A new IBM RedBook draft, ‘IBM technical computing clouds’ (TCC) describes a flexible high performance compute infrastructure build around IBM’s SmartCloud solutions. TCC includes a chapter on oil and gas where it is claimed that new approaches are needed to ‘improve discovery, production and recovery rates.’ TCC enumerates many of the forces acting on the oil and gas vertical from a macro economic standpoint (we will spare you the details) to reason that a ‘demand for innovation is creating opportunities to push IT boundaries.’
Seismic data is ‘exploding, doubling every year in terms of the data footprint’ and is ‘expected to go up dramatically.’ Seismic imaging is a key focus area where resolution has been constrained by available compute power. Now oil and gas company R&D divisions are planning for ‘exascale’ projects in 2020. This represents a ‘clear roadmap’ to compute requirements ‘a thousand times greater than we have today.’ Reservoir simulation and economics use less parallel algorithms than seismic and can require large amounts of memory per node. Large shared memory machines and high bandwidth interconnect such as InfiniBand are the norm.
To date while the cloud model has been of interest to oil and gas, there have been few deployments. This is because the systems used are so big that commercial cloud offerings do not have the necessary capacity. TCC’s authors claim that this is about to change at least for some parts of the workflow such as ‘remote 3D visualization and collaboration.’ Most visualization software and tools used in seismic imaging and reservoir simulation can leverage 3D desktop virtualization. Enter the IBM platform application center (PAC) remote visualization offering that includes built-in application templates for oil and gas.
TCC also covers more business-oriented applications such as using InfoSphere BigInsights, IBM’s Hadoop/MapReduce implementation for ‘big data’ analytics and PureData/Netezza data warehouse appliances. A ‘basic’ BigInsights edition is available free of charge for data environments up to 10 TB. For spreadsheet aficionados short on horsepower, IBM’s ‘BigSheets’ is available, a browser-based analytic tool that enables business users and users with no programming knowledge to explore and analyze data in the distributed file system. Finally IBM’s text analytics (as featured in IBM Watson) is available as a cloud-based service for unstructured text data analysis.
All in all TCC is a bit of a jumble. It does a better job of telling us what we already know than making a compelling case for doing it in the cloud. Perhaps this reflects IBM’s problem as a vendor of big iron that is trying not to cannibalize its business with services in the cloud.
© Oil IT Journal - all rights reserved.