New supercomputers and the exaFLOP race

China has an exaflop supercomputer budget of $150 million to $300 million. The exaflop supercomputer could be built as early as 2019.

It is to be built in Shandong province coast as soon as 2019 to support ocean research in the South China Sea and boost China’s maritime expansion.

Six leading US technology companies received $258 million in funding from the Department of Energy’s Exascale Computing Project (ECP) as part of its new PathForward program. This money is to accelerate the research necessary to deploy the nation’s first exascale supercomputers in about 2021.

Oak Ridge National Lab will have the 200-petaflop Summit supercomputer come online in mid-2018. It will use 15 megawatts of power.

Summit will deliver more than five times the computational performance of Titan’s 18,688 nodes, using only approximately 4,600 nodes when it arrives in 2018. Like Titan, Summit will have a hybrid architecture, and each node will contain multiple IBM POWER9 CPUs and NVIDIA Volta GPUs all connected together with NVIDIA’s high-speed NVLink. Each node will have over half a terabyte of coherent memory (high bandwidth memory + DDR4) addressable by all CPUs and GPUs plus 800GB of non-volatile RAM that can be used as a burst buffer or as extended memory. To provide a high rate of I/O throughput, the nodes will be connected to a non-blocking fat-tree using a dual-rail Mellanox EDR InfiniBand interconnect.

Upon completion, Summit will allow researchers in all fields of science unprecedented access to solving some of the world’s most pressing challenges.

Lawrence Livermore National Laboratory will have the 120 petaflop Sierra supercomputer in 2018.

Argonne National Laboratory plans to construct the Aurora exaflop supercomputer in 2021.