NCSA Delta GPU (Delta GPU)
National Center for Supercomputing Applications
Resource Type: Compute
User Guide: https://docs.ncsa.illinois.edu/systems/delta/en/latest/
Recommended Use: The Delta GPU resource is designed to support accelerated computation across a broad range of domains such as soft-matter physics, molecular dynamics, replica-exchange molecular dynamics, machine learning, deep learning, natural language processing, textual analysis, visualization, ray tracing, and accelerated analysis of very large in-memory datasets. Delta is designed to support the transition of applications from CPU-only to using the GPU or hybrid CPU-GPU models. Delta features a rich base of preinstalled applications, based on user demand. The system is optimized for capacity computing, with rapid turnaround for small to modest scale jobs, and features support for shared-node usage. Local SSD storage on each compute node benefits applications with random access data patterns or require fast access to significant amounts of compute-node local scratch space. This allocation type covers the use of all Delta GPU node types and all resources (CPU and GPU) within those nodes. If you have CPU only portions of your workflow you should also request an allocation of time under NCSA Delta CPU which provides access to CPU-only compute nodes.
Latitude: 40.11508556949748
Longitude: -88.22457072293128
Production Dates: 09/19/2022 - 08/31/2027
Public URL: https://cider.access-ci.org/public/resources/RDR_000742
Description: The Delta GPU resource comprises 4 different node configurations intended to support accelerated computation across a broad range of domains such as soft-matter physics, molecular dynamics, replica-exchange molecular dynamics, machine learning, deep learning, natural language processing, textual analysis, visualization, ray tracing, and accelerated analysis of very large in-memory datasets. Delta is designed to support the transition of applications from CPU-only to using the GPU or hybrid CPU-GPU models. Delta GPU resource capacity is predominately provided by 200 single-socket nodes, each configured with 1 AMD EPYC 7763 (“Milan”) processors with 64-cores/socket (64-cores/node) at 2.55GHz and 256GB of DDR4-3200 RAM. Half of these single-socket GPU nodes (100 nodes) are configured with 4 NVIDIA A100 GPUs with 40GB HBM2 RAM and NVLink (400 total A100 GPUs); the remaining half (100 nodes) are configured with 4 NVIDIA A40 GPUs with 48GB GDDR6 RAM and PCIe 4.0 (400 total A40 GPUs). Rounding out the GPU resource is 6 additional “dense” GPU nodes, containing 8 GPUs each, in a dual-socket CPU configuration (128-cores per node) and 2TB of DDR4-3200 RAM but otherwise configured similarly to the single-socket GPU nodes. Within the “dense” GPU nodes, 5 nodes employ NVIDIA A100 GPUs (40 total A100 GPUs in “dense” configuration) and 1 node employs AMD MI100 GPUs (8 total MI100 GPUs) with 32GB HBM2 RAM. A 1.6TB, NVMe solid-state disk is available for use as local scratch space during job execution on each GPU node type. All Delta GPU compute nodes are interconnected to each other and to the Delta storage resource by a 100 Gb/sec HPE Slingshot network fabric.