Skip to main content

BSC supercomputer adopts emerging technologies

The Barcelona Supercomputing Center (BSC) has announced a new supercomputer from IBM, valued at nearly €30 million.

The new supercomputer will have a performance capacity of 13.7 petaflops, with 11 petaflops coming from a central bank of 3,400 nodes across 48 racks comprised of Intel Xeon processors with 390 terabytes of central memory. The other 2.7 petaflops will be made up of emerging technologies emulating the latest supercomputing technologies being developed through the US CORAL programme and Japan’s Post K computer.

This purchase is to be made from IBM, which will integrate technologies of Lenovo, Intel, and Fujitsu.With this purchase, BSC-CNS is trying to achieve two distinct goals. The first is to acquire a general-purpose machine capable of executing all types of scientific and engineering tasks, the second is to provide BSC users with clusters built using emerging technologies. These clusters will serve users’ needs and, in turn, will allow the centre to test and analyse the performance of the most recent developments in the field of supercomputing.

Emerging technologies

The second element of MareNostrum 4 will be formed of clusters of three different technologies that represent the latest developments in supercomputing technology – these additions to the main cluster will be added as they become available.

One of these clusters will consist of IBM POWER9 processors and NVIDIA GPUs, which are the same components that IBM and NVIDIA will use for the Summit and Sierra supercomputers that the US Department of Energy has commissioned for the Oak Ridge and Lawrence Livermore National Laboratories. Its computing power will be over 1.5 petaflops. 

The second cluster will be made up of Intel Knights Landing (KNL) and Intel Knights Hill (KNH) processors provided by Fujitsu and Lenovo respectively. They are the same processors that will be inside the Theta and Aurora supercomputers purchased by the US Department of Energy for the Argonne National Laboratory. Its computing power will be more than 0.5 petaflops. 

Finally, a third cluster will be formed of 64 bit ARMv8 processors that Fujitsu will provide in a prototype machine, using state-of-the-art technologies from the Japanese Post-K supercomputer. This cluster’s computing power will also be over 0.5 petaflop/s. 

MareNostrum4 will also provide new storage capabilities, the system will include disk storage capacity exceeding 10 petabytes that will be connected to the Big Data infrastructures of BSC-CNS, which has a total capacity of 24.6 petabytes. Like its predecessors, MareNostrum4 will also be connected to the network of European research centres and universities through the RedIris and Geant networks.

A visual representation of the MareNostrum 4 system can be found here. MareNostrum 4 will be more than 10 times more powerful than the previous supercomputer MareNostrum 3, which was installed between 2012 and 2013. Despite this increase in capacity, it will consume only 30 per cent more power, reaching 1.3 MW/year.

The MareNostrum machines have served over three thousand scientific and technical research projects since the first version was installed in 2004. At the time, MareNostrum had a calculation capacity of 42.35 Teraflops. In 2006, it was upgraded and doubled its capacity to 94.21 teraflops. Since the last upgrade (2012-2013), MareNostrum 3 has had a peak performance of 1.1 petaflops. 

Topics

Read more about:

HPC

Media Partners