The Ohio Supercomputer Center (OSC) today reported it is in the final stages of firing up its new 1.3 petaflops (theoretical peak) Pitzer Cluster from Dell-EMC. The system was announced in June and is expected to be in full production later this month.
Named for Russell M. Pitzer, a co-founder of OSC and emeritus professor of chemistry at The Ohio State University, the new system will feature 260 nodes, including Dell EMC PowerEdge C6420 servers with CoolIT Systems’ Direct Contact Liquid Cooling (DCLC) coupled with PowerEdge R740 servers. In total, the cluster will include 528 Intel Xeon Gold 6148 processors, 64 Nvidia Tesla V100 Tensor Core GPUs, all connected with EDR InfiniBand network.
“We worked with Dell EMC to create a highly efficient, dense and flexible petaflop-class system,” said Douglas Johnson, chief architect at OSC. “We have designed the Pitzer Cluster with some unique components to complement our existing systems and boost our total center performance to more than 2.8 petaflops.”
The Pitzer Cluster will join existing systems on the OSC data center floor at the State of Ohio Computer Center: The Dell EMC/Intel Owens Cluster (March 2017) and the HP/Intel Ruby Cluster (April 2015). The new system will replace the HP/Intel Oakley Cluster (March 2012).
Aggressive use of liquid cooling has helped boost rack density according to OSC; CoolIT’s Passive Coldplate Loop for the PowerEdge C6420 servers delivers dedicated liquid cooling to the Intel processors in each of the 256 CPU nodes, managed by a stand-alone, central pumping CHx650 Coolant Distribution Unit.
“The Pitzer Cluster follows the long-running HPC trend of higher performance in a smaller footprint, offering clients nearly as much performance as the center’s most powerful cluster, but in less than half the space and with less power,” said David Hudak, executive director of OSC.
Pitzer will provide clients with access to four Large Memory nodes (Dell EMC PowerEdge R940), with up to three terabytes of memory per node, especially helpful for data-intensive operations, such as DNA sequencing. The cluster’s V100-based GPU nodes GPUs offer large increases in speed over earlier generations and will be useful accelerating deep learning algorithms and artificial intelligence projects.
“Our group studies viruses that infect microbes in complex communities and the bigger the dataset, the more challenging it is to process. Currently, our major bottleneck is that we cannot even assemble some of these large-scale, fragmented metagenomic datasets, which means starting with pieces instead of ‘genomes.’ The use of existing large memory nodes has helped us map viral diversity globally in the oceans and make discoveries about viral roles in humans and soils. New, higher-memory nodes on the Pitzer Cluster will help us get unprecedented views into viruses in the wild and enable new discoveries,” said Matthew Sullivan, a microbiology researcher at OSU.
Link to full release: https://www.osc.edu/press/osc_installing_new_pitzer_cluster_built_by_dell_emc