论文信息 - Steps toward architecture-independent image processing

Steps toward architecture-independent image processing

Adapt, an architecture-independent language based on the split-and-merge model, is presented. It is specialized for efficient, parallel computation of image-processing algorithms. The split-and-merge programming model is first examined. The Adapt language and its implementation are then described, and its performance is considered.<<ETX>>

Jon A. Webb

[1] I-Chen Wu,et al. An architecture independent programming language for low-level vision , 1989, Comput. Vis. Graph. Image Process..

[2] I-Chen Wu,et al. Machine-independent image processing: Performance of apply on diverse architectures , 1989, Comput. Vis. Graph. Image Process..

[3] David Gelernter,et al. Generative communication in Linda , 1985, TOPL.

[4] W. Daniel Hillis,et al. Data parallel algorithms , 1986, CACM.

[5] Edward D. Lazowska,et al. Speedup Versus Efficiency in Parallel Systems , 1989, IEEE Trans. Computers.

[6] Michael Scudder. An Apply Compiler for the CAAPP , 1990 .

[7] H. T. Kung,et al. The Warp Computer: Architecture, Implementation, and Performance , 1987, IEEE Transactions on Computers.

[8] Robert H. Thomas,et al. The Uniform System: An approach to runtime support for large scale shared memory parallel processors , 1988, ICPP.