SAN DONATO MILANESE, Italy – Eni has started up its new HPC4 supercomputer at its Green Data Center in Ferrera Erbognone, 60 km (37 mi) from Milan.
The system will quadruple the company’s computing power, providing 18.6 Petaflops at peak. This, combined with theHPC3 supercomputing system already in operation, lifts Eni’s computational peak capacity to 22.4 Petaflops.
According to the latest official Top 500 supercomputers list published last November, Eni’s HPC4 is among the top 10 most powerful systems in the world.
The Green Data Center serves as a single IT Infrastructure to host all of the HPC architecture and other business applications.
Together, the HPC3 and the new HPC4 support the company’s process of digital transformation, from exploration and development of oil and gas reservoirs to management of big data generated in the operational phase by all Eni’s productive assets (upstream, refining, and petrochemicals).
HPC4 will support execution and evolution of the company’s 3D seismic imaging packages and advanced petroleum system modeling, with (Eni claims) state of the art reservoir simulation algorithms.
CEO Claudio Descalzi said: “We can store and process enormous quantities of data forgeophysical imaging, the modeling of oil systems and reservoirs, in addition to using predictive and cognitive computing algorithms for all our business activities.
“These technologies will enable us, on the one hand, to accelerate and make the entire upstream process more efficient and accurate, reducing risks in the exploration phase…”
Other benefits, he added, should be increased reliability, technical integrity and operability of all the company’s productive plants, and minimized operational risks, with benefits in terms of safety and environmental impact.”
“With HPC4 we are tracing the path for the use of exascale supercomputers in the energy sector that could revolutionize the way in which oil and gas activities are managed,” he continued.
The new hybrid HPC cluster provided by Hewlett Packard Enterprise (HPE) is built on 1600 HPE ProLiant DL380 nodes, each equipped with two Intel 24-core Skylake processors (more than 76,000 cores in total) and two NVIDIA Tesla P100 GPU accelerators, all connected through a high-speed EDR InfiniBand.
The new system will work alongside a high performance 15 Petabytes storage subsystem.