075582814553
A Graphics card (Video card, Display card, Video adapter) is one of the basic components of personal computers. It converts the display information required by the computer system to drive the display, which is an important component that connects the monitor and the PC motherboard, and is one of the important equipment of "human-machine". Its built-in parallel computing capability is also used for deep learning and other operations.
The graphics card is responsible for the task of outputting and displaying graphics. For those who like to play games and engage in professional graphics design, the video card is very important. The display chips of mainstream graphics cards are mainly manufactured by NVIDIA and AMD. Graphics cards that use NVIDIA display chips are usually called N cards, and those that use AMD display chips are called A cards. Computers with higher configurations all contain graphics card computing cores. In scientific computing, the graphics card is called a display accelerator card.
The video chipset is the main processing unit of the graphics card, so it is also called the Graphics Processing Unit (GPU). The GPU is the first concept proposed by NVIDIA when it released the GeForce 256 graphics processing chip. Especially when dealing with 3D graphics, the GPU enables the graphics card to reduce the dependence on the CPU and complete part of the work originally belonging to the CPU. The core technologies used by the GPU include hardware T&L (geometric conversion and lighting processing), cubic environment texture mapping and vertex blending, texture compression and bump mapping, dual texture four-pixel 256-bit rendering engine, etc...
The various 3D special effects supported by the graphics card are determined by the performance of the display chip. The type of display chip used roughly determines the grade and basic performance of the graphics card, such as NVIDIA's GT series and AMD's HD series.
The graphics card is inserted into the expansion slot on the motherboard (usually a PCI-E slot, before there were AGP, PCI, ISA, and other slots). It is mainly responsible for converting the display signal sent by the host to the display into a general electrical signal so that the display can understand what the personal computer is making it do. The graphics card is mainly composed of a graphics card motherboard, display chip, display memory, radiator (heat sink, fan), and other parts. The main chip of the graphics card is called "Video chipset" (also called GPU or VPU, graphics processor or visual processor), which is the main processing unit of the graphics card. The graphics card also has a memory similar to the computer memory, called "display memory".
Early graphics cards were purely graphics cards, which only played the role of signal conversion. The graphics cards we generally use have 3D graphics calculations and graphics acceleration functions, so they are also called "graphics acceleration cards" or "3D acceleration cards." The earliest graphics cards on the PC were the MDA and CGA 2D accelerator cards that were installed on the 5150 personal computer launched by IBM in 1981.
Graphics card is usually composed of bus interface, PCB board, display chip, video memory, RAMDAC, VGA BIOS, VGA function pins, D-sub socket, and other peripheral components. Most graphics cards also have a VGA, DVI display interface or HDMI interface and S-Video Terminal and Display Port interface.
The integrated graphics card is a component that integrates the display chip, video memory, and related circuits on the motherboard. The display chip of the integrated graphics card is almost integrated into the northbridge chip of the motherboard. The display effect and processing performance of the integrated graphics card are relatively weak, and hardware upgrades of the graphics card cannot be performed. However, you can use CMOS to adjust the frequency or flash a new BIOS file to achieve software upgrades to tap the potential of the display chip. The advantages of integrated graphics are low power consumption and low heat. The performance of some integrated graphics can be comparable to entry-level discrete graphics, so many people who like to assemble computers by themselves can get themselves without spending the extra money to buy dedicated graphics.
Integrated graphics
The disadvantage of the integrated graphics card is that the performance is relatively low, and it is solidified on the motherboard or CPU. It cannot be replaced by itself. If it must be replaced, the motherboard can only be replaced.
Dedicated graphics
A dedicated graphics card means that the display chip, video memory, and related circuits are separately built on a circuit board, which is self-contained and exists as an independent board card. It needs to occupy the expansion slot of the motherboard (ISA, PCI, AGP, or PCI- E). The advantage of a dedicated graphics card is that it has a separate installation of video memory, generally does not occupy system memory. It is technically much more advanced than integrated graphics, but its performance is certainly not worse than that of integrated graphics, and it is easy to upgrade the hardware of the graphics card. The disadvantage of the dedicated graphics card is that the power consumption of the system has increased, the heat generation is also larger. It needs to spend extra money to buy the graphics card, and at the same time (especially for notebook computers) takes up more space. As the performance of the graphics card has different requirements for the graphics card, dedicated graphics cards are actually divided into two categories, one type is graphics cards designed specifically for games, and the other is professional graphics cards used for graphics and 3D rendering.
The Core Graphics is the new generation graphics processing core of Intel products. Unlike previous graphics cards, Intel relies on its advanced processor manufacturing process and new architecture design to integrate the graphics core and the processing core on the same substrate. The design integration of the intelligent processor architecture greatly reduces the data turnaround time between the processing core, graphics core, memory, and memory controller, effectively improving processing efficiency and greatly reducing the overall power consumption of the chipset, which helps to reduce the cost of core components. The size provides more options for the design of notebooks, all-in-ones, and other products.
Core graphics
It should be noted that the core graphics card is not the same as the integrated graphics card in the traditional sense. The graphics solutions adopted by the notebook platform are mainly "dedicated" and "integrated". The former has a separate graphics core and independent video memory, which can meet the complex and huge graphics processing needs and provide efficient video encoding applications. The graphics core of integrated graphics cards is integrated on the motherboard as a separate chip, and part of the system memory is dynamically shared as video memory, so it can provide simple graphics processing capabilities and smoother coding applications.
Core Graphics architecture
Compared with the first two, core Graphics integrates the graphics core in the processor, further enhancing the efficiency of graphics processing, and integrates the "processor + south bridge + northbridge (graphic core + memory control + display output)" in the integrated graphics card. The three-chip solution is reduced to a dual-chip mode of "processor (processing core + graphics core + memory control) + motherboard chips (display output)", which effectively reduces the overall power consumption of core components and is more conducive to extending the battery life of the notebook time.
Low power consumption is the main advantage of the core graphics card. Due to the new streamlined architecture and integrated design, the core graphics card has better control of the overall energy consumption. The efficient processing performance greatly reduces the computing time and further reduces the consumption of the system platform. High performance is also its main advantage: core graphics cards have many advantageous technologies, which can bring sufficient graphics processing capabilities, and their performance is very obvious compared with the previous generation of products.
The structure of a general graphics card is as follows:
Capacitors: Capacitors are very important components in graphics cards, because the quality of the display image mainly depends on the quality of the capacitors, and the quality of the capacitors directly affects the quality of the graphics card circuit.
Video memory: Video memory is responsible for storing various data that the display chip needs to process. Its capacity and performance directly affect the display effect of the computer. The new graphics cards all use DDR6/DDR5 video memory, and the mainstream video memory capacity is generally 2GB ~ 4GB.
GPU and fan: GPU is the graphics chip, it is responsible for most of the calculation work of the graphics card, which is equivalent to the role of the CPU in the computer. The function of the GPU fan is to dissipate heat to the GPU.
Graphics card interface: It can be divided into three types: PCI, AGP, and PCI Express. PCI and AGP graphics card interfaces are basically eliminated. The mainstream graphics cards on the market use PCI Express graphics cards.
Peripheral interface: The peripheral interface of the graphics card is responsible for the output task of the graphics card. The new graphics card includes a traditional VGA analog interface and one or more digital interfaces (DVI, HDMI, and DP).
Bridge interface: Mid-to-high-end graphics cards can support multiple works at the same time, and the bridge interface is connected through a bridge between them.
ISA graphics card
The ISA graphics card is an old graphics card that the most commonly used VGA monitor can support.
VESA graphics card
VESA is the abbreviation of "Video Electronic Standards Association", co-founded in 1989 by a number of computer chip manufacturers. At the end of 1994, VESA published the 64-bit architecture "VESA Local Bus" standard. Most of the 80486 personal computers use this standard graphics card.
PCI graphics card
PCI (Peripheral Component Interconnect) graphics cards are usually used in earlier or streamlined computers. Such computers must rely on PCI interface graphics cards due to the removal of the AGP standard slot. Known to be used mostly from 486 to the early era of Pentium II. But until the display chip cannot directly support AGP, some manufacturers continue to manufacture graphics cards based on AGP to PCI. The latest known PCI interface graphics cards are GeForce GT 610 PCI (SPARKLE system) model GRSP610L1024LC, ATI HD 4350 PCI (HIS system) and HIS HD 5450 PCI (HIS system) HIS 5450 Silence 512MB DDR3 PCI DVI/HDMI/VGA Product number H545H512P.
AGP graphics card
AGP (Accelerated GraphicsPort) is a 32-bit bus interface developed by Intel Corporation in 1996 to enhance the display performance of computer systems. There are AGP 1X, AGP 2X, AGP 4X, and finally AGP 8X, with bandwidths of 266MB/s, 533MB/s, 1066MB/s, and 2133 MB/s. Among them, AGP 4X is not compatible with the previous voltage. Among them, "Wildcat4 7210" of 3DLABS is the strongest professional-grade AGP graphics accelerator card, while ATI's RadeonHD 4670 and HD3850 are the most powerful consumer-grade AGP graphics accelerator cards of the year (2007).
PCI Express graphics card
PCI Express (also known as PCI-E) is the latest graphics interface for graphics cards. It is used to replace AGP graphics cards. Faced with the continuous advancement of 3D display technology in the future, the bandwidth of AGP is no longer sufficient to handle huge data operations. The PCI-Express graphics cards with the highest performance are nVidia's "NVIDIA Titan V" and AMD's "Radeon Pro Duo (Fiji)". At present, the graphics cards produced after 2007 can support dual graphics technology (nVIDIA's SLi and nvlink and AMD's CrossFire).
External PCI Express graphics card
Use a USB or Thunderbolt high-bandwidth cable to connect to an external PCI Express graphics card box, which requires an independent power supply.
Catalogue
FPGA / CPLD
Memory
MOS 
MCU 
DSP
OCEP
Secondary 
Other 