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!

Raja Koduri and Satoshi Matsuoka Discuss the Future of HPC at SC21

November 29, 2021

HPCwire's Managing Editor sits down with Intel's Raja Koduri and Riken's Satoshi Matsuoka in St. Louis for an off-the-cuff conversation about their SC21 experience, what comes after exascale and why they are collaboratin Read more…

Jack Dongarra on SC21, the Top500 and His Retirement Plans

November 29, 2021

HPCwire's Managing Editor sits down with Jack Dongarra, Top500 co-founder and Distinguished Professor at the University of Tennessee, during SC21 in St. Louis to discuss the 2021 Top500 list, the outlook for global exascale computing, and what exactly is going on in that Viking helmet photo. Read more…

SC21: Larry Smarr on The Rise of Supernetwork Data Intensive Computing

November 26, 2021

Larry Smarr, founding director of Calit2 (now Distinguished Professor Emeritus at the University of California San Diego) and the first director of NCSA, is one of the seminal figures in the U.S. supercomputing community. What began as a personal drive, shared by others, to spur the creation of supercomputers in the U.S. for scientific use, later expanded into a... Read more…

Three Chinese Exascale Systems Detailed at SC21: Two Operational and One Delayed

November 24, 2021

Details about two previously rumored Chinese exascale systems came to light during last week’s SC21 proceedings. Asked about these systems during the Top500 media briefing on Monday, Nov. 15, list author and co-founder Jack Dongarra indicated he was aware of some very impressive results, but withheld comment when asked directly if he had... Read more…

SC21’s Student Cluster Competition Winners Announced

November 19, 2021

SC21 may have been the first major supercomputing conference to return to in-person activities, but not everything returned to the live menu: the Student Cluster Competition – held virtually at ISC 2020, SC20 and ISC 2021 – was again held virtually at SC21. Nevertheless, Students@SC Chair Jay Lofstead took the physical stage at SC21 on Thursday to announce the... Read more…

AWS Solution Channel

Royalty-free stock illustration ID: 1616974732

Using the Slurm REST API to integrate with distributed architectures on AWS

The Slurm Workload Manager by SchedMD is a popular HPC scheduler and is supported by AWS ParallelCluster, an elastic HPC cluster management service offered by AWS. Read more…

MLPerf Issues HPC 1.0 Benchmark Results Featuring Impressive Systems (Think Fugaku)

November 19, 2021

Earlier this week MLCommons issued results from its latest MLPerf HPC training benchmarking exercise. Unlike other MLPerf benchmarks, which mostly measure the training and inference performance of systems that are availa Read more…

Raja Koduri and Satoshi Matsuoka Discuss the Future of HPC at SC21

November 29, 2021

HPCwire's Managing Editor sits down with Intel's Raja Koduri and Riken's Satoshi Matsuoka in St. Louis for an off-the-cuff conversation about their SC21 experie Read more…

Jack Dongarra on SC21, the Top500 and His Retirement Plans

November 29, 2021

HPCwire's Managing Editor sits down with Jack Dongarra, Top500 co-founder and Distinguished Professor at the University of Tennessee, during SC21 in St. Louis to discuss the 2021 Top500 list, the outlook for global exascale computing, and what exactly is going on in that Viking helmet photo. Read more…

SC21: Larry Smarr on The Rise of Supernetwork Data Intensive Computing

November 26, 2021

Larry Smarr, founding director of Calit2 (now Distinguished Professor Emeritus at the University of California San Diego) and the first director of NCSA, is one of the seminal figures in the U.S. supercomputing community. What began as a personal drive, shared by others, to spur the creation of supercomputers in the U.S. for scientific use, later expanded into a... Read more…

Three Chinese Exascale Systems Detailed at SC21: Two Operational and One Delayed

November 24, 2021

Details about two previously rumored Chinese exascale systems came to light during last week’s SC21 proceedings. Asked about these systems during the Top500 media briefing on Monday, Nov. 15, list author and co-founder Jack Dongarra indicated he was aware of some very impressive results, but withheld comment when asked directly if he had... Read more…

SC21’s Student Cluster Competition Winners Announced

November 19, 2021

SC21 may have been the first major supercomputing conference to return to in-person activities, but not everything returned to the live menu: the Student Cluster Competition – held virtually at ISC 2020, SC20 and ISC 2021 – was again held virtually at SC21. Nevertheless, Students@SC Chair Jay Lofstead took the physical stage at SC21 on Thursday to announce the... Read more…

MLPerf Issues HPC 1.0 Benchmark Results Featuring Impressive Systems (Think Fugaku)

November 19, 2021

Earlier this week MLCommons issued results from its latest MLPerf HPC training benchmarking exercise. Unlike other MLPerf benchmarks, which mostly measure the t Read more…

Gordon Bell Special Prize Goes to World-Shaping COVID Droplet Work

November 18, 2021

For the second (and, hopefully, final) year in a row, SC21 included a second major research award alongside the ACM 2021 Gordon Bell Prize: the Gordon Bell Special Prize for High Performance Computing-Based COVID-19 Research. Last year, the first iteration of this award went to simulations of the SARS-CoV-2 spike protein; this year, the prize went... Read more…

2021 Gordon Bell Prize Goes to Exascale-Powered Quantum Supremacy Challenge

November 18, 2021

Today at the hybrid virtual/in-person SC21 conference, the organizers announced the winners of the 2021 ACM Gordon Bell Prize: a team of Chinese researchers leveraging the new exascale Sunway system to simulate quantum circuits. The Gordon Bell Prize, which comes with an award of $10,000 courtesy of HPC pioneer Gordon Bell, is awarded annually... Read more…

IonQ Is First Quantum Startup to Go Public; Will It be First to Deliver Profits?

November 3, 2021

On October 1 of this year, IonQ became the first pure-play quantum computing start-up to go public. At this writing, the stock (NYSE: IONQ) was around $15 and its market capitalization was roughly $2.89 billion. Co-founder and chief scientist Chris Monroe says it was fun to have a few of the company’s roughly 100 employees travel to New York to ring the opening bell of the New York Stock... Read more…

Enter Dojo: Tesla Reveals Design for Modular Supercomputer & D1 Chip

August 20, 2021

Two months ago, Tesla revealed a massive GPU cluster that it said was “roughly the number five supercomputer in the world,” and which was just a precursor to Tesla’s real supercomputing moonshot: the long-rumored, little-detailed Dojo system. Read more…

Esperanto, Silicon in Hand, Champions the Efficiency of Its 1,092-Core RISC-V Chip

August 27, 2021

Esperanto Technologies made waves last December when it announced ET-SoC-1, a new RISC-V-based chip aimed at machine learning that packed nearly 1,100 cores onto a package small enough to fit six times over on a single PCIe card. Now, Esperanto is back, silicon in-hand and taking aim... Read more…

US Closes in on Exascale: Frontier Installation Is Underway

September 29, 2021

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, held by Zoom this week (Sept. 29-30), it was revealed that the Frontier supercomputer is currently being installed at Oak Ridge National Laboratory in Oak Ridge, Tenn. The staff at the Oak Ridge Leadership... Read more…

AMD Launches Milan-X CPU with 3D V-Cache and Multichip Instinct MI200 GPU

November 8, 2021

At a virtual event this morning, AMD CEO Lisa Su unveiled the company’s latest and much-anticipated server products: the new Milan-X CPU, which leverages AMD’s new 3D V-Cache technology; and its new Instinct MI200 GPU, which provides up to 220 compute units across two Infinity Fabric-connected dies, delivering an astounding 47.9 peak double-precision teraflops. “We're in a high-performance computing megacycle, driven by the growing need to deploy additional compute performance... Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Intel Completes LLVM Adoption; Will End Updates to Classic C/C++ Compilers in Future

August 10, 2021

Intel reported in a blog this week that its adoption of the open source LLVM architecture for Intel’s C/C++ compiler is complete. The transition is part of In Read more…

Killer Instinct: AMD’s Multi-Chip MI200 GPU Readies for a Major Global Debut

October 21, 2021

AMD’s next-generation supercomputer GPU is on its way – and by all appearances, it’s about to make a name for itself. The AMD Radeon Instinct MI200 GPU (a successor to the MI100) will, over the next year, begin to power three massive systems on three continents: the United States’ exascale Frontier system; the European Union’s pre-exascale LUMI system; and Australia’s petascale Setonix system. Read more…

Leading Solution Providers

Contributors

Hot Chips: Here Come the DPUs and IPUs from Arm, Nvidia and Intel

August 25, 2021

The emergence of data processing units (DPU) and infrastructure processing units (IPU) as potentially important pieces in cloud and datacenter architectures was Read more…

D-Wave Embraces Gate-Based Quantum Computing; Charts Path Forward

October 21, 2021

Earlier this month D-Wave Systems, the quantum computing pioneer that has long championed quantum annealing-based quantum computing (and sometimes taken heat fo Read more…

Ahead of ‘Dojo,’ Tesla Reveals Its Massive Precursor Supercomputer

June 22, 2021

In spring 2019, Tesla made cryptic reference to a project called Dojo, a “super-powerful training computer” for video data processing. Then, in summer 2020, Tesla CEO Elon Musk tweeted: “Tesla is developing a [neural network] training computer... Read more…

HPE Wins $2B GreenLake HPC-as-a-Service Deal with NSA

September 1, 2021

In the heated, oft-contentious, government IT space, HPE has won a massive $2 billion contract to provide HPC and AI services to the United States’ National Security Agency (NSA). Following on the heels of the now-canceled $10 billion JEDI contract (reissued as JWCC) and a $10 billion... Read more…

The Latest MLPerf Inference Results: Nvidia GPUs Hold Sway but Here Come CPUs and Intel

September 22, 2021

The latest round of MLPerf inference benchmark (v 1.1) results was released today and Nvidia again dominated, sweeping the top spots in the closed (apples-to-ap Read more…

Quantum Computer Market Headed to $830M in 2024

September 13, 2021

What is one to make of the quantum computing market? Energized (lots of funding) but still chaotic and advancing in unpredictable ways (e.g. competing qubit tec Read more…

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…

2021 Gordon Bell Prize Goes to Exascale-Powered Quantum Supremacy Challenge

November 18, 2021

Today at the hybrid virtual/in-person SC21 conference, the organizers announced the winners of the 2021 ACM Gordon Bell Prize: a team of Chinese researchers leveraging the new exascale Sunway system to simulate quantum circuits. The Gordon Bell Prize, which comes with an award of $10,000 courtesy of HPC pioneer Gordon Bell, is awarded annually... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire