Operating Systems And Computer Architecture

Published Date: 02 Nov 2017

A truth table is a breakdown of a logic function by listing all possible values the function can attain. Such a table typically contains several rows and columns, with the top row representing the logical variables and combinations, in increasing complexity leading up to the final function (Rouse, 2005).

The truth table above shows the combinations of inputs A and B and the output for an AND GATE and for the EX-OR GATE to create a simple half adder.

As you can see by the table above there are two inputs to produce an output in binary, these can be represented in logic gates:-

AND gate (club, 2011)

The output Q is true if input A AND input B are both true: Q = A AND B

an AND gate can have two or more inputs, its output is true if all inputs are true.

Input A

Input B

Output Q

0

0

0

0

1

0

1

0

0

1

1

1

traditional AND gate symbol

Truth Table

EX-OR (Exclusive-OR) gate

The output Q is true if either input A is true OR input B is true, but not when both of them are true: Q = (A AND NOT B) OR (B AND NOT A) This is like an OR gate but excluding both inputs being true. The output is true if inputs A and B are DIFFERENT. EX-OR gates can only have 2 inputs.

Input A

Input B

Output Q

0

0

0

0

1

1

1

0

1

1

1

0

traditional EX-OR gate symbol

Truth table

Half Adder The half adder adds two single binary digits A and B. It has two outputs, sum (S) and carry (C). The carry signal represents an overflow into the next digit of a multi-digit addition. The value of the sum is 2C + S. The simplest half-adder design, pictured below, incorporates an XOR gate for S and an AND gate for C. With the addition of an OR gate to combine their carry outputs, two half adders can be combined to make a full adder (wikipedia, 2012).

http://t3.gstatic.com/images?q=tbn:ANd9GcQFPPM67SvpI9LJsoj1Z6oxjvdkQ4BOrrHAsh3ZUkUF1h1IQ4RE

Inputs

Outputs

( Lancaster, 2004)

You need an input of A OR B to get S

You need an input both A AND B to get C

But you would get an output of S first and then C

Server Report

Server Role

The server role will be a web server which will run windows 2008 R2 hosting the company’s websites which will include:-

The main website for publicity purposes

An on-line shop for trade sales for customers

The web server needs to be future proof for the possibility of a website which will sell goods direct to the public which a data base will be needed to collect information from customer i.e. names, addresses, etc. With all this in mind a powerful processor will be needed to accomplish the job in hand.

A process model is needed to run more than one web-site, web application or web-service securely and reliably on a single machine. In Shared Hosting scenarios hundreds or even thousands of web-sites run on an individual machine. The code running on these web-sites is usually not well tested, if at all. Without a powerful process model the result would be extremely poor reliability. But a process model not only guarantees availability; it also needs to isolate them so that individual web applications don't interfere with each other. The Windows Process Activation Service (WAS) is the system component providing the Process Model in IIS 7.0 (Thomad, 2008).

1. Application Pools

Processes are the containers that provide isolation and security boundaries in the Windows Operating System. Consequently web applications or web-sites have to run in separate processes in order to achieve isolation between them. In the IIS terminology the management unit for these separate IIS processes is called 'Application Pool'. An Application Pool can be configured to run a group of URLs, i.e. web-sites, web applications or web-services. When a client requests one of these Application Pool URLs an IIS worker process (w3wp.exe) is spawned by WAS to execute the code necessary to send a response. WAS's main task is to manage Application Pools - WAS spawns worker processes, monitors their health, recycles them if necessary and makes sure none of them consume more resources than specified in the corresponding AppPool configuration. WAS is also the arbiter and collector for run-time and state data, e.g. performance counters, site and Application Pool state (Thomad, 2008).

2. Architectural Diagram

The diagram below shows the core pieces of the IIS7 architecture.

Configuration is stored in the applicationhost.config file (left).

HTTP.SYS is a kernel-mode component that listens to the network, accepts connections, assigns requests into Application Pool queues and queues these requests if no IIS worker process is running. HTTP.SYS also caches responses and does SSL in IIS 7.0

The worker process on the right hosts all custom code (e.g. ASP and ASP.Net pages, modules, ISAPI filter and extensions etc.). There can be hundreds of these worker processes depending on how the IIS Administrator decides to isolate his web-sites and applications. IIS worker processes pick up waiting requests from the corresponding HTTP.SYS request queue.

The Windows Activation Service is a system service that runs in SVCHOST.EXE. WAS reads configuration from applicationhost.config, reacts to configuration changes, manages worker processes, controls their live time and health, recycles them if necessary and prevents resource exhaustion. W3SVC is another service living in the same SVCHOST.EXE as WAS. W3SVC hosts the HTTP specific part of the IIS process model; W3SVC configures HTTP.SYS with the URLs to listen on and is called by HTTP.SYS if requests arrive and worker processes are needed (Thomad, 2008).

procmod

3. Process Model Features

Web-Sites and applications get the following benefits by running in the WAS provided infrastructure:

Efficient Resource Management

On-Demand Activation

Resources like RAM and CPU are scarce in multi-tenant scenarios. WAS will start an IIS worker process only once requests for a particular web site or web application arrive.

Idle-timeout

Because resources are usually scarce WAS can shutdown web applications based on a configurable idle-timeout.

Health Monitoring

To ensure their health WAS monitors the worker processes it spawned. Health messages are periodically sent to each running worker process. If the worker process doesn't respond in a configurable time interval the worker process will be recycled or killed. This way undetected deadlock in worker processes get automatically fixed by restarting the worker process.

Startup Limit

Part of the Rapid-Fail Protection feature is the Startup limit. If a worker process doesn't report back to WAS within the configurable startup-limit it will be killed and the Rapid-Fail-Protection counter is incremented. Application Pools are stopped, i.e. restarting the worker process will not be tried anymore, if the Rapid-Fail-Protection counter reaches a configurable limit within a configurable time limit. This prevents scenarios where worker processes hang or crash during startup (Thomad, 2008).

Shutdown Limit

A worker process also has to shutdown in a configurable limit. If the shutdown doesn't happen in this time the worker process gets killed by WAS. This prevents resource overuse due to processes hanging in their shut-down phase. Additional shutdown settings allow an executable to be started (e.g. a debugger) when the shutdown doesn't complete within the allotted time.

CPU affinity

Configuration settings allow WAS to start worker processes that are affinities’ to one or more CPUs. This prevents tenants from interfering with each other if they share the same physical machine.

User Profile

WAS can start worker processes with or without loading the user profile (Thomad, 2008).

Security

Customizable User Account

IIS worker processes can run as a preconfigured process identity or built-in accounts (Local Service, Local System, and Network Service). Built-in accounts are advantages because they don't require password management. If a custom user identity is used the password is automatically encrypted. Configuration settings can be replicated to multiple machines by sharing the configuration encryption keys across machines.

Job Object Features

Job objects allow administrators to restrict worker processes to a particular CPU limit. A configurable action is taken if this CPU limit is exceeded. Job objects will also make sure that processes spawned by the worker process get terminated.

Configuration Isolation and Security

Before WAS starts an Application Pool and its worker process it generates a unique configuration file for this Application Pool. WAS also creates a unique SID for each Application Pool (similar to Service SIDs introduced in Windows Server 2008). The Application Pool configuration file is then secured with this unique SID. This ensures that Application Pool configuration files can only be read by Administrators and the Application Pool itself (Thomad, 2008).

Diagnostics and Monitoring

Event Logging

Events regarding invalid configuration, recycling, startup or shutdown of worker processes are reported to the System Event log.

Currently Executing Requests

WAS exposes a run-time and state control interface that allows scripts and tools to query for the currently executing requests of a particular worker process. This is useful to find requests that hang or requests that take a very long time to complete.

Performance Counters

All IIS performance counters get funneled through WAS. WAS gathers these performance counters because IIS counters are site-based and web applications can live in different Application Pools.

Recycling

Recycling allows the refresh of worker processes without losing a single request due to down-time. This is done via a feature called "overlapping recycling".

Overlapping Recycling

WAS does this by spawning up a new worker process parallel to the old one that is still handling requests. Once the new worker process is up it starts picking up requests from the request queue while the old worker process is instructed by WAS to stop picking up requests. Once the old worker process finishes all executing requests it shuts down. This feature is called "overlapping recycling". It ensures that no requests are lost during a recycle (Thomad, 2008).

Recycling Configuration

Recycling parameters are configurable in the IIS configuration system.

Scheduled Recycling

Customers might want to recycle their applications based on a regular schedule. Via configuration settings recycling can be scheduled periodically, e.g. every 4 hours, every day at 1am etc.

Recycling Based on Memory Consumption

Applications might leak memory over time. WAS can monitor the memory consumption of each worker processes to ensure that no worker process uses more than its preconfigured limit. Reaching a configured virtual or private memory threshold will trigger the recycling of a worker process.

Process Orphaning

Some errors only happen in a production environment. Killing worker processes ensures up-time but troubleshooting of these errors becomes difficult, e.g. if the failing worker process needs to be debugged. The process orphaning feature in WAS allows worker processes to be recycled without killing the failed worker process. Now a debugger can be attached to it. Additional process orphaning settings allow the execution of a process (e.g. a debugger) if orphaning happens (Thomad, 2008).

Evaluation

The Intel Xeon X5687(Appendix page14) is designed to work in a dual processor configuration and because of this the processor and the board will both be more expensive. Also the Intel Xeon X5687 shares the same microarchitecture as the 1st generation Intel Core i7-9XX processor. The 2nd generation Intel Core processors are outperforming the 1st by 10% to 15%. You would get better performance from the Intel Core i7-2600K before you ever overclock it than you would from the Intel Xeon X5687 running in a single threaded mode at a much lower price point (Wood, 2011).

AMD Opteron (Appendix page 16) processor line-up, offers up to 16 cores and 84-percent more performance than rival chips, and more energy-efficient data centres. The new AMD Opteron 6200 Series have their focus resolutely set on new cloud implementations, demanding half the power per core of their predecessors and cutting price and space by a third. Up to four memory channels – with support for up to 1600MHz memory – with up to 12 DIMMs per CPU available for a potential total of 384GB memory per processor catered for. The new Opteron’s are the only x86 chips to support ultra-low voltage 1.25v memory, adding to the platform’s energy frugality (Davies, 2011).

Multicore versus multiprocessor

Multi-core chips tend to be more efficient than multi-CPU systems. Another benefit of multi-core systems is that having only a single CPU keeps system board prices low since there is only a need for one CPU socket and the corresponding hardware that facilitates its use. Today nearly every computer on the market contains a processor with at least two cores, while every server sold today has at least two cores (some have four). The longstanding question of whether or not you should buy a dual-core system is not even an issue anymore because practically every modern system supports two or more cores.

The difference between a dual-core system and a system with two physical processors and which configuration offers better performance .

Having two processors does not double a machine's performance. There are two main reasons for this.

In order for a machine to benefit from multiple processors (or multiple cores for that matter), the machine must be running multiple threads. This is not a problem; most of the Windows operating systems in use today are multi-threaded. And even though most applications are not multi-threaded, users of dual-core or dual-CPU systems could still see a considerable performance boost if they multitask.

The inherent overhead in multi-CPU systems does not double a machine's performance because some of each CPU's power is lost to scheduling tasks. This is necessary because the computer must have some way of deciding which thread will run on each CPU. Even more performance is lost to communications occurring between processors. For multiple processors to work cooperatively, the two processors must be able to communicate with each other. Imagine what would happen if two processors tried to apply conflicting changes to the same memory location at the same time. To prevent this type of catastrophe, a processor must verify that the contents of a memory location that it is about to manipulate are up to date in the system's memory, and are not presently residing in another processor's cache (Posey, 2007).

The final analysis

The following graph shows a comparison of a selection of Opteron 6200 series CPUs with Xeon E7s. Most are in a quad-socket configuration, although it will be found that there are a couple in dual and octal-socket configurations for comparison.

SPEC Results Opteron vs Xeon, Jan 2012

Looking at the graph it can be seen that there are integers and floating points showing the performance for systems possessing four CPUs each, in both Intel and AMD. It becomes quickly apparent that the Intel E7 CPUs, with 32 and 40 cores are of equivalent performance with the AMD systems ranging from 48 to 64 cores in total. For example, note that the top-end 16-core 6282SE Opteron is a match for the top-end 10-core Xeon on floating points, and is not far behind it on integers either. And the mid-range Opteron 12-core 6234 compares with the "entry-level" E7-4820.The fact that the Opteron CPU needs more cores to match the Xeon is expected. In general AMD have made up for their weaker core performance by simply piling more cores into each CPU package, up to 60% more than Intel. Apart from relative cost (which will be discussed below), the core count is perhaps the most significant difference between the two offerings, and one likely to affect end-user choice. This is because certain enterprise software applications benefit from a smaller number of more powerful cores, either through cheaper software licensing, or through the design of the software being limited to lower core-counts (either through design or just poor programming). A decision as to which way to go (lower core count and faster cores vs. higher core count and slower cores), should be made in full consultation with the primary software vendor. It is very often the case, however, that software will be able to fully utilize all available cores efficiently - this is especially common in academic computing where the end-user has full control over the software development process.

Summary

AMD and Intel are comparable in raw performance, but AMD must use up to 60% more cores than Intel to get this performance. As high core counts benefit scientific programming more than general purpose server computing, it would seem that AMD would be the choice for academics and engineers.

AMD have a huge price-performance advantage over Intel in the four-socket enterprise computing space. This alone may push most end-users toward AMD over Intel.

AMD no longer provide an eight-socket solution, whereas Intel does. So the absolute maximum performance in a single box prize still goes to Intel. For some end-users, this is all that counts, regardless of the price.

The newer generations of CPUs offer equivalent or better performance than the previous generation, at a fraction of the price. This advantages consumers.

Overall, therefore, I would favour AMD at this time, on the basis of their very large advantage in price over Intel in this space. But Intel still has the lead when it comes to maximum raw performance in a single box at any cost (Ranson, 2012).

Thick and Thin Clients

Thick Client

A thick client is a computer that does not require a connection to a server system in order to run (unlike a thin client), although they can benefit from being connected to a network and a server. Thick clients are often found in the business environment, where servers are used to provide some data and application support, but the thick client (office computer) is largely independent. Thick clients have their own operating system and software applications and can be used offline (not connected to a network or server).Thick clients have several advantages including being able to be used offline, improve performance for multimedia applications (including video games), increased flexibility and higher server capacity (less of a load on a thick client server, allowing for support of more users) (Hope, 2012).

Advantages

•Fewer server requirements because it does most of the application processing

•More offline work because a server connection is often not required

•Multimedia-rich application processing, such as video gaming facilitation, because there are no increased server bandwidth requirements

•Runs more applications because many thick clients require that an operating system resides on a local computer

•Easy network connection at no extra cost because many users have fast local PCs

•Higher server capacity because each thick client handles more processing, allowing the server to serve more clients ( Janssen, 2010/2012).

Disadvantages

1. More expensive to develop than web based application.

2. More work for IT department to deploy and maintain software on multiple PCs.

3. Needs continual communication with server; works well for PCs over local area network

(Green, 2005).

Thin Client

In a thin client network, all of the applications and data reside on the server. The thin client is simply a device from which to send requests and on which to see the results. Thin clients are essentially empty boxes, much like the original "dumb" terminals that are connected to a mainframe. Since they do not process anything themselves, thin clients do not need any internal memory. Furthermore, they run at the speed of the server rather than at the speed of an internal processor. Often no bigger than a trade paperback, today's thin clients also come equipped with USB ports to support a variety of removable media including floppy disk, CD-ROM, and flash memory drives (Romm, 2006).

Types

A physical thin client can be something as minimalistic as a graphic display and an input mechanism like a keyboard, mouse, or touchscreen. Generally speaking, these devices contain just enough information to start up and connect to a more powerful computer, the server. Many do not have the peripherals that come with personal computers like an optical drive or input/output ports, which are where wires connecting the computer to other devices come into it. They may also lack a hard drive, which means that if the thin client computer needs to use a program or save a file, it will connect to the network server computer to do so (Petersen, 2003/2012).

Uses

Thin clients are typically used in settings where a lot of people need to use computers. This includes public places like libraries, airports, and schools. The thin client setup is also popular in places where people need to be able to save and access information from a central location, like an office, a call centre, or a manufacturing plant. For instance, an office might use this type of setup to allow all employees to save all their work on an office server, or to control the programs and information that they can access (Petersen, 2003/2012).

Advantages

The reasons someone might use hardware and software versions of a thin client include reduced cost, ease of maintenance, ease of use, and security. Thin clients are much simpler than complete computers, which mean they may be less likely to break. A standard computer has a lot of parts, and a thin client only has a few — fewer parts mean fewer things can go wrong. The simplicity also makes it much easier to diagnose problems and repair them. Additionally, in a situation in which many people need to perform a similar task, it is often more cost-effective to have one network server computer and many cheaper thin client computers than to have many complete devices.

People who are not computer literate may have an easier time using a thin client than a standard computer or software program because it has fewer features and functions to learn to use. Although thin clients are relatively easy to secure, users generally have restricted access to programs or functions that could breach security. Restricting all of the real computing power to a single network server also means that security can be focused in one place (Petersen, 2003/2012).

Disadvantages

Downsides to this type of setup include the lack of peripheral devices, the limited performance of certain tasks, and sometimes, the nature of the security system. Those thin clients that do not have optical drives cannot play CDs or DVDs, and if a thin client does not have input/output ports, it may be unable to easily connect to other devices, like a printer. Additionally, since most thin clients are so stripped down, their performance may not be fast enough for tasks like video rendering, graphics editing, or gaming. This is particularly true if several clients are doing very intensive tasks at once, which can affect the server and slow other clients down.

Though the ability to have one end point for all the security in a network can be beneficial, it also means that a problem with that one point can compromise all the client computers. Likewise, if none of the clients have hard drives and all the data is saved on the server, then if the server crashes, all the data from all the clients will be lost (Petersen, 2003/2012).

Hybrid

A hybrid client is a mixture of the above two client models. Similar to thick client, it processes locally, but relies on the server for storage data. This approach offers features from both the thick client (multimedia support, high performance) and the thin client (high manageability, flexibility) (Wikipedia, n.d.).

Advantages

Client/Server access provides high-quality interfaces for specialized applications

Intranet/Internet access provides simple, platform-independent access from any location

Less restrictions on equipment usage – legacy systems can be used

Ease of information deployment to the Internet

Decreased levels of maintenance for Thin Clients

Provides off-site access to users – perfect for telecommuters (miteinc, 2012).

Disadvantages

Hybrid clients rely on a server, and if the server ceases to operate due to hardware or software failure or under a heavy load, the communication link between the two will be unable to transfer data (Howe , 2012).

Smart Client

An Internet-connected device that allows the user's local applications to interact with server-based applications through the use of Web services. For example, a smart client running a word processing application can interface with a remote database over the Internet in order to collect data from the database to be used in the word processing document. Smart clients can work with data even when they are not connected to the Internet (which distinguishes them from browser-based applications, which do not work when the device is not connected to the Internet). Smart client applications have the ability to be deployed and updated in real time over the network from a centralized server; Smart client applications support multiple platforms and languages because they are built on Web services; Smart client applications can run on almost any device that has Internet connectivity, including desktops, workstations, notebooks, tablet PCs, PDAs, and mobile phones (webopediea, n.d.).

Advantages

Smart clients have additional advantages over the old client-server models, such as the ability to be deployed and updated over the Internet from the central server. Also, smart clients are less cross-platform dependent because of their reliance on web services (Stojanovski, 2006).

Disadvantages

On the other hand, there are the challenges inherent in such smart clients, including contending with the speed, security, and bandwidth limitations of data access over the intranet or Internet

(Eini, 2011).

Thick or Thin

The main deciding factor when choosing between thin and thick clients is price. Thick clients are going to cost a lot more because they function at a higher level and operate independently of the server. Thin clients are the most common type of computer in business today. Very few businesses want a thick client because they will have a hard time backing up and updating the files on it. While thick clients are separate from the network and eliminate the chance that any activities on them will hinder the integrity of the overall network, they become a bit of a burden due to the time spent trying to maintain them as opposed to the thin clients.

A thick client is no different from the computer that people use at home. Thin clients are a little more streamlined and stripped down. They are governed by their server and everything that occurs within them depends primarily on what goes on with the server. The lineup of installed programs on thick clients can change on a moment’s notice while most thin clients have every program screened to ensure that it is free from infection. Thick clients are at their best when they are used as testing machines. Nobody wants to install suspicious software on a computer that is attached to a network. They will want to put it on a machine that can take the damage and crash if it needs to. Nothing important should be stored on thick clients. Keeping files on there when a virus wreaks havoc and erases everything will be regretted.

The independence of a thick client is the main reason businesses should look at it as being undesirable. Very few businesses have employees on computers independent from the other computers within the company. They want to unite all their computers using a server to help in the process of securing and backing up files and systems. Going to each computer and completing this process manually is difficult for even the most experienced IT personnel. Sometimes IT professionals have to address the problems of computers attached to the network. Each network computer is like a bulb in a string of Christmas tree lights. When one bulb goes out, the rest of them will follow suit before long .In the battle of thick and thin clients, it is best to choose thin clients. These machines open the doors for buying additional computers when hiring more people.

A business that does not require a lot of collaboration could use thick clients. This approach is not recommended however because of the difficulty in keeping them maintained. Thin clients are a win from an economic and practical perspective; therefore, you should not have to wonder which one you need to choose (oppertunites, n.d.).

Appendix

Intel X5687 CPU Specifications Intel

Technical Specifications

This is the number of processing units in the processor.

Cores

4 cores

Number of Threads

8

This describes the number of cycles per second that the processor is capable of performing.

Clock Speed

3.60 GHz

This is the maximum clock speed that is allowed by the processor's built-in overclocking functionality.

Maximum Overclocked Speed

3.86 GHz

This is the size of the cache on the processor.

Cache/Smart Cache

12 MB

The instruction set refers to the computer architecture that determines how the processor handles information, especially in regard to RAM.

Instruction Set

64 bit

Compare 64 bit Processors

The lithography refers to the thickness of the die on which the processor was manufactured.

Lithography

32 nm

Additional Technologies

Power (TDP)

130 W

Technical Specifications

The Intel X5687 is a Quad-Core Server processor and has a maximum clock speed of 3.60 GHz, which is 50% faster than the average for all Server Processors (CPUs). Additionally, this processor offers built-in over-clocking which increases the maximum clock speed to 3.86 GHz, which is far faster than the average for all Server Processors (CPUs).

Memory Specifications

The Intel X5687 processor is capable of accommodating 288 GB of RAM, which is 256 GB more than the average for all Server Processors (CPUs). Additionally, this processor offers 3 memory channels, and has a maximum memory bandwidth of 32.0 GB/s, which is 25% faster than the average for all Server Processors (CPUs) (Best, 2012).

Memory Specifications

This is the maximum amount of memory that is supported by the processor.

Maximum Memory

Memory Supported

DDR3-1066

DDR3-1333

DDR3-800

This is the number of memory channels that the processor supports.

Memory Channels

Memory Bandwidth

Package Specifications

Maximum CPU Configuration

Package Size Height

Package Size Width

(intel, n.d.)

AMD 6200 Series Processors

http://products.amd.com/global/images/partnerlogo/amd.gif

Processor

AMD Opteronâ„¢ 6200 Series Processor

Model

6282 SE

AMD Virtualization Technology

Yes

AMD-P (Power Management)

Yes

OPN Tray

OS6282YETGGGU

OPN PIB

n/a

Revision

B2

Core Count

16

Base Speed (MHz)

2600

System Bus Speed (MT/s)

6400

Voltages

Max Temps (C)

55 to 64

Wattage

140 W

L1 Cache Size (KB)

48

L1 Cache Count

16

L2 Cache Size (KB)

1000

L2 Cache Count

16

L2 Cache Speed (MHz)

2600

L3 Cache Size (KB)

16384

CMOS

32nm

Integrated Memory Controller Speed (MHz)

2000

Floating Point Unit

Socket

G34

AMD-P 2.0

FEATURE

FUNCTION

END-USER BENEFIT

APML (Advanced Platform Management Link)

Provides an interface for processor and systems management monitoring and controlling of system resources (in APML-enabled platforms); Comprised of the Remote Power Management Interface (RPMI) and the Precision Thermal Monitor

Remote Power Management Interface (RPMI):

Ability to monitor and control platform power consumption via p-state limits

Access to processor identification and health

Precision Thermal Monitor:

Provides accurate information about CPU thermals to closely monitor power/cooling and proactively alert the Base Management Controller (BMC)

Early notification helps save time and money by providing intelligence that can be used to more effectively monitor power and thermals to optimize cooling solutions in an IT datacentre

TDP Power Cap

Allows the user to set the maximum processor power ceiling via BIOS or APML

This technology gives enterprises the ability to customize their chips to meet power and workload demands, providing:

More control over power settings

Flexibility to set power limits without capping CPU frequencies

AMD Cool Speed Technology

Protects processor integrity by reducing power-states, when a temperature limit is reached

Server can automatically drop into lower power mode if processor’s thermal environment exceeds safe operational limits Offers platform providers the ability to safely reduce system fan speeds, which helps deliver greater platform efficiency

C1E

Reduces memory controller and Hyper Transport technology links’ power

This feature can equate to a significant power savings in your datacentre depending on system configuration, when the Northbridge and Hyper Transport technology links are powered down and cores are at idle.

C6 Support

Core power gating: When a core is halted its context is exported to system memory and voltage is removed from the core.

Helps reduce power consumption at idle by up to 46% over the previous generation3

LV-DDR3 Support

Supports 1.25V and 1.35V DDR3

Helps to reduce overall power consumption

Higher DDR3 Frequencies

DDR3-1600 now supported for typical memory configurations; DDR3-1866 supported in slightly loaded memory configurations (1 of 1 DIMM per channel)

Helps to improve overall system performance

LR-DIMM Support

Support for LR-DIMM memory

LR-DIMMs provide more capacity per DIMM, which can enable higher overall server memory configurations. Virtualization, cloud computing and other high-capacity applications greatly benefit from LR-DIMMs.

Direct Connect Architecture 2.0

FEATURE

FUNCTION

END-USER BENEFIT

Quad Channel Memory

Doubles the memory channels compared to Six-Core AMD Opteron processors

Can increase performance especially in memory-intensive workloads

Hyper Transport Technology Assist (HT Assist)

Helps to increase coherent memory bandwidth and reduce latency in multi-node systems by reducing cache probe traffic between cores

Can result in faster queries that can increase performance for cache sensitive applications such as database, virtualization and compute intensive applications

Hyper Transport 3.0 Technology (HT3)

Provides superior system bandwidth between CPUs and I/O, increasing interconnect rate up to a maximum 6.4GT/s with HT3

Helps improve overall system balance and scalability for scale-out computing environments like HPC, database and web serving

Cache and Core Count

Integration of up to 16 cores within the same package, 1MB L2 cache per core (up to 16MB of L2 cache per socket), and a shared 16MB L3 cache per socket

Offers improved performance and performance/watt (compared to prior generations) for multi-threaded environments like virtualization, database and web serving

Performance

FEATURE

FUNCTION

END-USER BENEFIT

New Core Architecture

Optimized performance per watt:

Full performance from each core

High frequency and low-power design

Virtualization enhancements

Shared double-sized Flex FP

ISA enhancements

The new processor core can enhance power efficiency for server products:

Help minimize cooling solution complexities

Help reduce power at low utilization

Enable more control for IT managers

AMD Turbo CORE Technology

Turns unused TDP headroom into added clock speed for improved performance

The industry’s best full-core boost1 with up to a 500MHz frequency increase2

ISA Enhancements

In addition to baseline instruction support, added SSE4.1, SSE4.2, SSSE3, AVX, AES, PCLMULQDQ, FMA4 and XOP

Provides performance enhancements to a wide range of applications

Flex FP

The world’s only flexible 256-bit FPU. Two 128-bit FMACs shared per module, allowing for dedicated 128-bit execution per core or shared 256-bit execution per module.

Enhances flexibility and performance in technical computing

(AMD, 2012)