Texas Advanced Computing Center Interconnects With Mellanox EDR 100Gb/s IB

Mellanox Technologies, Ltd. announced that the Texas Advanced Computing Center (TACC) at The University of Texas in Austin has selected Mellanox’s end-to-end 100Gb/s EDR interconnect solutions to develop North America’s first end-to-end 100Gb/s EDR HPC cluster.

It is TACC’s mission to provide researchers with cutting edge technology, which led the center to select Mellanox for their next generation solutions. Mellanox is currently the only company offering end-to-end 100Gb/s interconnect solutions.

“TACC has had a number of IB systems over the years and we were looking to take our research capabilities to the next level,” said Bill Barth, director of HPC, TACC. “Mellanox was the obvious choice for this project to ensure that we are able to provide our users with the advanced performance capabilities necessary for research that will further developments in biophysics, atmospheric chemistry and aerospace engineering.”

This new cluster, named Hikari, utilizes Mellanox ConnectX-4 adapters, Switch-IB switch systems, LinkX cables and HPC-X software, which work in concert to deliver unparalleled scalable application performance and system efficiency.

Hikari leverages Hewlett Packard Enterprise (HPE) Compute platforms, including 432 HPE Apollo 8000 XL730f servers coupled with HPE DL380 and DL360 nodes that are interconnected with Mellanox solutions to deliver a hybrid configuration for the exploration of alternate supercomputing energy sources. The HPE Apollo 8000 installation allows TACC to supply DC power directly to Hikari as part of the university’s collaboration with the New Energy and Industrial Technology Development Organization (NEDO) to use alternative energy sources to power some of TACC’s high-performance computers.

“The TACC cluster is truly exciting because it the first of its kind in North America, both from a performance and energy standpoint,” said Gilad Shainer, VP marketing, Mellanox. “The combination of the Mellanox EDR 100Gb/s IB interconnects and the HPE Apollo 8000 platform will enable the ground breaking performance needed for the center to fulfill its mission to expedite research and accelerate discoveries that advance science and society.”

“The demand for HPC resources is growing rapidly and today’s data centers are ill-equipped to handle the extensive power and infrastructure necessary to run the required level of processing power,” said Scott Misage, VP and GM, HPC, HPE servers. “The HPE Apollo 8000 System delivers the highest level of density and compute performance, allowing organizations like TACC to fuel the future of science and technology with a solution that is also highly energy efficient.”