A fast asynchronous algorithm for linear feature extraction on IBM SP-2

We present a fast parallel implementation of linear feature extraction on IBM SP-2. We first analyze the machine features and the problem characteristics to understand the overheads in parallel solutions to the problem. Based on these, we propose an asynchronous algorithm which enhances processor utilization and overlaps communication with computation by maintaining algorithmic threads in each processing node. Our implementation shows that, given a 512/spl times/512 image, the linear feature extraction task can be performed in 0.065 seconds on a SP-2 having 64 processing nodes. A serial implementation takes 3.45 seconds on a single processing node of SP-2. A previous implementation on CM-5 takes 0.1 second on a partition of 512 processing nodes. Experimental results on various sizes of images using 4, 8, 16, 32, and 64 processing nodes are also reported.

[1]  Viktor K. Prasanna,et al.  Image Feature Extraction on Connection Machine CM-5 , 1994 .

[2]  Prithviraj Banerjee,et al.  Compilation of scientific programs into multithreaded and message driven computation , 1994, Proceedings of IEEE Scalable High Performance Computing Conference.

[3]  Anant Agarwal,et al.  Performance Tradeoffs in Multithreaded Processors , 1992, IEEE Trans. Parallel Distributed Syst..

[4]  Thomas W. Crockett,et al.  Parallel polygon rendering for message-passing architectures , 1994, IEEE Parallel & Distributed Technology: Systems & Applications.

[5]  Viktor K. Prasanna,et al.  Scalable Data Parallel Implementations of Object Recognition Using Geometric Hashing , 1994, J. Parallel Distributed Comput..

[6]  Edward W. Felten,et al.  Improving the performance of message-passing applications by multithreading , 1992, Proceedings Scalable High Performance Computing Conference SHPCC-92..

[7]  James Robergé.  A data reduction algorithm for planar curves , 1985, Comput. Vis. Graph. Image Process..

[8]  Cho-Chin Lin,et al.  Analysis of cost of performing communications using various communication mechanisms , 1995, Proceedings Frontiers '95. The Fifth Symposium on the Frontiers of Massively Parallel Computation.

[9]  Seth Copen Goldstein,et al.  Active messages: a mechanism for integrating communication and computation , 1998, ISCA '98.

[10]  Bruce P. Lester.  The art of parallel programming , 1993 .

[11]  James George Dunham,et al.  Optimum Uniform Piecewise Linear Approximation of Planar Curves , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  K. Ramesh Babu,et al.  Linear Feature Extraction and Description , 1979, IJCAI.