Introduction 9th January, 2006 CSL718 : Architecture of High Performance Systems.

Slides:



Advertisements
Similar presentations
Superscalar and VLIW Architectures Miodrag Bolic CEG3151.
Advertisements

SE-292 High Performance Computing
Multiprocessors— Large vs. Small Scale Multiprocessors— Large vs. Small Scale.
Instruction-Level Parallel Processors {Objective: executing two or more instructions in parallel} 4.1 Evolution and overview of ILP-processors 4.2 Dependencies.
Anshul Kumar, CSE IITD CSL718 : VLIW - Software Driven ILP Hardware Support for Exposing ILP at Compile Time 3rd Apr, 2006.
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:
Parallel computer architecture classification
Chapter 4 Advanced Pipelining and Intruction-Level Parallelism Computer Architecture A Quantitative Approach John L Hennessy & David A Patterson 2 nd Edition,
C SINGH, JUNE 7-8, 2010IWW 2010, ISATANBUL, TURKEY Advanced Computers Architecture, UNIT 1 Advanced Computers Architecture Lecture 4 By Rohit Khokher Department.
Anshul Kumar, CSE IITD CSL718 : Pipelined Processors PipelineTimings 12th Jan, 2006.
Taxanomy of parallel machines. Taxonomy of parallel machines Memory – Shared mem. – Distributed mem. Control – SIMD – MIMD.
Cache Coherent Distributed Shared Memory. Motivations Small processor count –SMP machines –Single shared memory with multiple processors interconnected.
CSCI 8150 Advanced Computer Architecture Hwang, Chapter 1 Parallel Computer Models 1.2 Multiprocessors and Multicomputers.
1 Introduction to MIMD Architectures Sima, Fountain and Kacsuk Chapter 15 CSE462.
1 COMP 206: Computer Architecture and Implementation Montek Singh Mon, Dec 5, 2005 Topic: Intro to Multiprocessors and Thread-Level Parallelism.
©UCB CS 162 Computer Architecture Lecture 1 Instructor: L.N. Bhuyan
Chapter 17 Parallel Processing.
Lecture 10 Outline Material from Chapter 2 Interconnection networks Processor arrays Multiprocessors Multicomputers Flynn’s taxonomy.
1 Computer Science, University of Warwick Architecture Classifications A taxonomy of parallel architectures: in 1972, Flynn categorised HPC architectures.
CMSC 611: Advanced Computer Architecture Parallel Computation Most slides adapted from David Patterson. Some from Mohomed Younis.
Chapter 5 Array Processors. Introduction  Major characteristics of SIMD architectures –A single processor(CP) –Synchronous array processors(PEs) –Data-parallel.
Computer Architecture Parallel Processing
Basics and Architectures
Anshul Kumar, CSE IITD CS718 : Data Parallel Processors 27 th April, 2006.
CS668- Lecture 2 - Sept. 30 Today’s topics Parallel Architectures (Chapter 2) Memory Hierarchy Busses and Switched Networks Interconnection Network Topologies.
1 Chapter 1 Parallel Machines and Computations (Fundamentals of Parallel Processing) Dr. Ranette Halverson.
Instruction-Level Parallelism for Low-Power Embedded Processors January 23, 2001 Presented By Anup Gangwar.
Outline Classification ILP Architectures Data Parallel Architectures
Shared Address Space Computing: Hardware Issues Alistair Rendell See Chapter 2 of Lin and Synder, Chapter 2 of Grama, Gupta, Karypis and Kumar, and also.
Chapter One Introduction to Pipelined Processors.
CHAPTER 12 INTRODUCTION TO PARALLEL PROCESSING CS 147 Guy Wong page
Chapter 2 Parallel Architecture. Moore’s Law The number of transistors on a chip doubles every years. – Has been valid for over 40 years – Can’t.
Chapter 6 Multiprocessor System. Introduction  Each processor in a multiprocessor system can be executing a different instruction at any time.  The.
Anshul Kumar, CSE IITD CSL718 : Multiprocessors Interconnection Mechanisms Performance Models 20 th April, 2006.
An Overview of Parallel Computing. Hardware There are many varieties of parallel computing hardware and many different architectures The original classification.
Anshul Kumar, CSE IITD CSL718 : Pipelined Processors  Types of Pipelines  Types of Hazards 16th Jan, 2006.
RISC architecture and instruction Level Parallelism (ILP) based on “Computer Architecture: a Quantitative Approach” by Hennessy and Patterson, Morgan Kaufmann.
Super computers Parallel Processing By Lecturer: Aisha Dawood.
1 Introduction CEG 4131 Computer Architecture III Miodrag Bolic.
CSE Advanced Computer Architecture Week-1 Week of Jan 12, 2004 engr.smu.edu/~rewini/8383.
Spring 2003CSE P5481 Issues in Multiprocessors Which programming model for interprocessor communication shared memory regular loads & stores message passing.
PARALLEL PROCESSOR- TAXONOMY. CH18 Parallel Processing {Multi-processor, Multi-computer} Multiple Processor Organizations Symmetric Multiprocessors Cache.
Anshul Kumar, CSE IITD Other Architectures & Examples Multithreaded architectures Dataflow architectures Multiprocessor examples 1 st May, 2006.
Pipelining and Parallelism Mark Staveley
Outline Why this subject? What is High Performance Computing?
CPS 258 Announcements –Lecture calendar with slides –Pointers to related material.
Winter-Spring 2001Codesign of Embedded Systems1 Essential Issues in Codesign: Architectures Part of HW/SW Codesign of Embedded Systems Course (CE )
VU-Advanced Computer Architecture Lecture 1-Introduction 1 Advanced Computer Architecture CS 704 Advanced Computer Architecture Lecture 1.
EE 382 Processor DesignWinter 98/99Michael Flynn 1 EE382 Processor Design Winter 1998 Chapter 8 Lectures Multiprocessors, Part I.
Lecture 13 Parallel Processing. 2 What is Parallel Computing? Traditionally software has been written for serial computation. Parallel computing is the.
COMP 740: Computer Architecture and Implementation
Parallel Architecture
CSL718 : Superscalar Processors
Parallel computer architecture classification
buses, crossing switch, multistage network.
CPE 731 Advanced Computer Architecture ILP: Part V – Multiple Issue
CS 147 – Parallel Processing
Morgan Kaufmann Publishers
MIMD Multiple instruction, multiple data
Superscalar Processors & VLIW Processors
buses, crossing switch, multistage network.
CC423: Advanced Computer Architecture ILP: Part V – Multiple Issue
Introduction SYSC5603 (ELG6163) Digital Signal Processing Microprocessors, Software and Applications Miodrag Bolic.
Chapter 4 Multiprocessors
COMPUTER ARCHITECTURES FOR PARALLEL ROCESSING
CSL718 : Multiprocessors 13th April, 2006 Introduction
The University of Adelaide, School of Computer Science
COMPUTER ORGANIZATION AND ARCHITECTURE
Presentation transcript:

Introduction 9th January, 2006 CSL718 : Architecture of High Performance Systems

Anshul Kumar, CSE IITD slide 2 High Performance Architectures Who needs high performance systems? How do you achieve high performance? How to analyse or evaluate performance?

Anshul Kumar, CSE IITD slide 3 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks

Anshul Kumar, CSE IITD slide 4 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks Flynn’s[66] Feng’s[72] Händler’s[77] Modern (Sima, Fountain & Kacsuk)

Anshul Kumar, CSE IITD slide 5 Flynn’s Classification Architecture Categories SISDSIMDMISDMIMD

Anshul Kumar, CSE IITD slide 6 SISDSISD CP M IS DS

Anshul Kumar, CSE IITD slide 7 SIMDSIMD C P P M IS DS

Anshul Kumar, CSE IITD slide 8 MISDMISD C C P P M IS DS

Anshul Kumar, CSE IITD slide 9 MIMDMIMD C C P P M IS DS

Anshul Kumar, CSE IITD slide 10 Feng’s Classification K word length bit slice length MPP STARAN C.mmP PDP11 PEPE IBM370 IlliacIV CRAY-1

Anshul Kumar, CSE IITD slide 11 Händler’s Classification control data word dash  degree of pipelining TI - ASC CDC 6600 x (I/O) C.mmP + + PEPE Cray-1

Anshul Kumar, CSE IITD slide 12 Modern Classification Parallel architectures Data-parallel architectures Function-parallel architectures

Anshul Kumar, CSE IITD slide 13 Data Parallel Architectures Data-parallel architectures Vector architectures Associative And neural architectures SIMDs Systolic architectures

Anshul Kumar, CSE IITD slide 14 Function Parallel Architectures Function-parallel architectures Instr level Parallel Arch Thread level Parallel Arch Process level Parallel Arch (ILPs) (MIMDs) Pipelined processors VLIWs Superscalar processors Distributed Memory MIMD Shared Memory MIMD

Anshul Kumar, CSE IITD slide 15 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks Pipelining VLIW Superscalar

Anshul Kumar, CSE IITD slide 16 PipeliningPipelining IF D RF EX/AG M WB faster throughput with pipelining Simple multicycle design : resource sharing across cycles all instructions may not take same cycles

Anshul Kumar, CSE IITD slide 17 Hazards in Pipelining Procedural dependencies => Control hazards –conditional and unconditional branches, calls/returns Data dependencies => Data hazards –RAW (read after write) –WAR (write after read) –WAW (write after write) Resource conflicts => Structural hazards –use of same resource in different stages

Anshul Kumar, CSE IITD slide 18 Pipeline Performance CPI = 1 + (S - 1) * b Time = CPI * T / S T S stages Frequency of interruptions - b

Anshul Kumar, CSE IITD slide 19 Cache/ memory Fetch Unit Single multi-operation instruction multi-operation instruction FU Register file ILP in VLIW processors

Anshul Kumar, CSE IITD slide 20 Cache/ memory Fetch Unit Multiple instruction Sequential stream of instructions FU Register file Decode and issue unit Instruction/control Data FUFuntional Unit ILP in Superscalar processors

Anshul Kumar, CSE IITD slide 21 Why Superscalars are popular ? Binary code compatibility among scalar & superscalar processors of same family Same compiler works for all processors (scalars and superscalars) of same family Assembly programming of VLIWs is tedious Code density in VLIWs is very poor - Instruction encoding schemes

Anshul Kumar, CSE IITD slide 22 FU Register file Instruction encoding Scalability: Access time, area, power consumption sharply increase with number of register ports Issues in VLIW Architecture

Anshul Kumar, CSE IITD slide 23 Tasks of superscalar processing Parallel Superscalar Parallel Preserving the Preserving the decoding instruction instruction sequential sequential issue execution consistency of consistency of execution exception processing

Anshul Kumar, CSE IITD slide 24 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks SIMD Processors Vector Processors Associative Processors Systolic Arrays

Anshul Kumar, CSE IITD slide 25 Data Parallel Architectures SIMD Processors –Multiple processing elements driven by a single instruction stream Vector Processors –Uni-processors with vector instructions Associative Processors –SIMD like processors with associative memory Systolic Arrays –Application specific VLSI structures

Anshul Kumar, CSE IITD slide 26 Systolic Arrays [ H.T. Kung 1978] Simplicity, Regularity, Concurrency, Communication Example : Band matrix multiplication

B 11 B 12 B 21 B 31 A 11 A 12 A 21 A 22 A 31 A 23 T=0

Anshul Kumar, CSE IITD slide 28 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks MIMD Processors - Shared Memory - Distributed Memory

Anshul Kumar, CSE IITD slide 29 Why Process level Parallel Architectures? Function-parallel architectures Instruction level PAs Thread level PAs Process level PAs (MIMDs) Distributed Memory MIMD Shared Memory MIMD Data-parallel architectures Built using general purpose processors

Anshul Kumar, CSE IITD slide 30 MIMD Architectures Design Space Extent of address space sharing Location of memory modules Uniformity of memory access

Anshul Kumar, CSE IITD slide 31 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks User’s perspective Architect’s perspective

Anshul Kumar, CSE IITD slide 32 Issues from user’s perspective Specification / Program design –explicit parallelism or –implicit parallelism + parallelizing compiler Partitioning / mapping to processors Scheduling / mapping to time instants –static or dynamic Communication and Synchronization

Anshul Kumar, CSE IITD slide 33 Parallel programming models Concurrent control flow Functional or logic program Vector/array operations Concurrent tasks/processes/threads/objects With shared variables or message passing Relationship between programming model and architecture ?

Anshul Kumar, CSE IITD slide 34 Issues from architect’s perspective Coherence problem in shared memory with caches Efficient interconnection networks

Anshul Kumar, CSE IITD slide 35 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks Coherence Protocols - Bus or directory based - Invalidate or update - Definition of states

Anshul Kumar, CSE IITD slide 36 Cache Coherence Problem Multiple copies of data may exist  Problem of cache coherence Options for coherence protocols What action is taken? –Invalidate or Update Which processors/caches communicate? –Snoopy (broadcast) or directory based Status of each block?

Anshul Kumar, CSE IITD slide 37 OutlineOutline Classification ILP Architectures Data Parallel Architectures Process level Parallel Architectures Issues in parallel architectures Cache coherence problem Interconnection networks Switching and control Topology

Anshul Kumar, CSE IITD slide 38 Interconnection Networks Architectural Variations: –Topology –Direct or Indirect (through switches) –Static (fixed connections) or Dynamic (connections established as required) –Routing type store and forward/worm hole) Efficiency: –Delay –Bandwidth –Cost

Anshul Kumar, CSE IITD slide 39 BooksBooks D. Sima, T. Fountain, P. Kacsuk, "Advanced Computer Architectures : A Design Space Approach", Addison Wesley, M.J. Flynn, "Computer Architecture : Pipelined and Parallel Processor Design", Narosa Publishing House/ Jones and Bartlett, D.A. Patterson, J.L. Hennessy, "Computer Architecture : A Quantitative Approach", Morgan Kaufmann Publishers, K. Hwang, "Advanced Computer Architecture : Parallelism, Scalability, Programmability", McGraw Hill, H.G. Cragon, "Memory Systems and Pipelined Processors", Narosa Publishing House/ Jones and Bartlett, D.E. Culler, J.P Singh and Anoop Gupta, "Parallel Computer Architecture, A Hardware/Software Approach", Harcourt Asia / Morgan Kaufmann Publishers, 2000.