Introduction to ARCHITECTURE. Link to download slides. Goals and learning objectives. Goals and learning objectives

Transcription

1 Introduction to COMPUTER ARCHITECTURE Link to download slides Professor Mihai ROMANCA Course web page: (Or IESC -> DEC -> Members -> Romanca Mihai) Electronics and Computers Department COMPUTER ARCHITECTURE 2 Goals and learning objectives Introduction in computers architecture and organization; the course will focus on the computer system buses memory system computer arithmetic and related structures for data-path I/O system parallel processing basics and specific architecture. Classification and exemplification of modern computer architectures Goals and learning objectives At the end of this course the student will be able to: define and describe different computer architectures describe the operation of different hardware subsystems use acquired information (together with data sheets and application notes) for installation, repairing or design different interfaces to computers. analyze and compare different high performance computer system. Some of the topics usually included in Computer Architecture lectures and describing the Input / Output system are brief discussed in our lectures because these topics are the subject of another course in the next study year: Interfaces and Peripheral COMPUTER ARCHITECTURE 3 COMPUTER ARCHITECTURE 4

2 SYLLABUS 1. INTRODUCTION TO COMPUTER ARCHITECTURE Organization and architecture Historical perspective of Computer architecture: ISA, organization, implementation, architecture classification System buses: bus structure, multiple bus hierarchies, arbitration, timings. Measuring performance: Evaluation of computer performance, comparison between different machines, Metrics, different benchmarks, Amdahl s Law for compute the performance improvement SYLLABUS 2. MEMORY ORGANIZATION Memory hierarchy, main characteristics. Main memory: ROM, static RAM, dynamic RAM Auxiliary memory - main components (will be studied at the Interfaces and Peripherals Course). Cache memory, mappings, writing into cache Memory management: static and dynamic allocation, segmentation, paging and page translation, memory protection Virtual memory, address space and memory space, address mapping using pages, associative memory page table, page replacement COMPUTER ARCHITECTURE 5 COMPUTER ARCHITECTURE 6 SYLLABUS 3. INPUT-OUTPUT ORGANIZATION Input-Output Interface, isolated versus memory-mapped IO Asynchronous data transfer, strobe control, handshaking Modes of transfer, priority interrupt arbitration: controlled by CPU, by Programmable Interrupt Controllers, and by daisy-chaining. SYLLABUS 4. INTRODUCTION IN PARALLEL PROCESSING ARCHITECTURES Advanced pipelining; Branch prediction, out-of-order execution, predicated execution, speculative execution, data speculation; VLIW Architectures, organization, advantages and limitations; Vector processor architecture, vector processing and vector operations; Introduction to multiprocessor architecture, characteristics of multiprocessors, multithreading, classification of architectures for parallel processing COMPUTER ARCHITECTURE 7 COMPUTER ARCHITECTURE 8

3 REFERENCES Hayes P. John, Computer Architecture and Organisation, McGrow Hill Comp., Mano M., Computer System Architecture, Prentice-Hall Inc Romanca, M., Calculatoare Arhitectură şi organizare, Ed. Universităţii Transilvania, Braşov, 2004; Patterson, D., Hennessy, J., Computer Architecture - A Quantitative Approach, second edition, Morgan Kaufmann Publishers, Inc. 1996; Stallings, William, Computer Organization and Architecture, 5th edition, Prentice Hall International, Inc., Tanenbaum, A., Structured Computer Organization, 4 th ed., Prentice- Hall Inc COMPUTER ARCHITECTURE 9 ASSESSMENT FORMS Colloquy Laboratory written Effective work in the computer network 80% 10% Attendance 10% A successful final qualification is conditioned by obtaining at least the grade of 5 both to the final examination and to the laboratory evaluation. If your mark at the final exam is higher than 9,50 the percents for the final qualification are: 90 / 10 / 0 (final mark do not consider course attendance) COMPUTER ARCHITECTURE 10 HISTORICAL PERSPECTIVE OF 1944 ENIAC (The Electronic Numerical Integrator and Calculator ) The first completely electronic, operational general-purpose machine built using vacuum tubes. Designed and built by Eckert and Mauchly at the University of Pennsylvania during tons, 72 square meters, 200KW Performance : Read in 120 cards per minute; Addition took 200 µs; Division 6 ms; Application: Ballistic calculations HISTORICAL PERSPECTIVE OF 1947: William Shockley, John Bardeen and Walter Brattain of Bell Laboratories invent the transistor. 1958: Jack Kilby and Robert Noyce invent the integrated circuit. Kilby was awarded the Nobel Prize in Physics in 2000 for his work , Mainframe computers used primarily by large organizations for critical applications, bulk data processing such as census,, industry and consumer Large: size, power consumption, cooling COMPUTER ARCHITECTURE 11 COMPUTER ARCHITECTURE 12

4 HISTORICAL PERSPECTIVE OF 1970, Minicomputers, is a class of smaller computers that developed in the mid-1960s and sold for much less than mainframe and mid-size computers from IBM and its direct competitors. Minicomputers: machine initially focused on applications in scientific laboratories, but rapidly branching out as the technology of time-sharing - multiple users sharing a computer interactively through independent terminals - became widespread 1971, Intel introduced the first microprocessor, the Intel : Robert Metcalfe, a member of the research staff for Xerox, develops Ethernet for connecting multiple computers and other hardware HISTORICAL PERSPECTIVE OF 1977 The birth of the first personal computer (PC) Apple computer series 1981: The first IBM personal computer, code-named Acorn, is introduced It uses Microsoft s MS-DOS operating system. It has an Intel chip, two floppy disks and an optional color monitor. 1990: Tim Berners-Lee, a researcher at CERN, the highenergy physics laboratory in Geneva, develops HyperText Markup Language (HTML), giving rise to the World Wide Web. COMPUTER ARCHITECTURE 13 COMPUTER ARCHITECTURE 14 HISTORICAL PERSPECTIVE OF 1980s and 1990s - the introduction of many commercial parallel computers with multiple processors. Intel followed suit by introducing the first of the most popular microprocessor, the 80x86 series. PCs from Compaq, Apple, IBM, Dell, and many others, soon became pervasive, and changed the face of computing The number of processors in a single machine ranged from several in a shared memory computer to hundreds of thousands in a massively parallel system COMPUTER PROGRESS (1) The rapid rate of improvements in computers has come both from: Developing the semiconductor technology See Moore Low Innovations in organization and design of computer machines COMPUTER ARCHITECTURE 15 COMPUTER ARCHITECTURE 16

5 Computer technology progress Integration Technology Typical number of devices Typical functions SSI Bipolar Gates, Flip-flops MSI Bipolar & MOS Adders, Counters LSI Bipolar & MOS ,000 ROM, RAM VLSI Mostly CMOS 10,000-5,000,000 Processors WSI CMOS >5,000,000 DSP, Special purposes IC COMPUTER ARCHITECTURE 17 Computer technology progress (2) Generalization of high-level language programming reduced the need for object-code compatibility. Creation of standardized, vendor-independent operating systems, lowered the cost and risk of bringing out a new architecture. These changes made it possible to successfully develop a new set of architectures, called RISC (Reduced Set Computer) architectures, in the early 1980s. The RISC-based machines focused the attention of designers on two critical performance techniques, the exploitation of instruction-level parallelism (initially through pipelining and later through multiple instruction issue) and the use of caches (initially in simple forms and later using more sophisticated organizations and optimizations). COMPUTER ARCHITECTURE 18 BROAD CLASSIFICATION OF TODAY COMPUTER CATEGORIES Desktops Examples: PCs, workstations Metrics: latency (graphics & IO) Servers - to provide file and computing services. Examples: Web, database servers Metrics: throughput, reliability, scalability Embedded Systems Examples:PDAs, cell phones, ATMs Metrics: complexity, power, latency Computer system A computer system consists usually of a computer and its peripherals. Computer organisation: CPU (datapath and control path) Main memory Input output system (link with external devices - peripherals) Computer peripherals include Input devices (keyboard, mouse, secondary memories) Output devices (display, speakers, secondary memories, printer). COMPUTER ARCHITECTURE 19 COMPUTER ARCHITECTURE 20

6 General organization of a uni-processor computer STRUCTURE Flux of the information controlled by CPU on two paths: control path - the brain of the processor. Control tells the datapath, memory and I/O devices what to do according to the wishes of the instructions of a program. datapath - the brawn of the processor. The datapath performs transfers and arithmetic/logic operations CPU Computer ALU Registers data s Main memory Control Unit address and command COMPUTER ARCHITECTURE 21 COMPUTER ARCHITECTURE 22 von Neumann / Harvard Arch. COMPUTER ARCHITECTURE Computer architecture Set Architecture Implementation Organization Hardware COMPUTER ARCHITECTURE 23 COMPUTER ARCHITECTURE 24

7 Set Architecture Interface between the hardware and the lowest level software. ISA includes anything programmers need to know to make a binary machine language program work correctly, including instructions, registers, I/O devices, memory addressing and so on. ISA permits that two different machines (different implementation, costs, and performance) to run the same software if they have the same defined ISA COMPUTER ARCHITECTURE 25 Implementation Organization includes the high-level aspects of a computer's design, such as the memory system, the bus structure, the internal CPU design, etc. Two machines can have the same ISA but different organizations Hardware is used to refer to the specifics of a machine. This would include the detailed logic design, semiconductor technology, and the packaging technology of the machine COMPUTER ARCHITECTURE 26 The von Neumann Architecture (defined in 1945) A structural representation of a GPC (von Neumann Architecture) The principles: Data and instructions are both stored in the main memory stored program concept The content of the memory is addressable by location (without regard to what is stored in that location: data or code); s are executed sequentially (from one instruction to the next, in order of their location in memory) unless the order is explicitly modified. The computer contains the following subsystems: input / output system, memory, control unit, arithmetic/logic unit (ALU); von Neumann computers are general purpose computers. Computers based on von Neumann Architecture are sequential computers. Input devices Computer system - "stored program" concept Input system Control Unit (CU) CPU Computer Main Memory I D ALU & Registers Output system Output devices COMPUTER ARCHITECTURE 27 COMPUTER ARCHITECTURE 28

8 Central Processing Unit The primary function of a CPU is to execute the instructions fetched from the main memory. An instruction tells the CPU to perform one of its basic operations (an arithmetic or logic operation, to transfer a data from/to main memory, etc.). The Control Unit (CU) is the one which interprets (decodes) the instruction to be executed and which "tells" the different other components what to do. The CPU includes a set of registers that are temporary storage devices typically used to hold intensively used data and intermediate results. Each instruction is performed as a sequence of steps - instruction cycle COMPUTER ARCHITECTURE 29 cycle view A simple view of the instruction cycle: fetch execute To run a program, CPU have a cyclic operation in executing every instruction A refined view of the instruction cycle: fetch execute decode Operand fetch COMPUTER ARCHITECTURE 30 Control unit Control unit (CU) is the brain of the processor CU control - synchronize all the elements inside the CPU and the interface to the external datapath Register Status and condition Flags Control Unit Clock Control signals internal to the CPU Control signals on the system bus Signals from the system bus COMPUTER ARCHITECTURE 31 Processing unit (ALU & Registers) Arithmetic and logic unit (ALU) performs arithmetic or logic operations with operands addressed by Control Unit Before processing, the operands are stored in a set of general purpose registers used as temporary memory CPU registers are a local, high-speed memory The set of general purpose registers can be used, however, to store addressing information to access data memory Depending on the result of operations carried out, ALU set some (condition) flags in a special register, as feedback to the CU. COMPUTER ARCHITECTURE 32

9 MAIN (INTERNAL) MEMORY Input / Output system Adress 0 Adress 1 Adress k Adress 2 a-1-1 Adress 2 a -1 d bits Input / Output system - addressable places (ports) through the computer exchange information with external world. The system comprise circuits for: change the format of data (serial / parallel) temporarily store data (latch) verify / check the correctness (validity) of data transferred synchronization between peripheral and CPU because of the large differences in the operation speed. decoding logic COMPUTER ARCHITECTURE 33 COMPUTER ARCHITECTURE 34 Peripherals Input (peripheral) devices - receive information from external world (through different sensors) and transform the physical nature and representation format of information compatible with voltage levels specific to computer. Output device - inverse / opposite function to input devices. Process data from computer and transform the information in the format acceptable for the output device. COMPUTER ARCHITECTURE 35