4. Applicability
•Utility of architecture for what it was
intended for.
Efficiency
•Measure of the average amount of
hardware that remains busy during normal
computer use.
•Because of the low cost of hardware
now, efficiency is considered very
5. Malleability
•Ease with which computers in the same family can
be implemented using this architecture
•Example- machines that differ in size and
performance
Expandability
•The measure of how easy is to increase the
capabilities of a computer system such as its
maximum memory size or arithmetic capabilities.
Compatibility
7. Open Architecture
• Are so called Open System, it refers to a hardware specification or
design that is publicly released, allowing other manufacturers to
produce similar products that are compatible and usually compliant
with one another.
• A good example of open architecture is IBM compatible
computers(International Business Machine); these computers allow
anyone to purchase a product from any manufacturer with the
understanding it will work with their compatible computer.
Adv. Any one can add-on products for it.
That is designed to make adding, upgrading and swapping components easy
from it.
OPEN
ARCHITECTURE
8. Example of Open
Architecture:
1.IBM PC- International Business Machine (IBM) The IBM
Personal Computer, commonly known as the IBM PC
2. The Apple IIe (styled as Apple //e) is the third model in
the Apple II series of personal computers produced by Apple computer.
The e in the name stands for enhanced, referring to the fact that several
popular features were now built-in that were available only as upgrades
or add-ons in earlier models
9. CLOSED
ARCHITECTURE• A computer or other hardware design that a manufacturer
will not share or open to other manufacturers, making it
incompatible with other software and computers.
• For example, the Apple computers are closed
architecture computers and a brand of computer only
developed and manufactured by Apple.
• A system whose technical specifications are not made
public. Such systems restrict third parties from building
products that interface with or add enhancements to them.
Example of Closed:
10. SYSTEM PERFORMANCE
• is the amount of work accomplished by
a computer system.
•is the process of collecting, analyzing
and/or reporting information regarding
the performance of an individual, group,
organization, system or component.
11. Overall, the performance of a computer is
dependant on how well it works together as a
whole. Continually upgrading one part of the
computer while leaving outdated parts installed
will not improve performance much, if at all.
Below, we discuss some of the most important
parts of the computer regarding it's speed and
computing power
Processor speed
System RAM speed and size
Disk speed and size
WHAT AFFECTS A SYSTEM
PERFORMANCE?
12. Processor Speed
• Clock speed, a.k.a. Processor speed is
often played up to be the major factor in a
computer's overall performance.
• Things like encoding video or encrypting
files, or anything that computes large,
complex, numbers requires a lot of
processor power. Most users spend most of
their time typing, reading email or viewing
web pages
13. System RAM
speed and size
• The amount and speed of the RAM in your
computer makes a huge difference in how
your computer performs.
• Memory affects computer speed because the
CPU must move information into memory and
retrieve data from it when running
applications.
• If you have a lot of memory, the CPU can
move larger chunks of it faster. Computers
also use your hard drive as a virtual memory
area when your RAM cannot hold any more
14. Disk
speed and size
• The biggest factor in your computer's performance
is the hard disk speed. How fast the hard drive
can find (average seek time), read, write, and
transfer data will make a big difference in the way
your computer performs. A well-organized drive,
with plenty of empty space and no heavy
fragmenting, will help the read/write head find the
requested information faster. Hard drives are
measured in rotations per minute, or RPM, which
essentially means how fast they spin to allow the
read/write head to find the requested data.
15. Video Card
• Whenever your computer puts an image on
the screen something has to render it. If a
computer is doing this with software it is often
slow and will affect the performance of the
rest of the computer. Also, the image will not
be rendered as crisp or as smoothly in the
case of video. Even a low-end video card will
significantly improve the performance of the
computer by taking the large task of rendering
the images on the screen from the CPU to
the graphics card. If you work with large
image files, video or play games you will want
a higher end video card.
• Video editing programs, your graphic card's
speed may become important. The speed at
16. SPEED OF THE
COMPUTER
• The general term, computer speed, refers to CPU
clock speed. This is how fast the CPU operates,
usually measured in gigahertz (GHz). One gigahertz
is equal to 1 billion hertz, or cycles per second. So
a 1 GHz computer has a CPU that operates at 1
billion cycles per second.
• Operating at 1 GHz does not mean a computer can
do 1 billion operations every second. Different CPUs
use different instructions that affect how many
cycles it takes to complete an operation or how
many operations can be completed in one cycle. So
two different CPUs might not operate practically at
the same speed even if their clock speeds are
17. • a test using a benchmark to evaluate a computer system's
performance
• that measure the chips' abilities to do actual work
BENCHMARKS
• Benchmark is the act of running
a computer program, a set of programs, or
other operations, in order to assess the
relative performance of an object, normally
by running a number of standard tests and
trials against it.
BENCHMARK TESTS
18. TYPES OF
BENCHMARK1. Real programs
• word processing software
(Ex. MSWord, Excel, Photoshop,CAD...)
2. Kernels – Unlike real programs, no user would run kernel
programs. They exist solely to evaluate performance
• contains key codes
• normally abstracted from actual program
• popular kernel: Livermore loop
EX .Linpack benchmark (contains basic linear algebra subroutine
written in FORTRAN language)- Is a method of measuring the floating
point rate of execution of a computer by running a program that solves
a system of linear equations
19. 3.Toy Benchmarks - are typically between 10 and 100 lines
of code and produce a result the user already knows before
running the toy program
• Examples: Sieve of Eratosthenes, Puzzle, Quicksort
4. Synthetic benchmarks
• which are fake programs invented to try to match the
profile and behavior of real applications, such as Dhrystone
• code that matches frequency of key instructions and
operations to real programs
• 2 types
-Whetstone (floating point operations)
20. 5.I/O benchmarks
6.Database benchmarks
• to measure the throughput and response times
of database management systems (DBMS')
7. Parallel benchmarks
• used on machines with multiple cores,
processors or systems consisting of multiple
machine
21. SPEC -THE STANDARD
PERFORMANCE EVALUATION
CORPORATION• SPEC is a non-profit corporation formed to
"establish, maintain and endorse a standardized set
of relevant benchmarks that can be applied to the
newest generation of high-performance computers"
• SPEC develops suites of benchmarks intended to
measure computer performance
– These suites are packaged with source code and
tools and are extensively tested for portability before
release
– They are available to the public for a fee covering
development and administrative costs
22. SPEC - BENCHMARK
SUITEMain categories of benchmark suites:
•– Desktop benchmarks: CPU, memory, and
graphics performance–
• Sever benchmarks: throughput-oriented, I/O
and OS intensive
•– Embedded benchmarks: measuring the
ability to meet deadline and save power