Glossary of computer hardware terms
From Wikipedia, the free encyclopedia
(Redirected from Glossary of computers)
||It has been suggested that List of computer hardware be merged into this article. (Discuss) Proposed since June 2016.|
This is a glossary of terms relating to computer hardware – physical computer hardware, architectural issues, and peripherals.
- a microprocessor, ASIC or expansion card designed to offload a specific task from the CPU, often containing fixed function hardware; a common example is a Graphics processing unit.
- AI accelerator
- an accelerator aimed running artificial neural networks or other machine learning and machine vision algorithms (either training or deployment), e.g. Movidius Myriad 2, TrueNorth, Tensor processing unit etc.
- Advanced Technology extended - a motherboard form factor specification developed by Intel in 1995 to improve on previous DE factor standards like the AT form factor.
- Accelerated Graphics Port - a high-speed point-to-point channel for attaching a video card to a computer's motherboard, primarily to assist in the acceleration of 3D computer graphics.
- a subsystem that transfers data between computer components inside a computer or between computers.
- Blu-ray Disc
- a optical disc storage medium designed to supersede the DVD format.
- A small, fast local memory that transparently buffers access to a larger but slower or more distant/higher latency memory or storage device, organised into cache lines. Automatically translates accesses to the underlying resources address space to locations in the cache.
- cache line
- A small block of memory within a cache; the granularity of allocation,refills,eviction; typically 32-128 bytes in size.
- cache coherency
- The process of keeping data in multiple caches synchronised in a multi-processor shared memory system, also required when DMA modifies the underlying memory.
- cache eviction
- freeing up data from within a cache to make room for new cache entries to be allocated; controlled by a cache replacement policy. Caused by a cache miss whilst a cache is already full.
- cache hit
- finding data in a local cache, preventing the need to search for that resource in a more distant location (or to repeat a calculation).
- cache miss
- Not finding data in a local cache, requiring use of the cache policy to allocate and fill this data, and possibly performing evicting other data to make room.
- cache thrashing
- A pathological situation where access in a cache cause cyclical cache misses by evicting data that is needed in the near future.
- cache ways
- The number of potential cache lines in an associative cache that a specific physical addresses can be mapped to; higher values reduce potential collisions in allocation.
- Cache-only memory architecture, a multiprocessor memory architecture where an address space is dynamically shifted between processor nodes based on demand.
- (Compact Disc Read-Only Memory) - a pre-pressed optical compact disc which contains data or music playback.
- (or integrated circuit) - a miniaturised electronic circuit that has been manufactured in the surface of a thin substrate of semiconductor material.
- the portion of a CPU which actually performs arithemetic and logical operations. A CPU may have multiple cores (e.g. "a quad-core processor").
- core memory
- in modern usage, a synonym for main memory, dating back from the pre-semiconductor-chip times when the dominant main memory technology was magnetic core memory.
- Central processing unit - the portion of a computer system that executes the instructions of a computer program.
- Conventional PCI
- Conventional Peripheral Component Interconnect - a computer bus for attaching hardware devices in a computer.
- Computer case
- Computer chassis, cabinet, box, tower, enclosure, housing, system unit or simply case - the enclosure that contains most of the components of a computer (usually excluding the display, keyboard and mouse).
- Computer form factor
- The name used to denote the dimensions, power supply type, location of mounting holes, number of ports on the back panel, etc.
- (or chip set) - a group of integrated circuits, or chips, that are designed to work together. They are usually marketed as a single product.
- Channel I/O
- a generic term that refers to a high-performance input/output (I/O) architecture that is implemented in various forms on a number of computer architectures, especially on mainframe computers..
- data cache
- a cache in a CPU or GPU servicing data load and store requests, mirroring main memory (or VRAM for a GPU).
- Device memory
- local memory associated with a hardware device such as an graphics processing unit or OpenCL compute device, distinct from main memory.
- (Direct Access Storage Device) A mainframe terminology introduced by IBM denoting secondary storage with random access, typically (arrays of) hard disk drives.
- (dual in-line memory module);A series of dynamic random-access memory integrated circuits. These modules are mounted on a printed circuit board and designed for use in personal computers, workstations and servers.
- DisplayPort is a digital display interface developed by the Video Electronics Standards Association (VESA). The interface is primarily used to connect a video source to a display device such as a computer monitor, though it can also be used to transmit audio, USB, and other forms of data.
- Direct mapped cache
- a cache where each physical address may only be mapped to one cache line, indexed using the low bits of the address. Simple but highly prone to allocation conflicts.
- Direct memory access - the ability of a hardware device such as a disk drive or network interface to access main memory without intervention from the CPU, provided by one or more DMA channels in a system.
- (Digital Video Disc or Digital Versatile Disc) - an optical compact disc - of the same dimensions as compact discs (CDs), but store more than six times as much data.
- Digital Visual Interface (DVI) is a video display interface developed by the Digital Display Working Group (DDWG). The digital interface is used to connect a video source to a display device, such as a computer monitor.
- (Dynamic random-access memory) - a type of random-access memory that stores each bit of data in a separate capacitor within an integrated circuit and which must be periodically refreshed to retain the stored data.
- dual issue
- refers to a superscalar pipeline capable of executing 2 instructions simultaneously.
- A hardware device or software to protect a computer from viruses, malware, trojans etc.
- fixed programs and data that internally control various electronic devices.
- floppy disk
- a data storage medium that is composed of a disk of thin, flexible ("floppy") magnetic storage medium encased in a square or rectangular plastic shell.
- floppy disk drive
- a device for reading floppy disks.
- Flash Memory
- a type of non volatile computer storage chip that can be electrically erased and reprogrammed.
- hard drive
- a non-volatile storage device that stores data on rapidly rotating rigid (i.e. hard) platters with magnetic surfaces.
- the physical components of a computer.
- (High-Definition Multimedia Interface) - a compact interface for transferring encrypted uncompressed digital audio and video data to a device such as a computer monitor, video projector or digital television.
- Harvard architecture
- a memory architecture where program machine code and data are held in separate memories, more commonly seen in microcontrollers and digital signal processors.
- input device
- any peripheral equipment used to provide data and control signals to an information processing system.
- the communication between an information processing system (such as a computer), and the outside world.
- (Input/Output Operations Per Second, pronounced eye-ops) - a common performance measurement used to benchmark computer storage devices like hard disk drives.
- a group of several bits in a computer program that contains an operation code and usually one or more memory addresses.
- instruction cache
- a cache in a CPU or GPU servicing instruction fetch requests for program code (or shaders for a GPU), possibly implementing modified Harvard architecture if program machine code is stored in the same address space and physical memory as data.
- Instruction fetch
- A stage in a pipeline that load the next instruction referred to by the program counter.
- an input device, partially modeled after the typewriter keyboard, which uses an arrangement of buttons or keys, to act as mechanical levers or electronic switches.
- Load-store architecture
- An instruction set architecture where arithmetic/logic instructions may only be performed between processor registers, relying on separate load/store instructions for all data transfers.
- Local memory
- memory associated closely with a processing element, e.g. a cache, scratchpad, the memory connected to one processor node in a NUMA or COMA system, or device memory (such as VRAM) in an accelerator
- powerful computer used mainly by large organizations for bulk data processing such as census, industry and consumer statistics, enterprise resource planning, and financial transaction processing.
- main memory
- the largest random access memory in a memory hierarchy (before offline storage) in a computer system; i.e. distinct from caches or scratchpads; usually consists of DRAM.
- memory architecture
- Computer memory architecture
- a memory architecture in a computer system, e.g. NUMA, uniform memory access, COMA, etc.
- memory access pattern
- The pattern with which software or some other system (a accelerator , or DMA channel) accesses memory, affecting locality of reference and parallelism.
- Modified Harvard architecture
- a variation of Harvard architecture used for most CPUs with separate non-coherent instruction and data caches (assuming that code is immutable), but still mirroring the same main memory address space, and possibly sharing higher levels of the same cache hierarchy
- the central printed circuit board (PCB) in many modern computers which holds many of the crucial components of the system, while providing connectors for other peripherals.
- devices that are used to store data or programs on a temporary or permanent basis for use in an electronic digital computer.
- an electronic visual display for computers.
- a pointing device that functions by detecting two-dimensional motion relative to its supporting surface; motion is usually mapped to a cursor in screen space; typically used to control a graphical user interface on a desktop computer or for CAD etc.
- small connectors used on some laptops and other systems in place of the standard VGA connector.
- a layer of hardware-level instructions involved in the implementation of higher level machine code instructions in many computers and other processors.
- Mask ROM
- a type of read-only memory (ROM) whose contents are programmed by the integrated circuit manufacturer.
- a collection of computers and other devices connected by communications channels, e.g. by ethernet or wireless networking
- network on a chip
- a computer network on a single semiconductor chip, connecting processing elements, fixed function units or even memories and caches. Increasingly common in System on a chip designs.
- Non-volatile random-access memory
- random-access memory that retains its data when power is turned off.
- optical disc drive
- a disk drive that uses laser light or electromagnetic waves near the light spectrum as part of the process of reading or writing data to or from optical discs.
- Operating system
- the set of software that manages computer hardware resources and provide common services for computer programs, typically loaded by the BIOS on booting.
- Operation code
- Several bits in a computer program instruction that specify which operation to perform.
- a device attached to a computer but not part of it.
- personal computer
- Any general-purpose computer whose size, capabilities, and original sales price make it useful for individuals, and which is intended to be operated directly by an end user, with no intervening computer operator.
- The pre-loading of instructions or data before needed either by dedicated cache control instructions or predictive hardware, to mitgate latency.
- A peripheral which produces a text or graphics of documents stored in electronic form, usually on physical print media such as paper or transparencies.
- Process node
- refers to a level of semiconductor manufacturing technology, one of several successive transistor shrinks.
- Processor node
- a processor in a multiprocessor system or cluster, connected by dedicated communication channels or a network.
- Processing element
- an electronic circuit (either a microprocessor or a internal component of one) that may function autonomously or under external control, performing arithmetic and logic operations on data, possibly containing local memory, and possibly connected to other processing elements via a network,network on a chip, or cache hierarchy.
- Prefetch (cache)
- the process of pre-loading instructions or data into a cache ahead of time, either under manual control via prefetch instructions or automatically by a prefetch unit which may use runtime heuristics to predict the future memory access pattern.
- Power supply unit - A unit of the computer that converts mains AC to low-voltage regulated DC for the power of all the computer components.
- Programmable Read-Only Memory - a type of non-volatile memory chip that may be programmed after the device is constructed.
- Peripheral Component Interconnect Express - a computer expansion bus standard designed to replace the older PCI, PCI-X, and AGP bus standards.
- PCI-eXtended - a computer bus and expansion card standard that enhances the 32-bit PCI Local Bus for higher bandwidth demanded by servers.
- (Redundant Array of Independent Disks) - data storage schemes that can divide and replicate data across multiple hard disk drives in order to increase reliability, allow faster access, or both.
- Random-access memory - any form of computer data storage that allow stored data to be accessed in any order (i.e., at random).
- Read Only Memory - a type of memory chip that retains its data when its power supply is switched off.
- a computer which may be used to provide services to clients.
- Single in-line memory module - a type of memory module containing random access memory used in computers from the early 1980s to the late 1990s.
- Solid-state drive
- (or solid-state disk or electronic disk) a data storage device that uses integrated circuit assemblies as memory to store data persistently.
- Static random-access memory - a type of semiconductor memory that uses bistable latching circuitry to store each bit. The term static differentiates it from DRAM which must be periodically refreshed.
- Synchronous dynamic random access memory - dynamic random access memory that is synchronized with the system bus.
- tape drive
- A peripheral storage device that allows only sequential access, typically using magnetic tape.
- An electronic or electromechanical hardware device that is used for entering data into, and displaying data from, a computer or a computing system.
- Also known as a touchpad; a pointing device consisting of specialized surface that can translate the motion and position of a user's fingers or a stylus to a relative position on a screen.
- Universal Serial Bus - a specification to establish communication between devices and a host controller (usually a personal computers).
- USB flash drive
- A flash memory device integrated with a USB interface. USB flash drives are typically removable and rewritable.
- Video Graphics Array - the last graphical standard introduced by IBM to which the majority of PC clone manufacturers conformed.
- Volatile memory
- memory that requires power to maintain the stored information.
- A video camera that feeds its images in real time to a computer or computer network, often via USB, Ethernet, or Wi-Fi.
- Write back cache
- A cache where store operations are buffered in cache lines, only reaching main memory when the entire cache line is evicted
- Write through cache
- A cache where store operations are immediately written to the underlying main memory.
- Working set
- The set of data used by a processor during a certain time interval, which should ideally fit into a CPU cache for optimum performance.
- List of computer term etymologies
- Glossary of backup terms
- Glossary of Internet-related terminology
- Glossary of reconfigurable computing
- Glossary of computer graphics
- Glossary of computer software terms