Parallel distributed seismic migration

Abstract

We report significant speedup for seismic migration running in parallel on network-connected IBM RISC/6000 workstations. A sustained performance of 15 Mflops is obtained on a single entry-level model 320, and speedups as high as 5 are obtained for six workstations connected by ethernet or token ring. Our parallel software uses remote procedure calls provided by NCS (Network Computing System). We have run over a dozen workstations in parallel, but speedups become limited by network data rate. Fiber optic communication should allow much greater speedups, and we describe our preliminary results with the fiber optic serial link adapter of the RISC/6000. We also present a simple theoretical model that agrees well with our measurements and allows speedup to be predicted from a knowledge of the ratio of computation to communication, which can be determined empirically before the program is parallelized. We conclude with a brief discussion of alternative software approaches and programming models for network-connected parallel systems.