Surface

Surface is an unclassified resource for visualization and data analysis work.  It is limited access.

Here is a breakdown of the "mixed" composition of CPU/GPU architectures on Surface:

Architecture Clock Speed (GHz) CPUs
GPUs
Cores/CPU Node
Cores/GPU Node
Cores Total Memory/Node (GB) Memory Total (GB) TFLOPS peak
Intel 8-core Xeon E5-2670
NVIDIA Tesla K40 GPU
2.6
745 MHz
162
158*2
16
2880
2,592
910,080
256
12*2
41,472
3,792
53.9
451.9
Intel 18-core Xeon E5-2695 v4
NVIDIA Tesla M60 GPU
2.1
1178 MHz
20
20*4
36
2048
720
163,840
256
16*2
5,120
640
12.1
6

The chart, below, is necessarily simplified to the limitations of the database and consistency with other systems.

Zone
CZ
Vendor
Appro
CPU Clock Speed (Ghz)
2.6
Nodes
Login Nodes*
Batch Nodes
158
GPU nodes
158
Total Nodes
162
CPUs
CPU Architecture
Intel Xeon (mixed)
Cores/Node
16
Total Cores
2,592
GPUs
GPU Architecture
NVIDIA Tesla (mixed)
Total GPUs
316
GPUs per compute node
2
GPU peak performance (TFLOP/s double precision)
452.00
GPU global memory (GB)
3 792
Memory Total (GB)
41,500
Memory/Node (GB)
256
Peak Performance
Peak TFLOPS (CPUs)
53.9
Peak TFLOPs (GPUs)
451.9
Peak TFLOPS (CPUs+GPUs)
505.8
OS
TOSS 2
Interconnect
IB QDR
Parallel job type
multiple nodes per job
Run Command
srun
Recommended location for scratch file space
Program
ASC, M&IC
Password Authentication
OTP, Kerberos
Compilers
Job limits
Documentation

Introduction to LC Resources
Linux Clusters Overview

/usr/local/docs/linux.basics
/usr/local/docs/lustre.basics

Availability
Limited