Title :
Optimization algorithms for magnetics and their parallelizability
Author :
Ratnajeevan, S. ; Hoole, H. ; Agarwal, Kanishka
Author_Institution :
Dept. of Eng., Harvey Mudd Coll., Claremont, CA, USA
fDate :
3/1/1997 12:00:00 AM
Abstract :
Parallelization of optimization routines is now increasingly resorted to, because of the heavy computation associated with the optimization of electromagnetic products in the process of their design. This paper evaluated the possibilities for parallelization in electromagnetic product design. The several optimization algorithms available are evaluated for their parallelizability. It is further shown that, given the present limits of technology in relation to the number of processors available on shared memory computers of parallel architecture, parallelization in electromagnetic optimization is not necessarily worth attempting at present. Thus, works of this nature, are of necessity, for the future, in readiness for that day when a new generation of parallel computer is available to us
Keywords :
CAD; electrical engineering; electrical engineering computing; electromagnetic devices; optimisation; parallel algorithms; parallel architectures; shared memory systems; electromagnetic product design; magnetics; optimization routines; parallel architecture; parallel computer; parallel optimization algorithms; processors; shared memory computers; Algorithm design and analysis; Concurrent computing; Design optimization; Finite element methods; Iterative algorithms; Magnetics; Optimization methods; Parallel architectures; Parallel processing; Product design;
Journal_Title :
Magnetics, IEEE Transactions on
