IBM released today a series of new servers but the interesting news is that one of them is the first systems (except the DGX-1 developed by NVIDIA) using NVLink to connect CPUs to GPUs. The IBM Power Systems S822LC, that is its name, can receive Pascal GP100 GPUs in SMX2 form factor while offering an incredible bandwidth between GPUs. It couples two New Power8 with NVlink CPUs with four NVIDIA Tesla P100 GPU accelerators with one main objective: keep the massively parallel GPUs fed with data. According to Big Blue, the results in performance are over 2.5 times than the traditional Intel x86 servers using PCIe Gen3.

To bring those innovations to the market, IBM has collaborated with fellow industry leaders through the OpenPOWER Foundation to re-design the platform at the chip and system levels and by incorporating the use of a wide range of accelerators to achieve greater levels of performance than available on traditional commodity servers.

Accelerating Deep Learning Applications
The results in Deep learning applications are stunning as the Power Systems S822LC reduces time to training and opens new opportunities in optimization and performance. “The user insights and the business value you can deliver with advanced analytics, machine learning and artificial intelligence is increasingly gated by performance.  Accelerated computing that can really drive big data workloads will become foundational in the cognitive era,” said Doug Balog, General Manager of POWER, IBM Systems. “Based on OpenPOWER innovations from partners such as NVIDIA, our new OpenPOWER Linux servers with POWERAccel set a new standard for these workloads compared with x86 processor-based servers.”

“The open and collaborative model of the OpenPOWER Foundation has propelled system innovation forward in a major way with the launch of the IBM Power System S822LC for High Performance Computing,” said Ian Buck, VP of Accelerated Computing at NVIDIA. “NVIDIA NVLink provides tight integration between the POWER CPU and NVIDIA Pascal GPUs and improved GPU-to-GPU link bandwidth to accelerate time to insight for many of today’s most critical applications like advanced analytics, deep learning and AI.”

Three new systems available
The three new systems are an expansion of IBM’s Linux server portfolio comprised of IBM’s specialized line of servers co-developed with fellow members of theOpenPOWER Foundation.  The new servers join the Power Systems LC lineup that is designed to outperform x86-based servers on a variety of data-intensive workloads.

Pricing, Specifications and Availability
The new Power LC lineup is announced by IBM to cost 30% less over comparatively configured Intel x86-based servers.  Online pricing begins at $5999. Additional models with smaller configurations and lower pricing are available through IBM Business Partners. General availability is immediate for all variations of the lineup with the exception of the IBM Power System S822LC for High Performance Computing, due to ship September 26.