A Skeleton for Parallel Csg with a Performance Model

We describe a methodology for modelling the performance of parallel algorithmic skeletons and illustrate it using a new skeleton which supports set membership classiication problems in Constructive Solid Geometry. These problems are characterised by potentially unbalanced tree structures with data-dependent computations at the nodes. The skeleton achieves good parallel eeciency even with highly unbalanced trees and, with some restrictions on the class of computations permitted , the methodology accurately predicts the asymptotic performance of speciic CSG applications.