The document discusses OpenPOWER, an open ecosystem using the POWER architecture to share expertise, investment, and intellectual property. It outlines the goals of the OpenPOWER Foundation to serve evolving customer needs through collaborative innovation and solutions. Examples are provided of innovations developed through partnerships, such as accelerated databases, optimized flash storage, and high performance computing systems. The benefits of the OpenPOWER approach for customers are affirmed through adoption of Linux distributions and cloud deployments.
2. AgendaAgendaAgendaAgenda
Why OpenPOWER ?
OpenPOWER Members
POWER Architecture - Differentiators
Collaborative Innovation / Solutions
Adoption Ease & Affirmation of Strategy
Backup
Membership, Workgroups, POWER Licensing models
3. Industry Trends Drive Innovation Beyond The Chip
Processors
Semiconductor Technology
System stack innovations are required to drive Cost/Performance
Applications and Services
Firmware, Operating System
and Hypervisor
System Stack
Systems Management &
Cloud Deployment
Systems Acceleration &
HW/SW Optimization
Workload Acceleration
Services Delivery Model
Advanced Memory Tech
Network & I/O Acceleration
Use Cases
Microprocessors alone no longer drive sufficient Cost/Performance improvements
Processors
Semiconductor Technology
4. • Moore’s law no longer
satisfies performance gain
• Growing workload
demands
• Numerous IT consumption
models
• Mature Open software
ecosystem
OpenPOWER, a catalyst for Open Innovation
• Rich software ecosystem
• Spectrum of power
servers
• Multiple hardware options
• Derivative POWER chips
The goal of the OpenPOWER Foundation is to create an open ecosystem, using
the POWER Architecture to share expertise, investment, and server-class
intellectual property to serve the evolving needs of customers.
Performance of
POWER architecture
amplified capability
Open Development
open software, open hardware
Collaboration of
thought leaders
simultaneous innovation,
multiple disciplines
Feeds back …Feeds back …Feeds back …Feeds back …
resulting in client choiceresulting in client choiceresulting in client choiceresulting in client choice
New Open InnovationMarket Shifts
Founding Members
5. August 2013 Announced Intent; December 2013 Incorporated with 5 members
Fueling an Open Development Community [140+ Members in 22+ Countries]
6. New Chips &
Components
Components
& Systems
New Systems &
Platforms
Integrated
Solutions
First Open server specification and motherboard combining
OpenPOWER, Open Compute and OpenStack
First GPU-accelerated
OpenPOWER developer platform
Prototype of a new high-performance
server on the path to exascale
First commercially available OpenPOWER server
RedPower, the first China OpenPOWER
2-socket system coming in 2015 Inspur 2-socket POWER8 Server
ChuangHe China-branded
OpenPOWER system with POWER8
Data Engine for NoSQL with 40TB CAPI-attached flash
Open Source
Redis
Clustering 192 Vcores
+ CAPI
40TB in 2U
First China “local” POWER derivative chip, CP1Convey’s CAPI developer kit based on the company’s Xilinix-
based co-processors
DMI connection between an Altera Stratix V FPGA
accelerator and a POWER8 CPU
First commercially available OpenPOWER
third-party server
New CAPI-based solution: the ConnectX-4
adapter card by Mellanox
Nallatech’s OpenPOWER CAPI
Developer Kit
24:1 Server consolidation for 3x lower cost per user
9. CAPP PCIe
POWER8 Processor
FPGA
Functionn
Function0
Function1
Function2
CAPI
IBM Supplied POWER Service
Layer
Typical I/O Model Flow
Flow with a Coherent Model
Advantages of Coherent Attachment Over I/O Attachment
Virtual Addressing & Data Caching (significant latency reduction)
Easier, Natural Programming Model (avoid application restructuring, focus on workload rather than IO)
Enables Apps Not Possible on I/O (Pointer chasing, shared mem semaphores, …)
What isWhat isWhat isWhat is CAPICAPICAPICAPI –––– Coherent Accelerator ProcessorCoherent Accelerator ProcessorCoherent Accelerator ProcessorCoherent Accelerator Processor Interface ?Interface ?Interface ?Interface ?
300 Instructions 10,000 Instructions 3,000 Instructions
1,000 Instructions
1,000 Instructions
400 Instructions 100 Instructions
10. Demonstrating the Value of CAPI Flash IO
Identical hardware with 2 different
paths to data
FlashSystem
Conventional
I/O (FC) CAPI
0
20,000
40,000
60,000
80,000
100,000
120,000
Conventional CAPI
IOPS per Hardware Thread
0
50
100
150
200
250
300
350
400
450
500
Conventional CAPI
Latency (microseconds)
IBM POWER S822L > 5x better IOPS
per HW thread
> 2x lower latency
13. What is NoSQL and who uses it
List of Companies using NoSQLs in production
*DATASTAX CORPORATION
NoSQL = Not Only SQL
– Not relational
– Simple data models
– Fast, Scalable, Highly Available
Types of NoSQLs
– Key Value
• Redis, WebSphere XS
– Column Store
• Cassandra, BigTable
– Document Store
• mongoDB, Cloudant
– Graph
• neo4j, titan
Who uses them
– Twitter
– Instagram
– Pinterest ………
14. Key Technologies & Open POWER Partners
Open Source RedisClustering
192 Vcores + CAPI 40TB in 2U
Data Engine for NoSQL
15. strategy ( )
Exploiting CAPI Acceleration for Optimized Flash IO
Attach IBM FlashSystem to POWER8 via CAPI Coherent Attach
Issues Read/Write Commands from applications to eliminate 90% of code
path length
Saves 20-24 cores per 1M IOPs
Pin buffers, Translate,
Map DMA, Start I/O
Application
Read/Write Syscall
Interrupt, unmap,
unpin,Iodone scheduling
20K
instructions
reduced to
< 2k
Disk and Adapter DD
strategy ( ) iodone ( )
FileSystem
Application
User Library
Posix Async
I/O Style API
Shared Memory
Work Queue
aio_read()
aio_write()
iodone ( )
LVM
16. Data Engine for NoSQL with 40TB CAPI-attached flash
Load Balancer
500GB Cache
Node
10Gb Uplink
POWER8 Server
Flash Array w/ up
to 40TB
After: NoSQL POWER8 + CAPI Flash
WWW
10Gb Uplink
WWW
Backup Nodes
500GB Cache
Node500GB Cache
Node500GB Cache
Node500GB Cache
Node
Before: NoSQL in memory (x86)
24U
4U
Less is More
24:1 physical server consolidation =
6x less rack space
24:1
server consolidation
3x
lower cost per user
Infrastructure Requirements
- Large Distributed (Scale out)
- Large Memory per node
- Networking Bandwidth Needs
- Load Balancing
Acceptable
latency
CAPI
Memory
Conventional PCIe I/O
network
network
network
17. IBM & Partner collaboration on OpenPOWER RoadmapIBM & Partner collaboration on OpenPOWER RoadmapIBM & Partner collaboration on OpenPOWER RoadmapIBM & Partner collaboration on OpenPOWER Roadmap
2015 2016 2017
POWER8 POWER8+ POWER9
OpenPower
CAPI Interface NVLink
Enhanced
CAPI & NVLink
Connect-IB
FDR Infiniband
PCIe Gen3
ConnectX-4
EDR Infiniband
CAPI over PCIe Gen3
ConnectX-5
Next-Gen Infiniband
Enhanced CAPI over PCIe Gen4
Mellanox
Interconnect
Technology
IBM CPUs
NVIDIA GPUs
Kepler
PCIe Gen3
Volta
Enhanced NVLink
Pascal
NVLink
Systems
18. Monte Carlo
250x faster
than POWER8 core alone, reduced C code 40x over non-CAPI FPGA
Altera FPGA acceleration and IBM CAPI
19. • In-memory distributed database
using GPUs for processing
• Order of magnitude gains:
• Performance over CPU solutions
• Power reduction
• Cost savings
• Anticipate order of magnitude gains
with POWER based NVLink solutions
in 2016
GPUdb in-memory Accelerated Database
Ultrafast ingest and analysis of billions of objects
20. 10x higher throughput, 10x lower
latency accelerating NoSQL workloads
PHP (Zend)
PHP (Zend)
Linux (Ubuntu)
A
(Ubuntu)
Apache Web Server
(Ubuntu)
MariaDB (MariaDB)
PHP (Zend)
Orchestration-JujuOrchestration-Juju
(Ubuntu)
High Speed Data Transfer (Mellanox)
Turbo LAMP Stack for mobile and web apps
Future
TurboLAMP
Dramatically less data center infrastructure
Dramatically faster responsiveness to customers
21. • Accelerated appliance with novel data-flow implementation of Memcached
on FPGA.
• Up to 36x improved performance and power response times in
microsecond range.
• CAPI integration of memory allows both host memory and coherent-
attached flash to be used as value store.
Up to 36x performance
improvement
for Key-Value Store acceleration
23. OpenPOWER Developer System
• Single socket ATX form factor board, BMC based evaluation board
• Service subsystem identical to x86
• Reference System for ISV application and OpenPOWER partners
• OpenPOWER Software Stack
24. OpenPOWER System
Habanero 2U
• 1 socket POWER8 “Stradale” Module (up to 190w)
• Up to 1TB DDR4 Memory
• Up to 12 HDD/SDD Storage
• Full storage, networking and DC infrastructure
25. Linux Distro Support For POWER
RHEL 7
Aavailable for existing RHEL
customers
POWER8 (native mode) and
POWER 7/7+ at GA
LE support in RHEL7.1
Baremetal support in RHEL 7.2
RHEL 6
• POWER8 supported with U5 (P7-
compatibility mode)
• Full support of POWER6 and
POWER7
(native mode)
Fedora
• Fedora supports POWER, actively
develpped
• Fedora 20 has POWER8 support
Supported add-ons
• JBoss
• High Performance Network Add-on
• More SW in future
Built from the same source as x86
Delivered on the same schedule as x86
Supported at the same time as x86
Close development relationship with IBM
Ubuntu 15.04
Docker container support
Baremetal host support
KVM support
Ubuntu 14.04
POWER8 enabled (native mode)
No official support for POWER7+
and older systems
No support for 32-bit
applications. 64-bit only.
Supported in KVM only at this
time
Baremetal / host supported as
tech preview, official support in
near future
Supported add-ons
• Ubuntu openstack
• JuJu Charms
• MaaS (Metal as a Service)
• Landscape
Debian
• Community enablement,
officially supported architecture
• Consensus distribution for
OpenPower
SLES 12
Baremetal and LE support
SLES 11
• POWER8 supported with SP3 (P7-
compatibility mode)
• P7+ encryption, RNG accelerators
• Full support of POWER6 and
POWER7
(native mode)
OpenSUSE
• OpenSuSE 12.2 re-launched with
IBM POWER
• OpenSuSE 13.2 includes Power8
support
Supported add-ons
• SUSE Linux Enterprise High
Availability Extension
• More SW in future
26. Open Deployment Architecture
H/W Management
- Custom scripting
- Heavily Automated
- Open technologies
Platform Management
- Custom management
- Cloud based
Enablement strategy:
Bring base components in parity with KVM on x86 – “KVM should be KVM”
Co-exists peacefully with other end-points, whenever makes sense.
Enables hybrid clouds with common management environments
Manage
Provision
Deploy
Procure
Openstack Ironic
xCat
Puppet
Chef
Custom Scripts
PXE
IPMI
OpenStack
Custom Scripts
27. IBM, Mellanox, and NVIDIA awarded
$325M U.S. Department of Energy’s Super Computer bids
Two super computers for Oak Ridge and
Lawrence Livermore Labs in 2017. Sequoia (LLNL)
2012 - 2017
Mira (ANL)
2012 - 2017
Titan (ORNL)
2012 - 2017
Current DOE Leadership Computers
5x – 10x Higher Application Performance versus Current Systems
>100 PF, 2 GB/core main memory, 800GB/node local NVRAM, 120PB, ~10MW
Mellanox EDR 100Gb/s InfiniBand, IBM POWER CPUs, NVIDIA Volta GPUs
http://www-03.ibm.com/press/us/en/pressrelease/45387.wss
28. http://www-03.ibm.com/press/us/en/pressrelease/47056.wss
£313 million collaboration to boost Big Data research in the UK
The research program will leverage OpenPOWER high performance computing innovations to
enable complex analytics on massive amounts of data.
IBM contributions
• Latest data-centric and cognitive computing technologies, including
‘Watson’ cognitive computing platform
• 24 IBM researchers to be based at the Hartree Centre
• Joint commercialization of intellectual property produced in
partnership with STFC
29. Cloud Adoptions
New: SoftLayer Bare Metal POWER cloud
New: Rackspace joins OpenPOWER, declares
Open Compute OpenPOWER system
New: Docker for POWER Systems
Update: OpenStack HEAT and Chef Server for Power
New: Bluemix Cloud Integration and SQLDB Services
with POWER Systems for SOE/SOR integration
Up to 100x
the power of a classic x86 setup
30. • 50 IBM Innovation Centers
• Compelling PoCs
• Support for little endian applications
Over 1,600 Linux ISVs
developing on POWER
Big Data & Machine
Learning
Big Data & Machine
Learning
Cloud Mobile Enterprise
Major Linux Distros
HPC
miniDFT
CTH
BLAST
Bowtie
BWA
FASTA
HMMER
GATK
SOAP3
STAC-A2
SHOC
Graph500
Ilog
CHARMM
GROMACS
NAMD
AMBER
RTM
GAMESS
WRF
HYCOM
HOMME
LES
MiniGhost
AMG2013
OpenFOAM
31. Engage in the OpenPOWER community
ACTIONOUTCOMEINTEREST
Technology and Software
Innovators
Discuss areas of
collaboration and synergy in
OpenPOWER.
Sign up for membership
and join a work group.
Build technical and business
relationships.
Develop
collaborative innovations
with compelling value
Innovators, Integrators,
and Partners
Deep understanding of
workload demands and
consumption preferences of
end users.
Team with innovators and
end users to drive
requirements, engage in
specific projects.
Deliver
collaborative innovations
with compelling value
End Users
Strategic imperatives and
workload demands for
performance and cost
optimization.
Require open software and
systems with choice and
flexibility.
Engage directly on system
design options.
Deploy
collaborative innovations
with compelling value
34. Membership
Level
Annual Fee
$ USD
FTEs Technical Steering Committee Board / Voting position
Platinum $100k 10
One seat per member not otherwise
represented
Includes board position
Includes TSC position
Gold $60k 3
May be on TSC if
Work group lead
Gold members may elect one board
representative per three gold
members
Silver
$20k
$5k if <300
employees
0 May be on TSC if
Work group lead
Sliver members may elect one board
representative for all silver members
Associate &
Academic
$0 0 May be on TSC if
Work group lead
May be elected to one community
observer, non-voting Board seat
The OpenPOWER Foundation is a Not-for-profit entity with a Board of Directors and a Technical
Steering Committee.
• Membership levels provide either a default Board of Director position (Platinum) or an opportunity to be elected
to the Board (Gold, Silver, and Assoc/Academic members). The Bylaws include additional governance detail.
• Technical Steering Committee is formed from Work group Leads and Platinum members.
Membership options include Platinum, Gold, Silver, and Associate / Academic memberships
• Annual fee and dedicated full-time equivalent (FTEs) - verification of FTEs on honor system
• Contributors, committers, Work group leads and project leads influence Technical Steering Committee
• Associate / Academic level is not available to corporations
Membership agreement, Bylaws, and IP Rights Policy available for review
www.openpowerfoundation.org
Anyone may participate in OpenPOWER. Membership levels are designed for those that are
investing to grow and enhance the OpenPOWER community and its proliferation within the industry.
Membership Options
35. OpenPOWER Work Group Roadmap
2014 2015 2016
Developer Platform
System SW
HW Architecture
Accelerator
Compliance
Proposed Work Groups Integrated Solutions
Pers Med
SP010 – Tyan OpenPOWER Customer Reference System
CAPI – Coherent Accelerator Processor Interface
AFU – Accelerator Function Unit
FSI – Field Replaceable Unit (FRU) Service Interface
25g IO Compatibility
Memory
OpenPOWER I/O
9 Work Groups
Charter
Compliance Specification
Draft Review WG Spec
Comp
STD
Charter
OpenPOWER ISA Profile V1
IO Device Architecture V2
Coherent Accel Intf Arch
OpenPOWER ISA Profile V2
IO Device Architecture V3
Coherent Accel Intf Arch
Charter
P8 SP010
Data
P8 2U2S
Reference
P8+ 1U1S
Reference
P8+ 2U2S
Reference
OPMB Intf. Spec V1Charter
Charter
CAPI AFU Intf Spec V1
OpenCL SDK
CAPI AFU Intf Spec V2
Charter
CAPI Linux
SDK
64b ABI
Platform Ref
Sys I/O Enablement GuideCharter
Charter 25g IO Spec
OPMB – OpenPOWER Memory Bus
ABI – Application Binary Interface
FSI Specification FSI SpecCharter
SDK – Software Developer Kit