Seismic Imaging on the Intel Paragon
نویسندگان
چکیده
A key to reducing the risks and costs of associated with oil and gas exploration is the fast, accurate imaging of complex geologies, such as salt domes in the Gulf of Mexico and overthrust regions in U.S. onshore regions. Prestack depth migration generally yields the most accurate images, and one approach to this is to solve the scalar wave equation using nite diierences. Current industry computational capabilities are in-suucient for the application of nite-diierence, 3-D, prestack, depth-migration algorithms. A 3-D seismic data can be several terabytes in size, and the multiple runs necessary to reene the velocity model may take many years. The oil companies and seismic contractors need to perform complete velocity eld reenements in weeks and single iterations overnight. High performance computers and state-of-the-art algorithms and software are required to meet this need. As part of an ongoing ACTI project funded by the U.S. Department of Energy, we have developed a nite-diierence, 3-D prestack, depth-migration code for the Intel Paragon. The goal of this work is to demonstrate that massively parallel computers (thousands of processors) can be used eeciently for seismic imaging, and that suucient computing power exists (or soon will exist) to make nite-diierence, prestack, depth migration practical for oil and gas exploration.
منابع مشابه
Parallel Climate Data Assimilation PSAS Package Achieves 18 GFLOPS on 512-node Intel Paragon
We have designed and implemented a set of highly efficient and highly scalable algorithms for an unstructured computational package, the PSAS data assimilation package, as demonstrated by detailed performance analysis of systematic runs on up to 512-node Intel Paragon. The preconditioned Conjugate Gradient solver achieves a sustained 18 Gflops performance. As the results, we achieved an unprece...
متن کاملCommunication on the Paragon
In this note we describe the results of some tests of the message-passing performance of the Intel Paragon. These tests have been carried out under both the Intel-supplied OSF/1 operating system with an NX library, and also under an operating system called SUNMOS (Sandia UNM Operating System). For comparison with the previous generation of Intel machines, we have also included the results on th...
متن کاملParaNIS - Towards NIS client support for OSF/1 AD on the Intel Paragon
This paper presents the ParaNIS project, an attempt to implement Sun Microsystems’ Network Information Service Version 2 (formerly known as Yellow Pages) for the client side on the service partition of the Intel Paragon supercomputer. After a brief introduction to user administration on traditional UNIX systems, an overview of the classical NIS service is given. Whereas NIS was designed for c...
متن کاملReal-time Parallel Software Design Case Study: Implementation of the Rassp Sar Benchmark on the Intel Paragon
متن کامل
Experimental Validation of Parallel Computation Models on the Intel Paragon
Experimental data validating some of the proposed parallel computation models on the Intel Paragon is presented. This architecture is characterized by a large bandwidth and a relatively large startup cost of a message transmission, which makes it extremely important to employ bulk transfers. The models considered are the BSP model, in which it is assumed that all messages have a fixed short siz...
متن کامل