Major Trends Which Affect Microprocessor Information Technology Essay

Major Tr closings Which Affect Micro central central processing unit Information engineering science EssayIn the first section I selected the examination ab bring out entrepot wariness social unit of Linux operation carcass. In this section I described the strategies and mechanism utilize by Memory Management, jobs set about by these techniques and solutions to overcome it.In the section number cardinal I chose the question about micro mainframe computer. This question discussed how micro processors work, major trends affecting to their performance, differences between microprocessors design closes for laptops, servers, screen backgrounds and embedded organisations.2Section1 Linux Operating SystemIntroductionLinux, mavin of the slack open source operational arrangement does sufficient repositing management activities to keep the clay stable and drug go forrs demand for errors free. As processes and threads executes, they read instructions from keeping and decode it. In such act, instructions would be fetched or store circumscribe of a localization principle in a shop. Then, the processor would execute the instructions which in either way the storehoexercising would be accessed in fetching instructions or storing the entropy.Linux uses a copy-on-write scheme. If two or more(prenominal) computer syllabusmes argon victimisation the same block of retrospect, still one copy is actu every(prenominal)y in RAM, and all the programs read the same block. If one program writes to that block, indeed a copy is made for undecomposed that program. All other programs still sh ar the same memory board.Linux handles memory in such a way that when RAM is non in use, the operating organisation uses it as phonograph record squirrel away. Below diagram illustrate a brief overview of Linux operating system.CUsersuserDesktop go throughs.jpg3Memory ManagementThe term memory management refers to the one of the most important split of the operati ng system. It cope in provision of memory-related services to coats.These services complicate virtual memory (use of a hard-fought disk or other non-RAM storage media to put forward additional program memory), encourageed memory (exclusive access to a region of memory by a process), and sh atomic number 18d memory (cooperative access to a region of memory by multiplex processes).Linux memory management does use the platform of Memory Management Unit which realize physiologic memory steeres to classr ones employ by the system and page fault interrupt be requested when the processor tries to access to memory that is not entitled to.Virtual MemoryVirtual memory of Linux is using a disk as an extension of RAM therefore that the effective size of convenient memory grows respectively. The kernel will write the substance of a soon dormant block of memory to the hard disk so that the memory can be used for other function. When the original contents ar necessary again, they are read back into memory. This is all made completely transparent to the user programs running under Linux solely see the larger essence of memory available and dont notice that parts of them reside on the disk from season to age. Obviously, reading and writing the hard disk is s note (on the put up of a thousand times slower) than using real memory, so the programs dont run as fast. The part of the hard disk that is used as virtual memory is called the sell space.Virtual memory system harp of all virtual addresses not physical addresses. These virtual addresses are transformed into physical addresses by the processor based on information held in a set of tables maintained by the operating system.To clear this conversion easier, virtual and physical memory are shared into handy sized pieces called pages. These pages are all the same size, if they were different size, the system would be very hard to administer4The schemes for Memory ManagementThe simplicity of Linux memory model facilitates program implementation and portability in different systems. There exist two schemes for implementation of memory management in Linux1.Paging2.SwappingPagingDemand PagingCurrently, saving is done using physical memory by virtual pages when compiling a program. In latter content when a program runs to query a database, not all database will respond, and only those with data records to be checked. For instance a database request for search query will only be loaded and not database with programs that works to add new records. This is also referred to as demand summon.The purpose of using demand paging is to load performing images into a process of virtual memory. Every time when a command is complete, the buck containing it is opened and its contents are displayed into the processs virtual memory. Memory mapping is executed by modifying the data bodily structure which is describing this process. Even so the rest of the image is left on disk ,only the first part of the image is actually sent into physical memory. Linux uses memory map to identify parts of image to load into memory by generating page faults as the image executes.5CUsersfoxDesktopmmu-vs-iommu-memory.pngPage FaultsPage fault exception are generated when a process tries to access an unkn profess page to memory management unit. The handler goes save in examining the currently running processs memory information and MMU state, hence determines whether the fault is skillful or corked. As good page faults cause the handler to give more memory to the process, the forged faults invoke the handler to terminate the process. From good page faults are expected behaviour to whenever a program al points a dynamic memory to run a section of code, write a for the first time a section of data or increases its stack size. In such a case when a process tries to access this newly memory, page fault is declared by MMU and the system adds a perfumed page of memory to the processs table. The interrupted process is the resumed. In cases where a process start to access a memory that its doesnt own or follows a NULL pointer indeed bad faults occur. Additionally, it could also be due to bugs in the kernel in which case the handler will scratch an oops information before terminates/killing the process.6SwappingLinux separates its physical RAM (random access memory) into pieces of memory called pages. The process of Swapping is accomplished by copying a page of memory to the preconfigured space on the hard disk, known as a swap space, to exempt that page of memory. The combined sizes of the physical memory and the swap space is the amount of virtual memory available.Swapping is done mainly for two reasons One is insufficient memory required by the system when physical memory is not available. The kernel does swaps out the less used pages and supply the resources to currently running processes. Second, a significant number of the pages used by an application during its sta rt-up phase may only be used for initialization and then never used again. The system can swap out those pages and free the memory for other applications or even for the disk cache.Nevertheless, swapping does have a disadvantage. If Compare with memory, disks are very slow. For example, memory speeds are measured in nanoseconds, but disks are measured in milliseconds, so admittance to the physical memory can be significantly faster than accessing disk. It depends how often swapping occurs, if it happens frequently your system will be slower. Sometimes excessive swapping or thrashing occurs where a page is swapped out and then very soon swapped in and then swapped out again and so on. In such situations the system is struggling to find free memory and keep applications running at the same time. In this case only adding more RAM will help.There are two forms of swap space the swap partition and the swap file. The swap partition is a substantive section of the hard disk which is used o nly for swapping other files cannot locate there. A fussy file in the file system which stands amongst your system and data files called a swap file.7Problems of virtual memory management in LinuxThere are several possible problems with the page replacement algorithm in Linux , which can be listed as follows The system may react badly to changeable VM load or to load build ups after a bound of no VM activity. Since the Kswapd, the page out daemon, only scans when the system is low on memory, the system can end up in a state where some pages have reference bits from the last 5 seconds, season other pages have reference bits from 20 minutes ago. This means that on a load spike the system have no clue which are the right pages to evict from memory, this can lead to a swapping storm, where the wrong pages are evicted and almost immediately after towards faulted back in, leading to the page out of another random page, etc. There is no method to prevent the possible memory deadlock. With the arrival of journaling and bide allocation file systems it is possible that the systems will need to allocate memory in rig to free memory, that is, to write out data so memory can become free. It may be useful to introduce some algorithm to prevent the possible deadlock under extremely low memory situation.ConclusionAll in all, Linux memory management seems to be effective than before and this is based on the assumption that Linux has less applications that it runs as to compared to windows machines which has more users and more applications. Beside, the system may react badly to variable VM load However, regular updates from Linux has managed to lessen the bugs.Swapping does require more disk memory in case the physical memory is insufficient toserve more demanding applications and if the disk space is too low the user runs the stake of waiting or kill other process for other programs to work. Additionally, resuming the swapped pages may result into corrupted data, but Linux has been in upper hand to solve such bugs.8Frequently Ask QuestionsWhat is the main goal of the Memory Management?The Memory Management Unit should be able to decide which process should locate in the main memory should control the parts of the virtual space of a process which is non-core nonmigratory responsible for monitoring the available main memory and for the writing processes into the swap device in order to supply more processor fit in the main memory at the same time.What is called a page fault?Page fault appear when the process addresses a page in the functional set of the process but the process is not able to locate the page in the workings set. To overcome this problem kernel should updates the working set by reading the page from the secondary device.What is the stripped Memory Requirement?Linux needs at least 4MB, and then you will need to use special installation procedures until the disk swap space is installed. Linux will run comfortably in 4MB of RAM, although running graphical user interface apps is impractically slow because they need to swap out to disk.9Section 2 MicroprocessorIntroductionMicroprocessor incorporates all or most of the functions of Central Processor Unit (CPU) on a unity incorporated circuit, so in the world of personal computers, the terms microprocessor and CPU are used interchangeably. The microprocessor is the brain of any computer, whether it is a background signal machine, a server or a laptop. It processes instructions and communicates with outside devices, controlling most of the operation of the computer.How Microprocessors move aroundMicroprocessor LogicA microprocessor performs a collection of machine instructions that tell the processor what to do. A microprocessor does 3 main things based on the instructionsUsing its ALU (Arithmetic/Logic Unit), a microprocessor is able to perform mathematical operations wish addition, subtraction, multiplication and division.A microprocessor is able to move d ata from one memory location to another.A microprocessor is able to make decisions and jump to a new set of instructions based on those decisions.10The following diagram shows how to extremely simple microprocessor capable of doing of 3 jobs.The microprocessor containsAn address bus that sends an address to memoryA data bus that can sends data to memory or receive data from memoryA RD (read) and WR (write) line to tell the memory whether to set or get the addressA clock line lets a clock pulse sequence the processorA specify line that resets the program counter to zero and restarts execution11Here the explanation of components and how they performRegisters A, B and C are kind of latches that made out of flip-flopsThe address latch is just like registers A, B and C.The program counter is a latch with the extra capacity to increment by 1 when or reset to zero it is needed.Major trends which affect microprocessor performance and designIncreasing number of shopping mallsA dual-co re processor is aCPUwith two processors or execution cores in the sameintegrated circuit. Each processor has its owncacheand controller, which enables it to function as efficiently as a single processor. However, because the two processors are joined together, they can perform operations up to twice as fast as a single processor can. The Intel Core Duo, the AMD X2, and the dual-core PowerPC G5 are all examples of CPUs that use dual-core technologies. These CPUs each combine two processor cores on a single silicon chip. This is different than a dual processor configuration, in which two physically separate CPUs work together. However, some high-end machines, such as the PowerPC G5 Quad, use two separate dual-core processors together, providing up to quartet times the performance of a single processor.12Reducing size of processorSize of the processor the one of the major trend what is affecting to the processor in last years time. When the processor befitting weakened there will b e many advantages like it can include many cores to a processor, it will protect energy, it will increase its speed also.45nm Processor Technology Intel has introduced 45nm Technology in Intel Core 2 and Intel Core i7 ProcessorFamily. Intel 45nm High-K Silicon Processors contain Larger L2 Cache than65nm Processors.32nm ProcessorTechnology At research aim Intel have introduced 32nm processor (Code Name Nehalem- based Westmere) which will be released in 2nd quarter of 2009 aught savingEnergy is one of the most important resources in the world. Therefore we must save and protect it for future purpose. The business office using up in microprocessor would be one of the major trends. For instance, Intel Core 2 family of processors are very efficient processor, they have very intelligent power management features, such s, ability to inactivate unused cores it still draws up to 24 watts in idle mode.13High speed cache and busesIn Past year Microprocessor Manufactures like Intel has intro duced new cache technologies to their processors which can gain more ability improvements and reduce latency. Intel Advanced Smart Cache technology is a multicore cache that reduce latency to frequency used data in modern processor the cache size is increased up to 12MB induction a heat sink and microprocessor14Differences between MicroprocessorsServersOriginally the microprocessor for server should give uninterrupted time and stability with low power expending and less resources allocating processor for System Cache. Thats why most of the time they use Unix and Linux as the Server based operating systems, because they take less amount of hardware resources and use effectively so the heat which dispatches from the processor is less and the heating would be less.Desktop ProcessorsThe desktop microprocessors are a bit different from server microprocessors, because they are not very oftentimes concerned of power consumption or use less resources of Operation system. The goal of Desk top microprocessors is to deliver as much performance as possible while keeping the cost of the processor low and power consumption within reasonable limits. Another important fact is out there, it is most of the programs which are being used in desktop machines are designed to do long time processor scheduling jobs like rendering a high definition image, or compiling a source file. So the processors are also designed to adopt those kinds of processing.Laptop ProcessorThe CPU produces a lot of heats, in the desktop computers there are a systems of fans, heat sinks, channels and radiators that are uses to cool off the computer. Since laptop has small size, and far less room for any cooling methods, the CPU usuallyRuns at a lower voltage and clock speed (reduces heat output and power consumption but slows the processor down)Has a sleep or slow-down mode (when the computer is not in use or when the processor does not need to run as quickly the operation system reduces the CPU speed)15E mbedded Microprocessors or so of the embedded devices using Microcontrollers instead of separate Microprocessors they are an implementation of whole computer inside a small thumb size chip called Microcontroller. These microcontrollers are varying its performance due to battery consumption and Instruction length issues. Most of them are designed using RISC architecture to minimize the complexity and the number of instructions per processor. Embedded device processors have high speed potential but the problem they are having is high power consumption and heating.ConclusionCurrent technology allows for one processor socket to provide access to one logical core. But this approach is expected to change, enabling one processor socket to provide access to two, four, or more processor cores. Future processors will be designed to allow multiple processor cores to be contained inside a single processor module.16Frequently Ask Questions1. How does the operating system share the cpu in a mult itasking system?There are two prefatorial ways of establishing a multitasking milieu times lice and priority based.In a a times lice multitasking environment each application is given a set amount of time (250 milliseconds, 100 milliseconds, etc) to run then the scheduler turns over execution to some other process. In such an environment each READY application takes turns, allowing them to effectively share the CPU.In a priority based environment each application is depute a priority and the process with the highest priority will be allowed to execute as long as it is devise, meaning that it will run until it needs to wait for some kind of resource such as operator input, disk access or communication. Once a higher priority process is no longer ready, the next higher process will begin execution until it is no longer ready or until the higher priority process takes the processor back.Most real-time operating systems in use today tend to be some kind of combination of the two.2.W hat is a multi-core?Two or more independent core combined into a single package composed of a single integrated circuit is known as a multi-core processor.3. What is the difference between a processor and a microprocessor?generally, processor would be the part of a computer that interprets (and executes) instructions A microprocessor, is a CPU that is in just one IC (chip). For example, the CPU in a PC is in a chip so it can also be referred to as microprocessor. It has come to be called a microprocessor, because in the older old age processors would normally be implemented in many ICs, so it was considered quite a feat to include the whole CPU in one chip that they called it a Microprocessor17