PARO Cluster
Overview
PARO is the latest generation High Performance Computing (HPC) cluster at the University of Texas at El Paso, launched to provide researchers with powerful resources for advanced computation. Designed to support modern software stacks and research demands, PARO integrates high-core-count processors, vast memory capabilities, and high-throughput network infrastructure.
Cluster Summary
- Total Nodes: 20
- Total CPUs: 913
- Total RAM: 11.5 TB
- Partitions: 4
🧊 Air Cooled Compute
| Specification | Details |
|---|---|
| Manufacturer | Lenovo & Dell Inc. |
| Model | ThinkSystem SR630 V3 & PowerEdge R660 |
| Cores/Node | 64, and 48 (32, and 24 per socket) |
| Clock Rate | 2.00GHz to 2.80GHz (Base Frequency) |
| Memory/Node | 251Gi to 1Ti |
PARO Evolution
PARO 1.0 — Current Configuration (As of October 2024)
- Operating System: Red Hat Enterprise Linux (RHEL) 9.2
- Storage Protocol: GPFS (General Parallel File System), tuned for RHEL 9.2
- Scheduler: SLURM v3 for scalable, efficient job management
- Software Stack: OpenHPC version 3 for high-performance applications
- User Management: Local cluster accounts to optimize container integration
- Network Infrastructure: 10Gb Ethernet, with future plans for InfiniBand
- Computing Hardware:
- Intel Xeon processors
- 32 cores per dual socket
- Memory options: 500 GB and 1 TB RAM
- Ongoing hardware integration with Lenovo SR630v3 and Dell R660
Mission & Future
PARO is a critical step forward in UTEP’s research computing infrastructure, designed to meet the growing demands of data-intensive and parallel scientific workloads. Its flexible architecture and continuous hardware integration ensure that researchers remain equipped with state-of-the-art computational tools.