Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
23 Cards in this Set
- Front
- Back
Execution Time |
The total time required for a computer to complete a task. Includes: CPU execution time Memory access time I/O activities disk access time etc. |
|
Throughput |
The number of tasks completed per unit time. |
|
Data Path |
The ability to move data from one part of the CPU to another. |
|
Performance of a machine X is defined as the _______ of the CPU execution time. |
Inverse |
|
If the execution time on a machine Y is n times longer than it is on a machine X, that means... |
Machine X is n times faster than Y. |
|
Suppose a computer A runs a program in 10 seconds, and computer B runs the same program in 15 seconds. Which computer is faster and by how much? |
Computer A is faster than computer B. Computer A is 1.5 times faster than computer B. |
|
The average number of clock cycles per instruction is known as... |
CPI (Cycles Per Instruction) |
|
What is the Classic CPU Performance Equation? |
Also known as T = (I * CPI) / F |
|
How do you obtain SPEC ratio? |
Divide the execution time on a reference processor by the execution time on the measured processor for each of the benchmark programs. |
|
How do you obtain the CINT2006 summary measurement? |
Take the geometric mean of the twelve SPEC ratios of integer benchmarks. |
|
Mathematical Definition of Geometric Mean |
The nth root of the product of n numbers. |
|
Explain Binary Coded Decimal |
Each digit in decimal is represented in bits individually. |
|
What is good about excess-n code and how do you represent a number with it? |
It allows a range of negative and positive integers to be represented. To represent x, write x + n in binary. |
|
How do you perform two's compliment on a number? |
Flip the bits and add one. Alternatively, scan the bit pattern from right to left, keeping the bits as they are up to and including the first 1 seen; flip the remaining bits. |
|
What is overflow? |
When an integer value falls outside the allowed range. Alternatively, when you add two positive numbers and get a negative, or when you add two negative numbers and get a positive. |
|
What is IEEE normalized form? |
Moving the binary point so that there is a single 1 before the binary point. e.g. 00000000.0101 becomes 1.01 * 2^-2 |
|
What are the three components of IEEE representation? |
The signed bit, the exponent, and the fraction (mantissa). |
|
What is the term for the number after it has been normalized in IEEE format? i.e. 1.10110101 |
The significand. |
|
Give the number of bits for the exponent in both Single Precision (32 bit) Format and Double Precision (64 bit) Format in IEEE Floating-Point Standard 754. |
Single Precision: 8 bits Double Precision: 11 bits |
|
What is the effect of changing the number of bits for the exponent and fraction? |
More bits for exponent will allow a wider range. More bits for the fraction will allow better precision (less round off error). |
|
How do we handle representing numbers that cannot be expressed exactly? |
Round to the closest value that can be expressed. |
|
UTF-8 uses one byte for an ASCII character and up to four bytes for other characters. Thus, UTF-8 is a ______ _______ character encoding. |
Variable length |
|
What is the Hexadecimal value of uppercase A and lowercase a in ASCII? |
A: 41 a: 61 |