Industry Compute Partition

Zoom image: CCR General Compute Cluster CCR General Compute Cluster.

New Compute Nodes Available December 2024

The compute hardware available to industry partners includes two sets of purchases from 2021 and 2024.  These equipment purchases were funded by the Buffalo Institute for Genomics and a New York State Empire State Development grant to provide the WNY and NY State industrial community with access to state-of-the-art high-performance computing resources (hardware, software and consulting services) to help foster economic development.  

Check out the Case Study prepared by Intel on CCR's 2021 industry cluster Download pdf(787 KB)

Server (Node) Types (ordered oldest to newest):

Type of Node

# of Nodes

# CPUs

Processor

GPU

RAM

Network

SLURM TAGS

Local /scratch
"Ice Lake" Standard Compute
Node

67

56

Intel Xeon Gold 6330

-

512GB

HDR Infiniband

CPU-Gold-6330

960GB

"Ice Lake" Large Memory
Node

16

56

Intel Xeon Gold 6330

-

1024GB

HDR Infiniband

CPU-Gold-6330

960GB

"Ice Lake" GPU Node

16

56

Intel Xeon Gold 6330

2x NVIDIA A100
40GB (GPU memory)

512GB

HDR Infiniband

CPU-Gold-6330-A100

960GB
"Sapphire Rapids" Standard Compute Node 75 64 Intel Gold-6448Y - 512GB Infiniband**** CPU-Gold-6448Y, SAPPHIRE-RAPIDS-IB 880GB
"Sapphire Rapids" Large Memory Node 12 64 Intel Gold-6448Y - 2TB Infiniband CPU-Gold-6448Y, SAPPHIRE-RAPIDS-IB 7TB
"Sapphire Rapids" GPU Node 4 64 Intel Gold-6448Y NVIDIA H100
80GB (GPU memory)		 512GB Infiniband CPU-Gold-6448Y, SAPPHIRE-RAPIDS-IB, H100 7TB
"Emerald Rapids" Standard Compute Node 71 64 Intel Platinum 8562Y+ - 512GB HDR Infiniband CPU-Platinum-8562Y, EMERALD-RAPIDS-IB 880GB
"Emerald Rapids" High Bandwidth Memory Node 8 64 Intel Max 9462 - 125GB HDR Infiniband CPU-Max-9462, HBM 833GB
"Emerald Rapids" NVIDIA HGX GPU Node 2 96 Intel Platinum 8468 8x H100
85GB (GPU memory)		 2TB HDR Infiniband CPU-Platinum-8468, H100, EMERALD-RAPIDS-IB 14TB
"Emerald Rapids"  GPU Node 8 64 Intel Platinum 8562Y+ 2x NVIDIA L40S
48GB (GPU memory)		 1TB HDR Infiniband CPU-Platinum-8562Y, L40S, EMERALD-RAPIDS-IB 7TB
"Emerald Rapids" Large Memory Compute Node 8 64 Intel Platinum 8562Y+ - 2TB HDR Infiniband CPU-Platinum-8562Y, EMERALD-RAPIDS-IB, LM 7TB

Requesting Specific Node Resources:

Refer to the CCR documentation

Partitions Available:

The industry nodes are in three partitions within the UB-HPC cluster: industry, industry-dgx, and industry-hbm.  These partitions are only available to industry partners.  UB faculty and students have the option of running their jobs in the "scavenger" partition.  This allows jobs to run when there are no other pending jobs in the industry partitions.  Once an industry user submits a job requesting resources, jobs in the scavenger partition are stopped and requeued. 

Note to use the scavenger partition, your jobs MUST be able to checkpoint and restart. 

Partition Name QOS Time Limit Max jobs per user Notes
industry
 industry 72 hours 1000 contains a mix of standard compute nodes, large memory and GPU nodes
industry-dgx industry 72 hours 10 contains NVIDIA HGX GPU nodes
industry-hbm industry 72 hours 10 contains high-bandwidth memory nodes
scavenger scavenger 72 hour 1 --requeue flag required for jobs to be restarted