Loop Level Parallelization of a Seismic Inversion Code
Abstract
We present a parallel implementation of a seismic inversion code. Parallelism is exploited at the loop level within the finite difference modeling, as this is the most time consuming part of the code. We give details of our implementation, and present numerical results. We have reached a performance of 250 Mflops on one processor, and speedups of 6 on 8 processors, on a Cray Y-MP.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1993
- Accession Number
- ADA444976
Entities
People
- Michel Kern
- William W. Symes
Organizations
- Rice University