Gila Computing System

NLR's Gila high-performance computing (HPC) system is allocated for NLR researchers and is intended for Laboratory Directed Research and Development, strategic partnership, or U.S. Department of Energy projects.

Allocations

A specific allocation is not needed for NLR employee use of Gila. Projects needing larger or dedicated resources may request those directly to Computational Science Management. Dedicated resources may also be requested through an annual "buy-in" process. For detailed information, please see Gila Access and Allocations (GitHub).

System Architecture

Gila is an OpenHPC-based cluster configured to run compute-intensive jobs and has a mixture of node types which include AMD EPYC 7352 Milan CPUs, AMD MI210 GPUs, NVIDIA A100 GPU nodes, and NVIDIA Grace Hopper nodes. The configuration and capabilities for Gila may be augmented over time.

The nodes are connected to each other and to storage by 25Gb Ethernet network utilizing RDMA. All nodes and storage are connected in a fat tree topology via ethernet. Partitions are flexible on Gila.

Learn more about Gila (GitHub).