Anselm Cluster at IT4Innovations
David Hrbáč 18.9.2015
Intro
What is the supercomputer
Infrastructure
Access to cluster
Support
References
Mission and Vision
Mission
Our mission is to deliver scientifically excellent and industry relevant research in the fields of high performance computing and embedded systems. We are providing state-of-the-art technology and expertise in high performance computing and embedded systems and make it available for Czech and international research teams from academia and industry.
Vision
To became top European Centre of Excellence in IT with the emphasis on high performance computing and embedded systems. With our research, know-how and infrastructure we aspire to improve the quality of life, to increase the competitiveness of industrial sector and to promote the cross-fertilization of high-performance computing, embedded systems and other scientific and technical disciplines.
The IT4Innovations National
Supercomputing Center
Prague
Brno
Ostrava
2013
2014
2015
80 TFLOPs system – most powerful supercomputer in Czech Republic, #6 in Central Europe (June 2013), operational since June 2013, 1 PFLOPs system planned for 2015
Early Days
The Future / HAL
Supercomputer
What is a Supercomputer
Bunch of computers
Having a lot of CPU power
Having a lot of RAM
Local storage
Shared storage
High-speed interconnected
Message Passing Interface
Supercomputer?!?
Supercomputer?!?
Areal View I.
Areal View II.
Diesel- generator
Four chillers
Cooling
infrastructure
Service
container
MOBULL
container
MOBULL Layout
MOBULL Inside III.
Anselm Hardware
Salomon vs. Anselm
0 200 400 600 800 1000 1200 1400 1600 1800 2000
Anselm
Velký cluster
Rpeak CPU
Rpeak GPU
Rpeak MIC
TFLOP
S
Salomo
n
Login Credential
Personal certificate
Signed request Credentials encrypted
Login
Password
SSH keys
Passphrase to the key
Credential Lifetime
Active project(s) or affiliation to IT4Innovations
Deleted 1 year after the last project Announcement
3 months before the removal 1 month before the removal 1 week before the removal
Anselm/Salomon SW Environment
Log-in
lSSH (X Forwarding)
lVNC
Modular software stack
lMultiple versions
lExtra data store
PBS Jobs scheduler
lQueues
lPriorities
lProjects
Accessing the Clusters
ssh
round-robin DNS record anselm.it4i.cz (login1,login2) salomon.it4i.cz (login1,login2,login3,login4)
Ssh Agent / Putty Pageant
Command line
Ssh Tmux – console multiplexer
Multisession Handles lost connection
Environment modules Modification to SW stack
GUI Access
X11 forward Slow Needs fast connection ssh –X [email protected]
VNC server access Dead lock (kill screensaver, kill vncserver) Handles lost connection Vpnpasswd Vncserver :72 –geometry 1920x1080 –depth 24 ssh –L 5972:localhost:5972 [email protected]
Support
Bug tracking and trouble ticketing system
Documentation
IT4I internal command line tools
IT4I web applications
End-user courses
Main Users
mapy.cz
Testing codes for computational fluid dynamics
Thermal expansions of materials for 4th generation reactors
Performance and scalability test of a hydrological model with remote execution
Simulations of particle acceleration by short ultra-intense laser pulses
Research to help Moravian-Silesian Region (regional grants)
Research to help CR (national grants & bilateral co-operations)
VSB-TUO, CVUT, VUT, CDV, CAMEA, CEDA, CE-Traffic, ELTODO, Kapsch, KVADOS
MOLDIMED FN OL, FN Brno, MU, VSB-TUO, UMG AV CR,
IntellMed, GENERI BIOTECH, Sofigen, IAB, CGB lab, EXBIO Praha
Research to Help Europe (grants within 7th framework programme)
POLIMI, IMEC, ICCS, UCY, IT4I, THALES, HENESYS
We Want You
Key Message
We will provide you with
Resources
Plenty of CPU time
Data store
Specialized HW – GPU cards
SW – you name
Support
Technical – what, how, when, where
Code experts
Optimization
Thank you for listening
Questions?
docs.it4i.cz
www.it4i.cz