RZHasGPU is a small, unclassified resource for visualization and data analysis work. It is a Limited Access resource.
Zone |
RZ
|
Vendor |
Appro
|
User-Available Nodes |
Login Nodes*
1
Batch Nodes
14
Debug Nodes
2
Total Nodes
20
|
CPUs |
CPU Architecture
Intel Xeon E5-2667 v3
Cores/Node
16
Total Cores
320
|
GPUs |
GPU Architecture
NVIDIA Tesla K80
Total GPUs
64
GPUs per compute node
4
GPU peak performance (TFLOP/s double precision)
60.00
GPU global memory (GB)
768.00
|
Memory Total (GB) |
2,560
|
CPU Memory/Node (GB) |
128
|
Peak Performance |
Peak TFLOPS (CPUs)
8.2
Peak TFLOPs (GPUs)
59.8
Peak TFLOPS (CPUs+GPUs)
68.00
|
Clock Speed (GHz) |
3.2
|
Peak single CPU memory bandwidth (GB/s) |
68
|
OS |
TOSS 3
|
Interconnect |
IB QDR
|
Parallel job type |
multiple nodes per job
|
Run Command |
srun
|
Recommended location for parallel file space |
/p/lustre1
|
Program |
ASC, M&IC
|
Password Authentication |
OTP, Kerberos
|
Compilers |
Compilers (TOSS 3) |
Documentation |