No abstract

Cloud computing is enabling users to instantiate and access high-performance computing clusters quickly. However, without proper knowledge of the type of application and the nature of the instances, it can become quite expensive. The objective is to show that adequately choosing the instances provides a fast execution, which, in turn, leads to a low execution price, using the pay-as-you-go model on cloud computing. We used graphics processing units instances on the spot market to execute a seismic-dataset interpolation job and compared their performance to regular on-demand CPU instances. Furthermore, we explored how scaling could also improve the execution times at small price differences. The experiments have shown that, by using an instance with eight accelerators on the spot market, we obtain up to three hundred times speed-up compared to the on-demand CPU options, while being one hundred times cheaper. Finally, our results have shown that seismic-imaging processing can be sped up by order of magnitude with a low budget, resulting in faster and cheaper turn around processing time and enabling possible new imaging techniques.

No abstract

No abstract

No abstract