CMPEN 331 Quiz 1

0.0(0)
studied byStudied by 0 people
0.0(0)
full-widthCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/25

encourage image

There's no tags or description

Looks like no tags are added yet.

Study Analytics
Name
Mastery
Learn
Test
Matching
Spaced

No study sessions yet.

26 Terms

1
New cards

Pipelining

Technique that allows the CPU to work on more than one instruction at a time

2
New cards

Amdahl's Law

Speedup a program using multiple processors compared to a single processor. The law indicates the amount of speedup as a function of the fraction of code that can be executed in parallel

3
New cards

Volatile memory

Storage (such as RAM chips) that is wiped clean when power is cut off from a device.

4
New cards

Response time

How long it takes to do a task

5
New cards

Throughput

total work per unit time

6
New cards

Performance

1/execution time

7
New cards

Elapsed time

• Total response time, including all aspects

• Processing, I/O, OS overhead, idle time

• Determines system performance

8
New cards

CPU time

time spent processing a given job

9
New cards

CPU Time equation

CPU Clock Cycles * Clock Cycle Time

(CPU Clock Cycles) / (Clock Rate)

10
New cards

Clock cycles

Instruction count * cycles per instruction (CPI)

11
New cards

What can affect Instruction Count>?

Algorithm, Programming Language, Compiler, instruction set

12
New cards

4 Parts of a CPU

CPU, main memory, I/O, system interconnection

13
New cards

CPU PArts

Control unit, ALU, registers (storage), and CPU interconnection

14
New cards

Power CPU

Capacitive Load Voltage^2 frequency

15
New cards

Power wall

We can't reduce voltage further and we can't remove more heat so we move to microprocessors

16
New cards

Characteristics of a benchmark

1. written in high level language

2. representative of a particular programming paradigm (systems, numerical, commercial)

3. Can be measured easily

4. Wide distribution

17
New cards

SPEC 2006

Benchmark suite that is an industry standard for processor intensive applications

Programs that spend most of their time doing computation rather than I/O

18
New cards

Amdahl's Law equation

Timproved = Taffected/improvement factor + Tunaffected

19
New cards

MIPS

millions of instructions per second, does not account for differences in ISA's between cmoputers and difference in complexity of instructions

20
New cards

MIPS equation

Instruction count / (execution time * 10^6)

21
New cards

Mega

10^6

22
New cards

Giga

10^9

23
New cards

ASSEMBLER

Translates symbolic version of instructions into the binary version

24
New cards

SRAM

Memory that is fast but less dense and more expensive than DRAM, used in cache in CPUq

25
New cards

DRAM

Random access to any location

26
New cards

Magnetic disk and Flash memory

Flash memory worse than DRAM but better than magnetic disk, both nonvolatile

Explore top flashcards