Parallel processes

This type of coil was prepared from copper cladded printed circuit board material by applying photolithographic techniques. The p.c. board material is available with difierent copper thicknesses and with either a stiff or a flexible carrier. The flexible material offers the opportunity to adapt the planar coil to a curved three dimensional test object. In our turbine blade application this is a major advantage. The thickness of the copper layer was chosen to be 17 pm The period of the coil was 100 pm The coils were patterned by wet etching, A major advantage of this approach is the parallel processing with narrow tolerances, resulting in many identical Eddy current probes. An example of such a probe is shown in fig. 10. 

Several groups have previously reported parallel implementations of multipole based algorithms for evaluating the electrostatic n-body problem and the related gravitational n-body problem [1, 2]. These methods permit the evaluation of the mutual interaction between n particles in serial time proportional to n logn or even n under certain conditions, with further reductions in computation time from parallel processing. 

Supported by NSF ASC-9318159, NSF CDA-9422065, NTH Research Resource RR08102, and computer time from the North Carolina Supercomputing Center. An earlier version of this paper was presented at the Eighth SIAM Conference on Parallel Processing for Scientific Computing. 

J. A. Board, Jr. et al.. Scalable variants of Multipole-Accelerated Algorithms for Molecular Dynamics Applications, Proceedings, Seventh SIAM Conference on Parallel Processing for Scientific Computing, SIAM, Philadelphia (1995), pp. 295-300. 

Kale, L. V. The Chare Kernel parallel programming language and system. In Proceedings of the international conference on parallel processing vol. II. CRC Press, Boca Raton, Florida, 1990. 

Kale, L. V., Bhandarkar, M., Jagathesan, N., Krishnan, S., Yelon, J. Converse An interoperable framework for parallel programming. In Proceedings of the 10th international parallel processing symposium. IEEE Computer Society Press, Los Alamitos, California, 1996. 

T. W. Clark, J. A. McCammon, L. R. Scott, Parallel molecular dynamics , Proc. of the fifth SIAM conference on Parallel Processing for Scientific Computing, 338-44, 1992. 

Iterative solution methods are more effective for problems arising in solid mechanics and are not a common feature of the finite element modelling of polymer processes. However, under certain conditions they may provide better computer economy than direct methods. In particular, these methods have an inherent compatibility with algorithms used for parallel processing and hence are potentially more suitable for three-dimensional flow modelling. In this chapter we focus on the direct methods commonly used in flow simulation models. 

The account begins with binary arithmetic, moves on to on-off (flip-flop) electronic switches, then to serial and parallel processing, and finally to computers/transputers. 

Parallel processing of information is a technique that speeds computer operations without the need to push the limits of existing technology by attempting to build increasingly faster processors. A typical outline of transputer architecture compared with that of a standard computer is shown m Figure 43.3. 

This big increase in speed has not been without cost. The everyday machine codes and high-level languages (Fortran, Pascal, C, etc.) used to control operations in a standard computer are inappropriate for parallel processing, which needs its own instruction set and has led to the development of special languages for use with the transputer. 

Parallel processing is inherently faster than serial processing, but special processors are needed, and these are called transputers. 

Parallel processing requires that each transputer be able to communicate efficiently with others (up to four immediate neighbors with current transputers) if the final result is not to be garbled. 

A special computer language (Occam) is needed to enable transputers to be programmed in this cooperative mode, yielding true parallel processing of information with all its advantages in speed. 

Parallel processing and the RISC set give transputers a considerable speed advantage over conventional serial processors for handling information or flows of data. 

Powerful mass spectrometer/computer systems can achieve simultaneous foreground/background operation, especially if transputers are used to provide the advantage of parallel processing. 

As CPU performance increases, the gap between CPU and disk and memory speeds will continue to widen. As limits of technology are approached, other techniques will be needed to gain performance advantages more functional units, multiple processors, and so on. These approaches are discussed in the sections on minisupercomputers and parallel processing. 

Many of the problems inherent in parallel processing are illustrated by the following anecdote. 

H.E. Fang, A. C. Ribinson, and K. Cho, Hydrocode Development on the Connection Machine, Minutes of the Fifth SIAM Conference on Parallel Processing for Scientific Computing, Houston, TX, 1991. 

High speed in conjunction with complex parallel processing... 

D. E. Rumelhart, G. E. Hilton, and R. J. Williams, Parallel Processing Explorations in Microstructure of Cognition. Vol. I Foundations. MIT Press, Cambridge, Massachusetts (1986). 

In considering the various theories it is also apparent that many of them may be considered as alternative descriptions of essentially the same physical process, or as descriptions of parallel processes which collaborate in the failure. Thus a complete description of hydrogen embrittlement in a given situation will almost inevitably incorporate aspects of several of the following theories. 

---