Oak Ridge's Summit Supercomputer Announced For Early 2022

The world of supercomputing is being infused with magnitude of performance which is being delivered with the latest hardware capabilities. A few years ago, Oak Ridge National Laboratory was proud of their Titan HPC super computer but that ha since been replaced in terms of functioning by two supercomputers from China, Tianhe-2 and the recently announced Sunway TaihuLight. At present Us is planning to make a comeback to accept the crown of the fastest supercomputer with their upcoming Sierra and Summit supercomputer machines.

The Tiptop Supercomputer will be the fastest in the world when it launches in early 2022.

Oak Ridge's Superlative Super calculator Announced With 200 Petaflops Peak Performance - Powered by Volta GPUs and Power9 CPUs

The announcement of the Tiptop supercomputer comes just a few days afterward China unveiled their Sunway TaihuLight supercomputer which is effectually 3 times faster than the Tianhe-2 supercomputer and also based on China's own hardware engineering science as seen during the reveal. The motorcar is currently the fastest supercomputer in the world and is placed at China'southward National Supercomputing Center in Wuxi. The system is able of delivering a peak performance of 125.4 PFLOPs which is insane.

The top ten supercomputers in the earth. (Image Credits: Top500.org)

The arrangement achieves these numbers with Cathay's custom made ShenWei CPUs that were made by the Jiangnan Computing Enquiry Lab in Wuxi. These chips use an RISC (reduced instruction set computer) compages. The supercomputer deploys several of these cores in nodes and each processor is capable of 3 TF (Teraflops) compute output. Each fleck has 260 cores and the entire machine features 10.65 million cores. Y'all can say that the reason Communist china developed their own CPUs for supercomputing was the ban on sale of Intel's high-terminate micro processors to China. Mainland china'south Tianhe-ii supercomputer is based on Intel Xeon-Phi processors which also ability several US based machines.

The Sunway TaihuLight is the fastest supercomputer in the world. (Image Credits: Pugam)

But now that the crown of supercomputing lands in Chinese hands, US is expecting to brand a comeback early next year with their ain machines. The US Department of Energy (DOE) has already appear two make new supercomputers for 2022, Acme from Oak Ridge National Laboratory and Sierra from Lawrence Livermore.

The DOE, in a argument responding to the news Monday about China's supercomputer, said U.S. supercomputing capabilities "have grown exponentially by a factor of 300,000" since 1993. "High-functioning calculating remains an integral priority for the DOE," the statement said. via Computerworld

The DOE said the government is "pursuing the goals of the National Strategic Computing Initiative: Accelerating the delivery of exascale calculating; increasing the coherence between the engineering base used for modeling and simulation and that for data analytic computing; charting a path frontward to a post-Moore'south Police force era; and building the overall chapters and capability of an enduring national HPC ecosystem." via Computerworld

Top 500 Supercomputer Features (Top500.org):

There are 95 systems with performance greater than a petaflop/s on the list, up from 81 six months ago.

Intel continues to provide the processors for the largest share – 455 systems or 91 percentage – of the TOP500 systems. The share of IBM Power processors is at present at 23 systems, down from 26 systems six month ago. The AMD Opteron family unit is used in 13 systems (2.6 per centum), down from 4.2 percent on the previous list.

Hewlett Packard Enterprise has the lead in the total number of systems with 127 systems (25.iv percentage) followed by Lenovo with 84 systems. Cray now has 60 systems, downward from 69 systems vi months ago. HPE had 155 systems six months ago. IBM is at present fifth in the systems category with 38 systems.

A total of 93 systems on the list are using accelerator/coprocessor applied science, down from 104 in Nov 2022. Sixty-seven of these employ NVIDIA fries, 26 systems with Intel Xeon Phi engineering science, three use ATI Radeon, and two utilise PEZY technology. Three systems utilize a combination of NVIDIA and Intel Xeon Phi accelerators/coprocessors.The average number of accelerator cores for these systems is 76,000 cores per system.

NVIDIA and IBM Hardware Being Used To Built The Fastest Supercomputer in The World

Rated at a peak performance of 150-300 PFLOPS, the Summit supercomputer will be based on more than than 3400 compute nodes with each node consistin of several next generation IBM POWER9 CPUs and NVIDIA Volta architecture based Tesla GPUs. Each node will deliver around twoscore TFLOPs of compute operation and is said to exist enough to outperform an entire rack of top of the line Haswell based x86 CPU servers.

With Summit come a few other enabling technologies such every bit NVLINK which is already shipping with Pascal GPU from NVIDIA. The Pascal GP100 based Tesla P100 is the commencement to innovate NVLINK which is the next generation Unified Virtual Memory link with Gen two.0 Cache coherency features and 5 – 12 times the bandwidth of a regular PCIe connection. This volition solve many of the bandwidth issues that high performance GPUs currently face up. The fast speed interconnect will let several nodes to balance utilization when working in parallel with cantankerous sharing of data and information through a speedy interface.

A comparison between the Titan and Acme Supercomputer.

On summit, each compute node will feature 512 GB of retentiveness through dense server DDR4 memory and high bandwidth HBM stacked designs which will work in complete coherency. Extending the impressive amount of memory is an boosted 800 GB of NVRAM per node, which can be configured either every bit a burst buffer or as extended memory.

Tiptop is the next leap in leadership-class computing systems for open science. With Acme we will be able to accost, with greater complexity and higher fidelity, questions concerning who we are, our place on earth, and in our universe.

Summit will deliver more v times the computational performance of Titan'due south xviii,688 nodes, using only approximately iii,400 nodes when it arrives in 2022. Similar Titan, Elevation will take a hybrid architecture, and each node will contain multiple IBM POWER9 CPUs and NVIDIA Volta GPUs all continued together with NVIDIA'due south high-speed NVLink. Each node will accept over one-half a terabyte of coherent retention (high bandwidth retentiveness + DDR4) addressable by all CPUs and GPUs plus 800GB of not-volatile RAM that can exist used as a burst buffer or as extended retention. To provide a high rate of I/O throughput, the nodes will exist connected in a non-blocking fat-tree using a dual-rails Mellanox EDR InfiniBand interconnect.

Upon completion, Summit will allow researchers in all fields of science unprecedented access to solving some of the globe's nearly pressing challenges. via OLCF

The system is interconnected with dual-rails Mellanox EDR InfiniBand, using the full, non-blocking fatty-tree design. Summit volition also include the GPFS parallel file organization with ane TB/s of I/O bandwidth and 120 PB of disk capacity. The acme reckoner will exist able to achieve 200 PFLOPs of compute performance at just 10MW peak power consumption, the Titan supercomputer accomplished a summit 27 TFLOPs performance at 9 MW and with eighteen,688 compute nodes.

Intel is as well working in-cooperation with Cray to evangelize two supercomputers for Argonne National Laboratory, named as Aurora and Theta. Both supercomputers accelerate the hyper computing world with unparalleled amounts of performance, pushing past the PetaFlops barrier with several thousand nodes. Built specifically for scientific purposes, these supercomputers will consume power in the Mega Watts range which gives usa a perspective of the size of these monsters. More on those hither.