INTERCONNECTS

Throughout the oil and gas industry, modeling and simulation data sets are growing in size exponentially, making it increasingly difficult to conduct large-scale computational tasks. At Houston-based Marathon Oil Company, the company's Reservoir Description and Management group recently installed an SGI Altix 3000 system driven by 12 Intel(R) Itanium(R) 2 processors for the intensive modeling tasks needed to describe the subsurface and predict fluid flow at Marathon fields around the world. The unique SGI(R) NUMAlfex(TM) shared-memory architecture enables Altix 3000 servers and superclusters to distribute calculations over an array of nodes. "With traditional distributed computing architecture, complex tasks based on large data sets need to be broken up into subsets. That becomes unwieldy and eventually impossible as those sets become increasingly dense," explains Mark Petersen, manager, Reservoir Description and Management, Marathon Oil. "With the NUMAflex shared memory architecture of the Altix 3000 family, all processors can work on the same task in resident memory simultaneously, even if the model is 30 gigabytes or more," said Bill Bartling, senior director, Market Strategy at SGI. "That dramatically speeds up -- currently by a factor of four -- what would otherwise be enormously difficult and time- consuming jobs." Petersen's department is involved with the first two of three steps in the well management process, all related to estimating oil and gas reserves in the subsurface and predicting how quickly the company can produce those reserves: -- the geocellular model, a static model describing the rocks and fluid properties of the field, -- reservoir simulation, a fluid dynamic model characterizing how fluids flow through and from those rocks, and -- the economic model, enabling the company to efficiently manage the monetary resources required to produce the hydrocarbons. "The first two steps allow Marathon to look at a number of possible production scenarios -- how many platforms do you build, when do you build them, how much do you spend, etc. -- and selecting the best one to produce the optimum rates of oil," explains Peterson. The third step models the cash flow from the project based on each of the scenarios under consideration. "Historically, throughout the industry, otherwise high-resolution reservoir models were decimated in order for yesterday's lower-performance computers to handle them," added Bartling. "Today, Altix systems allow companies to retain high-resolution models, computing them in the same time or less than was the case with yesterday's models. That equates to cost savings, better planning, more effective and efficient oil production, predicable revenues and increased shareholder value." "It's gratifying to know that SGI's family of products fulfills not only the industry's visualization and storage needs but also the increasingly demanding HPC needs of such leading international oil and gas companies as Marathon," added Bartling. "We look forward to working with Marathon to help meet its computing challenges for many years to come."