Systems Summary

The HPCMP provides a variety of supercomputing platforms with an array of installed software to enable multidisciplinary computational science and engineering. Multiple vendor platforms, system architectures, programming environments, memory complement, and disk subsystems provide the researcher with a variety of choices for matching his or her code to the appropriate HPC system. Our systems are summarized in the table below.

View Restricted Systems*
View Upcoming Systems

System Attributes
System Site Vendor /
Model		 Node Type OS Core
Type		 Core
Speed1		 Total #
of Nodes		 Cores per
Node		 Total #
of Cores		 Memory per Node (GBytes) Peak
TFLOPS		 End of
Life
Total Accessible
Centennial ARL SGI
ICE XA		 Login RHEL Intel Xeon 2.2 24 40 960 256 252 2600 07/19/2021
Standard RHEL Intel Xeon 2.2 1,784 40 71,360 128 124
Large Memory RHEL Intel Xeon 2.6 32 40 1,280 512 508
GPU RHEL Intel Xeon 2.2 32 40 + 1 GPU
(1 x 2,880 GPU cores)		 1,280 256 252
Gaffney NAVY HPE SGI
8600		 Login RHEL Intel Xeon 2.7 8 48 384 384 380 3050 01/01/2024
Standard RHEL Intel Xeon 2.7 704 48 33,792 192 180
Large Memory RHEL Intel Xeon 2.7 16 48 768 768 744
GPU RHEL Intel Xeon 2.7 32 48 + 1 GPU
(1 x 3,584 GPU cores)		 1,536 384 372
Koehr NAVY HPE SGI
8600		 Login RHEL Intel Xeon 2.7 8 48 384 384 380 3050 01/01/2024
Standard RHEL Intel Xeon 2.7 704 48 33,792 192 180
Large Memory RHEL Intel Xeon 2.7 16 48 768 768 744
GPU RHEL Intel Xeon 2.7 32 48 + 1 GPU
(1 x 3,584 GPU cores)		 1,536 384 372
Mustang AFRL HPE SGI
8600		 Login RHEL Intel Xeon 2.7 12 48 576 384 380 4870 12/08/2023
Standard RHEL Intel Xeon 2.7 1,128 48 54,144 192 180
Large Memory RHEL Intel Xeon 2.7 24 48 1,152 768 744
GPU RHEL Intel Xeon 2.7 24 48 + 1 GPU
(1 x 3,584 GPU cores)		 1,152 384 372
Onyx ERDC Cray
XC40/50		 Login SLES Intel Xeon 2.8 12 22 264 256 8 6060 08/18/2023
Standard CLE Intel Xeon 2.8 4,810 44 211,640 128 121
Large Memory CLE Intel Xeon 2.8 4 44 176 1024 991
KNL CLE Intel Xeon 1.3 32 64 2,048 96 90
GPU CLE Intel Xeon 2.8 32 22 + 1 GPU
(1 x 3,584 CUDA cores)		 704 256 247
SCOUT ARL IBM
Power9		 Login RHEL IBM Power9 2.55 4 40 160 512 502 1200 12/25/2024
Training RHEL IBM Power9 2.55 22 40 + 6 GPUs
(6 x 5,120 CUDA cores,
6 x 640 Tensor cores)		 880 700 690
Inference RHEL IBM Power9 2.55 128 40 + 4 GPUs
(4 x 2,500 CUDA cores,
4 x 320 Tensor cores)		 5,120 256 246
Visualization RHEL IBM Power9 2.55 2 40 + 2 GPUs
(2 x 5,120 CUDA cores,
2 x 640 Tensor cores)		 80 512 502

1) Core speed in GHz