IBM Delivers the First Racks of 20-Petaflop Sequoia Supercomputer

The first four racks of NNSA’s Sequoia supercomputer have arrived at Lawrence Livermore National Laboratory, where they will stand at the heart of what is to become the 20 petaflops Sequoia based on IBM Blue Gene technology.

In addition to its impressive number crunching capabilities, IBM also expects its system to become one of the most power-efficient supercomputers in the world, churning out no less than 2 gigaflops per watt.

These advancements in energy efficiency and computing power were made possible by IBM's new PowerPC A2 processing architecture which adds 16 computing cores to each processor installed, compared to the four cores used in its previous machine, the Blue Gene/P.

Together with these 16 cores dedicated to providing the computing power of the CPU, IBM's chip also sports a special core allocated to operating system administrative functions and a redundant spare core.

Sequoia's performance is also improved thanks to a series of hardware-based speculative execution capabilities, meant to facilitate writing multi-threaded code for the machine, as well as to the introduction of hardware-based transactional memory.

Deliveries of the system will continue through April 2012 as the supercomputer will use a total of 96 racks.

Integration will take place in phases with final acceptance of the machine being scheduled for September 2012, when is expected to the most powerful supercomputer in the world.

Right now, the fastest supercomputer on Earth is the Japanese K-Computer installed at the Riken Advanced Institute for Computational Science in Kobe, Japan which is capable of delivering 10.51 petaflops.

The system is comprised of 864 racks including a total of 88,128 interconnected Fujitsu Sparc64 VIIIfx CPUs featuring eight cores and running at 2GHz.

Sequoia will be used by the LLNL to ensure the safety and reliability of US’s aging nuclear arsenal.

Posted in: News