Todays topics l l Operating Systems Brookshear Chapter

Today’s topics l l Operating Systems Ø Brookshear, Chapter 3 Ø Great Ideas, Chapter 10 Ø Slides from Kevin Wayne’s COS 126 course Performance & Computer Architecture Ø Notes from David A. Patterson and John L. Hennessy, Computer Organization and Design: The Hardware/Software Interface, Morgan Kaufmann, 1997. Ø http: //computer. howstuffworks. com/pc. htm Slides from Prof. Marti Hearst of UC Berkeley SIMS Upcoming Ø Computability • Great Ideas, Chapter 15 • Brookshear, Chapter 11 Compsci 001 12. 1

Performance l l Performance= 1/Time Ø The goal for all software and hardware developers is to increase performance Metrics for measuring performance (pros/cons? ) Ø Ø Elapsed time CPU time • Instruction count (RISC vx. CISC) • Clock cycles per instruction • Clock cycle time MIPS vs. MFLOPS Ø Throughput (tasks/time) Ø Other more subjective metrics? What kind of workload to be used? Ø Applications, kernels and benchmarks (toy or synthetic) Ø l Compsci 001 12. 2

Boolean Logic l l l AND, OR, NOT, NOR, NAND, XOR Each operator has a set of rules for combining two binary inputs Ø These rules are defined in a Truth Table Ø (This term is from the field of Logic) Each implemented in an electronic device called a gate Ø Gates operate on inputs of 0’s and 1’s Ø These are more basic than operations like addition Ø Gates are used to build up circuits that • Compute addition, subtraction, etc • Store values to be used later • Translate values from one format to another Compsci 001 12. 3

Truth Tables Compsci 001 Images from http: //courses. cs. vt. edu/~csonline/Machine. Architecture/Lessons/Circuits/index. html 12. 4

The Big Picture Since 1946 all computers have had 5 components l Ø The Von Neumann Machine Processor Input Control Memory Datapath l Output What is computer architecture? Computer Architecture = Machine Organization + Instruction Set Architecture +. . . Compsci 001 12. 5

Fetch, Decode, Execute Cycle l l l Computer instructions are stored (as bits) in memory A program’s execution is a loop Ø Fetch instruction from memory Ø Decode instruction Ø Execute instruction Cycle time Ø Measured in hertz (cycles per second) Ø 2 GHz processor can execute this cycle up to 2 billion times a second Ø Not all cycles are the same though… Compsci 001 12. 6

Organization l l l Capabilities & Performance Logic Designer's View Characteristics of Principal Functional ISA Level Units (Fus) Ø (e. g. , Registers, ALU, Shifters, Logic FUs & Interconnect Units, . . . ) Ways in which these components are interconnected Information flows between components Logic and means by which such information flow is controlled. Choreography of FUs to realize the ISA Compsci 001 12. 7

Memory bottleneck l l CPU can execute dozens of instruction in the time it takes to retrieve one item from memory Solution: Memory Hierarchy Ø Use fast memory Ø Registers Ø Cache memory Ø Rule: small memory is fast, large memory is small Compsci 001 12. 8

What is Realtime? l Response time Ø Panic • How to tell “I am still computing” • Progress bar l l l Flicker Ø Fusion frequency Update rate vs. refresh rate Ø Movie film standards (24 fps projected at 48 fps) Interactive media Ø Interactive vs. non-interactive graphics • computer games vs. movies • animation tools vs. animation Ø Interactivity => real-time systems • system must respond to user inputs without any perceptible delay (A Primary Challenge in VR) Compsci 001 12. 9

A great idea in computer science l l Temporal locality Ø Programs tend to access data that has been accessed recently (i. e. close in time) Spatial locality Ø Programs tend to access data at an address near recently referenced data (i. e. close in space) Useful in graphics and virtual reality as well Ø Realistic images require significant computational power Ø Don’t need to represent distant objects as well Efficient distributed systems rely on locality Ø Memory access time increases over a network Ø Want to acess data on local machine Compsci 001 12. 10

Instruction Set Architecture. . . the attributes of a [computing] system as seen by the programmer, i. e. the conceptual structure and functional behavior, as distinct from the organization of the data flows and controls the logic design, and the physical implementation. – Amdahl, Blaaw, and Brooks, 1964 -- Organization of Programmable Storage SOFTWARE -- Data Types & Data Structures: Encodings & Representations -- Instruction Set -- Instruction Formats -- Modes of Addressing and Accessing Data Items and Instructions -- Exceptional Conditions Compsci 001 12. 11

The Instruction Set: a Critical Interface software instruction set hardware l What is an example of an Instruction Set architecture? Compsci 001 12. 12

Forces on Computer Architecture Technology Programming Languages Applications Computer Architecture Operating Systems Compsci 001 Cleverness History 12. 13

Technology DRAM chip capacity Microprocessor Logic Density DRAM l l Year Size 1980 64 Kb 1983 256 Kb 1986 1 Mb 1989 4 Mb 1992 1996 1999 2002 2004 16 Mb 64 Mb 256 Mb 1 Gb 4 Gb In ~1985 the single-chip processor (32 -bit) and the singleboard computer emerged Ø => workstations, personal computers, multiprocessors have been riding this wave since Now, we have multicore processors Compsci 001 12. 14

Technology => dramatic change l l Processor Ø logic capacity: about 30% per year Ø clock rate: about 20% per year Memory Ø DRAM capacity: about 60% per year (4 x every 3 years) Ø Memory speed: about 10% per year Ø Cost per bit: improves about 25% per year Disk Ø capacity: about 60% per year Ø Total use of data: 100% per 9 months! Network Bandwidth Ø Bandwidth increasing more than 100% per year! Compsci 001 12. 15

Performance Trends Log of Performance Supercomputers Mainframes Minicomputers Microprocessors Year 1970 Compsci 001 1975 1980 1985 1990 1995 12. 16

Laws? l Define each of the following. What has its effect been on the advancement of computing technology? Ø Moore’s Law Ø Amdahl’s Law Ø Metcalfe’s Law Compsci 001 12. 17