22 September 2016

IBM Power Systems for Big Data and Analytics

IBM Linux Servers Designed to Accelerate Artificial Intelligence, Deep Learning and Advanced Analytics

New IBM POWER8 Chip with NVIDIA NVLink(TM) Enables Data Movement 5x Faster than Any Competing Platform
Systems Deliver Average of 80% More Performance Per Dollar than Latest x86-Based Servers(1)
Expanded Linux Server Lineup Leverages OpenPOWER Innovations

A quick introduction to the IBM Power System S822LC from the IBM Client Center Montpellier

A major achievement stemming from open collaboration is the new IBM Power System S822LC for High Performance Computing server.

IBM Linux on Power Big Data Solutions

IBM Data Engine for Hadoop and Spark – Power Systems Edition

With more and more intelligent and interconnected devices and systems, the data companies are collecting is growing at unprecedented rates. As much as 90% of that data is unstructured, coming from social media, electronic documents, machine data, connected devices, etc., and growing at rates as high as 50% per year. This is big data.

Extracting insights from big data can make your business more agile, more competitive and provide insights that, in the past, were beyond reach. The emergence of recent technologies such as the real-time analytics processing capabilities of stream computing, high speed in-memory analytics using Apache Spark and the massive MapReduce scale-out capabilities of Hadoop® has opened the door to a world of possibilities. This has also created the need for robust infrastructures that combine computing power, memory and data bandwidth to process and move large quantities of data -- fast.

Understanding the IBM Power Systems Advantage

Based on this need, the IBM Power System S812LC was used to design a solution to create a big data environment built on a heritage of strong resiliency, availability and security -- the IBM Data Engine for Hadoop and Spark - Power Systems Edition.

With a data-centric design, this Linux-based solution offers a tightly-integrated and performance-optimized infrastructure for in-memory Spark and MapReduce-based Hadoop big data workloads. The IBM Data Engine for Hadoop and Spark can be tailored specifically to meet your Big Data workloads by using a simple building block approach to match the mix of memory, networking and storage to application requirements. This approach gives you the best possible infrastructure for your big data workload.

POWER8 Scale-Out: Massive Bandwidth

With a vision for enhanced bandwidth, IBM POWER8 has achieved vast improvements in latency, two-and-a-half time’s better memory performance, and a lot more.
POWER8 offers more than 32 channels of DDR memory funneling into the POWER8 processor. This is two times the 16-channel capacity for POWER7, and four times the eight-channel capacity of the most competitors.

Move Up to Power8 with Scale Out Servers

The result of a depth and breadth of innovation focused on optimizing for data centers, while increasing efficiency and lowering infrastructure cost, the POWER8 bandwidth contributes to a better system that does more while making technology leadership attainable for customers.

Each POWER8 socket supports up to 1 TB of DRAM in the initial server configurations, yielding 2 TB capacity Scale-out systems and 16 TB capacity Enterprise systems, and supports up to 230 GBs per second of sustained memory bandwidth per socket.
Having developed the first processor designed for Big Data with massive parallelism and bandwidth for real-time results, when coupled with IBM DB2 with BLU Acceleration and Cognos analytics software the capacity of POWER8 far outpaces industry standard options with 82x faster delivery to insights

Far more than a function of size, sophisticated innovations in the POWER8 memory organization is designed to enhance both reliability and performance. Key among the innovations:
Up to eight high-speed channels which each run up to 9.6 GHz for up to 230 GB of sustained performance
Up to 32 total DDR ports yielding 410 GB/sec peak at the DRAM
Up to 1 TB memory capacity per fully configured processor socket

Big Data’s Big Memory requirements call for nothing less than the industry’s most innovative, scalable, and massive bandwidth and capacity. POWER8 thrives on the kinds of complexities that your organization faces in the current environment, with a platform to keep you ahead of the game as unforeseen challenges and opportunities emerge.

Features and benefits

A comprehensive, fully integrated cluster that is designed for ease of procurement, deployment, and operation. It includes all required components for Big Data applications, including servers, network, storage, operating system, management software, Hadoop and Spark software, and runtime libraries.

An application optimized configuration. The configuration of the cluster is carefully designed to optimize application performance and reduce total cost of ownership. The cluster is integrated with IBM Platform™ Cluster Manager, IBM Open Platform with Apache Hadoop and Spark and optionally IBM Spectrum Scale and IBM Spectrum Symphony which include advanced capabilities for storage and resource optimization. This optimized configuration enables users to show results more quickly.
Power S812LC delivers 2.3X BETTER performance per dollar spent for Spark workloads1

Advanced technology for performance and robustness. The hardware and software components in this infrastructure are customizable to allow the best performance or the best price/performance ratio.

Big data clusters can start out small and grow as the demands from line of business increase. Choosing an infrastructure that can scale to handle these demands is vital to meeting service level agreements and continuing access to insights. Organizations must also consider the maintenance required. Smart businesses choose Power Systems because they know Power Systems is built for big data workloads that demand high performance and high reliability.

Analytics solutions
Unlock the value of data with an IT infrastructure that provides speed and availability to deliver accelerated insights to the people and processes that need them.

IBM Data Engine for Analytics - Power Systems Edition
A customized infrastructure solution with integrated software optimized for both big data and analytics workloads.

Co-Design Architecture for Exascale

IBM POWER8 as an HPC platform

The State of Linux Containers

IBM Data Engine for NoSQL – Power Systems Edition
Unique technology from IBM delivers dramatic reductions in the cost of large NoSQL databases.

SAP HANA benefits from the enterprise capabilities of Power Systems
SAP HANA runs on all POWER8 servers. Power Systems Solution Editions for SAP HANA BW are easy to order and tailored for quick deployment and rapid-time-to value, while offering flexibility to meet individual client demands.

DB2 with BLU Acceleration on Power Systems
Enable faster insights using analytics queries and reports from data stored in any data warehouse, with a dynamic in-memory columnar solution.

IBM Solution for Analytics – Power Systems Edition
This flexible integrated solution for faster insights includes options for business intelligence and predictive analytics with in-memory data warehouse acceleration.

IBM Data Engine for Hadoop and Spark – Power Systems Edition
A fully integrated Hadoop and Spark solution optimized to simplify and accelerate unstructured big data analytics.

OpenPOWER Update

IBM PureData System for Operational Analytics
Easily deploy, optimize and manage data intensive workloads for operational analytics with an expert integrated system.

IBM DB2 Web Query for i
Help ensure every decision maker across the organization can easily find, analyze and share the information needed to make better, faster decisions.

OpenPOWER Roadmap Toward CORAL

The Quantum Effect: HPC without FLOPS

More Information:




















0 reacties:

Post a Comment