G. C. Fox and J. G. Koller, "Code generation by a generalized neural network", Journal of Parallel and Distributed Computing, Vol. 7, No. 2, pp. 388-410, 1989. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Maximally Fast and Arbitrarily Fast Hardware Efficient.. - Potkonjak, Rabaey (1996) (Correct)
....probabilistic techniques often provide a good trade off between the run time and the quality of solution when no clear insight in a more targeted optimization process is available. Recently, neural network techniques were proposed for a probabilistic approach to the application of transformations [Fox89]. Compound approaches which combine probabilistic (probabilistic sampling and simulated annealing) and local heuristic approaches were used to demonstrate a significant reductions in area [Pot94] and power [Cha93] We will conclude our survey of related research by itemizing transformation ....
G.C. Fox, J.G. Koller: "Code Generation by a Generalized Neural Network", Journal of Parallel and Distributed Computing, Vol. 7, No. 2, pp. 388-410, 1989.
Power Optimization using Divide-and-Conquer Techniques for .. - Hong, Potkonjak, al. (1999) (4 citations) (Correct)
....have been proposed for ordering of transformations in both compiler and behavioral synthesis literature. For example, backward propagation based neural network techniques were used for developing a probabilistic approach to the application of transformations in compilers for parallel computers [Fox and Koller 1989] and approaches which combine both simulated annealing based probabilistic and local heuristic optimization mechanism were used to demonstrate significant reductions in area and power [Chandrakasan et al. 1995] In behavioral and logic synthesis several bottleneck identification and elimination ....
Fox, G. and Koller, J. 1989. Code generation by a generalized neural network. Journal of Parallel and Distributed Computing 7, 2, 388--410.
Parallel Computers and Complex Systems - Fox, Coddington (1994) (2 citations) Self-citation (Fox) (Correct)
....routing in a network [26] and more generally to combining networks which implement global reduction formulae such as forming a set of sums y j = X i M ji x i (19) where y j , M ji , and x i are all distributed over the nodes of a parallel computer. A very preliminary examination was given in [31] of the application of these ideas to register allocation for compilers. We have explored more deeply the application of these methods to multivehicle navigation [27, 16] In that case fx m (t)g is the path of vehicle m in a two or three dimensional space with m at position x m at time t. 5.2 ....
....approximation is used [55] This indicates that the problems found in using neural networks for optimization lie not with the method, but with the choice of variables and the necessity of introducing penalty terms. We have also used neural network optimization successfully for optimizing compilers [31, 28], and robotic vehicle navigation [27, 16] 7.4 Elastic Net The elastic net was introduced as a physically based approach that outperformed the neural network method for TSP [10] The basic idea behind the elastic net is to invent a physical system whose equilibrium state is the desired ....
Fox, G. C. & Koller, J. G. (1989). Code generation by a generalized neural network: General principles and elementary examples. J. Parallel and Distributed Computing 6(2), 388-- 410.
Behavioral Level Guidance Using Property-Based Design.. - Lisa Marie Guerra (1996) (1 citation) (Correct)
No context found.
G. C. Fox and J. G. Koller, "Code generation by a generalized neural network", Journal of Parallel and Distributed Computing, Vol. 7, No. 2, pp. 388-410, 1989.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC