Lecture 1 (Computer Abstractions and Technology) Flashcards
Types of Computers
Desktop: general use
Server: network based w great capacity and reliability
Embedded: hidden as components of systems
Algorithm
Tells you number of operations
Program language, compiler, architecture
number of machine instructions per operation
Processor and memory
determines speed of execution
I/O system
speed of i/o execution
Hardware systems
Application software (HLL)
System software: compiler converts HLL to machine code
Hardware: processer, memory, i/o controllers
Computer components
User interface: keyboard, display, mouse
Storage Devices: Hard disk, DVD
Network adapters: communicates with other computers.
Parts of a CPU
Datapath: performs data operations
Control: sequences datapath
Cache memory: small fast sram for immediate access
Volatile memory
loses data when powered off
Non-Volatile memory
does not have to be powered to store data
Response time
how long it takes to do a task
throughput
total work per unit time
relative performance
1/execution time, x is n times faster than y
relative performance equation
performance x / performance y = execution y / execution x
Elapsed time
total response time
CPU time
time spent processing given job
Clock period
duration of clock cycle
clock frequency
cycles per second
CPU time eqn
clock cycles * clock cycle time OR clock cycles / frequency
instruction count
number of instructions
Clock cycle
instruction count * CPI
CPU time eqn w/ instruction
Instruction count * CPI / frequency
Summary of CPU time eqn
Instructions/program = clock cycles/instruction = seconds/clock cycle`
Moore’s Law
number of transistors per chip doubles every year
Power eqn
Capacitive load * Voltage^2 * frequency
Amdal’s Law eqn
Time improved = time affected/improvement factor + time unaffected
MIPS
Millions of instructions per second
MIPS eqn
clock rate/ (CPI*10^6)
