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 a variety of choices for matching your code to the appropriate HPC system. Our systems are summarized below.

Allocated

System Attributes
System Site Vendor /
Model		 Node Type OS Processor Processor
Speed		 Total
Nodes		 Cores per
Node		 Total
Cores		 Useable Memory
per Node		 Peak
PFLOPS		 End of
Life
Centennial ARL SGI
ICE XA		 Login RHEL Intel E5-2698v4 Broadwell 2.2 GHz 24 40 960 252 GB 2.6 9/30/2022
Standard RHEL Intel E5-2698v4 Broadwell 2.2 GHz 1,784 40 71,360 124 GB
Large-Memory RHEL Intel E5-2698v4 Broadwell 2.6 GHz 32 40 1,280 508 GB
GPU RHEL Intel E5-2698v4 Broadwell 2.2 GHz 32 40
+1 NVIDIA K40P PCIe		 1,280 252 GB
Gaffney NAVY HPE SGI
8600		 Login RHEL Intel 8168 Skylake 2.7 GHz 8 48 384 320 GB 3.05 01/01/2024
Standard RHEL Intel 8168 Skylake 2.7 GHz 704 48 33,792 170 GB
Large-Memory RHEL Intel 8168 Skylake 2.7 GHz 16 48 768 742 GB
GPU RHEL Intel 8168 Skylake 2.7 GHz 32 48
+1 NVIDIA P100 PCIe		 1,536 367 GB
Koehr NAVY HPE SGI
8600		 Login RHEL Intel 8168 Skylake 2.7 GHz 8 48 384 320 GB 3.05 01/01/2024
Standard RHEL Intel 8168 Skylake 2.7 GHz 704 48 33,792 170 GB
Large-Memory RHEL Intel 8168 Skylake 2.7 GHz 16 48 768 742 GB
GPU RHEL Intel 8168 Skylake 2.7 GHz 32 48
+1 NVIDIA P100 PCIe		 1,536 367 GB
Mustang AFRL HPE SGI
8600		 Login RHEL Intel 8168 Skylake 2.7 GHz 12 48 576 380 GB 4.87 12/08/2023
Standard RHEL Intel 8168 Skylake 2.7 GHz 1,128 48 54,144 180 GB
Large-Memory RHEL Intel 8168 Skylake 2.7 GHz 24 48 1,152 744 GB
GPU RHEL Intel 8168 Skylake 2.7 GHz 24 48
+1 NVIDIA P100 PCIe		 1,152 372 GB
Narwhal NAVY HPE Cray
EX		 Login SLES AMD 7H12 Rome 2.6 GHz 11 128 1,408 226 GB 12.8 05/20/2026
Standard SLES AMD 7H12 Rome 2.6 GHz 2,176 128 278,528 238 GB
Large-Memory SLES AMD 7H12 Rome 2.6 GHz 12 128 1,536 995 GB
Visualization SLES AMD 7H12 Rome 2.6 GHz 16 128
+1 NVIDIA V100 PCIe		 2,048 234 GB
MLA 1-GPU SLES AMD 7H12 Rome 2.6 GHz 32 128
+1 NVIDIA V100 PCIe		 4,096 239 GB
MLA 2-GPU SLES AMD 7H12 Rome 2.6 GHz 32 128
+2 NVIDIA V100 PCIe		 4,096 229 GB
Onyx ERDC Cray
XC40/50		 Login SLES Intel E5-2699v4 Broadwell 2.8 GHz 12 44 264 247 GB 6.06 08/18/2023
Standard CLE Intel E5-2699v4 Broadwell 2.8 GHz 4,810 44 211,640 121 GB
Large-Memory CLE Intel E5-2699v4 Broadwell 2.8 GHz 4 44 176 1 TB
KNL CLE Intel 7230 Knights Landing 1.3 GHz 32 64 2,048 90 GB
GPU CLE Intel E5-2699v4 Broadwell 2.8 GHz 32 22
+1 NVIDIA P100 PCIe		 704 247 GB
2-MLA CentOS Intel 6148 Skylake 2.4 GHz 60 40
+2 NVIDIA V100 SXM2		 2,400 172 GB
10-MLA CentOS Intel 6148 Skylake 2.4 GHz 4 40
+10 NVIDIA V100 PCIe		 160 735 GB
SCOUT ARL IBM
POWER9		 Login RHEL IBM POWER9 2.55 GHz 4 40 160 502 GB 1.2 12/25/2024
Training RHEL IBM POWER9 2.55 GHz 22 40
+6 NVIDIA V100 PCIe		 880 690 GB
Inference RHEL IBM POWER9 2.55 GHz 128 40
+4 NVIDIA T4 PCIe		 5,120 246 GB
Visualization RHEL IBM POWER9 2.55 GHz 2 40
+2 NVIDIA V100 PCIe		 80 502 GB
Warhawk AFRL HPE Cray
EX		 Login SLES AMD 7H12 Rome 2.6 GHz 7 128 896 995 GB 6.8 05/20/2026
Standard SLES AMD 7H12 Rome 2.6 GHz 1,024 128 131,072 503 GB
Large-Memory SLES AMD 7H12 Rome 2.6 GHz 4 128 512 995 GB
Visualization SLES AMD 7H12 Rome 2.6 GHz 24 128
+1 NVIDIA V100 PCIe		 3,072 503 GB
Machine-Learning SLES AMD 7H12 Rome 2.6 GHz 40 128
+2 NVIDIA V100 PCIe		 5,120 503 GB

Non-Allocated

System Attributes
System Site Vendor /
Model		 Node Type OS Processor Processor
Speed		 Total
Nodes		 Cores per
Node		 Total
Cores		 Useable Memory
per Node		 Peak
PFLOPS		 End of
Life
Hokule'a MHPCC IBM
POWER8		 Login RHEL 7 IBM POWER 8 2.86 GHz 1 20 20 240 GB 690 9/30/2022
GPU RHEL 7 IBM POWER 8 2.86 GHz 32 20
+4 NVIDIA P100 PCIe		 640 244 GB
Talon AFRL Aspen Systems
Intel		 Login RHEL 6 Intel E5-2640v3 Haswell 2.6 GHz 1 16
+1 NVIDIA Grid K1 PCIe		 16 125 GB 13.5 9/30/2022
Project (dedicated) RHEL 6 Intel E5-2640v3 Haswell 2.6 GHz 5 16 80 125 GB
Standard RHEL 6 Intel E5-2670v3 Haswell 2.6 GHz 6 24 144 125 GB
GPU RHEL 6 Intel E5-2670v3 Haswell 2.3 GHz 1 24
+2 NVIDIA K80 PCIe		 24 125 GB
Phi RHEL 6 Intel E5-2670v3 Haswell 2.3 GHz 1 24
+2 Intel 7120P		 24 125 GB
Vulcanite ERDC SuperMicro
SuperServer MLA V100		 Login RHEL7 Intel 6126T Skylake 2.6 GHz 2 12 24 206 GB 60.5 10/01/2022
2-GPU RHEL7 Intel 6126T Skylake 2.6 GHz 26 12
+2 NVIDIA V100 PCIe		 312 206 GB
4-GPU RHEL7 Intel 6136 Skylake 3.0 GHz 8 24
+4 NVIDIA V100 SXM2		 192 384 GB
8-GPU RHEL7 Intel 8160 Skylake 2.1 GHz 5 48
+8 NVIDIA V100 SXM2		 240 764 GB

Upcoming

Implementation Schedule
SiteEstimated DateDescription
ARL DSRC 2nd Quarter, FY 2022 Jean will contain 57,696 Intel XEON "Cascade Lake Advanced Performance" compute cores and 280 NVIDIA Ampere A100 General-Purpose Graphics Processing Units (GPGPUs), interconnected with a 200 Gigabit per second InfiniBand network and supported by 323 terabytes of memory, and 12.5 petabytes of usable non-volatile memory express (NVMe)-based solid state storage.
ARL DSRC 3rd Quarter, FY 2022 Kay will contain 48,480 Intel XEON "Cascade Lake Advanced Performance" compute cores and 76 NVIDIA Ampere A100 General-Purpose Graphics Processing Units (GPGPUs), interconnected with a 200 Gigabit per second InfiniBand network and supported by 240 terabytes of memory, and 10 petabytes of usable non-volatile memory express (NVMe)-based solid state storage.
ERDC DSRC 3rd Quarter, FY 2022 Wheat will contain 890 Intel 9242 Cascade Lake AP compute nodes with 96 cores per node (85,440 cores). 770 nodes will be standard compute nodes, with 384 GB of memory per node; 16 will be visualization nodes, with 768 GB of memory and one nVidia A100 (Ampere) GPU each; 96 will be AI/ML nodes, with 384 GB of memory and one nVidia A100 (Ampere) GPU each; 8 will be large-memory nodes, with 2 TB of memory each. The /home file system will have 720 TB of usable NVMe storage, and the /app file system will have 360 TB.
Navy DSRC 3rd Quarter, FY 2022 Nautilus will contain 176,128 total compute cores comprised of future generation AMD EPYC processors, and 144 NVIDIA Ampere A100 GPUs interconnected by a 200 gigabit per second Mellanox HDR-200 InfiniBand network, and supported by 26 PB of usable Data Direct Networks storage, including over 4 PB of NVMe-based solid-state storage, and 382 TB of system memory.
AFRL DSRC 3rd Quarter, FY 2022 Raider will contain 189,440 total compute cores comprised of future generation AMD EPYC processors, and 152 NVIDIA Ampere A100 GPUs interconnected by a 200 gigabit per second Mellanox HDR-200 InfiniBand network, and supported by 26 PB of usable Data Direct Networks storage and 455 TB of system memory.