REAL-TIME STREAMING ANALYTICS DATA IN, ACTION OUT



Similar documents
print close Building Blocks

Big data platform for IoT Cloud Analytics. Chen Admati, Advanced Analytics, Intel

DATA MANAGEMENT FOR THE INTERNET OF THINGS

How To Build A Cisco Uniden Computing System

Cisco Integrated Video Surveillance Solution: Expand the Capabilities and Value of Physical Security Investments

Find the Information That Matters. Visualize Your Data, Your Way. Scalable, Flexible, Global Enterprise Ready

Powerful Management of Financial Big Data

Scalable. Reliable. Flexible. High Performance Architecture. Fault Tolerant System Design. Expansion Options for Unique Business Needs

Scalable. Reliable. Flexible. High Performance Architecture. Fault Tolerant System Design. Expansion Options for Unique Business Needs

Enhance Service Delivery and Accelerate Financial Applications with Consolidated Market Data

Scaling Objectivity Database Performance with Panasas Scale-Out NAS Storage

Detailed Design Report

Making Multicore Work and Measuring its Benefits. Markus Levy, president EEMBC and Multicore Association

Business opportunities from IOT and Big Data. Joachim Aertebjerg Director Enterprise Solution Sales Intel EMEA

Cisco UCS and Fusion- io take Big Data workloads to extreme performance in a small footprint: A case study with Oracle NoSQL database

White Paper. How Streaming Data Analytics Enables Real-Time Decisions

Fast Innovation requires Fast IT

QRadar Security Intelligence Platform Appliances

Cisco SFS 7000P InfiniBand Server Switch

Pentaho High-Performance Big Data Reference Configurations using Cisco Unified Computing System

COMPUTING. Centellis Virtualization Platform An open hardware and software platform for implementing virtualized applications

White paper. Axis Video Analytics. Enhancing video surveillance efficiency

Network Performance Channel

How To Write An Article On An Hp Appsystem For Spera Hana

Unified Computing Systems

Present and Act Upon. Register. Consume. Stream Analytics. Event Hubs. Field Gateway. Applications Cloud Gateway. Legacy IoT (custom protocols)

Dynamic M2M Event Processing Complex Event Processing and OSGi on Java Embedded

Load DynamiX Storage Performance Validation: Fundamental to your Change Management Process

Fog Computing and the Internet of Things: Extend the Cloud to Where the Things Are

Brocade Solution for EMC VSPEX Server Virtualization

Centralized Orchestration and Performance Monitoring

Web Traffic Capture Butler Street, Suite 200 Pittsburgh, PA (412)

PRIMERGY server-based High Performance Computing solutions

UCS M-Series Modular Servers

Elasticsearch on Cisco Unified Computing System: Optimizing your UCS infrastructure for Elasticsearch s analytics software stack

7 Principles of the IoT

NLSS Gateway Video Management Access Control Video Analytics Intrusion Remote Monitoring Cloud-Based Security

Internet of things (IOT) applications covering industrial domain. Dev Bhattacharya

Web Analytics Understand your web visitors without web logs or page tags and keep all your data inside your firewall.

SummitStack in the Data Center

Dell* In-Memory Appliance for Cloudera* Enterprise

The Purview Solution Integration With Splunk

Technical Data Sheet SCADE R17 Solutions for ARINC 661 Compliant Systems Design Environment for Aircraft Manufacturers, CDS and UA Suppliers

Accelerating I/O- Intensive Applications in IT Infrastructure with Innodisk FlexiArray Flash Appliance. Alex Ho, Product Manager Innodisk Corporation

Unisys ClearPath Forward Fabric Based Platform to Power the Weather Enterprise

IBM BladeCenter H with Cisco VFrame Software A Comparison with HP Virtual Connect

Implementation of a Video On-Demand System For Cable Television

SUN HARDWARE FROM ORACLE: PRICING FOR EDUCATION

Private cloud computing advances

From Ethernet Ubiquity to Ethernet Convergence: The Emergence of the Converged Network Interface Controller

Elevating Data Center Performance Management

Networking Remote-Controlled Moving Image Monitoring System

EMC XTREMIO EXECUTIVE OVERVIEW

UCS Network Utilization Monitoring: Configuration and Best Practice

Vortex White Paper. Simplifying Real-time Information Integration in Industrial Internet of Things (IIoT) Control Systems

IBM Netezza High Capacity Appliance

The Fusion of Supercomputing and Big Data. Peter Ungaro President & CEO

Support a New Class of Applications with Cisco UCS M-Series Modular Servers

Data Centric Systems (DCS)

EMC ISILON AND ELEMENTAL SERVER

The Challenge of Handling Large Data Sets within your Measurement System

How To Make Data Streaming A Real Time Intelligence

IBM System x reference architecture solutions for big data

SMARC Architecture for Industrial Internet of

Cisco Data Preparation

White Paper. Understanding Data Streams in IoT

Cloud Networking: A Novel Network Approach for Cloud Computing Models CQ1 2009

Data Center Infrastructure Management Managing the Physical Infrastructure for Greater Efficiency

White paper. Axis Video Analytics. Enhancing video surveillance efficiency

Vess. Architectural & Engineering Specifications For Video Surveillance. A2200 Series. Version: 1.2 Feb, 2013

Router Architectures

Real-time distributed Complex Event Processing for Big Data scenarios

Azul Compute Appliances

Data Driven Success. Comparing Log Analytics Tools: Flowerfire s Sawmill vs. Google Analytics (GA)

The Ultimate in Scale-Out Storage for HPC and Big Data

THE RTOS AS THE ENGINE POWERING THE INTERNET OF THINGS

Data Center Infrastructure Management Managing the Physical Infrastructure for Greater Efficiency

QRadar Security Management Appliances

Bricata Next Generation Intrusion Prevention System A New, Evolved Breed of Threat Mitigation

Virtualized Security: The Next Generation of Consolidation

Global Headquarters: 5 Speen Street Framingham, MA USA P F

Unified Computing System When Delivering IT as a Service. Tomi Jalonen DC CSE 2015

WANic 800 & or 2 HSSI ports Up to 52 Mbps/port. WANic 850 & or 2 T3 or E3 ports Full-speed CSU/DSU. WANic 880.

Low Latency Market Data and Ticker Plant Technology. SpryWare.

Affordable Building Automation System Enabled by the Internet of Things (IoT)

Integrated Grid Solutions. and Greenplum

Unified Batch & Stream Processing Platform

Get More Scalability and Flexibility for Big Data

Building the Internet of Things Jim Green - CTO, Data & Analytics Business Group, Cisco Systems

Security Frameworks. An Enterprise Approach to Security. Robert Belka Frazier, CISSP

Cisco UCS Business Advantage Delivered: Data Center Capacity Planning and Refresh

Java and the Internet of Things

Distributed Realtime Systems Framework for Sustainable Industry 4.0 applications

Solving I/O Bottlenecks to Enable Superior Cloud Efficiency

On Demand Satellite Image Processing

SummitStack in the Data Center

Windows Embedded Security and Surveillance Solutions

Cray: Enabling Real-Time Discovery in Big Data

Microsoft Private Cloud Fast Track Reference Architecture

IEC The Fast Guide to Open Control Software

Transcription:

REAL-TIME STREAMING ANALYTICS DATA IN, ACTION OUT SPOT THE ODD ONE BEFORE IT IS OUT flexaware.net

Streaming analytics: from data to action Do you need actionable insights from various data streams fast? Do you want to extract business value from data in motion, similar to traditional analytics tools that analyze data at rest? Streaming analytics enable near real-time decision making by letting you inspect, correlate and analyze data as it streams into the platform from a myriad of different sources. of data whose value decays fast over time. It is key to analyze and take action as soon as the data arrives, to extract the largest possible business value from the incoming data. Streaming analytics can be performed in software at the center of the network, but is much more performant when executed with optimized hardware at the right place in the network., the many-core processor platform for real-time streaming analytics Meet, a real-time streaming analytics embedded platform, built with hundreds of parallel processor cores and accelerators that can analyze your data extremely fast. extracts critical information from your streaming data and turns it into immediate action. is simple and straightforward, regardless of the underlying many-core hardware complexity. The embedded platform combines hardware for your application domain with a software development environment. A streaming analytics platform processes data before Instead of storing all incoming data for later analysis, The embedded platform was designed from it lands in a database, and allows you to act on the data much faster than traditional data analytics technologies do. This is important for the many types streaming analytics lets you analyze the incoming data immediately and select only those relevant pieces of data that can then be stored for later reference. the ground up to receive large amounts of streaming data in parallel, process in real-time, and turn the data into actions, corrections, or alerts. Programming Action Correction Alert

hardware: data in, action out FlexaMiner FM8 server analytics hardware offers superior data processing capabilities for real-time streaming analytics. It transfers vast amounts of real-time input data directly to the parallel processing cores and hardware accelerators. is a many-core embedded hardware design with a flexible, scalable and modular structure. Specific combinations of modules inside the "black box" determine the performance and cater to the application. To offer the best match for your data analytics applications, hardware is available in distinct configurations. FlexaGate FG4 IoT analytics gateway Specifications: Analytics gateway for fast IoT data processing at the edge of the cloud Allows instantaneous reaction to timesensitive data Saves cloud bandwidth, storage and processing costs 8 x Gbps RJ45 copper Ethernet inputs for streaming data ingestion from multiple sensors x Gbps RJ45 copper Ethernet output for communicating analysis results to the cloud Parallel data streams feed right into the processor network + RISC processor cores and optimized hardware accelerators for IoT data processing Low-latency local memories in a distributed memory architecture Passive cooling Size 2,4 (24,4) x 8,2 x 22,5 cm (width (mounting plate) x height x depth) Specifications: 9" U appliance Parallel data streams feed right into the processor network 6 x Gbps RJ45 copper Ethernet inputs An internal high-speed Gbps interconnect enables fast communication between cores 2+ RISC processor cores and hardware accelerators Low-latency local memories in a distributed memory architecture Hardware accelerators speed up compute-intensive data processing tasks 2x Gbps RJ45 copper Ethernet output communicates analysis results Active cooling 9" rack shelf form factor 44,2 (48,4) x 4,4 x 43,4 cm (width (mounting plate) x height x depth) Optional redundant power supplies

SDE: from idea to application in 3 simple steps You need processing power. Real-time performance. And you want simple programming. s software development environment (SDE) is an intuitive graphical tool with predefined and custom building blocks. You can turn ideas into a final product in 3 easy steps. Most distinctly, s SDE gives insight in how your application runs on the many-core hardware. 2 Get insight in application behavior Invisibly, under the hood, the runtime (a many-core OS ) automatically maps tasks and channels on the hardware. The runtime takes on scheduling, memory allocation and task mapping of your application, and coordinates the information exchange between the processor cores and the external I/O. The SDE takes in the information from the runtime and shows how the application would behave in real-life conditions. The SDE provides you with insights and suggestions that allow you to review and optimize your application design. Result: insight in your application. Task Task 2 Input NoiseFilter float <64> Estimator float <64> block_t <4> Block Matching Input 28 48 28 Task 3 Task 4 Task 5 block_t <6> Task 6 int<28> Task 7 Searching 2 vector_t<8> Encoding Output 6 28 Output Task 8 Task 9 vector_t<2> Task Task Task 2 Design your application in the SDE Assisted by the SDE, convert your application into sets of parallel tasks, and data flows. Being explicit about concurrency and parallelism in your application design allows the SDE to automatically optimize the application for the many-core hardware. 3 Finalize your application and your product Run it on the simulator or directly on the hardware. Capture performance figures on a live running system for further optimization. Explore alternative hardware configurations as your application target. In the Flexaware SDE, capture your applications graphically or describe them in C using the proprietary Tweak properties of tasks or communication channels to fine-tune. API (Application Programming Interface). Validate the expected data-to-action timing. Add predefined building blocks from s platform library or create your own reusable building Finalize. blocks to integrate unique functionality. Result: the initial version of your application. Result: the final, optimized version of your application.

Suggested applications Any application that requires the analysis (filtering, transformation, aggregation, correlation, etc.) of large amounts of data for immediate action. Examples are: IoT sensor analysis, Automotive ADAS, Machine vision inspection, Network monitoring, Security & safety monitoring, Access control, Operation and maintenance monitoring. Recore Systems PO Box 77 75 AB Enschede, NL +3 53 4753 info@recoresystems.com www.recoresystems.com flexaware.net