The continuum of data management techniques for explicitly managed systems
|
|
- Marsha Stewart
- 8 years ago
- Views:
Transcription
1 The continuum of data management techniques for explicitly managed systems Svetozar Miucin, Craig Mustard Simon Fraser University MCES Montreal
2 Introduction Explicitly Managed Memory systems lack conventional hardware cache mechanisms. Instead, they have small but fast scratchpad memories close to the cores, and slower global memories far away across an interconnect. And a DMA controller between them! Difference in access times between local/global is a couple of orders of magnitude.
3 Introduction EMM systems are important: Lower power consumption Higher computational power if used correctly But, they re hard to use correctly Lots of DMA transfers = lots of data management decisions.
4 Our setup STMicroelecronics STHORM Cluster = 16 PE cores + 1 Cluster controller core 256kB scratchpad per cluster
5 The discrete view Convolution kernel 56x faster!
6 What is the difference? We can run most code with global accesses without much modification. To get the manual version speedups, we need to try hard. Is there a compromise? Yes, there is.
7 Common bits, abstractions Many kernels have similar data access patterns. This can be exploited to abstract a lot of stuff away. Our example: NxM Convolution A textbook case for image processing.
8 Convolution accesses A single iteration of 3x3 convolution Read pattern Write pattern input: Access all data inside a 2D tile output: Access the central pixel relative to the input tile
9 Iterator interface Convolution access abstraction case is simple: init_area(...) Initializes the area that a core (or a cluster) will process get_next_tile(...) Returns a structure containing a batch of pixels to process and metadata
10 Double buffering Hiding the transfers behind processing. DMA transfer #1 Processing #1 DMA transfer #2 Example: DMA transfer #1 DMA transfer #2 Processing #1 initiate transfer of data chunk #2 process data chunk #1 wait for the transfer of chunk #2 to complete initiate transfer of data chunk #3 process data chunk #2 A tedious task, but it can be automated when accesses are predictable.
11 Border processing and Out-of-image pixels To process a pixel, we need to fetch its neighbours. The iterator interface returns metadata about which area of the fetched tile contains this extra data. We can also generate border pixels that fall outside of the image by providing custom generator functions.
12 The real benefit All of this can be done manually. Abstracting it through a library gives clean, small kernels that are easy to reason about: init_area(...); while (get_next_tile(&tile)!= NULL) { process(tile); }
13 Where does this place us?
14 Software cache Hide all data management from the programmer. data = softcache_fetch(address); 1. How well can software cache do versus manual management? Why? 2. How to achieve this performance. High-level.
15 The driver - Hough transform Algorithm for geometrical shape detection in images. Pseudo-random access patterns. Takes time to carefully organize memory transfers.
16 Software cache on Hough First try (Pseudo random access to data) 80x faster than naive Second try Software cache 2x as fast as the first manual 1.5x slower than the best manual version Manual data management code can be SLOWER than using software cache!
17 Software cache on Hough 2x as fast as one manual version. Why? 1. Software cache has less overhead than the manual management on the access pattern of Hough. 2. Software cache took better advantage of available space than the first version. Bonus #1: Software cache inspired the best performing manual version Bonus #2: Software cache was much easier to implement than either manual version (15 minutes: naive->softcache)
18 Software cache on Convolution (Very regular access to data) Classic interface New interface Classic interface: 10x faster than naive 2.5x slower than manual versions New interface: 1.2x slower than best manual version Manual management performs very well for regular data access patterns
19 Software cache on Convolution 2.5x slower than manual versions. Why? Overhead of function calls in software cache New interface reduces # of function calls by returning more data with a single function call. softcache_fetch(addr) - one item softcache_fetch_more(addr, &num) - N items
20 Software cache: the gory details We tested all features of a classic cache. Private/shared, line-size vs # of lines, prefetching, write policies To get the performance we showed: Per core (private) caches of 8K Read-only Tuned line-size vs number of lines (12 tests) Prefetching disabled (rarely ever good)
21 The continuous view Both the library and the software cache approach are just tools. They can be used together in any combination, to hit the desired ease-ofprogramming/performance trade-off.
22 The end
Speeding Up Cloud/Server Applications Using Flash Memory
Speeding Up Cloud/Server Applications Using Flash Memory Sudipta Sengupta Microsoft Research, Redmond, WA, USA Contains work that is joint with B. Debnath (Univ. of Minnesota) and J. Li (Microsoft Research,
More informationDatabase!Fatal!Flash!Flaws!No!One! Talks!About!!!
MarcStaimer,President&CDSDragonSlayerConsulting W h i t e P A P E R DatabaseFatalFlashFlawsNoOne TalksAbout AndHowtoAvoidThem WHITEPAPER DatabaseFatalFlashFlawsNoOneTalksAbout AndHowtoAvoidThem DatabaseFatalFlashFlawsNoOneTalksAbout
More informationExternal Sorting. Chapter 13. Database Management Systems 3ed, R. Ramakrishnan and J. Gehrke 1
External Sorting Chapter 13 Database Management Systems 3ed, R. Ramakrishnan and J. Gehrke 1 Why Sort? A classic problem in computer science! Data requested in sorted order e.g., find students in increasing
More informationComputer Architecture
Cache Memory Gábor Horváth 2016. április 27. Budapest associate professor BUTE Dept. Of Networked Systems and Services ghorvath@hit.bme.hu It is the memory,... The memory is a serious bottleneck of Neumann
More informationGPU File System Encryption Kartik Kulkarni and Eugene Linkov
GPU File System Encryption Kartik Kulkarni and Eugene Linkov 5/10/2012 SUMMARY. We implemented a file system that encrypts and decrypts files. The implementation uses the AES algorithm computed through
More informationExternal Sorting. Why Sort? 2-Way Sort: Requires 3 Buffers. Chapter 13
External Sorting Chapter 13 Database Management Systems 3ed, R. Ramakrishnan and J. Gehrke 1 Why Sort? A classic problem in computer science! Data requested in sorted order e.g., find students in increasing
More informationCUDA Optimization with NVIDIA Tools. Julien Demouth, NVIDIA
CUDA Optimization with NVIDIA Tools Julien Demouth, NVIDIA What Will You Learn? An iterative method to optimize your GPU code A way to conduct that method with Nvidia Tools 2 What Does the Application
More informationThe Classical Architecture. Storage 1 / 36
1 / 36 The Problem Application Data? Filesystem Logical Drive Physical Drive 2 / 36 Requirements There are different classes of requirements: Data Independence application is shielded from physical storage
More informationA3 Computer Architecture
A3 Computer Architecture Engineering Science 3rd year A3 Lectures Prof David Murray david.murray@eng.ox.ac.uk www.robots.ox.ac.uk/ dwm/courses/3co Michaelmas 2000 1 / 1 6. Stacks, Subroutines, and Memory
More informationCOS 318: Operating Systems
COS 318: Operating Systems File Performance and Reliability Andy Bavier Computer Science Department Princeton University http://www.cs.princeton.edu/courses/archive/fall10/cos318/ Topics File buffer cache
More informationOperating Systems. Virtual Memory
Operating Systems Virtual Memory Virtual Memory Topics. Memory Hierarchy. Why Virtual Memory. Virtual Memory Issues. Virtual Memory Solutions. Locality of Reference. Virtual Memory with Segmentation. Page
More informationArchitectures and Platforms
Hardware/Software Codesign Arch&Platf. - 1 Architectures and Platforms 1. Architecture Selection: The Basic Trade-Offs 2. General Purpose vs. Application-Specific Processors 3. Processor Specialisation
More informationSolid State Storage in Massive Data Environments Erik Eyberg
Solid State Storage in Massive Data Environments Erik Eyberg Senior Analyst Texas Memory Systems, Inc. Agenda Taxonomy Performance Considerations Reliability Considerations Q&A Solid State Storage Taxonomy
More informationOperating Systems Overview
Operating Systems Overview No single definition, but many perspectives: Role in an overall system: Intermediary between computer hardware and everything else User view: Provides an environment, preferably
More informationMapReduce. MapReduce and SQL Injections. CS 3200 Final Lecture. Introduction. MapReduce. Programming Model. Example
MapReduce MapReduce and SQL Injections CS 3200 Final Lecture Jeffrey Dean and Sanjay Ghemawat. MapReduce: Simplified Data Processing on Large Clusters. OSDI'04: Sixth Symposium on Operating System Design
More informationIndexing on Solid State Drives based on Flash Memory
Indexing on Solid State Drives based on Flash Memory Florian Keusch MASTER S THESIS Systems Group Department of Computer Science ETH Zurich http://www.systems.ethz.ch/ September 2008 - March 2009 Supervised
More informationOPTIMIZE DMA CONFIGURATION IN ENCRYPTION USE CASE. Guillène Ribière, CEO, System Architect
OPTIMIZE DMA CONFIGURATION IN ENCRYPTION USE CASE Guillène Ribière, CEO, System Architect Problem Statement Low Performances on Hardware Accelerated Encryption: Max Measured 10MBps Expectations: 90 MBps
More informationRecommended hardware system configurations for ANSYS users
Recommended hardware system configurations for ANSYS users The purpose of this document is to recommend system configurations that will deliver high performance for ANSYS users across the entire range
More informationChapter 7: Distributed Systems: Warehouse-Scale Computing. Fall 2011 Jussi Kangasharju
Chapter 7: Distributed Systems: Warehouse-Scale Computing Fall 2011 Jussi Kangasharju Chapter Outline Warehouse-scale computing overview Workloads and software infrastructure Failures and repairs Note:
More informationColdFusion 8. Performance Tuning, Multi-Instance Management and Clustering. Sven Ramuschkat MAX 2008 Milan
ColdFusion 8 Performance Tuning, Multi-Instance Management and Clustering Sven Ramuschkat MAX 2008 Milan About me Sven Ramuschkat CTO of Herrlich & Ramuschkat GmbH ColdFusion since Version 3.1 Authorized
More informationHave both hardware and software. Want to hide the details from the programmer (user).
Input/Output Devices Chapter 5 of Tanenbaum. Have both hardware and software. Want to hide the details from the programmer (user). Ideally have the same interface to all devices (device independence).
More informationOverlapping Data Transfer With Application Execution on Clusters
Overlapping Data Transfer With Application Execution on Clusters Karen L. Reid and Michael Stumm reid@cs.toronto.edu stumm@eecg.toronto.edu Department of Computer Science Department of Electrical and Computer
More informationA Novel Way of Deduplication Approach for Cloud Backup Services Using Block Index Caching Technique
A Novel Way of Deduplication Approach for Cloud Backup Services Using Block Index Caching Technique Jyoti Malhotra 1,Priya Ghyare 2 Associate Professor, Dept. of Information Technology, MIT College of
More informationImplementation of Canny Edge Detector of color images on CELL/B.E. Architecture.
Implementation of Canny Edge Detector of color images on CELL/B.E. Architecture. Chirag Gupta,Sumod Mohan K cgupta@clemson.edu, sumodm@clemson.edu Abstract In this project we propose a method to improve
More informationGoogle File System. Web and scalability
Google File System Web and scalability The web: - How big is the Web right now? No one knows. - Number of pages that are crawled: o 100,000 pages in 1994 o 8 million pages in 2005 - Crawlable pages might
More informationLecture 10: Dynamic Memory Allocation 1: Into the jaws of malloc()
CS61: Systems Programming and Machine Organization Harvard University, Fall 2009 Lecture 10: Dynamic Memory Allocation 1: Into the jaws of malloc() Prof. Matt Welsh October 6, 2009 Topics for today Dynamic
More informationCOSC 6374 Parallel Computation. Parallel I/O (I) I/O basics. Concept of a clusters
COSC 6374 Parallel I/O (I) I/O basics Fall 2012 Concept of a clusters Processor 1 local disks Compute node message passing network administrative network Memory Processor 2 Network card 1 Network card
More informationCloud Storage. Parallels. Performance Benchmark Results. White Paper. www.parallels.com
Parallels Cloud Storage White Paper Performance Benchmark Results www.parallels.com Table of Contents Executive Summary... 3 Architecture Overview... 3 Key Features... 4 No Special Hardware Requirements...
More informationParallel Processing and Software Performance. Lukáš Marek
Parallel Processing and Software Performance Lukáš Marek DISTRIBUTED SYSTEMS RESEARCH GROUP http://dsrg.mff.cuni.cz CHARLES UNIVERSITY PRAGUE Faculty of Mathematics and Physics Benchmarking in parallel
More informationEight Ways to Increase GPIB System Performance
Application Note 133 Eight Ways to Increase GPIB System Performance Amar Patel Introduction When building an automated measurement system, you can never have too much performance. Increasing performance
More informationBase One's Rich Client Architecture
Base One's Rich Client Architecture Base One provides a unique approach for developing Internet-enabled applications, combining both efficiency and ease of programming through its "Rich Client" architecture.
More informationPerformance Evaluation of NAS Parallel Benchmarks on Intel Xeon Phi
Performance Evaluation of NAS Parallel Benchmarks on Intel Xeon Phi ICPP 6 th International Workshop on Parallel Programming Models and Systems Software for High-End Computing October 1, 2013 Lyon, France
More informationParallel Algorithm Engineering
Parallel Algorithm Engineering Kenneth S. Bøgh PhD Fellow Based on slides by Darius Sidlauskas Outline Background Current multicore architectures UMA vs NUMA The openmp framework Examples Software crisis
More informationWhitepaper: performance of SqlBulkCopy
We SOLVE COMPLEX PROBLEMS of DATA MODELING and DEVELOP TOOLS and solutions to let business perform best through data analysis Whitepaper: performance of SqlBulkCopy This whitepaper provides an analysis
More informationChapter 11 I/O Management and Disk Scheduling
Operatin g Systems: Internals and Design Principle s Chapter 11 I/O Management and Disk Scheduling Seventh Edition By William Stallings Operating Systems: Internals and Design Principles An artifact can
More informationCSC 2405: Computer Systems II
CSC 2405: Computer Systems II Spring 2013 (TR 8:30-9:45 in G86) Mirela Damian http://www.csc.villanova.edu/~mdamian/csc2405/ Introductions Mirela Damian Room 167A in the Mendel Science Building mirela.damian@villanova.edu
More informationNetworking Virtualization Using FPGAs
Networking Virtualization Using FPGAs Russell Tessier, Deepak Unnikrishnan, Dong Yin, and Lixin Gao Reconfigurable Computing Group Department of Electrical and Computer Engineering University of Massachusetts,
More informationGPU for Scientific Computing. -Ali Saleh
1 GPU for Scientific Computing -Ali Saleh Contents Introduction What is GPU GPU for Scientific Computing K-Means Clustering K-nearest Neighbours When to use GPU and when not Commercial Programming GPU
More informationSlide Set 8. for ENCM 369 Winter 2015 Lecture Section 01. Steve Norman, PhD, PEng
Slide Set 8 for ENCM 369 Winter 2015 Lecture Section 01 Steve Norman, PhD, PEng Electrical & Computer Engineering Schulich School of Engineering University of Calgary Winter Term, 2015 ENCM 369 W15 Section
More information361 Computer Architecture Lecture 14: Cache Memory
1 361 Computer Architecture Lecture 14 Memory cache.1 The Motivation for s Memory System Processor DRAM Motivation Large memories (DRAM) are slow Small memories (SRAM) are fast Make the average access
More informationIn-memory Tables Technology overview and solutions
In-memory Tables Technology overview and solutions My mainframe is my business. My business relies on MIPS. Verna Bartlett Head of Marketing Gary Weinhold Systems Analyst Agenda Introduction to in-memory
More information1 Storage Devices Summary
Chapter 1 Storage Devices Summary Dependability is vital Suitable measures Latency how long to the first bit arrives Bandwidth/throughput how fast does stuff come through after the latency period Obvious
More informationChapter 1 Computer System Overview
Operating Systems: Internals and Design Principles Chapter 1 Computer System Overview Eighth Edition By William Stallings Operating System Exploits the hardware resources of one or more processors Provides
More informationGPUs for Scientific Computing
GPUs for Scientific Computing p. 1/16 GPUs for Scientific Computing Mike Giles mike.giles@maths.ox.ac.uk Oxford-Man Institute of Quantitative Finance Oxford University Mathematical Institute Oxford e-research
More informationThe Implementation of a Hybrid-Execute-In-Place Architecture to Reduce the Embedded System Memory Footprint and Minimize Boot Time
The Implementation of a Hybrid-Execute-In-Place Architecture to Reduce the Embedded System Memory Footprint and Minimize Boot Time Tony Benavides, Justin Treon, Jared Hulbert, and Willie Chang 1 Flash
More informationfind model parameters, to validate models, and to develop inputs for models. c 1994 Raj Jain 7.1
Monitors Monitor: A tool used to observe the activities on a system. Usage: A system programmer may use a monitor to improve software performance. Find frequently used segments of the software. A systems
More informationHigh Performance Computing. Course Notes 2007-2008. HPC Fundamentals
High Performance Computing Course Notes 2007-2008 2008 HPC Fundamentals Introduction What is High Performance Computing (HPC)? Difficult to define - it s a moving target. Later 1980s, a supercomputer performs
More informationStorage. The text highlighted in green in these slides contain external hyperlinks. 1 / 14
Storage Compared to the performance parameters of the other components we have been studying, storage systems are much slower devices. Typical access times to rotating disk storage devices are in the millisecond
More informationOpenMP Programming on ScaleMP
OpenMP Programming on ScaleMP Dirk Schmidl schmidl@rz.rwth-aachen.de Rechen- und Kommunikationszentrum (RZ) MPI vs. OpenMP MPI distributed address space explicit message passing typically code redesign
More informationSeeking Opportunities for Hardware Acceleration in Big Data Analytics
Seeking Opportunities for Hardware Acceleration in Big Data Analytics Paul Chow High-Performance Reconfigurable Computing Group Department of Electrical and Computer Engineering University of Toronto Who
More informationBetriebssysteme KU Security
Betriebssysteme KU Security IAIK Graz University of Technology 1 1. Drivers 2. Security - The simple stuff 3. Code injection attacks 4. Side-channel attacks 2 1. Drivers 2. Security - The simple stuff
More informationChapter 18: Database System Architectures. Centralized Systems
Chapter 18: Database System Architectures! Centralized Systems! Client--Server Systems! Parallel Systems! Distributed Systems! Network Types 18.1 Centralized Systems! Run on a single computer system and
More informationGraphics Cards and Graphics Processing Units. Ben Johnstone Russ Martin November 15, 2011
Graphics Cards and Graphics Processing Units Ben Johnstone Russ Martin November 15, 2011 Contents Graphics Processing Units (GPUs) Graphics Pipeline Architectures 8800-GTX200 Fermi Cayman Performance Analysis
More informationDATABASE VIRTUALIZATION AND INSTANT CLONING WHITE PAPER
DATABASE VIRTUALIZATION AND INSTANT CLONING TABLE OF CONTENTS Brief...3 Introduction...3 Solutions...4 Technologies....5 Database Virtualization...7 Database Virtualization Examples...9 Summary....9 Appendix...
More informationPARALLELS CLOUD STORAGE
PARALLELS CLOUD STORAGE Performance Benchmark Results 1 Table of Contents Executive Summary... Error! Bookmark not defined. Architecture Overview... 3 Key Features... 5 No Special Hardware Requirements...
More informationBig Fast Data Hadoop acceleration with Flash. June 2013
Big Fast Data Hadoop acceleration with Flash June 2013 Agenda The Big Data Problem What is Hadoop Hadoop and Flash The Nytro Solution Test Results The Big Data Problem Big Data Output Facebook Traditional
More informationCOS 318: Operating Systems. Virtual Memory and Address Translation
COS 318: Operating Systems Virtual Memory and Address Translation Today s Topics Midterm Results Virtual Memory Virtualization Protection Address Translation Base and bound Segmentation Paging Translation
More informationDevelopment at the Speed and Scale of Google. Ashish Kumar Engineering Tools
Development at the Speed and Scale of Google Ashish Kumar Engineering Tools The Challenge Speed and Scale of Google More than 5000 developers in more than 40 offices More than 2000 projects under active
More informationHow To Understand And Understand An Operating System In C Programming
ELEC 377 Operating Systems Thomas R. Dean Instructor Tom Dean Office:! WLH 421 Email:! tom.dean@queensu.ca Hours:! Wed 14:30 16:00 (Tentative)! and by appointment! 6 years industrial experience ECE Rep
More informationViolin: A Framework for Extensible Block-level Storage
Violin: A Framework for Extensible Block-level Storage Michail Flouris Dept. of Computer Science, University of Toronto, Canada flouris@cs.toronto.edu Angelos Bilas ICS-FORTH & University of Crete, Greece
More information1. Computer System Structure and Components
1 Computer System Structure and Components Computer System Layers Various Computer Programs OS System Calls (eg, fork, execv, write, etc) KERNEL/Behavior or CPU Device Drivers Device Controllers Devices
More informationStream Processing on GPUs Using Distributed Multimedia Middleware
Stream Processing on GPUs Using Distributed Multimedia Middleware Michael Repplinger 1,2, and Philipp Slusallek 1,2 1 Computer Graphics Lab, Saarland University, Saarbrücken, Germany 2 German Research
More informationConfinement Problem. The confinement problem Isolating entities. Example Problem. Server balances bank accounts for clients Server security issues:
Confinement Problem The confinement problem Isolating entities Virtual machines Sandboxes Covert channels Mitigation 1 Example Problem Server balances bank accounts for clients Server security issues:
More informationPhysical Data Organization
Physical Data Organization Database design using logical model of the database - appropriate level for users to focus on - user independence from implementation details Performance - other major factor
More informationIntroduction to Virtual Machines
Introduction to Virtual Machines Introduction Abstraction and interfaces Virtualization Computer system architecture Process virtual machines System virtual machines 1 Abstraction Mechanism to manage complexity
More informationComputers. Hardware. The Central Processing Unit (CPU) CMPT 125: Lecture 1: Understanding the Computer
Computers CMPT 125: Lecture 1: Understanding the Computer Tamara Smyth, tamaras@cs.sfu.ca School of Computing Science, Simon Fraser University January 3, 2009 A computer performs 2 basic functions: 1.
More informationPrinciples and characteristics of distributed systems and environments
Principles and characteristics of distributed systems and environments Definition of a distributed system Distributed system is a collection of independent computers that appears to its users as a single
More informationBENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB
BENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB Planet Size Data!? Gartner s 10 key IT trends for 2012 unstructured data will grow some 80% over the course of the next
More informationDatabase Management Systems
4411 Database Management Systems Acknowledgements and copyrights: these slides are a result of combination of notes and slides with contributions from: Michael Kiffer, Arthur Bernstein, Philip Lewis, Anestis
More informationMySQL performance in a cloud. Mark Callaghan
MySQL performance in a cloud Mark Callaghan Special thanks Eric Hammond (http://www.anvilon.com) provided documentation that made all of my work much easier. What is this thing called a cloud? Deployment
More informationIntroduction to Cloud Computing
Introduction to Cloud Computing Parallel Processing I 15 319, spring 2010 7 th Lecture, Feb 2 nd Majd F. Sakr Lecture Motivation Concurrency and why? Different flavors of parallel computing Get the basic
More informationWin at Life. with Unit Testing. by Mark Story
Win at Life with Unit Testing. by Mark Story Who is this goofball Art college graduate that needed to make money. CakePHP core contributor for 2.5 years. Developer of DebugKit, ApiGenerator and several
More informationThe Importance of Software License Server Monitoring
The Importance of Software License Server Monitoring NetworkComputer How Shorter Running Jobs Can Help In Optimizing Your Resource Utilization White Paper Introduction Semiconductor companies typically
More informationTypes Of Operating Systems
Types Of Operating Systems Date 10/01/2004 1/24/2004 Operating Systems 1 Brief history of OS design In the beginning OSes were runtime libraries The OS was just code you linked with your program and loaded
More informationBig Data With Hadoop
With Saurabh Singh singh.903@osu.edu The Ohio State University February 11, 2016 Overview 1 2 3 Requirements Ecosystem Resilient Distributed Datasets (RDDs) Example Code vs Mapreduce 4 5 Source: [Tutorials
More informationAn Exploration of Hybrid Hard Disk Designs Using an Extensible Simulator
An Exploration of Hybrid Hard Disk Designs Using an Extensible Simulator Pavan Konanki Thesis submitted to the Faculty of the Virginia Polytechnic Institute and State University in partial fulfillment
More informationUnderstanding the Benefits of IBM SPSS Statistics Server
IBM SPSS Statistics Server Understanding the Benefits of IBM SPSS Statistics Server Contents: 1 Introduction 2 Performance 101: Understanding the drivers of better performance 3 Why performance is faster
More informationPerformance Monitoring and Analysis System for MUSCLE-based Applications
Polish Infrastructure for Supporting Computational Science in the European Research Space Performance Monitoring and Analysis System for MUSCLE-based Applications W. Funika, M. Janczykowski, K. Jopek,
More informationSummer Student Project Report
Summer Student Project Report Dimitris Kalimeris National and Kapodistrian University of Athens June September 2014 Abstract This report will outline two projects that were done as part of a three months
More informationSecondary Storage. Any modern computer system will incorporate (at least) two levels of storage: magnetic disk/optical devices/tape systems
1 Any modern computer system will incorporate (at least) two levels of storage: primary storage: typical capacity cost per MB $3. typical access time burst transfer rate?? secondary storage: typical capacity
More informationTECHNICAL UNIVERSITY OF CRETE DATA STRUCTURES FILE STRUCTURES
TECHNICAL UNIVERSITY OF CRETE DEPT OF ELECTRONIC AND COMPUTER ENGINEERING DATA STRUCTURES AND FILE STRUCTURES Euripides G.M. Petrakis http://www.intelligence.tuc.gr/~petrakis Chania, 2007 E.G.M. Petrakis
More informationMatrox Imaging White Paper
Vision library or vision specific IDE: Which is right for you? Abstract Commercial machine vision software is currently classified along two lines: the conventional vision library and the vision specific
More informationA Framework for Automated Database TuningUsing Dynamic SGA Parameters and Basic Operating System Utilities
Database Systems Journal vol. III, no. 4/2012 25 A Framework for Automated Database TuningUsing Dynamic SGA Parameters and Basic Operating System Utilities Hitesh KUMAR SHARMA1, Aditya SHASTRI2, Ranjit
More informationultra fast SOM using CUDA
ultra fast SOM using CUDA SOM (Self-Organizing Map) is one of the most popular artificial neural network algorithms in the unsupervised learning category. Sijo Mathew Preetha Joy Sibi Rajendra Manoj A
More informationOperating Systems, 6 th ed. Test Bank Chapter 7
True / False Questions: Chapter 7 Memory Management 1. T / F In a multiprogramming system, main memory is divided into multiple sections: one for the operating system (resident monitor, kernel) and one
More informationBenchmark Hadoop and Mars: MapReduce on cluster versus on GPU
Benchmark Hadoop and Mars: MapReduce on cluster versus on GPU Heshan Li, Shaopeng Wang The Johns Hopkins University 3400 N. Charles Street Baltimore, Maryland 21218 {heshanli, shaopeng}@cs.jhu.edu 1 Overview
More information89 Fifth Avenue, 7th Floor. New York, NY 10003. www.theedison.com 212.367.7400. White Paper. HP 3PAR Adaptive Flash Cache: A Competitive Comparison
89 Fifth Avenue, 7th Floor New York, NY 10003 www.theedison.com 212.367.7400 White Paper HP 3PAR Adaptive Flash Cache: A Competitive Comparison Printed in the United States of America Copyright 2014 Edison
More information1 / 25. CS 137: File Systems. Persistent Solid-State Storage
1 / 25 CS 137: File Systems Persistent Solid-State Storage Technology Change is Coming Introduction Disks are cheaper than any solid-state memory Likely to be true for many years But SSDs are now cheap
More information1/20/2016 INTRODUCTION
INTRODUCTION 1 Programming languages have common concepts that are seen in all languages This course will discuss and illustrate these common concepts: Syntax Names Types Semantics Memory Management We
More informationEnterprise Mobile Application Development: Native or Hybrid?
Enterprise Mobile Application Development: Native or Hybrid? Enterprise Mobile Application Development: Native or Hybrid? SevenTablets 855-285-2322 Contact@SevenTablets.com http://www.seventablets.com
More informationReal Application Testing. Fred Louis Oracle Enterprise Architect
Real Application Testing Fred Louis Oracle Enterprise Architect The following is intended to outline our general product direction. It is intended for information purposes only, and may not be incorporated
More informationAdvances in Virtualization In Support of In-Memory Big Data Applications
9/29/15 HPTS 2015 1 Advances in Virtualization In Support of In-Memory Big Data Applications SCALE SIMPLIFY OPTIMIZE EVOLVE Ike Nassi Ike.nassi@tidalscale.com 9/29/15 HPTS 2015 2 What is the Problem We
More informationOutline. Database Management and Tuning. Overview. Hardware Tuning. Johann Gamper. Unit 12
Outline Database Management and Tuning Hardware Tuning Johann Gamper 1 Free University of Bozen-Bolzano Faculty of Computer Science IDSE Unit 12 2 3 Conclusion Acknowledgements: The slides are provided
More informationUpdate on filesystems for flash storage
JM2L Update on filesystems for flash storage Michael Opdenacker. Free Electrons http://free electrons.com/ 1 Contents Introduction Available flash filesystems Our benchmarks Best choices Experimental filesystems
More informationChapter 11 I/O Management and Disk Scheduling
Operating Systems: Internals and Design Principles, 6/E William Stallings Chapter 11 I/O Management and Disk Scheduling Dave Bremer Otago Polytechnic, NZ 2008, Prentice Hall I/O Devices Roadmap Organization
More informationSSD Performance Tips: Avoid The Write Cliff
ebook 100% KBs/sec 12% GBs Written SSD Performance Tips: Avoid The Write Cliff An Inexpensive and Highly Effective Method to Keep SSD Performance at 100% Through Content Locality Caching Share this ebook
More informationMulti-GPU Load Balancing for Simulation and Rendering
Multi- Load Balancing for Simulation and Rendering Yong Cao Computer Science Department, Virginia Tech, USA In-situ ualization and ual Analytics Instant visualization and interaction of computing tasks
More informationPERFORMANCE TUNING ORACLE RAC ON LINUX
PERFORMANCE TUNING ORACLE RAC ON LINUX By: Edward Whalen Performance Tuning Corporation INTRODUCTION Performance tuning is an integral part of the maintenance and administration of the Oracle database
More informationLOCKUP-FREE INSTRUCTION FETCH/PREFETCH CACHE ORGANIZATION
LOCKUP-FREE INSTRUCTION FETCH/PREFETCH CACHE ORGANIZATION DAVID KROFT Control Data Canada, Ltd. Canadian Development Division Mississauga, Ontario, Canada ABSTRACT In the past decade, there has been much
More information