What people are saying - Write a review
We haven't found any reviews in the usual places.
Vector and parallel architectures
Vector multiprocessor computing
Hypercube computing 69
5 other sections not shown
Other editions - View all
addition algorithm allocation apply architectures arithmetic array assigned assume AXPY begin block broadcast cache cells chapter coefficients combination communication complete computation consider constraints controlout dependence discuss distributed memory efficiency elements equal equations example execution figure Finally function Gaussian elimination given graph hence holds hypercube implementation initialize input instance length linear load loop machine matrix multiple neighbour node Note number of processors obtain operation optimal output parallel parallel algorithm partial path performance phase pipeline pivot column possible problem processing processors receive region requires result ring routine scalar schedule segment sequential shared single slice solution solve speedup step strategy systolic arrays task transformation triangular unit update vector register zero