E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS 4130 - Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University Instruction.

Slides:



Advertisements
Similar presentations
Instruction Level Parallelism and Superscalar Processors
Advertisements

Machine cycle.
PIPELINE AND VECTOR PROCESSING
Computer architecture
RISC and Pipelining Prof. Sin-Min Lee Department of Computer Science.
Computer Architecture Lecture 2 Abhinav Agarwal Veeramani V.
1 Advanced Computer Architecture Limits to ILP Lecture 3.
Lecture Objectives: 1)Define pipelining 2)Calculate the speedup achieved by pipelining for a given number of instructions. 3)Define how pipelining improves.
10/11: Lecture Topics Slides on starting a program from last time Where we are, where we’re going RISC vs. CISC reprise Execution cycle Pipelining Hazards.
ΜP rocessor Architectures To : Eng. Ahmad Hassan By: Group 18.
Extending the Unified Parallel Processing Speedup Model Computer architectures take advantage of low-level parallelism: multiple pipelines The next generations.
PZ13A Programming Language design and Implementation -4th Edition Copyright©Prentice Hall, PZ13A - Processor design Programming Language Design.
Midterm Wednesday Chapter 1-3: Number /character representation and conversion Number arithmetic Combinational logic elements and design (DeMorgan’s Law)
Chapter 2.2 Machine Language.
RISC. Rational Behind RISC Few of the complex instructions were used –data movement – 45% –ALU ops – 25% –branching – 30% Cheaper memory VLSI technology.
11/11/05ELEC CISC (Complex Instruction Set Computer) Veeraraghavan Ramamurthy ELEC 6200 Computer Architecture and Design Fall 2005.
Computer ArchitectureFall 2008 © October 6th, 2008 Majd F. Sakr CS-447– Computer Architecture.
(6.1) Central Processing Unit Architecture  Architecture overview  Machine organization – von Neumann  Speeding up CPU operations – multiple registers.
RISC CSS 548 Joshua Lo.
Prince Sultan College For Woman
RISC and CISC. Dec. 2008/Dec. and RISC versus CISC The world of microprocessors and CPUs can be divided into two parts:
Basics and Architectures
RISC:Reduced Instruction Set Computing. Overview What is RISC architecture? How did RISC evolve? How does RISC use instruction pipelining? How does RISC.
Very Long Instruction Word (VLIW) Architecture. VLIW Machine It consists of many functional units connected to a large central register file Each functional.
X86 Assembly Language Same Assembly Language for 8086,80286,80386,80486,Pentium I II and III Newer Processors add a few instructions but include all instructions.
What have mr aldred’s dirty clothes got to do with the cpu
RISC Architecture RISC vs CISC Sherwin Chan.
RISC architecture and instruction Level Parallelism (ILP) based on “Computer Architecture: a Quantitative Approach” by Hennessy and Patterson, Morgan Kaufmann.
The Central Processing Unit (CPU) and the Machine Cycle.
Chapter 2 Data Manipulation © 2007 Pearson Addison-Wesley. All rights reserved.
Chapter 2 Data Manipulation. © 2005 Pearson Addison-Wesley. All rights reserved 2-2 Chapter 2: Data Manipulation 2.1 Computer Architecture 2.2 Machine.
Ted Pedersen – CS 3011 – Chapter 10 1 A brief history of computer architectures CISC – complex instruction set computing –Intel x86, VAX –Evolved from.
RISC and CISC. What is CISC? CISC is an acronym for Complex Instruction Set Computer and are chips that are easy to program and which make efficient use.
Classic Model of Parallel Processing
Data Management for Decision Support Session-4 Prof. Bharat Bhasker.
Pipelining and Parallelism Mark Staveley
Stored Programs In today’s lesson, we will look at: what we mean by a stored program computer how computers store and run programs what we mean by the.
Sogang University Advanced Computing System Chap 2. Processor Technology Hyuk-Jun Lee, PhD Dept. of Computer Science and Engineering Sogang University.
Represents different voltage levels High: 5 Volts Low: 0 Volts At this raw level a digital computer is instructed to carry out instructions.
Cs 147 Spring 2010 Meg Genoar. History Started to emerge in mid-1970s 1988 – RISC took over workstation market.
E X C E E D I N G E X P E C T A T I O N S L3-CPU IS 4490 N-Tier Client/Server Architectures Dr. Hoganson Kennesaw State University Layer 3 - CPU CPU has.
CSIS Parallel Architectures and Algorithms Dr. Hoganson Speedup Summary Balance Point The basis for the argument against “putting all your (speedup)
Pipelining Pipelining is a design feature that allows multiple instructions to be run simultaneously. Speeds up the execution of instruction processing.
Chapter 2 Data Manipulation © 2007 Pearson Addison-Wesley. All rights reserved.
3/12/2013Computer Engg, IIT(BHU)1 CONCEPTS-1. Pipelining Pipelining is used to increase the speed of processing It uses temporal parallelism In pipelining,
RISC / CISC Architecture by Derek Ng. Overview CISC Architecture RISC Architecture  Pipelining RISC vs CISC.
CISC. What is it?  CISC - Complex Instruction Set Computer  CISC is a design philosophy that:  1) uses microcode instruction sets  2) uses larger.
1  2004 Morgan Kaufmann Publishers No encoding: –1 bit for each datapath operation –faster, requires more memory (logic) –used for Vax 780 — an astonishing.
1 Processor design Programming Language Design and Implementation (4th Edition) by T. Pratt and M. Zelkowitz Prentice Hall, 2001 Section 11.3.
Computer Organization CS345 David Monismith Based upon notes by Dr. Bill Siever and from the Patterson and Hennessy Text.
Immediate Addressing Mode
Central Processing Unit Architecture
William Stallings Computer Organization and Architecture 8th Edition
Scalable Processor Design
CISC (Complex Instruction Set Computer)
MIPS Assembly.
Figure 8.1 Architecture of a Simple Computer System.
CISC AND RISC SYSTEM Based on instruction set, we broadly classify Computer/microprocessor/microcontroller into CISC and RISC. CISC SYSTEM: COMPLEX INSTRUCTION.
Figure 8.1 Architecture of a Simple Computer System.
Chapter 2: Data Manipulation
Data Dependence Distances
PIPELINING Santosh Lakkaraju CS 147 Dr. Lee.
Chapter 2: Data Manipulation
Processor design Programming Language Design and Implementation (4th Edition) by T. Pratt and M. Zelkowitz Prentice Hall, 2001 Section 11.3.
Machine Language.
Course Outline for Computer Architecture
Processor design Programming Language Design and Implementation (4th Edition) by T. Pratt and M. Zelkowitz Prentice Hall, 2001 Section 11.3.
Chapter 2: Data Manipulation
Pipelining.
Presentation transcript:

E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University Instruction Sets Instruction Set: the set of instructions that the CPU has been designed to perform Defines the Machine Code, and Assembly Language One major area of variation is the handling of OPERANDS OPERANDS - the data values that the instruction works with –Register operands - values store in the CPU in registers –Memory operands - values stored in memory, that must be loaded into the CPU before the instruction can be executed Instruction sets vary –as to how many operands from memory are allowed –how many total instructions in the set –can an instruction be fetched and used in same instruction?

E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University CISC CISC - Complex Instruction Set Computer Large set of instruction Instructions are complex: they can do many things and operate upon multiple operands Can execute instructions that also require operands from memory Increases cost/size/transistor count of the instruction decoder STRUCTURAL HAZARDs present with pipelines –Instruction Fetch and Operand Fetch

E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University RISC RISC - Reduced Instruction Set Computer Instructions that fetch or store operands do nothing else Fewer instructions in set reduces STRUCTURAL HAZARDS - allowing higher speedups with more pipelines and more stages per pipeline more instructions required to do the same work DESIGN TRADEOFF - RISC is less work per instruction, but supports more instructions per time unit with high pipeline speedups

E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University RISC/CISC Sim Lab Demo of simulator CISC architecture - –Single pipe –five stages –1000 instructions, –single processor –flush and stall at 0.0 –100 interations –=3.982 Speedup CISC with flush at 30%-70% ( ) –= 1.35

E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University RISC/CISC Sim Lab RISC architecture - –Single pipe –five stages –2000 instructions, –single processor –flush at –100 interations –=3.35 Speedup

E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University Simulation comparison CISC at 1.35 speedup for 1000 instructions = 1/1.35 time units –0.74 time RISC at 3.35 speedup for 2000 instructions = 2/3.35 time units –0.59 time Even though the RISC machine had to do twice as many instructions for the same amount of work, because it ran at higher speedups, it completed the workload in less time.

E X C E E D I N G E X P E C T A T I O N S VLIW-RISC CSIS Parallel Architectures and Algorithms Dr. Hoganson Kennesaw State University VLIW VLIW - Very Long Instruction Word Convert CISC instructions to RISC instructions Store converted instructions in VLIW Send VLIW to RISC execution core for execution on multiple pipelines