Obtaining an optimal schedule for a set of precedence-constrained tasks with arbitrary costs is a well-known NP-complete problem. However, optimal solutions are desired in many situations. In this paper we propose sea...
详细信息
Obtaining an optimal schedule for a set of precedence-constrained tasks with arbitrary costs is a well-known NP-complete problem. However, optimal solutions are desired in many situations. In this paper we propose search-based algorithms for determining optimal schedules for moderately large problem sizes. The first algorithm which is based on the A* search technique uses a computationally efficient cost function for guiding the search with reduced complexity. We propose a number of state-pruning techniques to reduce the size of the search space. For further lowering the complexity, we parallelize the search. The parallel version is based on reduced interprocessor communication and is guided by static and dynamic load-balancing schemes to evenly distribute the search states to the processors. We also propose an approximate algorithm that guarantees a bounded deviation from the optimal solution but takes considerably shorter time. Based on an extensive experimental evaluation of the algorithms, we conclude that the parallel algorithm with pruning techniques is an efficient scheme for generating optimal solutions for medium to moderately large problems while the approximate algorithm is a useful alternative if slightly degraded solutions are acceptable.
In order to generate local addresses for an array section A(l:h:s) with block-cyclic distribution, an efficient compiling method is required. In this paper, two local address generation methods for the block-cyclic di...
详细信息
In order to generate local addresses for an array section A(l:h:s) with block-cyclic distribution, an efficient compiling method is required. In this paper, two local address generation methods for the block-cyclic di...
详细信息
ISBN:
(纸本)0780342291
In order to generate local addresses for an array section A(l:h:s) with block-cyclic distribution, an efficient compiling method is required. In this paper, two local address generation methods for the block-cyclic distribution are presented. One is a simple local address generation method that is modified from the virtual-block scheme. The other is a linear-time /spl Delta/M table construction method. The array elements of A(l:h:s) to be accessed at run-time build up a family of lines. By using the equation of the lines, a /spl Delta/M table can be generated in O(k) time. Experimental results show that a simple local address generation method has poor performance but a linear-time /spl Delta/M table generation method is faster than other algorithms in /spl Delta/M table generation time and access time for 10,000 array elements.
This paper describes the implementation of transmission-line matrix (TLM) method algorithms on a massively parallel computer (DECmpp 12000), the technique of distributed computing in the UNIX environment, and the comb...
详细信息
This paper describes the implementation of transmission-line matrix (TLM) method algorithms on a massively parallel computer (DECmpp 12000), the technique of distributed computing in the UNIX environment, and the combination of TLM analysis with Prony's method as well as with autoregressive moving average (ARMA) digital signal processing for electromagnetic field modelling. By combining these advanced computation techniques, typical electromagnetic field modelling of microwave structures by TLM analysis can be accelerated by a few orders of magnitude.
In order to solve the speed problem and shallow reasoning problem met in current research in fault diagnosis expert system, this paper presents a model based parallel fault diagnosis expert system for energy managemen...
Progress has been made in computational implementation of speech production based on physiological data. An inverse dynamics model of the speech articulator's musculo-skeletal system, which is the mapping from art...
Progress has been made in computational implementation of speech production based on physiological data. An inverse dynamics model of the speech articulator's musculo-skeletal system, which is the mapping from articulator trajectories to electromyographic (EMG) signals, was modeled using the acquired forward dynamics model and temporal (smoothness of EMG activation) and range constraints. This inverse dynamics model allows the use of a faster speech motor control scheme, which can be applied to phoneme-to-speech synthesis via musclo-skeletal system dynamics, or to future use in speech recognition. The forward acoustic model, which is the mapping from articulator trajectories to the acoustic parameters, was improved by adding velocity and voicing information inputs to distinguish acoustic parameter differences caused by changes in source characteristics.
This study demonstrates a paradigm for modeling speech production based on neural networks. Using physiological data from speech utterances, a neural network learns the forward dynamics relating motor commands to musc...
ISBN:
(纸本)9781558602748
This study demonstrates a paradigm for modeling speech production based on neural networks. Using physiological data from speech utterances, a neural network learns the forward dynamics relating motor commands to muscles and the ensuing articulator behavior that allows articulator trajectories to be generated from motor commands constrained by phoneme input strings and global performance parameters. From these movement trajectories, a second neural network generates PARCOR parameters that are then used to synthesize the speech acoustics.
暂无评论