Image processing on the massively parallel processor

Potter,

doi:10.1109/mc.1983.1654168

Cited by 56 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When the image size matches the size of the multiprocessor (e.g., NxN mesh for In order to cost-effectively build a multiprocessor with thousands of processors, individual processors must be small, given the technological limitations. Normally, a typical machine will have PEs with I-bit ALUs and a small memory, which may be sufficient for small pixel based operations but definitely lacks the power that is needed for intermediate [5,6,7], GRID [8], GAPP [9], and the MPP [10,11,12]. Each of-these machines has its own special features, but all of them have the same general form.…”

Section: Mesh Connected Computersmentioning

confidence: 99%

Parallel Architectures and Parallel Algorithms for Integrated Vision Systems

Patel

Choudhary

1990

The Kluwer International Series in Engineering and Computer Science

View full text Add to dashboard Cite

Computer vision has been regarded as one of the most complex and computationally intensive -problems. An integrated vision system (lVS) is a system that uses vision algorithms from all levels of processing to perform for a high level application (e.g, object recognition). An IVS normally A multiprocessor architecture for IVSs (called NETRA) is presented. NETRA is highly flexible without the use of complex interconnection schemes. NETRA is recursively defined hierarchical architecture whose leaf nodes consist of clusters processors connected with a programmable crossbar with a selective broadcast capability. Hence, it is easily scalable from small to large systems. Homogeneity of NETRA permits fault tolerance and graceful degradation under faults. Several refinements in the architecture over the original design are also proposed.Performance of several vision algorithms when they are mapped on one cluster is presented. It is shown that SIMD, MIMD and systolic algorithms can be easily mapped onto processor clusters, and almost linear speedups are possible. For some algorithms, analytical performance results are compared with those obtained using an implementation. It is observed that the analysis is very accurate.An extensive analysis of inter-cluster communication strategies in NETRA is presented. A methodology to evaluate performance of algorithms on NETRA is described. Performance analysis of parallel algorithms when mapped across clusters is presented. The parameters are derived from the characteristics of the parallel algorithms, which are then, used to evaluate the alternative communication strategies in NETRA. The effects of communication interference on the performance of algorithms are studied. It is observed that if communication speeds are matched with the computation speeds, almost linear speedups are possible when algorithms are mapped across clusters.Finally, several techniques to perform data decomposition, and static and dynamic load balancing for IVS afgorithms are described. These techniques can be used to perform load balancing for intermediate and high level, data dependent vision algorithms. These techniques are novel because they use knowledge about the data when it is produced and use knowledge about the computation in the next task to perform load balancing in an integrated environment. They are shown to perform well, using them on an implementation of a motion estimation system on a hypercube mUltiprocessor. attempting to define and solve pans of the problems for many years. However, to say that computer vision is in its infancy today is a correct judgment of the state of the an in artificial vision. Furthermore, nobody knows the answer to the question of whether it is possible to make artificial vision as powerful and general as human vision. One of the many reasons for not knowing the answer is that little is understood about human vision itself. LIST OF TABLESThere are several approaches to tackling the computational problems in computer vision. One of the approaches, which is also th...

show abstract

Section: Mesh Connected Computersmentioning

confidence: 99%

Parallel Architectures and Parallel Algorithms for Integrated Vision Systems

Patel

Choudhary

1990

The Kluwer International Series in Engineering and Computer Science

View full text Add to dashboard Cite

show abstract

“…Its regular and intuitive topology makes the mesh eminently suitable for VLSI implementation, with several models built over the years. Examples include the ILLIAC IV, the STARAN, the MPP, and the MasPar, among many others [4,5,11,32]. Yet, the mesh is not for everyone: its large computational diameter makes the mesh architecture less attractive in contexts where the computation involves data items spread over processing elements far apart.…”

Section: Introductionmentioning

confidence: 99%

Time-Optimal Proximity Graph Computations on Enhanced Meshes

Olariu

Zomaya

1998

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

“…This work ranges from the MPP machine developed at Goodyear [4] in the 1970's to the Connection Machine today [3]. These machines are generally viewed (and sometimes even advertised) as large "supercomputers."…”

Section: Introductionmentioning

confidence: 99%

The Data Structure Accelerator Architecture

Zippel¹

1991

View full text Add to dashboard Cite

Image processing on the massively parallel processor

Cited by 56 publications

References 4 publications

Parallel Architectures and Parallel Algorithms for Integrated Vision Systems

Parallel Architectures and Parallel Algorithms for Integrated Vision Systems

Time-Optimal Proximity Graph Computations on Enhanced Meshes

The Data Structure Accelerator Architecture

Contact Info

Product

Resources

About