UberCloud Customer Workshop for engineers and scientist and their software providers, discussing cloud challenges and their solution, based on novel UberCloud software container technology which allows access and use of cloud resources and engineering applications and data, on demand, at your fingertips.

1. High Performance Computing in the Cloud
UberCloud CustomerWorkshop
Wolfgang Gentzsch, President, UberCloud

2. Agenda
 UberCloud
 Workstations, Servers, Clouds: Benefits & Challenges
 Total Cost of Ownership: On-premise vs On-cloud
 Live Demo: Engineering Simulations in the Cloud
 Application Software Containers
 Cooperation

3. UberCloud: What we do for HPC*)
Taking engineering & scientific apps
in software containers to ANY computer,
from workstations, to servers, to any cloud
*) High Performance Computing

4. UberCloud
 July 2012: Building user community with ‘cloud experiments’ (190 so far),
feedback, measuring traction, cloud roadblocks
 March 2013: Starting HPC container development => Apps are easy
packageable, portable, accessible, usable, and scalable
 Nov 2014: Opening online marketplace with currently 35 stores & established
provider ecosystem (appl. software resources, software, expertise)
 April 2016: CAE software containers: ANSYS,CD-adapco,CFD Support,
CFturbo, COMSOL, Dacolt, Flow Science, Friendship Systems, LS-Dyna, NICE
DCV, Numeca,OpenFOAM, Red Cedar, Simulia, … On Clouds from Advania,
AmazonAWS, MicrosoftAzure, Bull/Atos,CPU 24/7, OzenCloud R-Systems,…
 April 2016:Go to Market with partners Azure, HPE, Intel, ANSYS, many more
 January 2017: Pre-A $1.7 M with EarlybirdVenture Capital

5. UberCloud:Why
 Engineers design every product we see, own, and use
 Using sophisticated engineering simulation software
 But most engineers (95%) still just use desktop computers
 Buying your own servers is too expensive (highTotal Cost of
Ownership)
 Hybrid approach is cost-effective solution:
 Small in-house cluster or workstation, plus bursting on
demand into HPC Clouds
 UberCloud: vendor-independent one-stop shop for consumer/
provider community, online marketplace, container technology

6. Your major computing tools:
, servers,and clouds
Let’s analyze the benefits & challenges
for 20 million engineers & scientists today
workstations

7. But, workstations have limited capacity
 Computing: too slow
 Memory: too small
57 % of users are dissatisfied with their desktop
computing capacity*
* Source: US Council of Competitiveness: http://www.compete.org/

8. Benefits of servers
 More compute power and memory
 Higher quality design and products
 Reducing product failure early
 Shorten time to market
=> Strengthen your company’s competitiveness.

9. Challenges with in-house servers
Our 193 UberCloud simulation experiments
exposed the following pain points:
 Long procurement cycles for buying h/w and s/w
 HighTotal Cost ofOwnership (TCO)
 Complex technical software and infrastructure
 Bursty usage
 Rapid technology refresh cycles, servers aging fast
 Need for trained server and system experts.

10. TCO: Servers are expensive and complex
$70,000 server => $0.5 - $1 mio cost over 3 years

11. http://www.databax.co.uk/blog/the-best-cloud-computing-infographics-and-images-ever#.Vt06X5MrIUE
On premise versus cloud

12. Benefits of clouds
 More (infinite) computing
 No upfront Cap-Ex investment
 On demand, pay per use, at your fingertips
 Scaling resources dynamically, up and down
 Choice, with multiple providers
 Result: better, faster, cheaper.

13. But: Cloud Challenges
 It’s new !
 Security / your intellectual property
 Traditional software licensing
 Data transfer
 Cloud expertise is needed
 Losing control over your jobs and data
 First access to clouds is often cumbersome
13

14. SoftwareContainers remove / reduce challenges

15. SoftwareContainers remove / reduce challenges
http://www.theubercloud.com/workstations
-servers-clouds-comparing-apples-apples/

16. Cost: server versus cloud
Table: real server cost depending on average utilization. http://www.theubercloud.com/cost/
• HPC Server: 16 nodes, 3-yearTCO
$1 million. Average utilization25%
results in $0.60 per core per hour
• HPC Cloud: $0.12 core per hour e.g. on
AWS,Azure, or CPU 24/7 cloud resources

17. Real example:
TCO for 100 node in-house cluster
http://www.nextplatform.com/2015/06/03/the-hpc-cloud-versus-cluster-cost-conundrum/

18. Cluster cost – owning, hosting, renting
 100-node cluster hardware = $41,721 per month
 12-node cluster hardware = $5,006 per month
 $5,006 * 5(*) = $25,032TCO per month or $0.18 per core hour
 This $0.18 per core hour is for 100% utilized cluster
Number of busy
compute nodes
1 2 3 4 6 8 9 12
Resulting in cluster
utilization of
8.3% 16.7% 25% 33.3% 50% 66.7% 75.0% 100%
In-house cluster
cost per core/h
$2.16 $1.08 $0.72 $0.54 $0.36 $0.27 $0.24 $0.18
Cost per core/h
cloud hosting
$1.20 $0.60 $0.40 $0.30 $0.20 $0.15 $0.13 $0.10
Cost per core/h,
cloud bursting
$0.13 $0.13 $0.13 $0.12 $0.13 $0.13 $0.13 $0.13
(*)TCO estimates in the literature are a factor of 3 – 7 of the hardware cost => Factor 5

19. Including CAE software cost
 1 hour in-house cluster, average utilization of x%
with x = 80%, 60%, 40% on 16, 32, 64 cores =
 1 hour in-house CAE software, average utilization of x%
with x = 80%, 60%, 40% on 16, 32, 64 cores =
 1 hour cloud resources on 16, 32, 64 cores =
 1 hourCAE software on 16, 32, 64 cores =

20. Cost of ISV software licensing
 In-house: perpetual, annual, cost for upgrade,
support & maintenance, etc.
 In-cloud: annual (hosting), monthly, weekly, daily,
hourly, on-demand
 Examples:
 eCADFEM => Software on demand (pay per use) =>
Simulation as a Service (hw / sw on demand) via
Customer Portal
 CADFEM Engineering Simulation Cloud (with Spirit/21)
 ANSYS Enterprise Cloud
 ANSYS Elastic Licensing

21. URL & pass:
http://52.164.231.11:5901/vnc.html
jDmcvczkZfiQ
Live Demo *)
OpenFOAM in der Cloud, im Container

22. UberCloud Marketplace
Go to the UberCloud online Marketplace

23. Welcome email in your Inbox:
Copy password and click on Login

24. New window in your Browser
Paste password and clickConnect

25. UberCloud desktop with
your application software folder

26. Every x hours: you receive email with
screenshot and log files*)
*) Allowing full control over your cloud activities

27. DemoVideos, 3 minutes each
- https://www.youtube.com/watch?v=EbKDOxVnxbE
- https://www.youtube.com/watch?v=cCSE0Lcj0wk
- https://www.youtube.com/watch?v=yFNM9dsCV44.

28. UberCloud application containers
based on Docker

29. The Foundation:
Docker-based HPC Container Technology
Docker is an open platform for developers and sysadmins
to build, ship, and run distributed applications,
whether on laptops, data center VMs, or the cloud
Enterprise micro services + HPC Layers => HPC macro services

31. Virtual Machines vs Docker
VM: Each virtualized application includes not only the application and the necessary
binaries and libraries, but also an entire guest operating system.
Docker Engine container comprises application and its dependencies. Isolated process
in user space on host operating system, sharing kernel with other containers. Enjoys
resource isolation and allocation benefits ofVMs but more portable and efficient.
31

32. UberCloud application containers
 Based on Docker, enhanced for engineering & scientific
applications
 Software packages designed to deliver the tools that an
engineer needs
 Ready to execute, in an instant. No need to install software,
deal with complex OS commands, or configure.
 Software is pre-installed, configured, and tested, and running
on bare metal, without loss of performance.
 ANSYS,CD-adapco, COMSOL, Numeca, OpenFOAM,
Gromacs, Scilab, and more

33. UberCloud’s unique HPC container features
Basic
 multi-container single-node
 ssh between containers
 Running withinVMs and on bare
metal
 Up-to-date Linux (CentOS,
Ubuntu,…)
 Screen sharing
 Cloud data storage connectors
(to Dropbox, Box.com,…)
 Emailing features (reporting job
status etc.)
 License server in every container
 MPI libraries
 NFS
Administrative
 Automated password
generation
 Self-service password change
for increased privacy
 Performance checking
 Log monitoring
 Automated build/refresh
process
 Diff utilities

34. Cont’d
Advanced
 Rapid file transfer (from Globus)
 VPN
 Pay-per-use
 multi-container multi-node / inter-
networking
 Infiniband
 NICE DCV remote visualization
 VCollab data extraction & visualization
 OwnCloud privacy & security for cloud
storage
 GPU and Intel Phi enabled
 RDMA
 UberCloud storage containers (USC)
Projects
 OpenHPC
 Pre-built images for ISV codes and
complex scientific and engineering
workflows
 Univa Grid Engine in-out integration:
containers hosting UGE and can be
managed by UGE
 Slurm container integration
 Automated QA testing suite
 OpenStack
 Qstack
 Living Heart Project
 Human Brain Project

35. Containers remove Portability & Standard related challenges.
By integrating 3rd party tools we tackle the following:

36. Builder
Launcher
Controller
ISV DataTools
Stackable units with tools (ex: encryption), ISV application codes (ex: OpenFOAM).
Just add your own codes and data.
Run anywhere with UberCloud Run Time.
Scale up or down the compute power as needed.
Collect granular usage data, logs.
Monitor, alert, report.
Any
Workstation
Any Cluster Any Cloud
Run Time Run Time Run Time
Containers: Build once, run anywhere

37. Builder
Launcher
Controller
ISV DataTools
Stackable units with tools (ex: encryption), ISV application codes (ex: OpenFOAM).
Just add your own codes and data.
Run anywhere with UberCloud Run Time.
Scale up or down the compute power as needed.
Collect granular usage data, logs.
Monitor, alert, report.
Any
Workstation
Any Cluster Any Cloud
Run Time Run Time Run Time
Containers: Build once, run anywhere

38. Builder
Launcher
Controller
ISV DataTools
Stackable units with tools (ex: encryption), ISV application codes (ex: OpenFOAM).
Just add your own codes and data.
Run anywhere with UberCloud Run Time.
Scale up or down the compute power as needed.
Collect granular usage data, logs.
Monitor, alert, report.
Any
Workstation
Any Cluster Any Cloud
Run Time Run Time Run Time
Containers: Build once, run anywhere

39. Builder
Launcher
Controller
ISV DataTools
Stackable units with tools (ex: encryption), ISV application codes (ex: OpenFOAM).
Just add your own codes and data.
Run anywhere with UberCloud Run Time.
Scale up or down the compute power as needed.
Collect granular usage data, logs.
Monitor, alert, report.
Any
Workstation
Any Cluster Any Cloud
Run Time Run Time Run Time
Containers: Build once, run anywhere

40. HTTPS/VPN Access*
OS Firewall
OS PKI Login
Disk Encryption*
Dedicated
Servers in High
Security Data
Centers
* HTTPS/VPN access and Disk Encryptionare optional
UberCloud Security Layers
We deploy on single tenant servers (not shared between
customers).These servers reside in professionally managed,
highly secured data centers.
Data at rest can be encrypted. Disk and file level
encryption are both available (optional, may degrade performance)
Admin access to our servers are protected by PKI
Public Key Encryption (vs passwords, which can be guessed)
Our servers are protected with firewalls. Only necessary
ports are turned on to reduce attacks
Connection to our servers are protected by strong
encryption techniques such as HTTPS andVPN

41. Security
 Information security, privacy:
 protecting the users intellectual property
 guarding raw data (physics, geometry, results)
 Recommendation:
 document your security requirements
 select a suitable provider
 Encryption,VPN, dedicated cloud server,TRUST, etc.
 Comment:
 Security in the cloud is at the same standard level as
any other IT infrastructure. It’s more a mental issue.

42. DataTransfer
 Internet too slow for heavy data transfer:
 Often GBytes of results
 Especially last mile problem
 Recommendation:
 Don’t ship every byte, just important ones (VCollab)
 Use remote visualization (NICE DCV)
 if necessary, fedex the data over-night
 Comment:
 Clouds can’t solve your last mile problem

43. CloudCost
 Cost of Cloud is often hidden:
 Server versus Cloud cost is often unclear
 pay-per-use billing can result in unpredictable cost
 project can easily run out of budget
 Recommendation:
 Cost estimation upfront (UberCloud paper www…./cost *)
 Automated, policy driven monitoring of usage & billing
 Comment:
 Replacement and bursting are 2 different questions
*) https://www.TheUberCloud.com/cost/

44. Software licensing
 Incompatible software licensing models:
 ISVs often still stick to their annual, perpetual licensing
 Recommendation:
 Check app software stack on UberCloud Marketplace
 Talk to your ISV
 ISVs should develop on-demand short-term s/w licensing
 Comment:
 Some ISVs have cloud licensing (CD-adapco,COMSOL,
ANSYS,…)
 Many ISVs are developing cloud licensing
 Engineers need pay-per-project (week, month)

45. Solving software licensing issue, with
containers
 200+ experiments led to an excellent network of ISV
relationships with 120+ ISVs
 Solution: UberCloud including a license server into every
container
License
Server
License
Server
License
Server
Any License
Server
ISV Software
ContainerCustomer
Software Provider

46. UberCloud multi-container environment
 Intel MPI libraries pre-setup for multi-node HPC
 Intel compilers achieve architecture specific HPC
 Networking between containers
 Setting up shared file system access (NFS)
 Secure communication (ssh) between containers
 Benefits from single-node transferred to multi-node
containers:
 No setup of the environment
 Portability and packaging
 Easy access and use
 Low overhead
+

47. UberCloud multi-container environment
Docker Runtime Docker Runtime Docker Runtime
. . . .
NFS
Host Host Host
Container Container Container
MPI
Verticalscaling
Horizontal scaling
Dramatically simplifying

48. UberCloud multi-container environment
Docker Runtime Docker Runtime Docker Runtime
. . . .
NFS
Host Host Host
Container Container Container
MPI
Verticalscaling
Horizontal scaling
Packaging, Porting, Access, Use, Scaling, with Low Overhead

49. When in multi-node cluster mode:
 Only the ‘master’ is accessible via GUI. GUI stays the same, with
tools included in the ‘master’ container.
 Additional servers are deployed, UC container finds &
communicates with other nodes automatically.
 Cluster nodes accessible from GUI node, containers automatically
establish password-less SSH group, with nodes talking to each
other.
 Machine file is automatically generated: MPI jobs are distributed
across cluster nodes, and workloads are being distributed.
 No need for queuing; all servers are dedicated to user.Workload
requiring queue software is handled as a special requirement.

50. OpenFOAMTest: Bare Metal vs Docker
OpenFOAM with 1.4 million cells on bare metal and in
UberCloud Docker container

51. Containers as basic technology
for the UberCloud SaaS Factory
UberCloud
SaaS Factory
Software SaaS
Commercial ISV
Open Source
In-house
PublicCloud
Private Cloud
On-Premise
$$$
We turn high-TCO, complex software into user-friendly pay-per-use services:
Development Services
(Docker)
--------------------
Deployment &
Management Services
------------------
Marketplace
Providers Consumers
$
UberCloud SaaS Factory

52. UberCloud Marketplace

53. Cooperation with UberCloud
 Proof of Concept Project: with your own application in the
Cloud
 Application – HPC-Container for one of your applications
 Training and Support: 24 hours on 32 cores, with up to 8
hours professional service
 TCO: Total Cost ofOwnership analysis for your on-prem
servers vs cloud vs hybrid cloud solution
 Vision: Private Cloud, Hybrid Cloud, PublicCloud, enabled by
UberCloud containers

54. ThankYou!
Questions?