Overcoming computational cost problems of reverse-time migration
Zaiming Jiang, Kayla Bonham, John C. Bancroft, Laurence R. Lines
Prestack reverse-time migration is computationally expensive. Program run times are long, in terms of the total number of CPU cycles, and it requires large amounts of hard disk free space. To accelerate computing, we do parallel processing using Intel Threading Building Blocks (TBB) and multi-core computers, for both the forward-time modelling and reverse-time migration phases of the computation. To solve the problem of limited free disk space, we use a technique that may seem counter-intuitive: the forward modelling phase is done twice instead of once. Two other enduring problems are described at the end of the paper: the requirement for large working memory, and limited access speeds of mass storage (hard disk) relative to the speed of computation.