IBM Deepens Plunge into Open Source; OpenPOWER to Join Linux Foundation

By John Russell

August 20, 2019

IBM today announced it was contributing the instruction set (ISA) for its Power microprocessor and the designs for the Open Coherent Accelerator Processor Interface (OpenCAPI) and Open Memory Interface (OMI) to the Linux Foundation. It also reported the OpenPOWER Foundation would become a Linux Foundation entity subject to its governance rules. Ken King, IBM general manager for OpenPOWER, made the announcements during his keynote at OpenPOWER Foundation Summit which this year is co-located with the Linux Foundation Open Source Summit in San Diego.

Not bombshell announcements – IBM has been working with open source communities for a long time and its $34B acquisition of Red Hat was a true bombshell – the latest moves are nevertheless significant and reflect IBM’s efforts to leverage open source approaches to establish its Power microprocessor line and the OpenPOWER ecosystem as long-term, viable constituents of the technology landscape.

Ken King, IBM

“We look at these announcements as incremental mechanisms to accelerate and drive more innovation around open hardware, hopefully some of that enabled on the Power platform and enabling even IBM to take some of that innovation [and] incorporate it back into our solutions,” King told HPCwire in a pre-briefing.

IBM has of course enjoyed tremendous success in delivering Summit and Sierra supercomputers, now the #1 and #2 fastest computers in the world. Gaining wider traction for Power-based systems in the server market has, perhaps not unexpectedly, been more difficult. IBM touts that its Power chip line and OpenPOWER architecture are deliberately designed to leverage heterogeneous architectures – “CPUs can no longer handle the rising demands alone, and IBM’s heterogeneous systems are built to maximize the flow of data between CPUs and attached devices for specialized workloads.”

Contributing the Power ISA and OpenCAPI/OMI designs to the Linux Foundation will make it easier for device and systems vendors to optimize products generally and around specific applications. IBM is licensing the Power ISA and OpenCAPI/OMI designs to the OpenPOWER Foundation which in turn will be governed by Linux Foundation rules.

“So there is a compliance requirement,” said King. “We’re trying to avoid fragmentation of the architectures which is not good for the ecosystem. But assuming compliance, anybody can implement any kind of accelerator, or controller or any other kind of hardware device on top of the instruction set, royalty-free with patent rights.” Compliance mostly means maintaining backward compatibility but even that’s not an absolute restriction.

“It won’t be IBM that makes the decision alone on changes and enhancements to the instruction set architecture. It will be done through a compliance work group where IBM only has one vote. IBM will have the rights to make changes or implementations independent of that, but anybody else will be able to incorporate changes or enhancements to it, just by a majority vote of the compliance work group,” said King. “If somebody wants to make changes to the instruction set that are not compliant, then it requires a unanimous vote.”

King’s comments on OpenCAPI/OMI and the emerging CXL effort led by Intel were startling as the two interconnect schemes jockey for sway. “I’ll be transparent about it – one of the objectives is also to try to drive convergence with CXL. When we first did OpenCAPI four or five years ago, the thought process was focused primarily on providing server reference designs enabling others to create their own server implementations on top of the architecture but not actually taking the architecture itself in opening up the rights to it.

“[But] we didn’t see the level of open hardware innovation that’s happening now in the market. We didn’t envision, you know, that a bunch of hyperscalars, and others will be creating custom hardware accelerators. But that is part of the market of evolution. [It’s] part of the need when you know you’re not getting what you need out of the processor alone. We’ve seen some things happening with RISC V that kind of validate that as well, even though RISC V is very nascent. It’s just demonstrating that the industry is ready for open hardware architectures.”

It’s easy to wonder what “convergence” with CXL means in this context. Asked why IBM doesn’t simply join CXL, King advised to keep an eye on this space. Comments by IBMer Jeff Stuecheli at Hot Chips, going on now, discussing details of OpenCAPI 4.0 were seemingly dismissive of CXL. Time will tell.

IBM’s embrace of open source began in earnest in 2013 with formation of the OpenPOWER Foundation, which is led by IBM, Mellanox, Nvidia, and now Red Hat. Since then IBM says it has “contributed thousands of development hours to both contribute and co-create thousands of pages of documentation around the POWER architecture.” Also implied amid the changes is IBM’s recognition that its AIX (Unix) market, though sizeable, is declining versus Linux’s rise and dominance, yet another win for open source.

Overall, said King, “IBM is the only processor vendor in the world that is open end to end from, the ISA to the firmware to the operating system, to the cloud container management all the way up the server stack, [and] the only truly open architecture in the ecosystem. We’re excited about this announcement in following the Red Hat [acquisition which] closed earlier this year, and what we think this will do for the ecosystem from an innovation perspective.”

One representative example is a new serial memory controller from Microchip, an OpenCAPI Consortium member, that was co-developed with IBM using OMI. According to Microchip, the new controller enables CPUs and other compute-centric devices to utilize four times the memory channels within the same device footprint. “Microchip is excited to introduce the industry’s first serial memory controller device to the market,” said Pete Hazen, vice president of the Data Center Solutions business unit at Microchip’s Microsemi subsidiary. “New memory interface technologies such as Open Memory Interface (OMI) enable a broad range of applications to support the increasingly demanding memory requirements of high-performance data center applications.”

IBM rounded up testimonials from several constituencies in support of the new moves. Here’s a sampling: 

  • Hitachi joined the OpenPOWER Foundation because we believe that an open ecosystem enabled with the latest technology will drive client value,” said Nobuhiro Kato, Vice President, IoT & Cloud Services Business Division, Hitachi, Ltd. “Today’s announcement from IBM underscore the open momentum and we look forward to accelerating open innovation to help our clients succeed.”
  • Mellanox and IBM have had deep technological collaborations over the years, culminating in building the world’s fastest supercomputers and leading cloud and enterprise data centers,” said Chuck Tybur, senior vice president of worldwide OEM & channel sales at Mellanox Technologies. “Mellanox is a top open-source software contributor, and believes in open standards and community development efforts. We are proud members of the OpenPOWER and OpenCAPI organizations, and are looking forward to continue our contributions in the future.”
  • “As one of the first public clouds to offer the POWER architecture for High Performance Computing and Deep Learning applications, and the first to support unique CAPI-accelerated workloads, we areexcited to see the next big evolution as these technologies move to open source,” said Steve Hebert, CEO, Nimbix. “The Nimbix JARVICE XE multi-cloud platform and HyperHub marketplace have day one support for both Power and CAPI workloads.”
  • Nvidia’s support of open ecosystems has helped ignite an era of innovation powered by our GPU-accelerated computing platform,” said Marc Hamilton, vice president of Solutions Architecture and Engineering at Nvidia. “IBM’s continued efforts to enable the open community with enterprise-grade hardware designs provides welcome flexibility and choice to Nvidia’s community of more than 1.3 million active developers worldwide.”
  • “As our industry continues to evolve, the open hardware communities will grow as evidenced in IBM’s announcement,” said Zvonimir Bandic, chairman of the OpenCAPI Consortium and chairman of the CHIPS Alliance. “Since its inception in 2016, the OpenCAPI Consortium has been a supporter of this direction while we also continue to investigate how we grow this community and further this strategy through engagement with other open source hardware organizations.”
  • Xilinx believes that an open community spawns more innovation,” said Donna Yasay, vice president of marketing, Data Center Group, Xilinx, Inc. “We believe that IBM’s move to contribute its POWER ISA and key hardware reference designs to the open source community, and now under the guidance of the Linux Foundation, will enable a broader ecosystem with better technology and platforms to solve critical computing challenges today and in the future.”
  • “The slowing down of Moore’s Law provides the open source community with the opportunity to develop innovative hardware that improves performance while reducing development and manufacturing costs,” said Bapi Vinnakota, director of silicon architecture at Netronome and the Open Compute Project’s (OCP) Open Domain Specific Architecture (ODSA) Sub-Project Lead.“IBM’s opening of the POWER ISA, along with open sourcing reference designs, shares the ODSA’s mission of enabling customers to bring open, cost-efficient, low-power accelerator products to market.”
  • Jim Zemlin, executive director of the Linux Foundation, said, “Back in 2013 we were excited to see IBM took the first steps in opening the company’s POWER architecture. The Linux Foundation itself has seen rising interest in open hardware communities and working with OpenPOWER Foundation will continue to make the OpenPOWER and open hardware technologies available to a growing, global audience.”

Many familiar names in the server OEM world have yet to embrace OpenPOWER – e.g. Dell, HPE, Cray, Lenovo – and it will be interesting to monitor how they respond to the latest changes.

Note: Tiffany Trader contributed to the reporting for this article.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Intel’s Optane/DAOS Solution Tops Latest IO500

August 11, 2020

Intel’s persistent memory technology, Optane, and its DAOS (Distributed Asynchronous Object Storage) stack continue to impress and gain market traction. Yesterday, Intel reported an Optane and DAOS-based system finishe Read more…

By John Russell

Summit Now Offers Virtual Tours

August 10, 2020

Summit, the second most powerful publicly ranked supercomputer in the world, now has a virtual tour. The tour, implemented by 3D platform Matterport, allows users to virtually “walk” around the massive supercomputer Read more…

By Oliver Peckham

Supercomputer Simulations Examine Changes in Chesapeake Bay

August 8, 2020

The Chesapeake Bay, the largest estuary in the continental United States, weaves its way south from Maryland, collecting waters from West Virginia, Delaware, DC, Pennsylvania and New York along the way. Like many major e Read more…

By Oliver Peckham

Student Success from ‘Scratch’: CHPC’s Proof is in the Pudding

August 7, 2020

Happy Sithole, who directs the South African Centre for High Performance Computing (SA-CHPC), called the 13th annual CHPC National conference to order on December 1, 2019, at the Birchwood Conference Centre in Kempton Pa Read more…

By Elizabeth Leake

New GE Simulations on Summit to Advance Offshore Wind Power

August 6, 2020

The wind energy sector is a frequent user of high-power simulations, with researchers aiming to optimize wind flows and energy production from the massive turbines. Now, researchers at GE are preparing to undertake a lar Read more…

By Oliver Peckham

AWS Solution Channel

AWS announces the release of AWS ParallelCluster 2.8.0

AWS ParallelCluster is a fully supported and maintained open source cluster management tool that makes it easy for scientists, researchers, and IT administrators to deploy and manage High Performance Computing (HPC) clusters in the AWS cloud. Read more…

Intel® HPC + AI Pavilion

Supercomputing the Pandemic: Scientific Community Tackles COVID-19 from Multiple Perspectives

Since their inception, supercomputers have taken on the biggest, most complex, and most data-intensive computing challenges—from confirming Einstein’s theories about gravitational waves to predicting the impacts of climate change. Read more…

Research: A Survey of Numerical Methods Utilizing Mixed Precision Arithmetic

August 5, 2020

Within the past years, hardware vendors have started designing low precision special function units in response to the demand of the machine learning community and their demand for high compute power in low precision for Read more…

By Hartwig Anzt and Jack Dongarra

Intel’s Optane/DAOS Solution Tops Latest IO500

August 11, 2020

Intel’s persistent memory technology, Optane, and its DAOS (Distributed Asynchronous Object Storage) stack continue to impress and gain market traction. Yeste Read more…

By John Russell

Summit Now Offers Virtual Tours

August 10, 2020

Summit, the second most powerful publicly ranked supercomputer in the world, now has a virtual tour. The tour, implemented by 3D platform Matterport, allows use Read more…

By Oliver Peckham

Research: A Survey of Numerical Methods Utilizing Mixed Precision Arithmetic

August 5, 2020

Within the past years, hardware vendors have started designing low precision special function units in response to the demand of the machine learning community Read more…

By Hartwig Anzt and Jack Dongarra

Implement Photonic Tensor Cores for Machine Learning?

August 5, 2020

Researchers from George Washington University have reported an approach for building photonic tensor cores that leverages phase change photonic memory to implem Read more…

By John Russell

HPE Keeps Cray Brand Promise, Reveals HPE Cray Supercomputing Line

August 4, 2020

The HPC community, ever-affectionate toward Cray and its eponymous founder, can breathe a (virtual) sigh of relief. The Cray brand will live on, encompassing th Read more…

By Tiffany Trader

Machines, Connections, Data, and Especially People: OAC Acting Director Amy Friedlander Charts Office’s Blueprint for Innovation

August 3, 2020

The path to innovation in cyberinfrastructure (CI) will require continued focus on building HPC systems and secure connections between them, in addition to the Read more…

By Ken Chiacchia, Pittsburgh Supercomputing Center/XSEDE

Nvidia Said to Be Close on Arm Deal

August 3, 2020

GPU leader Nvidia Corp. is in talks to buy U.K. chip designer Arm from parent company Softbank, according to several reports over the weekend. If consummated Read more…

By George Leopold

Intel’s 7nm Slip Raises Questions About Ponte Vecchio GPU, Aurora Supercomputer

July 30, 2020

During its second-quarter earnings call, Intel announced a one-year delay of its 7nm process technology, which it says it will create an approximate six-month shift for its CPU product timing relative to prior expectations. The primary issue is a defect mode in the 7nm process that resulted in yield degradation... Read more…

By Tiffany Trader

Supercomputer Modeling Tests How COVID-19 Spreads in Grocery Stores

April 8, 2020

In the COVID-19 era, many people are treating simple activities like getting gas or groceries with caution as they try to heed social distancing mandates and protect their own health. Still, significant uncertainty surrounds the relative risk of different activities, and conflicting information is prevalent. A team of Finnish researchers set out to address some of these uncertainties by... Read more…

By Oliver Peckham

Supercomputer-Powered Research Uncovers Signs of ‘Bradykinin Storm’ That May Explain COVID-19 Symptoms

July 28, 2020

Doctors and medical researchers have struggled to pinpoint – let alone explain – the deluge of symptoms induced by COVID-19 infections in patients, and what Read more…

By Oliver Peckham

Intel’s 7nm Slip Raises Questions About Ponte Vecchio GPU, Aurora Supercomputer

July 30, 2020

During its second-quarter earnings call, Intel announced a one-year delay of its 7nm process technology, which it says it will create an approximate six-month shift for its CPU product timing relative to prior expectations. The primary issue is a defect mode in the 7nm process that resulted in yield degradation... Read more…

By Tiffany Trader

Nvidia Said to Be Close on Arm Deal

August 3, 2020

GPU leader Nvidia Corp. is in talks to buy U.K. chip designer Arm from parent company Softbank, according to several reports over the weekend. If consummated Read more…

By George Leopold

Supercomputer Simulations Reveal the Fate of the Neanderthals

May 25, 2020

For hundreds of thousands of years, neanderthals roamed the planet, eventually (almost 50,000 years ago) giving way to homo sapiens, which quickly became the do Read more…

By Oliver Peckham

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

By Doug Black

Neocortex Will Be First-of-Its-Kind 800,000-Core AI Supercomputer

June 9, 2020

Pittsburgh Supercomputing Center (PSC - a joint research organization of Carnegie Mellon University and the University of Pittsburgh) has won a $5 million award Read more…

By Tiffany Trader

HPE Keeps Cray Brand Promise, Reveals HPE Cray Supercomputing Line

August 4, 2020

The HPC community, ever-affectionate toward Cray and its eponymous founder, can breathe a (virtual) sigh of relief. The Cray brand will live on, encompassing th Read more…

By Tiffany Trader

Leading Solution Providers

Contributors

Nvidia’s Ampere A100 GPU: Up to 2.5X the HPC, 20X the AI

May 14, 2020

Nvidia's first Ampere-based graphics card, the A100 GPU, packs a whopping 54 billion transistors on 826mm2 of silicon, making it the world's largest seven-nanom Read more…

By Tiffany Trader

Australian Researchers Break All-Time Internet Speed Record

May 26, 2020

If you’ve been stuck at home for the last few months, you’ve probably become more attuned to the quality (or lack thereof) of your internet connection. Even Read more…

By Oliver Peckham

15 Slides on Programming Aurora and Exascale Systems

May 7, 2020

Sometime in 2021, Aurora, the first planned U.S. exascale system, is scheduled to be fired up at Argonne National Laboratory. Cray (now HPE) and Intel are the k Read more…

By John Russell

‘Billion Molecules Against COVID-19’ Challenge to Launch with Massive Supercomputing Support

April 22, 2020

Around the world, supercomputing centers have spun up and opened their doors for COVID-19 research in what may be the most unified supercomputing effort in hist Read more…

By Oliver Peckham

Joliot-Curie Supercomputer Used to Build First Full, High-Fidelity Aircraft Engine Simulation

July 14, 2020

When industrial designers plan the design of a new element of a vehicle’s propulsion or exterior, they typically use fluid dynamics to optimize airflow and in Read more…

By Oliver Peckham

John Martinis Reportedly Leaves Google Quantum Effort

April 21, 2020

John Martinis, who led Google’s quantum computing effort since establishing its quantum hardware group in 2014, has left Google after being moved into an advi Read more…

By John Russell

$100B Plan Submitted for Massive Remake and Expansion of NSF

May 27, 2020

Legislation to reshape, expand - and rename - the National Science Foundation has been submitted in both the U.S. House and Senate. The proposal, which seems to Read more…

By John Russell

Google Cloud Debuts 16-GPU Ampere A100 Instances

July 7, 2020

On the heels of the Nvidia’s Ampere A100 GPU launch in May, Google Cloud is announcing alpha availability of the A100 “Accelerator Optimized” VM A2 instance family on Google Compute Engine. The instances are powered by the HGX A100 16-GPU platform, which combines two HGX A100 8-GPU baseboards using... Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This