EAS 3 systems
Tenaya, RZVernal, Tioga
Zone
SCF
Vendor
HPE Cray
User-Available Nodes
Login Nodes*
2
Batch Nodes
0
Debug Nodes
22
Total Nodes
24
CPUs
CPU Architecture
AMD Trento
Cores/Node
64
Total Cores
1,536
GPUs
GPU Architecture
AMD MI-250X
Total GPUs
96
GPUs per compute node
4
GPU peak performance (TFLOP/s double precision)
45.00
GPU global memory (GB)
128.00
Memory Total (GB)
16,384
CPU Memory/Node (GB)
512
Peak Performance
Peak TFLOPS (CPUs)
48.0
Peak TFLOPs (GPUs)
4,320.0
Peak TFLOPS (CPUs+GPUs)
4,368.00
Clock Speed (GHz)
2.0
OS
TOSS 4
Interconnect
HPE Slingshot 11
Parallel job type
multiple nodes per job
Program
ASC
Class
ATS-4/EA, CORAL-2
Password Authentication
OTP, Kerberos, ssh keys
Year Commissioned
2022
Compilers

See Compilers page

Documentation