Topics Map > •Research Computing
CRC NOTS Description
Back to main "Getting Started" document
Introduction
NOTS (Night Owls Time-Sharing Service; history of name) is a batch scheduled cluster for high-performance computing (HPC) and high-throughput computing (HTC). The system consists of 159 nodes with dual-socketed, hyperthreaded CPUs within HPE and Dell PowerEdge chassis. All the nodes are interconnected with 25 Gigabit Ethernet network. In addition, the nodes are connected with either high speed Omni-Path or InfiniBand HDR 100 for message passing applications. There is a 300TB VAST filesystem attached to the compute nodes via Ethernet. The system can support various work loads including single node, parallel, large memory multi-threaded, and GPU jobs.
Citation
If you use NOTS to support your research activities, please acknowledge (in publications, on your project web pages, …) our efforts to maintain this infrastructure for your use. An example acknowledgment that can be used follows. Feel free to modify wording for your specific needs but please keep the essential information:
This work was supported in part by the NOTS cluster operated by Rice University's Center for Research Computing (CRC).
Node Configurations
All nodes contain hyperthreaded CPUs. The Storage Network for all nodes is 25 GbE.
| Node Type | Node Count | Hardware | CPU | Core Count | System RAM |
Available |
Disk | GPUs (SLURM gres=...) |
High Speed Network | SLURM Features |
|---|---|---|---|---|---|---|---|---|---|---|
| Compute | 52 | HPE XL170r | Intel(R) Xeon(R) Gold 6230 CPU @ 2.10GHz | 40 | 192 GB | 182 GB | 960 GB | - | Omni-Path | cascadelake,opath |
| Compute | 8 | HPE XL170r | Intel(R) Xeon(R) Gold 6230 CPU @ 2.10GHz | 40 | 768 GB | 730 GB | 960 GB | - | Omni-Path | cascadelake,opath |
| Compute | 4 | HPE XL170r | Intel(R) Xeon(R) Gold 6230 CPU @ 2.10GHz | 40 | 1.5 TB | 1,461 GB | 960 GB | - | Omni-Path | cascadelake,opath |
| Compute | 3 | Dell PowerEdge C6520 | Intel(R) Xeon(R) Gold 6336Y CPU @ 2.40GHz | 48 | 256 GB | 250 GB | 960 GB | - | Omni-Path | icelake |
| Compute | 60 | HPE Proliant DL360 Gen11 | Intel(R) Xeon(R) Platinum 8468 | 96 | 256 GB | 251 GB | 960 GB | - | InfiniBand HDR 100 | sapphirerapids,ib |
| GPU | 1 | Dell PowerEdge R750xa | Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz | 24 | 256GB | 250 GB | 480 GB | 4 x Tesla A40 ( gpu:ampere) |
InfiniBand HDR 100 | icelake |
| GPU | 3 | HPE XL675d | AMD EPYC 7343 CPU @ 3.2GHz | 32 | 512 GB | 503 GB | 240 GB | 8 x Tesla A40 ( gpu:ampere) |
InfiniBand HDR 100 | milan, ib |
| GPU | 16 | HPE XL190 | Intel(R) Xeon(R) Gold 6230 CPU @ 2.10GHz | 40 | 192 GB | 182 GB | 960 GB | 2 x Tesla V100 (double- precision) ( gpu:volta) |
Omni-Path | cascadelake,opath |
| GPU | 12 | HPE ProLiant DL380a Gen11 | Intel(R) Xeon(R) Platinum 8468 | 96 | 512 GB | 503 GB | 960 GB | 4 x Tesla L40S ( gpu:lovelace) |
InfiniBand HDR 100 | sapphirerapids,ib |
Software environment on the nodes
- Operating system: Red Hat Enterprise Linux 9
- SLURM scheduler: version 24
- CUDA libraries: Run
module spider CUDAon the cluster to see versions available