Modeling Cone-Beam Tomographic Reconstruction Using LogSMP: An Extenced LogP Model for Clusters of SMPs

The tomographic reconstruction for cone-beam geometries is a computationally intensive task requiring large memory and computational power to investigate interesting objects. The analysis of its parallel implementation on widely available clusters of SMPs requires an extension of the original LogP model to account for the various communication channels, called LogSMP. The LogSMP model is used in analyzing this algorithm, which predicts speedup on a cluster of 4 SMPs using 10 Mbps, 100Mbps, and ATM networks. We detail the measurement of the LogSMP parameters and assess the applicability of LogSMP modeling to the cone-beam tomography problem. This methodology can be applied to similar problems involving clusters of SMPs.