1 / 17

BMW11: Dealing with the Massive Data Generated by Many-Core Systems Dr Don Grice

BMW11: Dealing with the Massive Data Generated by Many-Core Systems Dr Don Grice. Title: Dealing with the Massive Data Generated by Many Core Systems. Abstract:

mabyn
Download Presentation

BMW11: Dealing with the Massive Data Generated by Many-Core Systems Dr Don Grice

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. BMW11:Dealing with theMassive DataGenerated byMany-Core SystemsDr Don Grice

  2. Title: Dealing with the Massive Data Generated by Many Core Systems. Abstract: Multi-core and Many-core architectures are enabling computing systems that are more powerful than ever. The amount of data being generated by these systems is becoming an issue in several areas, including storage of results, movement of intermediate and final results, and the ability to consume the data and transform it into 'information'. As we move forward we need to be developing HW and SW methods to deal with this massive data explosion. Data reduction/simplification and real time analytics will involve more computation but may be one of the most promising methods for dealing with this flood of newly generated data.

  3. TYPES OF DATA MANIPULATION COMPUTE INTENSIVE DATA INTENSIVE NETWORK INTENSIVE

  4. Styles of Massively Parallel Workloads = compute node Data Intensive (Data At Rest) Data Intensive (Data Needs to Move) Global Analytics: View of All Data Required Data ‘Must be Moved’ Higher Velocity Network is Critical Hadoop/MapReduce (BigInsights) Input Data Data at Rest*: High Volume Mixed Variety Low Velocity Mappers Reducers Output Data (*pre-partitioned) Data Intensive : Data in Motion (Streaming) Compute Intensive (Data Generators) SPL, C, Java C/C++, Fortran, MPI, OpenMP Data in Motion: High Velocity Mixed Variety High Volume* Long Running Small Input Massive Output Generative Modeling Extreme Physics Reactive Analytics Extreme Ingestion (*over time)

  5. Styles of Massively Parallel Workloads = compute node Embarassingly Parallel Network Dependent Data Intensive (Data At Rest) Data Intensive (Data Needs to Move) Global Analytics: View of All Data Required Data ‘Must be Moved’ Higher Velocity Network is Critical Hadoop/MapReduce (BigInsights) Input Data Data at Rest*: High Volume Mixed Variety Low Velocity Mappers Reducers Output Data (*pre-partitioned) Data Intensive : Data in Motion (Streaming) Compute Intensive (Data Generators) SPL, C, Java C/C++, Fortran, MPI, OpenMP Data in Motion: High Velocity Mixed Variety High Volume* Long Running Small Input Massive Output Generative Modeling Extreme Physics Reactive Analytics Extreme Ingestion (*over time)

  6. Data Intensive Applications (Large Data)

  7. Exa Peta Tera Giga DeepQA 100s GB for Deep Analytics 3 sec/decision Mega yr mo wk day hr min sec … ms s Kilo Real-time Occasional Frequent New “Big Data” Brings New Opportunities, Requires New Analytics Up to 10,000 Times larger Telco Promotions 100,000 records/sec, 6B/day 10 ms/decision 270TB for Deep Analytics Data at Rest Data Scale Data Scale Traditional Data Warehouse and Business Intelligence Data in Motion Up to 10,000 times faster Smart Traffic 250K GPS probes/sec 630K segments/sec 2 ms/decision, 4K vehicles Decision Frequency

  8. Petascale Analytics, Appliances and Ecosystem Big Data is the new resource. The new opportunity is Big Analytics. Every Smarter Planet solution will depend on it. Market leadership in the Era of Analytics will be taken by the first player to deliver high volumes of easy-to-use Smarter Planet solutions. Ultimate success will requirea Petascale Analytics Appliance and a rich ecosystem of data, algorithms and skills. Smarter Planet Deeper Insights Faster Decisions

  9. Exa Peta Tera Feedback Giga Mega yr mo wk day hr min sec … ms s Kilo Real-time Occasional Frequent Maximum Insight Requires Combining Deep and Reactive Analytics Deep Analytics Government and Telco industries are leading this trend Deep Predictions Hypotheses History Directly integrating Reactive and Deep Analytics enables feedback-driven insight optimization Data Scale Integration Integration Data Scale Reality Traditional Data Warehouse and Business Intelligence Fast Actions Observations Integration Reactive Analytics Decision Frequency

  10. Watson IBM Research built a computer system that is able to compete with humans at the game of Jeopardy: Human vs. Machine contest. Named “Watson,” the computer is designed to rival the human mind Answering questions in natural language poses a grand challenge in computer science, and the Jeopardy! clue format is a great way to showcase:  Broad range of topics, such as history, literature, politics, popular culture and science  Nature of the clues, requires analyzing subtle meaning, irony, riddles and other complexities Based on the science of Question Answering (QA); differs from conventional search Natural Language / Human Interactions Critical for implementing useful business applications such as:  Medical diagnosis  Customer relationship management  Regulatory compliance  Help desk support Feb. 14 / 15 / 16

  11. Compute Intensive Workloads (Traditional ‘HPC’)

  12. Fundamental Issues with Large Scale HPC Compute Intensive Workloads • Power Efficiency • TCO • Programmability and Scaleout • Frequency is Plateaued • More Parallelism is needed • Balanced BWs are required for ‘sustained’ Perf • Shared Memory Model vs I/O ‘Accelerator’ Model • Availability and Reliability • More Circuitry is required • Technology Scale makes it worse • Design for Availability is required • Data Management and Cost of Storing/Moving Data • Time Steps & Checkpoints • Storage Cost, Energy Cost, BW, Latency • Life Cycle Management

  13. Amount of Data Generated Growing Much Faster Than BW to Store or Retrieve it • Example: 100x improvement in Machine Performance • Core Frequency has Plateaued • 100x Performance -> >100x more cores • Memory per core ~ constant? -> >100x more memory • Checkpoint Data Increase >100x • Plus frequency may increase due to reliability changes • Time Step Data Increase at least 100x? (with Performance) • Disk and Tape BWs are basically Plateaued (~100MB/s) • Compression Methods are not improving much • Only provides ~2x BW boost at most in any event • Capacity Growing at 20-30% CGR but not BW • Amount of Disk/Tape needs to grow >100x to match BW • Some relief possible with Write Duty Cycle Utilization • Cache locally and take full interval to write it out • Pre-stage Reads

  14. Example of Data Volume Gap • Example of Data Volume Gap Growing for Commercial Users • BW Gap is even larger! 4%CAGR

  15. Server(s) Server(s) CPU’s CPU’s Memory Memory FLASH FLASH I/O I/O ‘Local’ Storage Node ‘Local’ Storage Node ‘Remote’ Storage Node ‘Remote’ Storage Node Disk or Tape Disk or Tape Data Centric Computing Data Set Size Increases Downward ‘Domain’ ‘Network’ Functional Units Register Stack OS/SMP SMP Bus High Speed Cluster Network Cluster/’System’ High Speed Cluster Network Disk, Tape? Flash? Multi-Cluster LAN/SAN.. WAN? LAN/SAN Grid? WAN?

  16. SUMMARY • Data Volume and BW is Exploding in many Areas • Multicore/Many Core Compute Intensive Systems • Are generating more data and faster than ever before • Also using more Memory due to Frequency Stabilization • Data Storage BWs are not improving much • Balance of Compute to I/O and Storage will need to shift • Compute Intensive Workloads will also interact with • Data Intensive Workloads in Workflow environments • Data Life Cycle Management, Prestaging and Intelligent Writing • will become increasingly more important as machines grow • in capability

  17. Thank you... ...any Questions?

More Related