Topic ? Course Overview. Guidelines Questions are rated by stars –One Star Question  Easy. Small definition, examples or generic formulas –Two Stars.

Slides:



Advertisements
Similar presentations
SE-292 High Performance Computing
Advertisements

ILP: IntroductionCSCE430/830 Instruction-level parallelism: Introduction CSCE430/830 Computer Architecture Lecturer: Prof. Hong Jiang Courtesy of Yifeng.
Lecture 8 Dynamic Branch Prediction, Superscalar and VLIW Advanced Computer Architecture COE 501.
CPE 731 Advanced Computer Architecture ILP: Part V – Multiple Issue Dr. Gheith Abandah Adapted from the slides of Prof. David Patterson, University of.
POLITECNICO DI MILANO Parallelism in wonderland: are you ready to see how deep the rabbit hole goes? ILP: VLIW Architectures Marco D. Santambrogio:
Dynamic Branch PredictionCS510 Computer ArchitecturesLecture Lecture 10 Dynamic Branch Prediction, Superscalar, VLIW, and Software Pipelining.
5.1 Silberschatz, Galvin and Gagne ©2009 Operating System Concepts with Java – 8 th Edition Chapter 5: CPU Scheduling.
C SINGH, JUNE 7-8, 2010IWW 2010, ISATANBUL, TURKEY Advanced Computers Architecture, UNIT 1 Advanced Computers Architecture Lecture 4 By Rohit Khokher Department.
Computer Architecture Introduction to MIMD architectures Ola Flygt Växjö University
Introductory Courses in High Performance Computing at Illinois David Padua.
Static Analysis of Embedded C Code John Regehr University of Utah Joint work with Nathan Cooprider.
Chapter 3 Instruction-Level Parallelism and Its Dynamic Exploitation – Concepts 吳俊興 高雄大學資訊工程學系 October 2004 EEF011 Computer Architecture 計算機結構.
1 COMP 206: Computer Architecture and Implementation Montek Singh Mon, Dec 5, 2005 Topic: Intro to Multiprocessors and Thread-Level Parallelism.
Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania ECE Computer Organization Lecture 19 - Pipelined.
Instruction Level Parallelism (ILP) Colin Stevens.
Multiprocessors Andreas Klappenecker CPSC321 Computer Architecture.
Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania Computer Organization Pipelined Processor Design 3.
Microprocessors Introduction to ia64 Architecture Jan 31st, 2002 General Principles.
12/1/2005Comp 120 Fall December Three Classes to Go! Questions? Multiprocessors and Parallel Computers –Slides stolen from Leonard McMillan.
1 Computer Engineering Department Islamic University of Gaza ECOM 6301: Selected Topics in Computer Architectures (Graduate Course) Fall Prof.
Memory Consistency Models Some material borrowed from Sarita Adve’s (UIUC) tutorial on memory consistency models.
Advances in Language Design
Lecture 4: Parallel Programming Models. Parallel Programming Models Parallel Programming Models: Data parallelism / Task parallelism Explicit parallelism.
Parallel Computing Basic Concepts Computational Models Synchronous vs. Asynchronous The Flynn Taxonomy Shared versus Distributed Memory Interconnection.
18-447: Computer Architecture Lecture 30B: Multiprocessors Prof. Onur Mutlu Carnegie Mellon University Spring 2013, 4/22/2013.
HPC Technology Track: Foundations of Computational Science Lecture 2 Dr. Greg Wettstein, Ph.D. Research Support Group Leader Division of Information Technology.
Introduction 9th January, 2006 CSL718 : Architecture of High Performance Systems.
Outline Classification ILP Architectures Data Parallel Architectures
1 Advance Computer Architecture CSE 8383 Ranya Alawadhi.
2015/10/14Part-I1 Introduction to Parallel Processing.
Multiprocessors Speed of execution is a paramount concern, always so … If feasible … the more simultaneous execution that can be done on multiple computers.
Evaluating FERMI features for Data Mining Applications Masters Thesis Presentation Sinduja Muralidharan Advised by: Dr. Gagan Agrawal.
ECE200 – Computer Organization Chapter 9 – Multiprocessors.
Spring 2003CSE P5481 Midterm Philosophy What the exam looks like. Definitions, comparisons, advantages & disadvantages what is it? how does it work? why.
Shared Memory Consistency Models. SMP systems support shared memory abstraction: all processors see the whole memory and can perform memory operations.
DISTRIBUTED COMPUTING
RSIM: An Execution-Driven Simulator for ILP-Based Shared-Memory Multiprocessors and Uniprocessors.
Vector and symbolic processors
Outline Why this subject? What is High Performance Computing?
1 Introduction ELG 6158 Digital Systems Architecture Miodrag Bolic.
CPS 258, Fall 2004 Introduction to Computational Science.
3/12/2013Computer Engg, IIT(BHU)1 INTRODUCTION-1.
Final Review Prof. Mike Schulte Advanced Computer Architecture ECE 401.
CPS 258 Announcements –Lecture calendar with slides –Pointers to related material.
LECTURE #1 INTRODUCTON TO PARALLEL COMPUTING. 1.What is parallel computing? 2.Why we need parallel computing? 3.Why parallel computing is more difficult?
Computer Science and Engineering Parallel and Distributed Processing CSE 8380 April 28, 2005 Session 29.
Corse Overview Miodrag Bolic ELG7187 Topics in Computers: Multiprocessor Systems on Chip.
Lecture 1: Introduction CprE 585 Advanced Computer Architecture, Fall 2004 Zhao Zhang.
Elec/Comp 526 Spring 2015 High Performance Computer Architecture Instructor Peter Varman DH 2022 (Duncan Hall) rice.edux3990 Office Hours Tue/Thu.
Introduction to Parallel Processing
COMP 740: Computer Architecture and Implementation
Advanced Architectures
18-447: Computer Architecture Lecture 30B: Multiprocessors
Computer Architecture Principles Dr. Mike Frank
CPE 731 Advanced Computer Architecture ILP: Part V – Multiple Issue
Computer Architecture Principles Dr. Mike Frank
Martin Rinard Laboratory for Computer Science
L21: Putting it together: Tree Search (Ch. 6)
ECE/CS 757: Advanced Computer Architecture II
Coe818 Advanced Computer Architecture
Threading And Parallel Programming Constructs
Shared Memory Programming
CC423: Advanced Computer Architecture ILP: Part V – Multiple Issue
Lecture 25: Multiprocessors
EE 4xx: Computer Architecture and Performance Programming
Overview Prof. Eric Rotenberg
Lecture 24: Multiprocessors
Lecture 19: Coherence and Synchronization
The University of Adelaide, School of Computer Science
Presentation transcript:

Topic ? Course Overview

Guidelines Questions are rated by stars –One Star Question  Easy. Small definition, examples or generic formulas –Two Stars Questions  Medium. Long definitions or formulas –Three Stars Questions  Hard. A long exercise or definition with an example –Four Stars Questions  Very Hard. A time consuming question. Either a very large number of definitions referring to a topic or a time consuming exercise All questions have the same value Twelve must be answered –At least one per section Three extra credit questions are permitted Twenty four questions in total Attempt the one and two starts questions first.

Guidelines No project related topics will be in the final –No MESI But an architecture which implements it or other protocol from the MSI family –No Dimension Order Routing But routing in any other network type No specific architecture examples will be asked –Only the ones that are referred by name in this overview

Total Slide Count Topic 1112 Topic 288 Topic 3109 Topic 4100 Topic 564 Topic 6225 Total698 Not counting Tutorials or this set nor the Homework Solutions

Topic 1 Introduction to the general concepts of parallel machines and their components Different types of computers –Flynn’s Taxonomy –ILP Classification –Structural Composition The Illiac IV Supercomputer –Type –Interconnect network –Components and Configurations Denelcor HEP and the Tera’s MTA –Main Idea and parallelism exploitation SPMD –What is it?

Topic 1 Amdahl’s Law –Definition of both old and revised Interconnection Network –Main Concepts –Main Attributes of Networks –Different Types of networks What are they and their main attributes. –Routing along different networks

Topic 2 Vector Processors and Processing Vector problems and advantages –Stride and length –No data hazards, known access pattern and reduction of code size Cray 1 –Components Registers and functional units Vector Chaining Types of Vector operations Reservations Cray X-MP –Irregular vector operations Performance Analysis –Asymptotic Performance Parameter and the n ½ parameter –Serial, vector and vector chaining performance Vectors and Memory Systems –Finding and reducing contention between different memory modules

Topic 3 Hazards ILP and its exploitation Static ILP –VLIW and several static techniques Software Pipelining, loop unrolling, and trace scheduling Examples and limitations Dynamic ILP –Scoreboarding Approach Steps and Data hazards detection and resolution Components –Reorder Buffer Steps and Data hazards detection and resolution Components –Tomasulo Algorithm Steps and Data hazards detection and resolution Components –Comparison, advantages and disadvantages of each approach Comparison between Static and Dynamic ILP Examples of VLIW and Superscalar –Pentium 4 and its Out of Order Engine –TMSC62XXX DSP family of processors

Topic 4 TLP and SMT –Definitions and implementations Components of the Shared Memory Execution Model Coherence V.S. Consistency –Definitions and differences –MCM Attributes and Myths –Types of coherences Hybrid and uniform models –Sequential consistency and Hybrid-weaker consistency models SC definition and sufficient conditions Category of Access Definition and classification. –Sequential Consistency Compliancy –Cache Coherency Models States and rationale –DASH architecture Memory hierarchy, coherence and consistency models

Topic 5 Atomicity –Definition and Data Races Locks and Barriers –Implementations –Advantages and disadvantages –Main features of all implementations Higher Abstraction synchronization constructs –Semaphores –Mutex –Barriers –Critical Sections –Monitors –Conditional Variables Performance Characterization –Formulas and calculations

Topic 6 Dataflow –Actors, Snapshots and tokens Definitions, graphs and Schemes –Well behaved and Well Formed graphs Definitions –Static Versus Dynamic Dataflow Rationale behind their creation Main differences Advantages and Disadvantages of each approach –Recursive Program Graphs Tail Recursion –The I Structure Usage, definitions and operations –EARTH Model Synchronization and thread models

Topic 6 Transactional Memory –Main properties of TM –Definition of a transaction –Data versioning and Conflict detection Types Pros and cons for each approach –Nested Transactions Open and Close –Definitions and characteristics

Final Note GOOD LUCK!!!! Don’t worry too much –It is not as difficult as it sounds