OREANDA-NEWS. October 12, 2015. IBM (NYSE: IBM) today announced new Linux servers that perform data analytics workloads faster and cheaper than a comparable x86-based server.

The new Power Systems LC servers were designed based on technologies and development efforts contributed by OpenPOWER Foundation partners – including Canonical, Mellanox, NVIDIA, Tyan and Wistron. The OpenPOWER Foundation, an organization with more than 150 members worldwide, builds solutions on top of the open architecture of IBM’s POWER processor. This open and collaborative model allows for rapid innovation not currently available using alternative, closed innovation methods.

The LC servers bring the higher performance of POWER CPUs to the broad Linux community, in particular to data analytics, cloud, and high performance computing (HPC) workloads. For example, based on IBM internal testing, a new Power Systems LC server can complete an average of select Apache Spark workloads – including analyzing Twitter feeds, streaming web page views and other data-intensive analytics – for less than half the cost of an Intel E5-2699 V3 processor-based server, providing clients with 2.3X better performance per dollar spent. Additionally, the efficient design of a Power Systems LC server allows for 94% more Spark social media workloads in the same rack space as a comparable Intel-based server. (1)  (2)

“Clients need cognitive systems that are reliable, cost effective and capable of ingesting and making sense of incredible amounts of structured and unstructured data,” said Doug Balog, General Manager of IBM Power Systems. “Embracing an open model of innovation has enabled us to build systems that help translate mountains of data into actionable business insight. By collaborating with partners from the OpenPOWER Foundation, our new line of servers provides clients with the performance they need to analyze and act on their data in real time.” 

Allegiant Air, a leading low-cost American airline carrier, is among the clients running Linux on Power Systems to analyze data.  The airline is able to immediately analyze customer behavior on its website, looking for trends like price sensitivity in order to adjust quickly and provide on-the-spot promotional marketing offers to help convert a potential customer’s online browse into a purchase. 

 “All enterprises are facing growing amounts of data,” said Brian O’Neil, Director of Data Architecture, Allegiant Travel. “It’s how you analyze---and what you do with--- the results that allows you take the lead. Leveraging Linux on IBM Power Systems, we have been able to immediately glean valuable insights from a number of data sources, enabling us to take action quicker and more efficiently than ever before.”

Three Linux Server Choices as part of Power Systems LC Lineup

Generally available later this year, the Power Systems LC line of servers will be offered in three different variations; the Power Systems S812LC, the Power Systems S822LC for commercial computing and the Power Systems S822LC for high performance computing.

The S812LC is a 1-socket 2U system, equipped with up to 10 cores, 1TB of memory, 115GB/sec memory bandwidth, and up to 14 disk drives. The S812LC is a Linux system optimized for workloads that are memory and storage rich, such as Spark and Hadoop to provide immediate insights with incredible efficiency.

The 2-socket 2U Power Systems S822LC for commercial computing and high performance computing come similarly configured with up to 20 cores, 1TB of memory and 230GB/sec memory bandwidth. The S822LC for high performance computing also comes with two integrated NVIDIA® Tesla® K80 GPU accelerators, the flagship offering of the NVIDIA Tesla Accelerated Computing Platform. The two S822LC variants will offer over 2X performance per core, 40% better price performance and more than 2X memory bandwidth (with fully configured memory) compared to similarly configured x86-based E5-2699 V3 machines. (3)

New Digital experience for ease of use and purchasing servers

Implementing design thinking and agility in all aspects of the development of these new servers, IBM is also providing clients with a new purchasing experience on their mobile devices or on the web. From developers to small businesses to organizations of all sizes, this new digital experience gives access, visibility and transparency of simple pricing to purchase Power Systems. Rapidly evolving, later this year, the digital experience will include a “click to buy” option enabling clients to purchase these systems on the web with a credit card.

These new servers leverage standard Linux deployment tooling for ease and speed of deployment, bringing the benefits of POWER8 to clients without changing their operating model.

The new client experience is complemented by IBM’s global Business Partner network, providing customers with the ability to work with IBM Business Partners to create fully customized solutions. To experience the new Power Systems please visit www.ibm.com/power/announcement/

(1) Results are based on IBM internal testing of the average of 10 SparkBench benchmarks consisting of SQL RDD Relation, Twitter, Pageview Streaming, PageRank, Logistic Regression, SVD++, TriangleCount, SVM, MF, SQL Hive

IBM Power System S812LC 10 cores / 80 threads, POWER8; 2.9GHz, 256 GB memory, Ubuntu 15.04, Spark 1.4, OpenJDK 1.8

Intel Xeon; 24 cores / 48 threads, E5-2690 v3; 2.3GHz , 256 GB memory. Ubuntu 15.04, Spark 1.4, OpenJDK 1.8

Pricing is based on HW list prices of Intel-based server and estimated prices of IBM Power S812LC and both include the OS

(2) Power System S812LC and Intel server are 2U servers.

(3) Results are based on IBM internal testing of single system running multiple virtual machines with pgbench select only work load and are current as of October 5, 2015. Performance figures are based on running a 300 scale factor. Individual results will vary depending on individual workloads, configurations and conditions.

IBM Power System S822LC; 16 cores /  128 threads, POWER8; 3.6GHz, 256 GB memory, PostgreSQL 9.5 Alpha2, RHEL 7.1, PowerKVM

Competitive stack: 36 cores / 72  threads; Intel E5-2699 v3;  2.3 GHz; 256 GB memory, PostgreSQL 9.5 Aplha2, RHEL 7.1, RHEV