Think Fast: IBM Talks Acceleration in HPC and the Enterprise

By John Russell

November 16, 2015

At SC15 today, IBM provided a glimpse of its broadening vision for accelerator-assisted computing with announcements around Watson, a strategic alliance with FPGA specialist Xilinx, an expanded developer outreach via the SuperVessel program, and new efforts to accelerate the datacenter and a wide variety of applications used in both HPC and the enterprise.

“Accelerators have come to play a dominant role in HPC and we believe the notion of an accelerated datacenter is beginning to creep into the enterprise and will become a dominant factor,” Sumit Gupta, vice president, HPC and OpenPOWER operations at IBM told HPCwire. The IBM vision encompasses roles for both GPU- and FPGA- accelerated systems integrated with OpenPOWER architecture and taking advantage of CAPI interface. Gupta outlined what he called an ambitious three-pronged effort to accelerate computing, storage and networking.

GPUs, of course, have proven very powerful in HPC. More than 100 of the TOP500 machines from the list announced this morning rely on GPU acceleration, accounting for a total 143 petaflops – more than one-third of the list’s total FLOPS. NVIDIA Tesla GPU-based supercomputers comprise 70 of these systems – including 23 of the 24 new systems on the list.

Accelerators.TOP500.SC15As shown here the mix of accelerators powering the TOP500 is growing (source: Top500). With Moore’s Law topping out, IBM is betting accelerators, both GPUs and FPGAs, will become pivotal to improving performance not only for traditional HPC applications, but also for big data and data analytics challenges.

As part of the barrage of accelerator news, IBM noted for the first time that Watson, IBM’s “cognitive computing” platform, has been accelerated with NVIDIA Tesla K80 GPUs coupled to Watson’s POWER-based architecture. According to IBM, Watson’s retrieve and rank API capability is now 1.7x of its normal speed and Watson’s processing power up to 10x its prior performance according.

Other important bullet points include:

  • Newest OpenPOWER Platinum member Xilinx and IBM have a multi-year strategic collaboration to develop and market a series of data center and network function virtualization (NFV) solutions with systems, software, and management components around Xilinx FPGA accelerators. Solutions will focus on emerging workloads including high performance computing, cognitive computing, machine learning, genomics and big data analytics.
  • IBM reiterated Mellanox support of CAPI with its earlier release of the world’s first smart network switch, the Switch-IB 2, capable of delivering clients 10x system performance improvement. NEC announced availability of its ExpEther Technology that is also suited for POWER architecture-based systems, along with plans to leverage IBM’s CAPI technology in 2016.
  • OpenPOWER members, E4 Computer Engineering and Penguin Computing, announced new systems based on the OpenPOWER architecture and incorporating POWER8 and NVIDIA Tesla GPU accelerators.
  • IBM has ported a series of key IBM Internet of Things, Spark, Big Data and Cognitive Era applications to take advantage of the POWER architecture with accelerators.

As part of the IBM and Xilinx strategic collaboration, IBM Systems Group developers will create solution stacks for POWER-based servers, storage and middleware systems with Xilinx FPGA accelerators for data center architectures such as OpenStack, Docker, and Spark. IBM will also develop and qualify Xilinx accelerator boards into IBM Power Systems servers. Xilinx is developing and will release POWER-based versions of its leading software defined SDAccel Development Environment and libraries for the OpenPOWER developer community.

IBM suggests that as heterogeneous workloads have become increasingly prevalent, data centers are turning to application accelerators to keep up with the demands for throughput and latency at low power. Xilinx FPGAs, reports IBM, can deliver the power efficiency that makes accelerators practical to deploy throughout the data center.

SumitGupta_120x168Gupta couldn’t resist taking a swipe at Intel. “The difference between our platform and the x86 platform is that we actually partner with Xilinx and NVIDIA to build tightly integrated interfaces like CAPI and NVlink and put our investments together to come to market with an open collaborative solutions. This is in stark contrast to [the] competing solution which is completely closed, proprietary, and all designed from one vendor.”

The war of words aside, it will be interesting to watch the competing approaches play out. IBM and the OpenPOWER favor a multiple discrete component approach that is optimized and tightly glued together through collaborative design. Intel is betting that bringing these functions together under one roof, and mostly in silicon, will end up delivering higher performance. No doubt both have advantages. Stay tuned.

Commenting on the expanding role of FPGAs and GPUs, Gupta said IBM sees the two technologies as complementary. Some workloads such as deep learning and model training are currently best suited for GPUs, he said. Conversely, once the model is set and objects identified, FPGAs can handle those workloads well.

He added IBM is seeing more use of FPGAs in a variety of workloads – genomics is one – and network processing is another. The latter permits use of a standard server with FPGA-based specialization rather than the use of distinct dedicated boxes for differing network applications such as security or packet processing. Network virtualization will significantly benefit from FPGAs, he said.

Currently, IBM is working on accelerating a wide range of applications. “We have an accelerated storage solution [in which] we connect our flash using CAPI to the POWER system [which] is very useful to accelerate NoSQL database applications, which are basically analytics,” Gupta said. He pointed to Apache Spark and NoSQL databases Redis and Neo4j as examples of application acceleration being undertaken by IBM.

Obviously, getting OpenPOWER systems with accelerators into the hands of developers is a necessary part of IBM’s strategy. To that end, IBM reported expanding GPU services on SuperVessel, the global cloud-based OpenPOWER ecosystem resource launched in June and initially based only in China. SuperVessel now provides GPU-accelerated computing as-a-service capabilities, giving users access to high-performance NVIDIA Tesla GPUs to enable Caffe, Torch and Theano deep-learning frameworks to instantaneously launch from the SuperVessel cloud.

“We are also announcing a new SuperVessel system that will serve North America and Europe. This will dramatically increase developer access,” said Gupta. As part of the expansion, Xilinx and IBM have developed a new FPGA accelerator service on SuperVessel that makes coherent reconfigurable accelerators available to developers via the cloud. By enabling high-level language programming like C, C++ and OpenCL, Xilinx and IBM are attempting to dramatically expand how users leverage FPGAs in the cloud for innovation on applications like machine learning, big data analytics and HPC.

IBM is also adding developer resources at the University of Texas and Oregon State University aimed at the academic research community, “but which anyone can apply for” said Gupta. He noted IBM has already developed proof-point case studies such as one based on work at Baylor College, which used accelerators and a Power system for genomics applications.

  • The Baylor team, led by geneticist and computer scientist Erez Lieberman Aiden, developed a new procedure to modify how a human genome is arranged in three dimensions in the nucleus of a cell. The work was done using a Power System accelerated with NVIDIA Tesla GPUs and Mellanox network infrastructure “to build a 3-D map of the human genome and model the reaction of the genome to this surgical procedure, without disturbing the surrounding DNA.”
  • At OSU, the Open Source Lab (OSUOSL) has increased the footprint of POWER8-based systems in their existing OpenStack cluster with additional compute and memory capacity. The expansion significantly increases the number of distinct users OSUOSL can support for research and development on OpenPOWER/OpenStack infrastructures.

IBM logoIBM offered another bit of evidence for OpenPOWER Foundation’s gathering momentum: new member Texas Advanced Computing Center (TACC) at University of Texas at Austin, and IBM announced a POWER8 accelerated computing cluster to be made available to academic researchers and developers. The new cluster is currently running successfully in an early user mode, and will begin accepting requests for access this week.

On balance, today’s IBM news was all about the rise of accelerator-assisted computing and IBM’s embrace of it, including its steady march into the enterprise.

“There is a need for systems that provide greater speed to insight — for data and analytics workloads to help businesses and organization make sense of the data, to outthink competitors as we usher in a new era of Cognitive Computing,” said Brad McCredie, IBM Fellow and OpenPOWER Foundation President. “IBM and our more than 160 partners in the OpenPOWER Foundation are on the forefront driving the changes necessary for innovation at all levels of the technology stack, including the development the industry’s first open, high-speed interconnects between processors and accelerators.”

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!

Help Wanted: QED-C Survey Spotlights Skills Sought by Quantum Industry

September 28, 2021

Developing an adequate workforce for the young but fast-growing quantum information sciences industry is seen as a critical element for success. Just what that means in terms of skillsets and positions is becoming cleare Read more…

Pittsburgh Supercomputer Powers Machine Learning Analysis of Rare East Asian Stamps

September 27, 2021

Setting aside the relatively recent rise of electronic signatures, personalized stamps have been a popular form of identification for formal documents in East Asia. These identifiers – easily forged, but culturally ubi Read more…

Purdue Researchers Peer into the ‘Fog of the Machine Learning Accelerator War’

September 27, 2021

Making sense of ML performance and benchmark data is an ongoing challenge. In light of last week’s release of the most recent MLPerf (v1.1) inference results, now is perhaps a good time to review how valuable (or not) Read more…

Quantum Monte Carlo at Exascale Could Be Key to Finding New Semiconductor Materials

September 27, 2021

Researchers are urgently trying to identify possible materials to replace silicon-based semiconductors. The processing power in modern computers continues to increase even as the size of the silicon on which components a Read more…

The Case for an Edge-Driven Future for Supercomputing

September 24, 2021

“Exascale only becomes valuable when it’s creating and using data that we care about,” said Pete Beckman, co-director of the Northwestern-Argonne Institute of Science and Engineering (NAISE), at the most recent HPC Read more…

AWS Solution Channel

Introducing AWS ParallelCluster 3

Running HPC workloads, like computational fluid dynamics (CFD), molecular dynamics, or weather forecasting typically involves a lot of moving parts. You need a hundreds or thousands of compute cores, a job scheduler for keeping them fed, a shared file system that’s tuned for throughput or IOPS (or both), loads of libraries, a fast network, and a head node to make sense of all this. Read more…

Three Universities Team for NSF-Funded ‘ACES’ Reconfigurable Supercomputer Prototype

September 23, 2021

As Moore’s law slows, HPC developers are increasingly looking for speed gains in specialized code and specialized hardware – but this specialization, in turn, can make testing and deploying code trickier than ever. Now, researchers from Texas A&M University, the University of Illinois at Urbana... Read more…

Purdue Researchers Peer into the ‘Fog of the Machine Learning Accelerator War’

September 27, 2021

Making sense of ML performance and benchmark data is an ongoing challenge. In light of last week’s release of the most recent MLPerf (v1.1) inference results, Read more…

Quantum Monte Carlo at Exascale Could Be Key to Finding New Semiconductor Materials

September 27, 2021

Researchers are urgently trying to identify possible materials to replace silicon-based semiconductors. The processing power in modern computers continues to in Read more…

The Case for an Edge-Driven Future for Supercomputing

September 24, 2021

“Exascale only becomes valuable when it’s creating and using data that we care about,” said Pete Beckman, co-director of the Northwestern-Argonne Institut Read more…

Three Universities Team for NSF-Funded ‘ACES’ Reconfigurable Supercomputer Prototype

September 23, 2021

As Moore’s law slows, HPC developers are increasingly looking for speed gains in specialized code and specialized hardware – but this specialization, in turn, can make testing and deploying code trickier than ever. Now, researchers from Texas A&M University, the University of Illinois at Urbana... Read more…

Qubit Stream: Monte Carlo Advance, Infosys Joins the Fray, D-Wave Meeting Plans, and More

September 23, 2021

It seems the stream of quantum computing reports never ceases. This week – IonQ and Goldman Sachs tackle Monte Carlo on quantum hardware, Cambridge Quantum pu Read more…

Asetek Announces It Is Exiting HPC to Protect Future Profitability

September 22, 2021

Liquid cooling specialist Asetek, well-known in HPC circles for its direct-to-chip cooling technology that is inside some of the fastest supercomputers in the world, announced today that it is exiting the HPC space amid multiple supply chain issues related to the pandemic. Although pandemic supply chain... Read more…

TACC Supercomputer Delves Into Protein Interactions

September 22, 2021

Adenosine triphosphate (ATP) is a compound used to funnel energy from mitochondria to other parts of the cell, enabling energy-driven functions like muscle contractions. For ATP to flow, though, the interaction between the hexokinase-II (HKII) enzyme and the proteins found in a specific channel on the mitochondria’s outer membrane. Now, simulations conducted on supercomputers at the Texas Advanced Computing Center (TACC) have simulated... 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…

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 called Dojo to process truly vast amounts of video data. It’s a beast! … A truly useful exaflop at de facto FP32.” 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. “We’ve been scaling our neural network training compute dramatically over the last few years,” said Milan Kovac, Tesla’s director of autopilot engineering. 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…

CentOS Replacement Rocky Linux Is Now in GA and Under Independent Control

June 21, 2021

The Rocky Enterprise Software Foundation (RESF) is announcing the general availability of Rocky Linux, release 8.4, designed as a drop-in replacement for the soon-to-be discontinued CentOS. The GA release is launching six-and-a-half months after Red Hat deprecated its support for the widely popular, free CentOS server operating system. The Rocky Linux development effort... 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…

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…

AMD-Xilinx Deal Gains UK, EU Approvals — China’s Decision Still Pending

July 1, 2021

AMD’s planned acquisition of FPGA maker Xilinx is now in the hands of Chinese regulators after needed antitrust approvals for the $35 billion deal were receiv Read more…

Google Launches TPU v4 AI Chips

May 20, 2021

Google CEO Sundar Pichai spoke for only one minute and 42 seconds about the company’s latest TPU v4 Tensor Processing Units during his keynote at the Google I Read more…

Leading Solution Providers

Contributors

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…

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…

Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…

Quantum Roundup: IBM, Rigetti, Phasecraft, Oxford QC, China, and More

July 13, 2021

IBM yesterday announced a proof for a quantum ML algorithm. A week ago, it unveiled a new topology for its quantum processors. Last Friday, the Technical Univer Read more…

Frontier to Meet 20MW Exascale Power Target Set by DARPA in 2008

July 14, 2021

After more than a decade of planning, the United States’ first exascale computer, Frontier, is set to arrive at Oak Ridge National Laboratory (ORNL) later this year. Crossing this “1,000x” horizon required overcoming four major challenges: power demand, reliability, extreme parallelism and data movement. Read more…

Intel Launches 10nm ‘Ice Lake’ Datacenter CPU with Up to 40 Cores

April 6, 2021

The wait is over. Today Intel officially launched its 10nm datacenter CPU, the third-generation Intel Xeon Scalable processor, codenamed Ice Lake. With up to 40 Read more…

Intel Unveils New Node Names; Sapphire Rapids Is Now an ‘Intel 7’ CPU

July 27, 2021

What's a preeminent chip company to do when its process node technology lags the competition by (roughly) one generation, but outmoded naming conventions make it seem like it's two nodes behind? For Intel, the response was to change how it refers to its nodes with the aim of better reflecting its positioning within the leadership semiconductor manufacturing space. Intel revealed its new node nomenclature, and... 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…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire