代写代考 CS2305: Computer Architecture

CS2305: Computer Architecture
Fundamentals of Computer Design
(Computer Architecture: Chapter 1 )

Copyright By PowCoder代写 加微信 powcoder

Department of Computer Science and Engineering

Fundamentals Defining Computer Architecture Agenda
 Introduction
 Classes of Computers
 1.3 Defining Computer Architecture  Trends in Technology
 Trends in Power and Energy in ICs  Trends in Cost
 Dependability
 Measuring Performance
 Quantitative Principles

Fundamentals Defining Computer Architecture Defining Computer Architecture
“Old” view of computer architecture:
Instruction Set Architecture (ISA) design
i.e., decisions regarding:
 registers, memory addressing, addressing modes, instruction operands, available operations, control flow instructions, instruction encoding
The ISA is roughly the same as the programming model of a processor as seen by an assembly language programmer or compiler writer.

Fundamentals
Instruction Set Architecture
Applications
Operating System Firmware
Instruction Set Architecture Instruction Set Processor
I/O System
Datapath & Control Digital Design Circuit Design Layout
S/W and H/W consists of hierarchical layers of abstraction, each hides details of lower layers from the above layer
The instruction set arch. abstracts the H/W and S/W interface and allows many implementation of varying cost and performance to run the same S/W

Fundamentals
Contents of Instruction Set Architecture
Registers
Class of ISA
Memory addressing  Byte addressing
Addressing modes
Types and sizes of operands Operations
Control flow instructions
Encoding an ISA
 Fixed length and variable length

Fundamentals
Addressing Modes
Example Instruction
Register Immediate Displacement
Add R4, #3
Add R4, 100(R1)
R4 <- R4 + R3 R4 <- R4 + 3 R4 <- R4 + M[100+R1] Register deferred Add R4,(R1) R4 <- R4 + M[R1] Add R3, (R1 + R2) R3 <- R3 + M[R1+R2] Memory deferred Add R1, (1001) Add R1, @(R3) R1 <- R1 + M[1001] R1 <- R1 + M[M[R3]] Auto- increment Add R1, (R2)+ Add R1,-(R2) Add R1, 100(R2)[R3] R1 <- R1 +M[R2] R2 <- R2 + d Auto- decrement R1 <- R1 + M[R2] R1<-R1+M[100+R2+R3*d] Fundamentals Example ISAs  ARMv1-v7  ARMv7 extensions  Thumb-2  IBM 8100 instructions)  SSE4 – All streaming SIMD extensions 4 instructions (both  NEON – media acceleration technology[8]  x86 extensions  FPU (x87) – Floating-point-unit (FPU) instructions  MMX – MMX SIMD instructions  MMX Extended – extended MMX SIMD instructions  SSE – streaming SIMD extensions (SSE) instructions (70  VFP v3  HP 2100 instructions)  SSE2 – streaming SIMD extensions 2 instructions (144 new instructions)  SSE3 – streaming SIMD extensions 3 instructions (13 new  IBM Series SSE4.1 and SSE4.2)  SSE4a – streaming SIMD extensions 4a (AMD)  SSE5 – streaming SIMD extensions 5 (170 instructions)  XSAVE – XSAVE instructions  AVX – advanced vector extensions instructions  FMA – fused multiply-add instructions  AES – Advanced Encryption Standard instructions  CLMUL – Carry-less mtiply (PCLMULQDQ) instruction  3DNow![citation needed] – 3DNow! instructions (21  Power Architecture  POWER instructions)  3DNow! Extended – extended 3DNow! instructions (5  PowerPC AS instructions)  Cyrix – Cyrix-specific instructions  AMD – AMD-specific instructions (older than K6)  SMM – System management mode instructions  SVM – Secure virtual machine instructions  PadLock – VIA PadLock instructions instructions)  SSSE3 – supplemental streaming SIMD extensions (16 instructions)  SSE4.1 – streaming SIMD extensions 4, Penryn subset (47 instructions)  SSE4.2 – streaming SIMD extensions 4, Nehalem subset (7 Fundamentals MIPS Instruction Fields MIPS fields are given names to make them easier to refer to rd 5-bits shamt 5-bits funct 6-bits opcode that specifies the operation register file address of the first source operand register file address of the second source operand register file address of the result’s destination shift amount (for shift instructions) function code augmenting the opcode op rs rt rd shamt funct Fundamentals MIPS Addressing Modes Examples 1. Register addressing op rs rt rd funct Register word operand 2. Immediate addressing op rs rt operand 3. Base (displacement) addressing op rs rt offset base register word or byte operand 4. PC-relative addressing op rs rt offset Program Counter (PC) branch destination instruction Fundamentals Microarchitecture  microarchitecture, also called computer organization, is the way a given ISA is implemented on a processor.  A given ISA may be implemented with different microarchitectures.  The microarchitecture includes the constituent parts of the processor and how these interconnect and interoperate to implement the ISA. Intel i80286 microarchitecture Fundamentals Microarchitectural Concepts Instruction pipelining Hierarchical memory organization Cache Cache coherence Branch prediction Superscalar Out-of-order execution Register renaming Multiprocessing and multithreading Fundamentals Computer Architecture in General When we construct a building numerous practical considerations need to be taken into account: • Available materials • Worker skills • Budget Similarly, Computer Architecture is about working within constraints: • What will the market buy? • Cost/Performance • Tradeoffs in materials and processes Fundamentals Genuine Computer Architecture  Genuine definition: Designing the organization and hardware to meet goals and functional requirements  The implementation of a computer involves two components 1) organization (or microarchitecture) 2) hardware: detailed logic design and packaging  In this course, computer architecture covers all the three: (2) microarchitecture or organization, and (3) hardware Fundamentals Trends in Technology Agenda  Introduction  Classes of Computers  Defining Computer Architecture  1.4 Trends in Technology  Trends in Power and Energy in ICs  Trends in Cost  Dependability  Measuring Performance  Quantitative Principles Fundamentals Rapid Changes in Technology If an ISA is successful, it should survive rapid changes in implementation technology The designer of a computer should be aware of such rapid changes Five implementation technologies are critical to model implementations of computer design Fundamentals Five Critical Implementation Techs Integrated circuit logic technology • As Moore’s law, the transistors count doubles every 18-24 months Semiconductor DRAM • The capacity per DRAM chip doubles every two to three years Semiconductor Flash • Capacity doubles roughly every two years • Capacity doubles every three years • Bandwidth increases quickly Magnetic disk technology Network technology Fundamentals ENIAC - background Electronic Numerical Computer Eckert and Mauchly, University of Pennsylvania Purpose: Trajectory tables for weapons (1907-1980) & J. (1919-1995) Started 1943, Finished 1946 Too late for war effort Used until 1955 Fundamentals ENIAC - details  Decimal (not binary)  20 accumulators of 10 digits  Programmed manually by switches  18,000 vacuum tubes  15,000 square feet  140 kW power consumption  5,000 additions per second Fundamentals Transistors – the 2nd generation Replaced vacuum tubes  Advantages Smaller Less heat dissipation First working transisto Solid state device Made from Silicon (Sand) Invented 1947 at Bell Labs , and at Bell Labs, 1948. Fundamentals Transistor Based Computers Second generation machines NCR & RCA produced small transistor machines Produced IBM 7000 DEC - 1957 Produced PDP-1 Fundamentals Microelectronics – 3rd Generation Literally - “small electronics” A computer is made up of gates, memory cells and interconnections These can be manufactured on a semiconductor e.g. silicon wafer Fundamentals Trends in Technology Agenda  Introduction  Classes of Computers  Defining Computer Architecture  1.4 Trends in Technology  Trends in Power and Energy in ICs  Trends in Cost  Dependability  Measuring Performance  Quantitative Principles Fundamentals Trends in Technology Two Metrics: Bandwidth and Latency Bandwidth or throughput • Total work done in a given time • 10,000-25,000X improvement for processors • 300-1200X improvement for memory and disks Latency or response time • Time between start and completion of an event • 30-80X improvement for processors • 6-8X improvement for memory and disks Fundamentals Milestones for 1) microprocessors, 2) memory, 3) networks, and Fundamentals Trends in Technology Bandwidth and Latency  Latency improved 6x to 80x  Throughput improved 300x to 25,000x  Bandwidth has outpaced latency! Log-log plot of bandwidth and latency milestones Fundamentals Trends in Technology Feature Size and Its Impacts Feature size is the minimum size of transistor or wire in x or y dimension  Integration density scales quadratically with feature size 10 microns in 1971 to .032 microns in 2011 Wire delay does not scale well with feature Wire delay is proportional to the product of resistance and capacitance Fundamentals Trends in Power Agenda  Introduction  Classes of Computers  Defining Computer Architecture  Trends in Technology  1.5 Trends in Power and Energy in ICs  Trends in Cost  Dependability  Measuring Performance  Quantitative Principles Fundamentals Trends in Technology Power and Energy Problem: Get power in, get power or heat out  Thermal Design Power (TDP)  Characterizes sustained power consumption  Used as target for power supply and cooling system  Lower than peak power, higher than average power consumption  Clock rate can be reduced dynamically to limit power consumption Fundamentals Trends in Technology Dynamic Energy and Power  Dynamic energy per transistor  Used for a transistor switching from 0 -> 1 or 1 -> 0  1⁄2 x Capacitive load x Voltage2
The capacitive load is a function of number of transistors connected to output and the technology which determines the capacitance of wires and transistors
 Dynamic power per transistor
 1⁄2 x Capacitive load x Voltage2 x Frequency switched
 Voltage is the key
The voltage of processors has become lower and lower

Fundamentals
Trends in Technology
 Intel 80386 consumed ~ 2 W
 3.3 GHz Intel Core i7
consumes 130 W
 Heat must be dissipated from 1.5 x 1.5 cm chip
 This is the limit of what can be cooled by air

Fundamentals
Power vs. Energy
Power is defined as the energy consumed in a unit time
Question: Which metric should we use to compare processors: power or energy?
It is better to use energy used for a specific task
Energy is tied to the a specific task and the time required for that task

Fundamentals Trends in Technology Techniques for Reducing Power
Turn off the clock
• Turn off the clock of inactive modules • In periods of low activity, operate at
Dynamic Voltage- Frequency Scaling
lower frequency
• In low power states, accesses are not
Low power state for DRAM, disks
Overclocking, turning off cores
• To turn off other cores and just run on a few cores

Fundamentals Trends in Technology Static Power
Cause: The leakage current flows even when a transistor is off
Powerstatic = Currentstatic x Voltage Scales with number of transistors
To reduce static power: power gating, turning off the power supply

程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com