SGI Japan Chosen by Semiconductor Energy Laboratory

SGI Japan, Ltd., part of Silicon Graphics International Corp., announced the installation of a new, large-scale system at Semiconductor Energy Laboratory Co., Ltd. (SEL).

The system, which will be used to facilitate the R&D of semiconductor technologies, combines SGI’s large-scale shared-memory UV 2000 server and ICE X blade-type cluster server into a unified, large-scale system.

SEL is a specialized R&D company that patents semiconductor technologies. This supercomputing solution from SGI, which has been operational since March 2014, will facilitate the R&D of field-effect transistors that use oxide semiconductors, as well as a large number of other products related to active matrix displays, non-volatile memory, and lithium-ion batteries.

“We are privileged to be providing the computational resource that drives SEL’s achievements in developing cutting-edge technology for industry,” said Manabu Mochizuki, SGI Japan president and representative director. “With this installation, our collaboration with this impressive organization grows even stronger.“

“As a leader in partnering with research organizations to provide them with computational tools, SGI is proud to have been selected by SEL to support them in their innovative semiconductor research,” said Jorge Titinger, president and CEO, SGI. “We look forward to seeing the results of our technology combined with SEL’s leading research, and further showcasing how our offerings can power the work behind sophisticated R&D organizations globally.“

SEL first installed server solutions in 2008. As SEL is focused on exemplary R&D in the semiconductor field, it has worked to ensure that the computational resource driving its research has improved in parallel with its own offerings. This marks the second time that SEL has implemented a large-scale overhaul of its systems.

A primary reason SEL selected SGI was the ability to offer a supercomputer with a hybrid structure, which combine a large-scale shared memory server and distributed cluster servers into a single, unified system. Given this optimized configuration, application performance has increased as much as 2.6-fold compared to previous system, with a theoretical overall peak performance of 180 teraflops. Enabled with such a performing solution, SEL’s research and engineering staff can be more efficient in delivering innovation.

A large-scale shared-memory server allows a single system to make use of extensive memory space, while distributed cluster servers allow high-speed processing through parallel computations. By combining these two server types into a single, unified system, and by appropriately designating computation processes according to their content and characteristics, SEL has been able to create a computational environment of efficiency, facilitating R&D into ground-breaking semiconductor technologies.

The SGI UV 2000 large-scale shared-memory server boasts 768 cores from the Xeon processor E5-4600 v2 product family with 16TB of memory. The SGI ICE X large-scale blade-type cluster server combines 7,200 cores from the Xeon processor E5-2600 v2 product family with 46TB of memory. The systems’ nodes are connected by IB 4x FDR. Finally, the servers share the use of 370TB of RAID storage provided by the SGI InfiniteStorage 5600.