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.

As 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.

Gupta 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 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.”