compared to a conventional supercomputer. Results of some test computations were compared with results of computations performed on a Convex C230 supercomputer, which indicated a efficiency of 70% and a possible speed up of 4.7 times, with respect to the Convex C230. Current work is on the optimisation of the parallel implementation. © Springer-Verlag Berlin Heidelberg 1996.

At the Physics and Electronics Laboratory TNO much research is done in the field of computational electromagnetics (CEM). One of the tools in this field is the Finite Difference Time Domain method (FDTD), a method that has been implemented in a program in order to be able to compute electromagnetic scattering by complex objects. In this paper a parallel implementation of the FDTD code is presented. The implementation is used to investigate the efficiency of the code and to investigate the usefulness of such a parallel implementation, especially with respect to increase in problem size and speed up when compared to a conventional supercomputer. Results of some test computations were compared with results of computations performed on a Convex C230 supercomputer, which indicated a efficiency of 70% and a possible speed up of 4.7 times, with respect to the Convex C230. Current work is on the optimisation of the parallel implementation. © Springer-Verlag Berlin Heidelberg 1996.