Computer Systems

Architecture
Module Code ITU 07104

Lecture 2

Facilitator: Mr. Yona Sangula

 Learning objectives
Processor architecture
Intel x86 and the ARM architectures
Embedded systems
Intel's architecture
ARM architectures
Clod computing
 Computer architecture design
features
There are two common computer processor
families the Intel x86 and the ARM
architectures.
The current x86 offerings represent the results
of decades of design effort on complex
instruction set computers (CISCs).
The x86 incorporates the sophisticated design
principles once found only on mainframes and
supercomputers and serves as an excellent
example of CISC design.
 Cont.…
An alternative approach to processor design is
the reduced instruction set computer
(RISC).
The ARM architecture is used in a wide variety
of embedded systems and is one of the most
powerful and best-designed RISC-based
systems on the market.
In terms of market share, Intel has ranked as
the number one maker of microprocessors for
non- embedded systems for decades
 Embedded systems
Refers to the use of electronics and software
within a product, as opposed to a general-
purpose computer, such as a laptop or desktop
system.
Today, many, perhaps most, devices that use
electric power have an embedded computing
system.
Embedded systems often interact (sense,
manipulate, and communicate) with external
 Embedded systems examples
Examples include cell phones, digital cameras,
video cameras, calculators, microwave ovens,
home security systems, washing machines,
lighting systems, thermostats, printers, various
automotive systems (e.g., transmission control,
cruise control, fuel injection, anti- lock brakes,
and suspension systems), tennis rackets,
toothbrushes, and numerous types of sensors
and actuators in automated systems
Possible Organization of an
Embedded System
 Intel
History of Intel
Processors
Intel was founded on July 18, 1968
Founded by semiconductor engineers Robert Noyce
and Gordon Moore
Both engineers left Fairchild Semiconductor to start
Intel
Originally called “NM Electronics” (NM for Noyce and
Moore)
Purchased the rights to use “Intel” from a company
called Intelco
Intel is short for Integrated Electronics
 Intel 4004
4-bit central processing unit
2300 transistors
Clock rate of 740 kHz
Could not handle interrupts
First Available Microprocessor from Intel
First CPU in one chip
Contained CPU, ROM (4KB), RAM (640 bytes) and a
shift register (10 bit) for I/O
Mainly used in calculators
 Intel 8008
Clock rate of 800 kHz
16 KB of memory (ROM + RAM)
Could handle interrupts
Bigger stack than the Intel 4004
8 inputs ports
24 output ports
No direct memory addressing
First commercially available 8-bit CPU
Mainly used in calculators, industrial robots (i.e.
Bottling Machines), computer terminals
 Intel 8080
8-bit CPU
Clock rate of 4 MHz
64 KB of memory (ROM + RAM)
256 I/O ports
Source code compatible with 8008
Easy to port old applications
Introduction of the stack pointer (SP) register
Stack could now grow to the size of RAM
Mainly used in early microcomputers, MITS Altair
8800 Computer
Big part of the launch of personal computers
 Intel 8088
16-bit CPU
Up to 10 MHz clock speed
1 MB of memory (ROM + RAM)
Used in the original IBM PC
Established what we know today as the x86
architecture
First commercially available 16-bit CPU
 Intel 80386
32-Bit CPU
Up to 40 MHz clock speed
4 GB of memory (ROM + RAM)
Intel’s first 32-bit x86 CPU
Mainly used in Personal Computers
Introduced “Virtual Mode”
Ability to run legacy 16-bit applications while providing
protection to memory and other resources
 Intel Pentium 4
Intel’s first successful implementation of a 64-
bit x86 CPU
Up to 3.8 GHz
2 MB L2 cache
800 MHz Bus Speed
 Intel Core 2 Duo
In 2006, Intel released a new platform named
Intel Core 2 Duo.
This was the first processor based upon the
Core architecture which is still used by Intel
today.
It contained two cores, with each core being
able to process four instructions
simultaneously.
The popular Core i3, Core i5, and Core i7 all
 Intel Core First Generation -
Nehalem
The first Core i7 released by Intel was given the
codename “Bloomfield”.
Released in Q4 of 2008.
Quad-Core Design with a shared L3 cache between
the four different cores.
Each core has a split 8-way set associative L1 cache
and a unified 8-way set associative L2 cache.
To further improve the effectiveness of the cache,
Intel added prefetching.
Main memory controller reduced time taken to
access main memory.
 Intel Core i7 - Sandy Bridge
First released in early 2011
Similar cache to the Bloomfield generation of
i7.
Integrated Graphics Processor on same die as
cores.
Improved integrated memory controller
 Intel Core i7 - Ivy Bridge
Estimated 4%-6% gain in IPC
Improvement in cache prefetching
Virtualization of move operations
 Intel Core i7 - Haswell
Increase in Reservation Stations from 6 to 8
Additional integer ALUs and branch unit
One of the highest rates of per-clock
throughput at the time
 Intel Core i7 - Broadwell
Released in Early 2015
Estimated 5% increase in IPC
Increase in L3 cache size
Not very successful, replaced within a few
months
 Intel Core i7 - Skylake
Released late 2015, a few months after
Broadwell
10% faster than Broadwell
 Intel Core i7 - Kaby Lake
Released in Early 2017
256KB L2 cache
8MB L3 cache
 Intel Core i7 - Coffee Lake
Released October 2017
Increase to six cores over Kaby Lake’s four
As a result, L3 cache increased to 12MB
Base clock of Coffee Lake same as turbo boost
of Broadwell
 ARM architecture
Refers to a processor architecture that has
evolved from RISC design principles and is used
in embedded systems.
ARM is a family of RISC-based microprocessors
and microcontrollers designed by ARM Holdings
The company doesn’t make processors but
instead designs microprocessor and multicore
architectures and licenses them to
manufacturers
 ARM architecture cont.…
ARM Holdings has two types of licensable
products: processors and processor
architectures.
For processors, the customer buys the rights to
use ARM-supplied design in their own chips.
For a processor architecture, the customer buys
the rights to design their own processor
compliant with ARM’s architecture
 ARM architecture cont.…
ARM chips are high-speed processors that are
known for their small die size and low power
requirements.
Widely used in smartphones and other handheld
devices, including game systems, as well as a large
variety of consumer products.
ARM chips are the processors in Apple’s popular iPod
and iPhone devices, and are used in virtually all
Android smartphones as well
The ARM design matched a growing commercial
need for a high-performance, low- power-
consumption, small- size, and low- cost processor for
 Instruction Set Architecture
The ARM instruction set is highly regular,
designed for efficient implementation of the
processor and efficient execution.
All instructions are 32 bits long and follow a
regular format.
This makes the ARM ISA suitable for
implementation over a wide range of products
 ARM Products
There are three Cortex architectures,
conveniently labeled with the initials A, R,
and M
 The Cortex- A
The Cortex- A and Cortex- A50 are
application processors, intended for mobile
devices such as smartphones and eBook
readers, as well as consumer devices such as
digital TV and home gateways (e.g., DSL and
cable Internet modems).
These processors run at higher clock frequency
(over 1 GHz), and support a memory
management unit (MMU), which is required for
full feature OSs such as Linux, Android, MS
 Cortex- R
The Cortex- R is designed to support real- time
applications, in which the timing of events needs to
be controlled with rapid response to events.
They can run at a fairly high clock frequency (e.g.,
200MHz to 800MHz) and have very low response
latency
Examples of embedded systems that would use the
Cortex-R are automotive braking systems, mass
storage controllers, and networking and printing
devices.
 Cortex- m Cortex- M
Cortex- m Cortex- M series processors have
been developed primarily for the
microcontroller domain where the need for fast,
highly deterministic interrupt management.
It is coupled with the desire for extremely low
gate count and lowest possible power
consumption
The market for the Cortex- M includes IoT
devices, wireless sensor/actuator networks
used in factories and other enterprises,
 Cloud computing
Dfn: A model for enabling ubiquitous, convenient, on-
demand network access to a shared pool of
configurable computing resources (e.g., networks,
servers, storage, applications, and services) that can
be rapidly provisioned and released with minimal
management effort or service provider interaction
Cloud computing services first became
available in the early 2000s, particularly
targeted at large enterprises.
Nowadays the service has spread to small and
medium size businesses, and to consumers
 Cloud computing cont..
Cloud networking refers to the networks and
network management functionality that must
be in place to enable cloud computing
One example of cloud networking is the
provisioning of high-performance and/or high-
reliability networking between the provider and
subscriber
 Cloud Services
Software as a service (SaaS) As the name
implies, a SaaS cloud provides service to
customers in the form of software, specifically
application software, running on and accessible
in the cloud.
Platform as a service (PaaS) A PaaS cloud
provides service to customers in the form of a
platform on which the customer’s applications
can run
 Cloud Services cont..
Infrastructure as a service (IaaS) With IaaS,
the customer has access to the underlying
cloud infrastructure.
IaaS provides virtual machines and other
abstracted hardware and operating systems,
which may be controlled through a service
application programming interface (API).