Seismic migration algorithms on parallel computers

The authors study seismic migration algorithms with the aim of presenting a general framework for analyzing such algorithms, and propose some medium-grained paradigms for computation on parallel computers. They introduce parallel models for computation and discuss techniques to optimize the performance of the models on distributed concurrently executing processors. The computational and communication requirements of the algorithms are discussed and diverse optimization techniques are proposed. The memory limitation, I/O (input/output) bottleneck, and computational tradeoffs on hypercube multiprocessors are analyzed