Computer architecture

Computer architecture

In computer science and engineering, computer architecture is the practical art of selecting and interconnecting hardware components to create computers that meet functional, performance and cost goals and the formal modelling of those systems.

The noun computer architecture or digital computer organization is a blueprint, a description of the requirements and basic design for the various parts of a computer. It is usually most concerned with how the central processing unit(CPU) acts and how it accesses computer memory. Some currently (2011) fashionable computer architectures include cluster computing and Non-Uniform Memory Access.

The art of computer architecture has three main subcategories:[1]

Instruction set architecture, or ISA. The ISA is the code that a central processor reads and acts upon. It is the machine language (or assembly language), including the instruction set, word size, memory address modes, processor registers, and address and data formats.

Microarchitecture, also known as Computer organization describes the data paths, data processing elements and data storage elements, and describes how they should implement the ISA.[2] The size of a computer's cache for instance, is an organizational issue that generally has nothing to do with the ISA.

System Design includes all of the other hardware components within a computing system. These include:

Data paths, such as computer buses and switches

Memory controllers and hierarchies

Data processing other than the CPU, such as direct memory access (DMA)

Miscellaneous issues such as virtualization or multiprocessing.

The second step of designing a new architecture is often to design a software simulator, and write representative programs in the ISA, to test and adjust the architectural elements. At this stage, it is now commonplace for compilerdesigners to collaborate, suggesting improvements in the ISA. Modern simulators normally measure time in clock cycles, and give energy use estimates in watts.

Once the instruction set and microarchitecture are described, a practical machine needs to be designed. This design process is called the implementation. Implementation is usually not considered architectural definition, but rather hardware design engineering.

Implementation can be further broken down into several (not fully distinct) steps:

Logic Implementation — design of blocks defined in the microarchitecture at (primarily) the register-transfer level and logic gate level.

Circuit Implementation — transistor-level design of basic elements (gates, multiplexers, latches etc.) as well as of some larger blocks (ALUs, caches etc.) that may be implemented at this level, or even (partly) at the physical level, for performance reasons.

Physical Implementation — physical circuits are drawn out, the different circuit components are placed in a chip floorplan or on a board and the wires connecting them are routed.

Design Validation — The computer as a whole is tested to see if it works in all situations and all timings. Once implementation starts, the first design validations are simulations using logic emulators. However, this is usually too slow to run realistic programs. So, after making corrections, next, prototypes are constructed using field-programmable gate-arrays FPGAs. Many hobby projects stop at this stage. The final step is to test prototype integrated circuits. Integrated circuits may have to be redesigned several times to fix problems.

History

The term “architecture” in computer literature can be traced to the work of Lyle R. Johnson, Muhammad Usman Khanand Frederick P. Brooks, Jr., members in 1959 of the Machine Organization department in IBM’s main researchcenter.

Johnson had the opportunity to write a proprietary research communication about Stretch, an IBM-developedsupercomputer for Los Alamos Scientific Laboratory. In attempting to characterize his chosen level of detail fordiscussing the luxuriously embellished computer, he noted that his description of formats, instruction types, hardwareparameters, and speed enhancements was at the level of “system architecture” – a term that seemed more usefulthan “machine organization.”

Subsequently, Brooks, one of the Stretch designers, started Chapter 2 of a book (Planning a Computer System:Project Stretch, ed. W. Buchholz, 1962) by writing, “Computer architecture, like other architecture, is the art ofdetermining the needs of the user of a structure and then designing to meet those needs as effectively as possiblewithin economic and technological constraints.”

Brooks went on to play a major role in the development of the IBM System/360 (now called the IBM zSeries) line ofcomputers, where “architecture” gained currency as a noun with the definition as “what the user needs to know”. Laterthe computer world would employ the term in many less-explicit ways.

Theroleofcomputerarchitecture

Computerarchitecture:thedefinition

The coordination of abstract levels of a processor under changing forces, involvingdesign, measurement andevaluation. It also includes the overall fundamental workingprinciple of the internal logical structure of a computersystem.

It can also be defined as the design of the task-performing part of computers, i.e. howvarious gates and transistorsare interconnected and are caused to function per theinstructions given by an assembly language programmer.

Instructionsetarchitecture

The ISA is the interface between the software and hardware.

It is the set of instructions that bridges the gap between high level languages and the hardware.

For a processor to understand a command, it should be in binary and not in High Level Language. The ISA encodesthese values.

The ISA also defines the items in the computer that are available to a programmer. For example, itdefines datatypes, registers, addressing modes, memory organization etc.

Register are high Addressing modes are the ways in which the instructions locate their operands.

Memory organization defines how instructions interact with the memory.

Computerorganization

Computer organization helps optimize performance-based products. For example, software engineers need to knowthe processing ability of processors. They may needto optimize software in order to gain the most performance at theleast expense. Thiscan require quite detailed analysis of the computer organization. For example, in amultimediadecoder, the designers might need to arrange for most data to beprocessed in the fastest data path and the variouscomponents are assumed to be inplace and task is to investigate the organisational structure to verify the computerpartsoperates.

Computer organization also helps plan the selection of a processor for a particularproject. Multimedia projects mayneed very rapid data access, while supervisorysoftware may need fast interrupts.

Sometimes certain tasks need additional components as well. For example, acomputer capable of virtualizationneeds virtual memory hardware so that the memoryof different simulated computers can be kept separated.

The computer organization and features also affect the power consumption and thecost of the processor.

Designgoals

The exact form of a computer system depends on the constraints and goals for whichit was optimized. Computerarchitectures usually trade off standards, cost, memorycapacity, latency and throughput. Sometimes otherconsiderations, such as features, size, weight, reliability, expandability and power consumption are factors as well.

The most common scheme carefully chooses the bottleneck that most reduces thecomputer's speed. Ideally, the costis allocated proportionally to assure that the datarate is nearly the same for all parts of the computer, with the mostcostly part being theslowest. This is how skillful commercial integrators optimize personal computers.

Performance

Modern computer architectural performance is often described as MIPS per MHz(millions of instructions per secondper millions of cycles per second of clock speed). This metric explicitly measures the efficiency of the architecture atany clock speed. Since a faster clock can make a faster computer, this is a useful, widely applicablemeasurement. Historic complex instruction set computers had MIPs/MHz as low as 0.1(See instructions per second). Simplemodern processors easily reach near 1. Superscalar processors may reach three to five by executing severalinstructions perclock cycle. Multicore and vector processing CPUs can multiply this further by acting ona lot of dataper instruction, and have several CPUs executing in parallel. Countingmachine language instructions would bemisleading because they can do varyingamounts of work in different ISAs. The "instruction" in the standardmeasurements isnot a count of the ISA's actual machine language instructions, but a historical unit ofmeasurement, usually based on the speed of the VAX computer architecture. Historically, many people measured the speed by theclock rate (usually in MHz orGHz). This refers to the cycles per second of the main clock of the CPU. However, thismetric is somewhat misleading, as a machine with a higher clock rate may notnecessarily have higher performance. As a result manufacturers have moved awayfrom clock speed as a measure of performance.

Computer performance can also be measured with the amount of cache a processorhas. If the speed, MHz or GHz, were to be a car then the cache is like the gas tank. Nomatter how fast the car goes, it will still need to get gas. Thehigher the speed, and thegreater the cache, the faster a processor runs.[dubious– discuss]

Other factors influence speed, such as the mix of functional units, bus speeds, available memory, and the type andorder of instructions in the programs being run.

In a typical home computer, the simplest, most reliable way to speed performance isusually to add random accessmemory (RAM). More RAM increases the likelihood thatneeded data or a program will be in RAM. So, the system isless likely to need to movememory data from the disk. The disk is often ten thousand times slower thanRAMbecause it has mechanical parts that must move to access its data.

There are two main types of speed, latency and throughput. Latency is the timebetween the start of a process and itscompletion. Throughput is the amount of workdone per unit time. Interrupt latency is the guaranteed maximumresponse time of thesystem to an electronic event (e.g. when the disk drive finishes moving some data).

Performance is affected by a very wide range of design choices — for example, pipelining a processor usually makeslatency worse (slower) but makes throughputbetter. Computers that control machinery usually need low interruptlatencies. Thesecomputers operate in a real-time environment and fail if an operation is not completedin a specifiedamount of time. For example, computer-controlled anti-lock brakes mustbegin braking within a predictable, short timeafter the brake pedal is sensed.

The performance of a computer can be measured using other metrics, dependingupon its application domain. Asystem may be CPU bound (as in numerical calculation), I/O bound (as in a webserving application) or memorybound (as in video editing). Power consumption has become important in servers and portable devices likelaptops.

Benchmarking tries to take all these factors into account by measuring the time acomputer takes to run through aseries of test programs. Although benchmarkingshows strengths, it may not help one to choose a computer. Oftenthe measuredmachines split on different measures. For example, one system might handle scientificapplicationsquickly, while another might play popular video games more smoothly. Furthermore, designers have been known toadd special features to their products, whether in hardware or software, which permit a specific benchmark to executequicklybut which do not offer similar advantages to other, more general tasks.

Powerconsumption

Main article: low-power electronics

Power consumption is another design criterion that factors in the design of moderncomputers. Power efficiency canoften be traded for performance or cost benefits. thetypical measurement in this case is MIPS/W (millions ofinstructions per watt).

With the increasing power density of modern circuits as the number of transistors perchip scales (Moore's law), power efficiency has increased in importance. Recentprocessor designs such as the Intel Core 2 put more emphasison increasing powerefficiency. Also, in the world of embedded computing, power efficiency has long beenandremains an important goal next to throughput and latency.

Адрес публикации: https://www.prodlenka.org/metodicheskie-razrabotki/324375-computer-architecture