Corona

Zone
CZ
Vendor
Penguin
Nodes
Login Nodes*
Batch Nodes
285
Debug Nodes
0
GPU nodes
285
Total Nodes
291
CPUs
CPU Architecture
170 nodes AMD Naples, 121 nodes AMD Rome
Cores/Node
48
Total Cores
14,064
GPUs
GPU Architecture
82 nodes AMD 4xMI50 GPUs; 82 nodes AMD 4xMI60 GPUs, 123 nodes AMD 8xMI50
Total GPUs
1,640
GPU peak performance (TFLOP/s double precision)
10 948.00
GPU global memory (GB)
52 480
Memory
Memory Total (GB)
127,488
Peak single CPU memory bandwidth (GB/s)
153
Peak Performance
Peak TFLOPS (CPUs)
387
Peak TFLOPs (GPUs)
10,948
Peak TFLOPS (CPUs+GPUs)
11,335
OS
TOSS
Interconnect
IB HDR
Parallel job type
multiple nodes per job
Recommended location for parallel file space
Program
ASC, M&IC, CARES
Password Authentication
OTP, Kerberos
Year Commissioned
2019
Compilers

See Compilers page

Availability
Limited

NOTE Due to the mixed nature of the GPUs in this machine, some of the fields that would normally have single integer inputs are not rendering. Here is additional information:

GPU peak performance (TFLOP/s double precision): MI25 = 0.76 , MI60 = 7.4

GPU Memory/Node: (GB): MI25 = 16GB , MI60 = 32GB

Peak TFLOPs (GPUs): MI25 = 250TF , MI60 = 2,427TF

Also, local NVRAM storage, mounted on each node as /l/ssd (GB): 1500