It’s celebration time at the Los Alamos National Laboratory, with their new supercomputer; the Tsubame2.0, being voted the most eco-friendly and efficient among its class in the Green500 List.
The Tsubame 2.0 uses just 1.2MW of power to reach i2.0 petaflops (two times thousand trillion floating point operations per second) of performance, making it 3.4 times more efficient than a similar system.
Each individual element of the new Tsubame cluster is a HP ProLiant SL390 server that has a strong Xeon chip behind it, along with Tesla boards inside. The Tesla hardware’s speed in certain kinds of general-purpose and often very parallel computing, such as vector math, lets it handle about 80 percent of the workload without the requirement of either faster Xeons or more PCs. With manufacture of cards dedicated only towards computing, Nvidia has scored it at the super computer level this time.
The purpose of the Green500 is to provide a ranking of the most energy-efficient supercomputers in the world. For decades, the notion of performance has been synonymous with speed (as measured in FLOPS, short for floating-point operations per second).
This particular focus has led to the emergence of supercomputers that consume intolerable amounts of electrical power and produce so much heat that extravagant cooling facilities must be constructed to ensure proper operation.