Energy Companies Lead in Commercial Supercomputer Adoption

Energy exploration and production is highly dependent on the rapid analysis of increasingly more complex and larger seismic imaging datasets. At the same time, the modeling, reserve management, and analytics algorithms being used on that data are becoming more granular and sophisticated requiring enormous processing power. 

The field has always been a big user of high performance computing (HPC). But the growing need for faster and more precise results is driving some companies to really push the envelope when it comes to using computing power. 

To that point, within the last year three energy companies started using supercomputing systems that normally only would be found in government labs or major academic research facilities.

Total E&P (headquartered in France) installed a system that ranked fourteenth on the Top500 list of the world's most powerful supercomputers. The Top500 list is published twice a year and ranks computers based on the results of a benchmark performance test, the LINPACK benchmark.^*

The Total E&P system is the only commercial system on the list in the top 25 and one of only four commercial systems in the top 50. It was benchmarked as having a performance of 2.3 petaflops (a petaflop is a measure of a computer's processing speed, specifically the ability to perform one quadrillion floating point operations per second).

This computing power will be used to help reduce the uncertainty of oil and gas exploration and production. It also will allow Total E&P to take more physical phenomena into account in its simulations. 

The second system of note is one installed by BP at its Center for High-Performance Computing in Houston. The system is a 2.2 petaflops system that will help BP to render precise images of the subsurface, which in turn will boost the company's ability to find and develop new energy resources. The system's high-speed processing capability will reduce the time it takes to analyze massive quantities of seismic data and it will enable more detailed in-house modeling of rock formations before drilling begins.

In late November, after the most recent Top500 list was published, Italian energy company Eni announced it had installed a new supercomputer that delivers in excess of 3 petaflops of processing power. The new supercomputer will support the firm's seismic imaging and hydrocarbon exploration activities. 

Certainly, there are other industries that rely on HPC such as automotive and aeronautics. But in the commercial world, the use of such powerful supercomputers such as the ones installed at Total, BP, and Eni is unprecedented.

Simply put, Total, BP, and Eni are running three of the largest private supercomputers in the world. A few other energy industry companies have announced their plans to deploy similarly powerful systems in the years to come. 

The need for such processing power highlights how energy exploration and production is becoming an ever-more data-driven operation, which relies on rapid analysis of large datasets.

^* One note about the Top500 list: Entry on the list is voluntary. And some companies intentionally do not participate to keep information about their computing capacity hidden from competitors. As a result, there might be other commercial systems that are more powerful than those included on the list.