IBM Launches Power8 Linux Servers For Deep Learning

IBM recently launched three Power8 Linux Servers, which have been designed so as to accelerate artificial intelligence, deep learning, and advanced analytics Applications.

IBM recently launched three Power8 Linux servers, which have been designed so as to accelerate artificial intelligence, deep learning, and advanced analytics Applications.
Stefanie Chiras, IBM Vice President inform The Verge that the new system comes with the Nvidia NVLink technology, so as to move the data five times faster than any completing platform.
IBM has gone on to claim that the combination of Power8 processors and Linux software results in systems which deliver 80 percent more performance compared to the latest x86-based (Intel or AMD) Servers. The systems leverage the innovations from the OpenPower community, so as to deliver better computing efficiency.
Chiras states,
“We are very focused in competing head-to-head in the Linux market. The workloads in this space are changing at a very fast rate.”
Collaboratively developed with an array of tech companies, the latest Power Systems target A.I., deep learning, high performance data analytics, along with other compute-heavy workloads, which help the business alongside Cloud Services provided, which goes on to save money on the data center costs.
The previous testing by China’s Tencent, which is among the world’s largest internet service provider, has shown that the largest cluster of the latest IBM OpenPower Servers were able to run a data-intensive work load thrice as faster in comparison to the former x86-based infrastructure. This was even possible when the number of Servers had been reduced by two-thirds. Tencent is currently integrating the latest Servers into its hyperscale data center for the largest adat Workloads, which will go on to help it in keeping the lid on the data center sprawl.
Chiras states,
“Linux has taught us a lot about collaborative development. And Power is still an alternative to the x86 architecture in the market.”
With the advent of GPGPU computing or using graphics chips for the non-graphics tasks, Nvidia’s technology is breaking into a lot of data centers. Even though a group of interconnected innovations, collectively referred as PowerAccel, contributes towards the OpenPower ecosystem, it will continue to develop the system as well as other solutions on Power platform, which goes on to optimize for the accelerated Applications.
One of the results for this collaboration is IBM Power System S822LC Server for high-performance computing. The NVLink technology connects directly to the new IBM Power8 processor (a 4.5-billion transistor chip) with Nvidia’s Tesla P100 Pascal GPU (a 15-billion transistor chip).
Ian Buck, Vice President of Accelerated Computing at Nvidia, in a statement, states,
“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.”
The two additional LC Servers now available — IBM Power System S821LC and the IBM Power System S822LC for Big Data — can also go on to leverage GPU acceleration technology, so as to increase the system performance levels on a range of accelerated Applications. Clients can now easily go on to attach Nvidia Telsa K80 GPU accelerators by PCIe. Online prices start at $6,000. The S822LC ships on September 26 and the other two models are now available.
IBM introduced its first Power8 chips in the second quarter of 2014 and with time, it has continued to add more versions. The company has also gone on to launch OpenPower Foundation in 2014, which now has around 250 members. Powedr9 chips are expected to be launched in the second half of 2017.