inside the machine an introduction to architecture
play

Inside the Machine: An Introduction to Architecture, Parallelism - PowerPoint PPT Presentation

Feb 04, 2023 •472 likes •667 views

Inside the Machine: An Introduction to Architecture, Parallelism & its Applications Soumyabrata Dev The ADAPT SFI Research Centre https://soumyabrata.github.io/ UCD - Beijing-Dublin International College (BDIC) 7-May-2019 The ADAPT Centre

  1. Inside the Machine: An Introduction to Architecture, Parallelism & its Applications Soumyabrata Dev The ADAPT SFI Research Centre https://soumyabrata.github.io/ UCD - Beijing-Dublin International College (BDIC) 7-May-2019 The ADAPT Centre is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.

  2. Course Overview www.adaptcentre.ie Course website is available here: https://www.scss.tcd.ie/~devs/bdic.html

  3. www.adaptcentre.ie (1/3) Computer Architecture

  4. Computer Components www.adaptcentre.ie At the most basic level, a computer is a device consisting of three pieces: ● A processor to interpret and execute programs ● A memory to store both data and programs ● A mechanism for transferring data to and from the outside world.

  5. How computer understands our code? www.adaptcentre.ie

  6. www.adaptcentre.ie (2/3) Pipelining

  7. Laundry Example www.adaptcentre.ie ● Ann, Brian, Cathy, Dave each have one load of clothes to wash, dry, and fold. ● Washer takes 30 minutes. ● Dryer takes 40 minutes. ● Folder takes 20 minutes.

  8. Sequential Processing www.adaptcentre.ie ● Sequential laundry takes 6 hours for 4 loads. ● If they learned pipelining, how long would laundry take?

  9. Pipelined Processing www.adaptcentre.ie ● Pipelined laundry takes 3.5 hours for 4 loads.

  10. Thoughts on pipelining www.adaptcentre.ie ● Pipelining doesn't help latency of single task, it helps throughput of entire workload. ● Pipeline rate limited by slowest pipeline stage. ● Multiple tasks operating simultaneously using different resources. ● Potential speedup = Number pipe stages.

  11. Use of Pipelining in computer www.adaptcentre.ie ● Instruction-level parallelism (ILP) is a measure of how many operations in a computer program can be performed. “in parallel” at the same time.

  12. Activity Time www.adaptcentre.ie Consider the following program: e = a + b f = c + d m = e*f ● Suppose, each instruction takes 1 unit of time to complete. ● Sequential processing = 3 units of time ● How much time needed, if I employ ILP here?

  13. Types of parallelism www.adaptcentre.ie Three major categories to exploit parallelism: ● Instruction-level parallelism Multiple instructions from one instruction stream are executed simultaneously. ● Thread-level parallelism Multiple instruction streams are executed simultaneously. ● Vector data parallelism The same operation is performed simultaneously on arrays of elements.

  14. www.adaptcentre.ie (3/3) High Performance Computing

  15. HPC: Powering Deep Learning www.adaptcentre.ie 1 “Are AI/Machine Learning/Deep Learning in Your Company’s Future?”, insideBigData + NVIDIA 2 EMC Digital Universe with Research & Analysis by IDC

  16. HPC Application www.adaptcentre.ie HPC technology is implemented in multidisciplinary areas including: ● Biosciences ● Geoscience and remote sensing data ● Oil and gas industry modeling ● Electronic design automation ● Climate modeling ● Media and entertainment

  17. HPC Application www.adaptcentre.ie HPC technology is implemented in multidisciplinary areas including: ● Biosciences ● Geoscience and remote sensing ● Oil and gas industry modeling ● Electronic design automation ● Climate modeling ● Media and entertainment

  18. Thank You The ADAPT Centre is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Inside the Machine: An Introduction to Architecture, Parallelism & Electronics Soumyabrata

Inside the Machine: An Introduction to Architecture, Parallelism & Electronics Soumyabrata

Inside the Machine: An Introduction to Architecture, Parallelism & Electronics Soumyabrata Dev The ADAPT SFI Research Centre https://soumyabrata.github.io/ Bucknell University 13-July-2018 The ADAPT Centre is funded under the SFI Research

864 views • 57 slides
3.1 Architecture 3 Systems Alexander Smola Introduction to Machine Learning 10-701

3.1 Architecture 3 Systems Alexander Smola Introduction to Machine Learning 10-701

3.1 Architecture 3 Systems Alexander Smola Introduction to Machine Learning 10-701 http://alex.smola.org/teaching/10-701-15 Real Hardware Machines Bulk transfer is at least 10x faster CPU 8-64 cores (Intel/AMD servers) 2-3 GHz

892 views • 66 slides
Trustworthy decompilation: Extracting models of machine code inside an ITP Magnus O. Myreen

Trustworthy decompilation: Extracting models of machine code inside an ITP Magnus O. Myreen

Trustworthy decompilation: Extracting models of machine code inside an ITP Magnus O. Myreen University of Cambridge TEITP 2010 The GCD program in ARM machine code: E1510002 B0422001 C0411002 01AFFFFFB Problems with machine code Formal

660 views • 46 slides
UPPAAL tutorial Modeling Verification 1 2 Architecture of UPPAAL Whats inside UPPAAL

UPPAAL tutorial Modeling Verification 1 2 Architecture of UPPAAL Whats inside UPPAAL

UPPAAL Tool Simulation UPPAAL tutorial Modeling Verification 1 2 Architecture of UPPAAL Whats inside UPPAAL Linux, Windows, Solaris, MacOS 3 4 All Operations on Zones Inside the UPPAAL tool (needed for verification)

468 views • 13 slides
Inside Kepler Manuel Ujaldon Nvidia CUDA Fellow Computer Architecture Department University of

Inside Kepler Manuel Ujaldon Nvidia CUDA Fellow Computer Architecture Department University of

Inside Kepler Manuel Ujaldon Nvidia CUDA Fellow Computer Architecture Department University of Malaga (Spain) Talk outline [46 slides ] 1. Introducing the architecture [2] 2. Cores organization [9] 3. Memory and data transport [6] 4. Major

649 views • 63 slides
The openais Architecture An inside look at an implementation of SA Forum's AIS Steven Dake

The openais Architecture An inside look at an implementation of SA Forum's AIS Steven Dake

The openais Architecture An inside look at an implementation of SA Forum's AIS Steven Dake Presented by Tim Anderson 14 September 2004 1 History of openais Started life as cmgr in February 2002 Hotswap manager for ATCA

1.08k views • 31 slides
IN INSIDE A COMPUTER COMPUTER BU BUS S ARCHITECTURE ECE 422 DATA COMMUNICATIONS &

IN INSIDE A COMPUTER COMPUTER BU BUS S ARCHITECTURE ECE 422 DATA COMMUNICATIONS &

DATA COMMUNICATION IN INSIDE A COMPUTER COMPUTER BU BUS S ARCHITECTURE ECE 422 DATA COMMUNICATIONS & COMPUTER NETWORKS Friday, 13 March 2020 GENERAL BL BLOCK DIA IAGRAM OF TH THE COMPUTER SYSTEM Processing Input Output Input

639 views • 33 slides
Introduction to C++11 and its use inside Qt Olivier Goffart February 2013 1/43 Introduction to

Introduction to C++11 and its use inside Qt Olivier Goffart February 2013 1/43 Introduction to

Introduction to C++11 and its use inside Qt Olivier Goffart February 2013 1/43 Introduction to C++11 and its use inside Qt About Me http://woboq.com http://code.woboq.org 2/43 Introduction to C++11 and its use inside Qt History 1979: C

775 views • 51 slides
cse141: Introduction to Computer Architecture Steven Swanson Alice Liang 1 Todays Agenda

cse141: Introduction to Computer Architecture Steven Swanson Alice Liang 1 Todays Agenda

cse141: Introduction to Computer Architecture Steven Swanson Alice Liang 1 Todays Agenda What is architecture? Why is it important? Whats in this class? 2 Computer Architecture 3 What is architecture? How do you build a machine

949 views • 72 slides
AM A O SAbstract Machine for Xcerpt Principles Architecture PPSWR 06, Budva,

AM A O SAbstract Machine for Xcerpt Principles Architecture PPSWR 06, Budva,

AM A O SAbstract Machine for Xcerpt Principles Architecture PPSWR 06, Budva, Montenegro, June 11th, 2006 Franois Bry, Tim Furche , Benedikt Linse Abstract Machine(s) Definition and Variants abstract machine :=

339 views • 21 slides
INSIDE Mee)ng Report on the group ac)vi)es on the HW PET detector Back End Electronics 20

INSIDE Mee)ng Report on the group ac)vi)es on the HW PET detector Back End Electronics 20

INSIDE Mee)ng Report on the group ac)vi)es on the HW PET detector Back End Electronics 20 January 2016 G. Sportelli The INSIDE PET Back End Electronics Ini)al architecture Provide a full in-beam PET system able to sustain annihila)on

252 views • 14 slides
The New Global Invention Machine: A Look Inside the R&D Networks of U.S. Multinationals Lee

The New Global Invention Machine: A Look Inside the R&D Networks of U.S. Multinationals Lee

The New Global Invention Machine: A Look Inside the R&D Networks of U.S. Multinationals Lee Branstetter, Carnegie Mellon University and NBER Britta Glennon, University of Pennsylvania Brad Jensen, Georgetown University and NBER 1 Since

387 views • 19 slides
Cap 1 Introduction Introduction What is Parallel Architecture? Why Parallel Architecture?

Cap 1 Introduction Introduction What is Parallel Architecture? Why Parallel Architecture?

Cap 1 Introduction Introduction What is Parallel Architecture? Why Parallel Architecture? Adaptado dos slides da editora por Mario Crtes IC/Unicamp Evolution and Convergence of Parallel Architectures Fundamental Design Issues pag 1 2

1.47k views • 106 slides
CS 126 Lecture A1: TOY Machine Outline Introduction Toy machine Machine language

CS 126 Lecture A1: TOY Machine Outline Introduction Toy machine Machine language

CS 126 Lecture A1: TOY Machine Outline Introduction Toy machine Machine language instructions Example machine language programs Conclusions CS126 9-1 Randy Wang Brief History Leading to the Dominance of von Neumann

446 views • 33 slides
Best Practices for Deploying OpenStack Trove: An Inside look at Database as a Service Architecture

Best Practices for Deploying OpenStack Trove: An Inside look at Database as a Service Architecture

Best Practices for Deploying OpenStack Trove: An Inside look at Database as a Service Architecture OpenStack Summit at Barcelona, October 2016 Who are we? Sriram Kalyanasundaram, Director Implementations Tesora Inc. OpenStack Summit

812 views • 23 slides
Lanyrd's Inside Architecture Andrew Godwin Web Engineer, Lanyrd @andrewgodwin WHO AM I?

Lanyrd's Inside Architecture Andrew Godwin Web Engineer, Lanyrd @andrewgodwin WHO AM I?

Lanyrd's Inside Architecture Andrew Godwin Web Engineer, Lanyrd @andrewgodwin WHO AM I? Andrew Godwin Web developer Systems administrator Technical architect Django core developer LANYRD: THE EARLY YEARS The Origin Story LANYRD: THE

952 views • 55 slides
Results and summary of the award procedure for the fourth 3G licence 18 December 2009 Contents

Results and summary of the award procedure for the fourth 3G licence 18 December 2009 Contents

Results and summary of the award procedure for the fourth 3G licence 18 December 2009 Contents Context Analysis of the application Results Next stages 2 Fourth mobile operator planned for since 2000 The plan since

421 views • 18 slides
CS543 / ECE549 Computer Vision Spring 2020 Course webpage URL: https://s-gupta.github.io/ece549/

CS543 / ECE549 Computer Vision Spring 2020 Course webpage URL: https://s-gupta.github.io/ece549/

CS543 / ECE549 Computer Vision Spring 2020 Course webpage URL: https://s-gupta.github.io/ece549/ The goal of computer vision To extract meaning from pixels What we see What a computer sees Source: S. Narasimhan What kind of

425 views • 40 slides
The European Research Council: Excellent Researchers with Excellent Ideas The ERC Research at

The European Research Council: Excellent Researchers with Excellent Ideas The ERC Research at

The European Research Council: Excellent Researchers with Excellent Ideas The ERC Research at the Frontier In its own words, the ERCs mission is To encourage the work of the established and the next generation of independent

296 views • 16 slides
Handling Heterogeneous EO Datasets via the Web Coverage Processing Service Piero Campalani a* ,

Handling Heterogeneous EO Datasets via the Web Coverage Processing Service Piero Campalani a* ,

Handling Heterogeneous EO Datasets via the Web Coverage Processing Service Piero Campalani a* , Simone Mantovani b , Alan Beccati a , Peter Baumann a a a Jacobs University Bremen (DE) / b MEEO Srl (IT) * {p.campalani@jacobs-university.de FOSS4G

447 views • 27 slides
Engaging Information Professionals in the process of Authoritative Linked Data Interlinking

Engaging Information Professionals in the process of Authoritative Linked Data Interlinking

Engaging Information Professionals in the process of Authoritative Linked Data Interlinking 2018-11-28 at SWIB 2018 Lucy McKenna, Christophe Debruyne & Declan OSullivan ADAPT Centre, Trinity College Dublin, Ireland The ADAPT Centre is

410 views • 30 slides
Programme ^ / v]vP ]v ^ ]vo o}uv _ The

Programme ^ / v]vP ]v ^ ]vo o}uv _ The

EUROPEA N UNION Structural Instruments GOVERNMENT OF ROMANIA 2007-2013 Extreme Light Infrastructure-Nuclear Physics (ELI-NP) - Phase II Project co-financed by the European Regional Development Fund through the Competitiveness Operational

577 views • 30 slides
Scrutable & Persuasive Push-Notifications Kieran Fraser, Bilal Yousuf, Owen Conlan ADAPT

Scrutable & Persuasive Push-Notifications Kieran Fraser, Bilal Yousuf, Owen Conlan ADAPT

Scrutable & Persuasive Push-Notifications Kieran Fraser, Bilal Yousuf, Owen Conlan ADAPT Centre, Trinity College Dublin The ADAPT Centre is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the

673 views • 31 slides
Inferring Translation Candidates for Multilingual Dictionary Generation with Multi-Way Neural

Inferring Translation Candidates for Multilingual Dictionary Generation with Multi-Way Neural

Inferring Translation Candidates for Multilingual Dictionary Generation with Multi-Way Neural Machine Translation Mihael Arcan, Daniel Torregrosa*, Sina Ahmadi* and John P. McCrae This publication has emanated from research supported in part

591 views • 42 slides

More recommend