Abstract
Seismic data-sets are extremely large and are broken into data files, ranging in size from 100s of GiBs to 10s of TiBs and larger. The parallel I/O for these files is complex due to the amount of data along with varied and multiple access patterns within individual files. Properties of legacy file formats, such as the de-facto standard SEG-Y, also contribute to the decrease in developer productivity while working with these files. SEG-Y files embed their own internal layout which could lead to conflict with traditional, file-system-level layout optimization schemes. Additionally, as seismic files continue to increase in size, memory bottlenecks will be exacerbated, resulting in the need for smart I/O optimization not only to increase the efficiency of read/writes, but to manage memory usage as well. The ExSeisDat (Extreme-Scale Seismic Data) set of libraries addresses these problems through the development and implementation of easy to use, object oriented libraries that are portable and open source with bindings available in multiple languages. The lower level parallel I/O library, ExSeisPIOL (Extreme-Scale Seismic Parallel I/O Library), targets SEG-Y and other proprietary formats, simplifying I/O by internally interfacing MPI-I/O and other I/O interfaces. The I/O is explicitly handled; end users only need to define the memory limits, decomposition of I/O across processes, and data access patterns when reading and writing data. ExSeisPIOL bridges the layout gap between the SEG-Y file structure and file system organization. The higher level parallel seismic workflow library, ExSeisFlow (Extreme-Scale Seismic workFlow), leverages ExSeisPIOL, further simplifying I/O by implicitly handling all I/O parameters, thus allowing geophysicists to focus on domain-specific development. Operations in ExSeisFlow focus on prestack processing and can be performed on single traces, individual gathers, and across entire surveys, including out of core sorting, binning, filtering, and transforming. To optimize memory management, the workflow only reads in data pertinent to the operations being performed instead of an entire file. A smart caching system manages the read data, discarding it when no longer needed in the workflow. As the libraries are optimized to handle spatial and temporal locality, they are a natural fit to burst buffer technologies, particularly DDN’s Infinite Memory Engine (IME) system. With appropriate access semantics or through the direct exploitation of the low-level interfaces, the ExSeisDat stack on IME delivers a significant improvement to I/O performance over standalone parallel file systems like Lustre.
Highlights
Parallel I/O allows for multiple processors on a system to perform input/output operations at the same time
In order to show how ExSeisPIOL is ideal for use in existing seismic codes with complex I/O the Kirchhoff migration with a time-shift extended imaging condition used in (O’Brien et al, 2017) was ported to use ExSeisPIOL for its I/O back end
The libraries can be used to port existing seismic analysis code, like the Kirchhoff migration code, with significant improvements to maintainability as well as portability on new architectures and with execution times close to expertly hand-optimized codes. This porting work is expected to uncover a number of functionalities that will be useful to include in ExSeisDat
Summary
Overall resolution and size (Stanghellini and Carrara, 2017) of seismic studies have increased of the past several decades; individual files range in size from 100s of GiBs to greater than 10 TB. Various access patterns for different processing stages can lead to effectively random access patterns, causing contention for disk access (in both serial and parallel file systems), along with limiting the effectiveness of caching and pre-fetching by the operating system. The size of these files mean that reading entire files into memory for preprocessing is not a scalable solution, for files in the terabyte and, looking forward, petabyte range. Neither the trace attributes nor sets of trace data are stored contiguously on disk, even when written in a continuous block of storage This layout strategy leads to poor cache usage and pre-fetching by the operating system, increasing I/O time. Designed in partnership with Tullow Oil plc and DataDirect Networks (DDN) to be both scalable and user friendly, ExSeisDat includes two open source libraries: ExSeisPIOL, a low-level seismic parallel I/O library, and ExSeisFlow, a high level parallel seismic workflow library
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
