Overblog Suivre ce blog
Editer l'article Administration Créer mon blog
8 janvier 2011 6 08 /01 /janvier /2011 08:00

A video card, video adapter, graphics accelerator card, display adapter, or graphics card is an expansion card whose function is to generate output images to a display  (Dell XPS M1210 Batteryhttp://www.hdd-shop.co.uk .

Many video cards offer added functions, such as accelerated rendering of 3D scenes and 2D graphics, video capture, TV-tuner adapter, MPEG-2/MPEG-4 decoding, FireWire, light pen, TV output, or the ability to connect multiple monitors (multi-monitor)  (Dell Studio XPS 1340 Battery)      .

Other modern high performance video cards are used for more graphically demanding purposes, such as PC games.

Video hardware can be integrated on the motherboard, often occurring with early machines. In this configuration it is sometimes referred to as a video controller or graphics controller (Dell Studio XPS 1640 Battery)   .

Modern low-end to mid-range motherboards often include a graphics chipset developed by the developer of the northbridge(i.e. an nForce chipset with Nvidia graphics or an Intel chipset with Intel graphics) on the motherboard. This graphics chip usually has a small quantity of embedded memory and takes some of the system's main RAM, reducing the total RAM available (Dell Studio XPS 1640 Battery)      .

This is usually called integrated graphics or on-board graphics, and is low-performance and undesirable for those wishing to run 3D applications. A dedicated Graphics Card on the other hand has its own RAM and Processor specifically for processing video images, and thus offloads this work from the CPU and system RAM  (Dell Vostro 1710 Battery)   .

Almost all of these motherboards allow the disabling of the integrated graphics chip in BIOS, and have an AGP, PCI, or PCI Express slot for adding a higher-performance graphics card in place of the integrated graphics. Despite the performance limitations, around 95% of new computers are sold with integrated graphics processors  (Dell KM958 battery)    ,

leaving it for the individual user to decide whether to install a dedicated Graphics card.

Components

A modern video card consists of a printed circuit board on which the components are mounted  (Sony VGP-BPS13 battery)  .

These include:

Graphics processing unit (GPU)

A GPU is a dedicated processor optimized for accelerating graphics. The processor is designed specifically to perform floating-point calculations, which are fundamental to 3D graphics rendering   (Sony VGP-BPS13/B battery)    .

The main attributes of the GPU are the core clock frequency, which typically ranges from 250 MHz to 4 GHz and the number of pipelines (vertex and fragment shaders), which translate a 3D image characterized by vertices and lines into a 2D image formed by pixels  (Sony VGP-BPS13/S battery)      .

Modern GPUs are massively parallel, and fully programmable. Their computing power is orders of magnitude higher than that of CPUs. As consequence, they challenge CPUs in high performance computing, leading manufacturers like Intel and AMD to integrate video, or massive parallelism, on processors   (Sony VGP-BPS13A/B battery)    .

Video BIOS

The video BIOS or firmware contains the basic program, which is usually hidden, that governs the video card's operations and provides the instructions that allow the computer and software to interact with the card. It may contain information on the memory timing, operating speeds and voltages of the graphics processor, RAM, and other information  (Sony VGP-BPS13B/B battery)    .

It is sometimes possible to change the BIOS (e.g. to enable factory-locked settings for higher performance), although this is typically only done by video card overclockers and has the potential to irreversibly damage the card.

Video memory

The memory capacity of most modern video cards ranges from 128 MB to 4 GB  (Sony VGP-BPL9 battery)        .

Since video memory needs to be accessed by the GPU and the display circuitry, it often uses special high-speed or multi-port memory, such as VRAM, WRAM, SGRAM, etc. Around 2003, the video memory was typically based on DDR technology. During and after that year   (Sony VGP-BPS13B/B battery)    ,

manufacturers moved towards DDR2, GDDR3, GDDR4 andGDDR5. The effective memory clock rate in modern cards is generally between 400 MHz and 3.8 GHz.

Video memory may be used for storing other data as well as the screen image, such as the Z-buffer  Sony VGP-BPL15 battery ,

which manages the depth coordinates in3D graphics, textures, vertex buffers, and compiled shader programs.

RAMDAC

The RAMDAC, or Random Access Memory Digital-to-Analog Converter, converts digital signals to analog signals for use by a computer lay that uses analog inputs such as CRT displays   Dell Inspiron E1505 battery .

The RAMDAC is a kind of RAM chip that regulates the functioning of the graphics card. Depending on the number of bits used and the RAMDAC-data-transfer rate, the converter will be able to support different computer-display refresh rates. With CRT displays, it is best to work over 75 Hz and never under 60 Hz, in order to minimize flicker   Dell Latitude E6400 battery .

(With LCD displays, flicker is not a problem.) Due to the growing popularity of digital computer displays and the integration of the RAMDAC onto the GPU die, it has mostly disappeared as a discrete component. All current LCDs, plasma displays and TVs work in the digital domain and do not require a RAMDAC   HP Pavilion dv6000 Battery .

There are few remaining legacy LCD and plasma displays that feature analog inputs (VGA, component, SCART etc.) only. These require a RAMDAC, but they reconvert the analog signal back to digital before they can display it, with the unavoidable loss of quality stemming from this digital-to-analog-to-digital conversion  SONY VAIO VGN-FZ Battery .

Motherboard interface

Chronologically, connection systems between video card and motherboard were, mainly:

  • S-100 bus: designed in 1974 as a part of the Altair 8800, it was the first industry-standard bus for the microcomputer industrySONY VAIO VGN-FZ18 Battery .
  • ISA: Introduced in 1981 by IBM, it became dominant in the marketplace in the 1980s. It was an 8 or 16-bit bus clocked at 8 MHz.
  • NuBus: Used in Macintosh II, it was a 32-bit bus with an average bandwidth of 10 to 20 MB/s  SONY VAIO VGN-FZ180E Battery .
  • MCA: Introduced in 1987 by IBM it was a 32-bit bus clocked at 10 MHz.
  • EISA: Released in 1988 to compete with IBM's MCA, it was compatible with the earlier ISA bus. It was a 32-bit bus clocked at 8.33 MHz  SONY VAIO VGN-FZ220E Battery .
  • VLB: An extension of ISA, it was a 32-bit bus clocked at 33 MHz.
  • PCI: Replaced the EISA, ISA, MCA and VESA buses from 1993 onwards. PCI allowed dynamic connectivity between devices, avoiding the jumpers manual adjustments. It is a 32-bit bus clocked 33 MHz  SONY VAIO VGN-FZ340E Battery .
  • UPA: An interconnect bus architecture introduced by Sun Microsystems in 1995. It had a 64-bit bus clocked at 67 or 83 MHz.
  • USB: Mostly used for other types of devices, but there are USB displays  SONY VAIO VGN-FZ430E Battery .
  • AGP: First used in 1997, it is a dedicated-to-graphics bus. It is a 32-bit bus clocked at 66 MHz.
  • PCI-X: An extension of the PCI bus, it was introduced in 1998. It improves upon PCI by extending the width of bus to 64-bit and the clock frequency to up to 133 MHz  SONY VAIO VGN-FZ460E Battery .
  • PCI Express: Abbreviated PCIe, it is a point to point interface released in 2004. In 2006 provided double the data-transfer rate of AGP. It should not be confused with PCI-X, an enhanced version of the original PCI specification  SONY VAIO VGN-FZ480E Battery .

In the attached table  is a comparison between a selection of the features of some of those interfaces.
Cooling devices

Video cards may use a lot of electricity, which is converted into heat. If the heat isn't dissipated, the video card could overheat and be damaged  SONY VAIO VGN-FZ4000 Battery .

Cooling devices are incorporated to transfer the heat elsewhere. Three types of cooling devices are commonly used on video cards:

  • Heat sink: a heat sink is a passive-cooling device. It conducts heat away from the graphics card's core, or memory, by using a heat-conductive metal (most commonly aluminum or copper)  SONY VAIO VGN-FZ31E Battery ;
  • sometimes in combination with heat pipes. It uses air (most common), or in extreme cooling situations, water (see water block), to remove the heat from the card. When air is used, a fan is often used to increase cooling effectiveness  SONY VAIO VGN-FZ31B Battery .
  • Computer fan: an example of an active-cooling part. It is usually used with a heat sink. Due to the moving parts, a fan requires maintenance and possible replacement. The fan speed or actual fan can be changed for more efficient or quieter cooling  SONY VAIO VGN-FZ31J Battery .
  • Water block: a water block is a heat sink suited to use water instead of air. It is mounted on the graphics processor and has a hollow inside. Water is pumped through the water        SONY VAIO VGN-FZ31M Battery

Power demand

As the processing power of video cards has increased, so has their demand for electrical power. Current high-performance video cards tend to consume a great deal of power. While CPU and power supply makers have recently moved toward higher efficiency, power demands of GPUs have continued to rise, so the video card may be the biggest electricity user in a computer  SONY VAIO VGN-FZ31Z Battery .

Although power supplies are increasing their power too, the bottleneck is due to the PCI-Express connection, which is limited to supplying 75 Watts.Modern video cards with a power consumption over 75 Watts usually include a combination of six-pin (75W) or eight-pin (150W) sockets that connect directly to the power supply  SONY VAIO VGN-FZ38M Battery .

The Feature connector was an internal connector found mostly in some older VESA Local Bus, ISA and PCI graphics cards, but also on some early AGP ones       SONY VGP-BPS8 Battery .

It was intended for use by devices which needed to exchange large amounts of data with the graphics card without hogging a computer system's CPU or data bus, such as TV tuner cards, video capture cards, MPEG video decoders, first generation 3D graphic acceleratorcards and the such     SONY VGP-BPS13 Battery .

Several standard existed for feature connectors, depending on the bus and graphics card type. Most of them were simply an 8, 16 or 32-bit wide internal connector, transferring data from and to the graphics card to another device, bypassing the system's CPU and memory completely      SONY VGP-BPS13/S Battery .

Their speeds often far exceeded the speed of normal ISA or even early PCI buses, (e.g. 40 MByte/s for a standard ISA-based SVGA, up to 150 MByte/s for a PCI or VESA-based one, while the standard 16 bit ISA bus ran at ~5.3 MByte/s and the VESA bus at up to 160 MByte/s bandwidth      SONY VGP-BPS13A/B Battery .

The Feature connector bandwidths were far beyond the capabilities of e.g. a 386, 486 and barely handled by an earlyPentium.

Depending on the implementation, it could be uni or bi-directional, and carry analog color information as well as data  SONY VGP-BPS13B/B Battery .

Unlike analog overlay devices however, a feature connector carried mainly data and essentially allowed an expansion card to access the graphics cardVideo RAM directly, although directing this data stream to the system's CPU and RAM was not always possible, limiting its usefulness mainly to display purposes  SONY VGP-BPS13A/S Battery .

Although its use rapidly declined after the introduction of the faster AGP internal bus, it was, at its time, the only feasible way to connect certain types of graphics-intensive devices to an average computing system without exceeding the available CPU power and memory bandwidth, and without the disadvantages and limitations of a purely analog overlay  SONY VGP-BPS13AS Battery .

The idea of accessing a video card's memory directly has recently resurfaced with the introduction of the Scalable Link Interface (SLI) technology, although this technology is aimed at connecting two equally powered and complete graphic cards in order to produce a single, increased performance visual output, and not e.g. directly interfacing TV tuner cards Dell Inspiron 1320n Battery .

General-purpose computing on graphics processing units (GPGPU, also referred to as GPGP and less often GP²) is the technique of using a GPU, which typically handles computation only forcomputer graphics, to perform computation in applications traditionally handled by the CPU  Dell Inspiron 1464 Battery .

It is made possible by the addition of programmable stages and higher precision arithmetic to the rendering pipelines, which allows software developers to use stream processing on non-graphics data  Dell Inspiron 1564 Battery .

GPU improvements

GPU functionality has, traditionally, been very limited. In fact, for many years the GPU was only used to accelerate certain parts of the graphics pipeline. Some improvements were needed before GPGPU became feasible   Dell Inspiron 1764 Battery .

Programmability

Programmable vertex and fragment shaders were added to the graphics pipeline to enable game programmers to generate even more realistic effects. Vertex shaders allow the programmer to alter per-vertex attributes, such as position, color, texture coordinates, and normal vector     Dell Studio 1450 Battery .

Fragment shaders are used to calculate the color of a fragment, or per-pixel. Programmable fragment shaders allow the programmer to substitute, for example, a lighting model other than those provided by default by the graphics card, typically simple Gouraud shading      Dell Studio 1457 Battery .

Shaders have enabled graphics programmers to create lens effects, displacement mapping, and depth of field.

The programmability of the pipelines have trended , according to Microsoft’s DirectX specification, with DirectX8 introducing Shader Model 1.1, DirectX8.1 Pixel Shader Models 1.2, 1.3 and 1.4, and DirectX9 defining Shader Model 2.x and 3.0  Dell Latitude D610 Battery .

Each shader model increased the programming model flexibilities and capabilities, ensuring the conforming hardware follows suit. The DirectX10 specification introduces Shader Model 4.0 which unifies the programming specification for vertex, geometry (“Geometry Shaders” are new to DirectX10) and fragment processingallowing for a better fit for unified shader hardware, thus providing a single computational pool of programmable resource  Toshiba NB100 Battery .

Data types

Pre-DirectX9 graphics cards only supported paletted or integral color types. Various formats are available, each containing a red element, a green element, and a blue element . Sometimes an additional alpha value is added, to be used for transparency  Toshiba Satellite M65 battery .

Common formats are:

  • 8 bits per pixel – Palette mode[vague], where each value is an index in a table with the real color value specified in one of the other formats. Possibly two bits for red, three bits for green, and three bits for blue  Toshiba Satellite M60 battery .
  • 16 bits per pixel – Usually allocated as five bits for red, six bits for green, and five bits for blue.
  • 24 bits per pixel – eight bits for each of red, green, and blue
  • 32 bits per pixel – eight bits for each of red, green, blue, and alpha      Dell Latitude D830 Battery

For early fixed-function or limited programmability graphics (i.e. up to and including DirectX8.1-compliant GPUs) this was sufficient because this is also the representation used in displays     Dell Latitude D620 Battery .

This representation does have certain limitations, however. Given sufficient graphics processing power even graphics programmers would like to use better formats, such as floating point data formats, in order to obtain effects such as high dynamic range imaging  Dell Inspiron Mini 10 Battery .

Many GPGPU applications require floating point accuracy, which came with graphics cards conforming to the DirectX9 specification.

DirectX9 Shader Model 2.x suggested the support of two precision types: full and partial precision. Full precision support could either be FP32 and FP24 (floating point 24-bit per component) or greater, while partial precision was FP16  Sony VGN-FW11S Battery.

ATI’s R300 series of GPUs supported FP24 precision only in the programmable fragment pipeline (although FP32 was supported in the vertex processors) whileNvidia’s NV30 series supported both FP16 and FP32; other vendors such as S3 Graphics and XGI supported a mixture of formats up to FP24  Sony VGN-FW11M Battery .

Shader Model 3.0 altered the specification, increasing full precision requirements to a minimum of FP32 support in the fragment pipeline. ATI’s Shader Model 3.0 compliant R5xx generation (Radeon X1000 series) supports just FP32 throughout the pipeline while Nvidia’s NV4x and G7x series continued to support both FP32 full precision and FP16 partial precisions  Sony VGN-FW139E/H battery .

Although not stipulated by Shader Model 3.0, both ATI and Nvidia’s Shader Model 3.0 GPUs introduced support for blendable FP16 render targets, more easily facilitating the support for High Dynamic Range Rendering      Dell Latitude E5400 Battery .

The implementations of floating point on Nvidia GPUs are mostly IEEE compliant; however, this is not true across all vendors. This has implications for correctness which are considered important to some scientific applications   Dell Latitude E4200 Battery .

While 64-bit floating point values (double precision float) are commonly available on CPUs, these are not universally supported on GPUs; some GPU architectures sacrifice IEEE compliance while others lack double-precision altogether. There have been efforts to emulate double-precision floating point values on GPUs  Dell Inspiron 300M Battery ;

however, the speed tradeoff negates any benefit to offloading the computation onto the GPU in the first place.

Most operations on the GPU operate in a vectorized fashion: a single operation can be performed on up to four values at once  Dell Vostro A840 Battery .

For instance, if one color <R1, G1, B1> is to be modulated by another color <R2, G2, B2>, the GPU can produce the resulting color <R1*R2, G1*G2, B1*B2> in a single operation. This functionality is useful in graphics because almost every basic data type is a vector (either 2-, 3-, or 4-dimensional)   Dell Studio 1737 battery .

Examples include vertices, colors, normal vectors, and texture coordinates. Many other applications can put this to good use, and because of their higher performance, vector instructions (SIMD) have long been available on CPUs   Dell Inspiron E1505 battery .

In November 2006 Nvidia launched CUDA, a SDK and API that allows a programmer to use the C programming language to code algorithms for execution on Geforce 8 series GPUs. AMD offers a similar SDK+API for their ATI-based GPUs, that SDK and technology is called FireStream SDK (formerly a thin hardware interfaceClose to Metal)  Dell RM791 battery ,

designed to compete directly with Nvidia's CUDA. OpenCL from Khronos Group is used paired with OpenGL to unify the C languages extension between different architectures; it support both Nvidia and AMD/ATI GPUs and general-purpose CPUs too  Dell XPS M1530 battery .

GPGPU compared, for example, to traditional floating point accelerators such as the 64-bit CSX700 boards from ClearSpeed that are used in today's supercomputers, current top-end GPUs from Nvidia and AMD emphasize single-precision (32-bit) computation; double-precision (64-bit) computation executes much more slowly  Dell XPS M2010 battery .

GPGPU programming concepts

GPUs are designed specifically for graphics and thus are very restrictive in terms of operations and programming. Because of their nature, GPUs are only effective at tackling problems that can be solved using stream processing and the hardware can only be used in certain ways   Acer Aspire One battery .

Stream processing

GPUs can only process independent vertices and fragments, but can process many of them in parallel. This is especially effective when the programmer wants to process many vertices or fragments in the same way   Toshiba Satellite P10 Battery .

In this sense, GPUs are stream processors – processors that can operate in parallel by running a single kernel on many records in a stream at once   SONY VGN-FZ210CE Battery .

A stream is simply a set of records that require similar computation. Streams provide data parallelism. Kernels are the functions that are applied to each element in the stream. In the GPUs, verticesand fragments are the elements in streams and vertex and fragment shaders are the kernels to be run on them   Dell Precision M70 Battery .

Since GPUs process elements independently there is no way to have shared or static data. For each element we can only read from the input, perform operations on it, and write to the output. It is permissible to have multiple inputs and multiple outputs, but never a piece of memory that is both readable and writable Toshiba Satellite L305 Battery .

Arithmetic intensity is defined as the number of operations performed per word of memory transferred. It is important for GPGPU applications to have high arithmetic intensity else the memory access latency will limit computational speedup .

Ideal GPGPU applications have large data sets, high parallelism, and minimal dependency between data elements  Toshiba Satellite T4900 Battery .

GPU programming concepts

Computational resources

There are a variety of computational resources available on the GPU:

  • Programmable processors – Vertex, primitive, and fragment pipelines allow programmer to perform kernel on streams of data
  • Rasterizer – creates fragments and interpolates per-vertex constants such as texture coordinates and color Toshiba PA3399U-2BRS battery
  • Texture Unit – read only memory interface
  • Framebuffer – write only memory interface    Toshiba Satellite A200 Battery

In fact, the programmer can substitute a write only texture for output instead of the framebuffer. This is accomplished either through Render to Texture (RTT), Render-To-Backbuffer-Copy-To-Texture(RTBCTT), or the more recent stream-out  Toshiba Satellite 1200 Battery .

Textures as stream

The most common form for a stream to take in GPGPU is a 2D grid because this fits naturally with the rendering model built into GPUs. Many computations naturally map into grids: matrix algebra, image processing, physically based simulation, and so on  Toshiba Satellite M300 Battery .

Since textures are used as memory, texture lookups are then used as memory reads. Certain operations can be done automatically by the GPU because of this.

Kernels

Kernels can be thought of as the body of loops         Sony Vaio PCG-5G2L Battery .

For example, if the programmer were operating on a grid on the CPU they might have code that looked like this:

On the GPU, the programmer only specifies the body of the loop as the kernel and what data to loop over by invoking geometry processing      Sony Vaio PCG-5G3L Battery .

Flow control

In sequential code it is possible to control the flow of the program using if-then-else statements and various forms of loops. Such flow control structures have only recently been added to GPUs. Conditional writes could be accomplished using a properly crafted series of arithmetic/bit operations, but looping and conditional branching were not possible  Sony Vaio PCG-5J1L Battery .

Recent GPUs allow branching, but usually with a performance penalty. Branching should generally be avoided in inner loops, whether in CPU or GPU code, and various techniques, such as static branch resolution, pre-computation, and Z-cull  can be used to achieve branching when hardware support does not exist   Sony Vaio PCG-5K2L Battery .

GPU techniques

Map

The map operation simply applies the given function (the kernel) to every element in the stream. A simple example is multiplying each value in the stream by a constant (increasing the brightness of an image)  Sony Vaio PCG-5J2L Battery .

The map operation is simple to implement on the GPU. The programmer generates a fragment for each pixel on screen and applies a fragment program to each one. The result stream of the same size is stored in the output buffer.

Reduce

Some computations require calculating a smaller stream (possibly a stream of only 1 element) from a larger stream Sony Vaio PCG-5K1L Battery .

This is called a reduction of the stream. Generally a reduction can be accomplished in multiple steps. The results from the previous step are used as the input for the current step and the range over which the operation is applied is reduced until only one stream element remains     Sony Vaio PCG-5L1L Battery .

Stream filtering

Stream filtering is essentially a non-uniform reduction. Filtering involves removing items from the stream based on some criteria.

Scatter

The scatter operation is most naturally defined on the vertex processor   Sony Vaio PCG-6S2L Battery .

The vertex processor is able to adjust the position of the vertex, which allows the programmer to control where information is deposited on the grid. Other extensions are also possible, such as controlling how large an area the vertex affects  Sony Vaio PCG-6S3L Battery .

The fragment processor cannot perform a direct scatter operation because the location of each fragment on the grid is fixed at the time of the fragment's creation and cannot be altered by the programmer. However, a logical scatter operation may sometimes be recast or implemented with an additional gather step     Sony Vaio PCG-6V1L Battery .

A scatter implementation would first emit both an output value and an output address. An immediately following gather operation uses address comparisons to see whether the output value maps to the current output slot.

Gather

The fragment processor is able to read textures in a random access fashion, so it can gather information from any grid cell, or multiple grid cells, as desired       Sony Vaio PCG-6W1L Battery .

Sort

The sort operation transforms an unordered set of elements into an ordered set of elements. The most common implementation on GPUs is using sorting networks.

Search

The search operation allows the programmer to find a particular element within the stream, or possibly find neighbors of a specified element.       Sony Vaio PCG-6W2L Battery .

The GPU is not used to speed up the search for an individual element, but instead is used to run multiple searches in parallel.

GeForce is a brand of graphics processing units (GPUs) designed by Nvidia. As of 2009, there have been eleven iterations of the design       Sony Vaio PCG-6W3L Battery .

The first GeForce products were discrete GPUs designed for use on add-on graphics boards, intended for the high-margin PC gaming market. Later diversification of the product-line covered all tiers of the PC graphics market, from cost-sensitive (Proof) motherboard-integrated GPUs to mainstream add-in retail-boards       Sony Vaio PCG-7111L Battery .

Most recently, Geforce technology has been introduced into Nvidia's line of embedded application processors, designed for electronic handhelds and mobile handsets  Sony Vaio PCG-7112L Battery .

With respect to discrete GPUs, found in add-in graphics-boards, Nvidia's GeForce and ATI's Radeon GPUs are the only remaining competitors in the high-end market. With the recent announcement of Larrabee, Intel has stated its intention to (eventually) compete in the same high-end GPU market as AMD and Nvidia   Sony Vaio PCG-7113L Battery .

Along with its nearest competitor, the AMD (ATI) Radeon, the Geforce architecture is moving toward GPGPU (General Purpose-Graphics Processor Unit). GPGPU is expected to expand GPU functionality beyond the traditional rasterization of 3D graphics, to turn it into a high-performance computing device able to execute arbitrary programming code in the same way a CPU does  Sony Vaio PCG-7133L Battery .

Name origin

The "GeForce" name originated from a contest held by Nvidia in early 1999. Called "Name That Chip", the company called out to the public to name the successor to the RIVA TNT2 line of graphics boards. There were over 12,000 entries received and 7 winners received a RIVA TNT2 Ultra graphics card as a reward      Sony Vaio PCG-7Z2L Battery .

Generations

GeForce 256

Launched on August 31, 1999, the GeForce 256 (NV10) was the first PC graphics chip with hardware transform, lighting, and shading although 3D games utilizing this feature did not appear until later. Initial GeForce 256 boards shipped with SDR SDRAM memory, and later boards shipped with faster DDR SDRAM memory     Sony Vaio PCG-8Y1L Battery .

GeForce 2 Series

Launched in April 2000, the first GeForce2 (NV15) was another high-performance graphics chip. Nvidia moved to a twin texture processor per pipeline (4x2) design, doubling texture fillrate per clock compared to GeForce 256  Sony Vaio PCG-8Y2L Battery .

Later, Nvidia released the GeForce2 MX (NV11), which offered performance similar to the GeForce 256 but at a fraction of the cost. The MX was a compelling value in the low/mid-range market segments and was popular with OEM PC manufacturers and users alikeSony Vaio PCG-8Z1L Battery .

GeForce 3 Series

Launched in February 2001, the GeForce3 (NV20) introduced programmable pixel shaders to the GeForce family. It had good overall performance and shader support, making it popular with enthusiasts although it never hit the midrange price point. A derivative of the GeForce3, NV2A, was developed for the Microsoft Xbox game console  Sony Vaio PCG-8Z2L Battery .

GeForce 4 Series

Launched in February 2002, the high-end GeForce4 Ti (NV25) was mostly a refinement to the GeForce3. The biggest advancements included enhancements to anti-aliasing capabilities, an improved memory controller, a second vertex shader, and a manufacturing process size reduction to increase clock speeds  Sony VAIO PCG-5G2L Battery .

Another "family member," the budget GeForce4 MX, was based on the GeForce2, with a few additions from the new GeForce4 Ti line. It targeted the value segment of the market and lacked pixel shaders  Sony VAIO PCG-5G3L Battery .

GeForce FX Series

Launched in 2003, the GeForce FX (NV30) was a huge change in architecture compared to its predecessors. The GPU was designed not only to support the new Shader Model 2 specification but also to perform well on older titles. However, initial models suffered from weak floating point shader performance and excessive heat which required two-slot cooling solutions  Sony VAIO PCG-5J1L Battery .

Products in this series carry the 5000 model number, as it is the fifth generation of the GeForce, though Nvidia marketed the cards as GeForce FX instead of GeForce 5 to show off "the dawn of cinematic rendering"   Sony VAIO PCG-5K2L Battery .

GeForce 6 Series

Launched in April 2004, the GeForce 6 (NV40) added Shader Model 3.0 support to the GeForce family, while correcting the weak floating point shader performance of its predecessor  Sony VAIO PCG-5J2L Battery .

It also implemented high dynamic range imaging and introduced SLI (Scalable Link Interface) and PureVideo capability (integrated DVD Video decoder, eliminates the need for software video decoders).

GeForce 7 Series

The 7th generation GeForce (G70/NV47) was launched in June 2005 and was the last video card designed for AGP bus  Sony VAIO PCG-5K1L Battery .

The design was a refined version of GeForce 6, with the major improvements being a widened pipeline and an increase in clock speed. The GeForce 7 also offers new transparency supersampling and transparency multisampling anti-aliasing modes (TSAA and TMAA). These new anti-aliasing modes were later enabled for the GeForce 6 series as well  Sony VAIO PCG-5L1L Battery .

A modified version of GeForce 7800GTX called the RSX 'Reality Synthesizer' is used as the main GPU in the PlayStation 3 from Sony.

GeForce 8 Series

Released on November 8, 2006, the 8th generation GeForce (G80 originally) was the first ever GPU to fully support Direct3D 10  Sony VAIO PCG-6S2L Battery .

Built on a brand new architecture, manufactured in 80 nm, it has a fully unified shader architecture. Originally just the 8800GTX, the GTS was released months into the product line's life, and it took nearly 6 months for mid-range and OEM/mainstream cards to be integrated into the 8-series  Sony VAIO PCG-6S3L Battery .

The Die-shrink down to 65 nm and a revision to the G80 design, codenamed G92, were implemented into the 8 series with the 8800GS, the 8800GT, and 8800GTS-512. First released on October 29, 2007, almost one whole year after the initial G80 release  Sony VAIO PCG-6V1L Battery .

GeForce 9 Series / GeForce 100 Series

The first product was released on February 21, 2008.  Not even four months older than the initial G92 release, all 9-series designs, both currently-out and speculated, are simply revisions to existing late 8-series products  Sony VAIO PCG-6W1L Battery .

The 9800GX2 uses two G92 GPUs, as used in later 8800 cards, in a dual PCB configuration while still only requiring a single PCI-Express 16x slot. The 9800GX2 utilizes two separate 256-bit memory busses, one for each GPU and its respective 512MB of memory, which equates to an overall of 1GB of memory on the card Sony VAIO PCG-6W2L Battery

(although the SLI configuration of the chips necessitates mirroring the frame buffer between the two chips, thus effectively halving the memory performance of a 256-bit/512MB configuration). The later 9800GTX features a single G92 GPU, 256-bit data bus, and 512MB of GDDR3 memory       Sony VAIO PCG-6W3L Battery .

Prior to the release, no concrete information was known except officials claiming the next generation products having close to 1 TFLOPS performance while the GPU cores still being manufactured in the 65 nm process, and reports about Nvidia downplaying the significance of Direct3D 10.1   Sony VAIO PCG-7111L Battery .

On March 2009, several sources reported that nVidia had quietly launched a new series of its flagship GeForce products, designated GeForce 100 Series, which consists of rebadged 9 Series parts. The only official source of information on GeForce 100 Series at this time is "nVidia GeForce Family" web page and corresponding product pages   Sony VAIO PCG-7112L Battery .

According to this web page, GeForce 100 products are not available for individual purchase.

GeForce 200 Series / GeForce 300 Series

Based on the GT200 graphics processor consisting of 1.4 billion transistors, the 200 series was launched on 16 June 2008 Sony VAIO PCG-7113L Battery .

The next generation of the GeForce series takes the card-naming scheme in a new direction, by replacing the series number (such as 8800 for 8-series cards) with the GTX or GTS suffix (which used to go at the end of card names, denoting their 'rank' among other similar models), and then adding model-numbers such as 260 and 280 after that   Sony VAIO PCG-7133L Battery .

The series features the new GT200 core on a 65nm die. The first products were the GeForce GTX 260 and the more expensive GeForce GTX 280. The GeForce 310 was released on November 27, 2009, which is a rebrand of GeForce 210. According to Nvidia, the naming for the 300 series will be allocated for DirectX 10.1 compatible GPU rebrand in the future  Sony VAIO PCG-7Z1L Battery .

GeForce 400 Series / GeForce 500 Series

Nvidia announced and released the GeForce GTX 470 and GTX 480, the first cards based on the new Fermi architecture codenamed GF100, and the first to utilize 1GB or more of newerGDDR5 memory  Sony VAIO PCG-7Z2L Battery .

They were released on April 7, 2010. Later that year, Nvidia introduced the GeForce GTX 465 as a cutdown, cheaper version of the GF100 chip to target at mainstream users. The GTX 465 was quickly replaced by the GTX 460, based on the GF104 architecture, which featured lower power consumption and better performance Sony VAIO PCG-8Y1L Battery .

Soon after, Nvidia released mainstream versions of Fermi architecture, also known as GF106 and GF108, for consumers as well as OEMs. NVIDIA also released a flagship GPU based on a revised GF100 architecture (GF110), called the GTX 580, that featured higher performance/power efficiency than the GTX 480    Sony VAIO PCG-8Y2L Battery .

Future development

  • In September 2010, nVidia officially revealed general information regarding two future lines of GeForce cards, codenamed "Kepler" and "Maxwell". The Kepler architecture, which nVidia states will be available in 2011, will be the successor to Fermi and will be produced on a 28 nm fabrication process     Sony VAIO PCG-8Z1L Battery .
  • Maxwell, the probable successor to Kepler, is currently expected to be available in 2013.

mGPUs

Beginning with the nForce 4, nVidia has included onboard graphics solutions in their motherboard chipsets. These onboard graphics solutions are called mGPUs (motherboard GPUs). As technology progressed, Nvidia developed a break-through mobile GPU called the NVidia ION graphics processor    Sony VAIO PCG-8Z2L Battery .

The ION GPU can deliver 1080p video without lag or video tearing. ION video evidence

Mobile GPUs

Since the GeForce2, Nvidia has produced a number of graphics chipsets for notebook computers under the GeForce Go branding. Most of the features present in the desktop counterparts are present in the mobile ones  Sony VGP-BPS21 Battery .

However these GPUs do not perform as well as their desktop counterpart. Nvidia later rebranded their mobile chipset for the GeForce 8 based GPUs the GeForce 8M series. In 1st Quarter 2009 the Geforce 200M series were released   Sony VGP-BPS21A Battery .

However these cards are actually based on the G92 core also found in 8 and 9 series GPUs, as opposed to a true GT200 core, mainly for power consumption reasons.

Product naming scheme

With the release of the GeForce 100 series of cards, nVidia cards now use a prefix to designate their category   Sony VGP-BPS21B Battery .

So far, the GTX, GTS, GT and G prefixes have been announced.The first digit in the name of a card represents its generation, while the second and third digits represent the performance of the card relative to others in the family        Sony VGP-BPS21/S Battery .

AMD Radeon, formerly ATI Radeon, is a brand of graphics processing units (GPU) that since 2000 has been manufactured by ATI Technologies and subsequently AMD and is the successor to their Rage line. There are four different groups, which can be differentiated by the DirectX generation they support    Sony VGP-BPS21A/B Battery .

More specific distinctions can also be followed, such as the HyperZ version, the number of pixel pipelines, and of course, the memory andprocessor clock speeds. The brand was previously known as "ATI Radeon" until August 2010, when it was renamed to create a more unified brand image  SONY VGP-BPS21 Battery .

Current products will retain the ATI moniker, however future products will utilise the new branding.

Card brands

AMD no longer sells Radeon cards directly at the retail level. Instead, it sells Radeon GPUs to third-party manufacturers, who build and sell the Radeon-based video cards to the OEM and retail channels        SONY VGP-BPS21A Battery .

Manufacturers of the Radeon cards include Sapphire, XFX, Asus, Gigabyte, MSI, Biostar, Gainward, Diamond, HIS, PowerColor, Club 3D, VisionTek and Force3D.

Naming scheme

At current, ATI names each card by generation, series, and by performance   SONY VGP-BPS21B Battery .

The first number is the generation number, for example, 5000, and this is related to the chipset used by the video card. The second number indicates the series quality in the generation, starting from 0400 to 0600 at entry level, for media and home theatre, 0700 for low intensity video games     SONY VGP-BPS21/S Battery

(typically using older graphics engines, or widespread games, such as Starcraft and World of Warcraft) or high-intensity games with lowered settings, and 0800 for high-intensity games, such as Crysis or Far Cry 2. 0900 is a special denotation, first used on the Radeon 5970, relating to a dual chip or internal ATI CrossFire card      SONY VGP-BPS21A/B Battery .

The third digit is the relative quality, within a series- a 5850 is less powerful than a 5870. Typically, a card of a higher series will always have more processing power than a card in a lower series, even if the relative quality is better (a 5770 will be trumped by a 5850)     WD passport essential (500GB/640GB) .

Windows

The ATI Radeon graphics driver package for Windows operating system is called ATI Catalyst.

There are unofficial modifications available such as Omega drivers and DNA drivers       WD passport essential (250GB/320GB) .

These drivers typically consist of mixtures of various driver file versions with some registry variables altered and are advertised as offering superior performance or image quality. They are, of course, unsupported, and as such, are not guaranteed to function correctly  WD  passport essential SE (750GB/1TB)         .

Some of them also provide modified system files for hardware enthusiasts to run specific graphics cards outside of their specifications.

Macintosh

ATI previously offered driver updates for their retail and integrated Macintosh video cards and chipsets       WD  passport elite(250GB/320GB) .

However, ever since ATI's acquisition by AMD, ATI no longer supplies or supports drivers for Mac OS Classic, or OS-X. OS-X drivers can be downloaded from Apple's support website, while Mac OS Classic drivers can be obtained from 3rd party websites that host the older drivers for users to download     WD passport elite(500GB/640GB) .

ATI used to provide a preference panel for use in Mac OS X called ATI Displays which can be used both with retail and OEM versions of its cards. Though it gives more control over advanced features of the graphics chipset, ATI Displays has limited functionality compared to their Catalyst for Windows product      WD  passport studio for Mac(320GB/500GB) .

ATI stopped support for Mac OS 9 after the Radeon R200 cards, making the last officially supported card the Radeon 9250. The Radeon R100 cards up to the Radeon 7200 can still be used with even older Mac OS versions such as System 7, although not all features are taken advantage of by the older operating system      WD  passport studio for Mac(500GB/640GB) .

Linux

Initially, ATI did not produce Radeon drivers for Linux, instead giving hardware specifications and documentation to Direct Rendering Infrastructure (DRI) developers under various non-disclosure agreements           WD  Elements series(250GB/320GB) .

In mid 2004, however, ATI started to support Linux (XFree86, X.Org), hiring a new Linux driver team to produce fglrx. Their new proprietary Linux drivers, instead of being a port of the Windows Catalystdrivers, were based on the Linux drivers for the FireGL  WD  Elements SE(500GB/640GB)

(the FireGL drivers worked with Radeons before, but didn't officially support them), a card geared towards graphics producers, not gamers; though the display drivers part is now based on the same sources as the ones from Windows Catalyst since version 4.x in late 2004. The proprietary Linux drivers could support R200 (Radeon 8500-9200, 9250) chips  WD Elements SE(750GB/1TB) .

For a better display driver, the repository drivers are recommended.

The frequency of driver updates increased in late 2004, releasing Linux drivers every two months, half as often as their Windows counterparts. Then since late 2005 this has been increased to monthly releases, inline with the Windows Catalyst releases WD  Elements desktop(500GB/640GB) .

In 2008, ATI changed its release cycles and driver versions; now referred to as Catalyst <year>.<month>, the driver package still includes an internal 8.xx.x driver revision, but it is now monthly, sharing a common code base with the Windows driver (starting with internal release 8.43) WD  Elements desktop(750GB/1TB) .

In 2009, the Catalyst driver officially dropped support for R500 and older chips, the FOSS driver being deemed stable and complete enough. The last driver release supporting older architectures is Catalyst 9.3.

For information on alternative Open Source drivers, see below         WD  Elements desktop(1.5 TB/2TB) .

FreeBSD

FreeBSD systems have the same open-source support for Radeon hardware as Linux, including 2D and 3D acceleration for Radeon R100, R200, and R300-series chipsets       WD  passport essential SE (750GB/1TB)--USB 3.0)      .

The R300 support, as with Linux, remained experimental due to being reverse-engineered from ATI's proprietary drivers, but with the release of official documentation by AMD (following its buyout of ATI), all Radeon families up to R700 have at least 2D support in the FOSS drivers    WD  passport essential (500GB/640GB) ,

with basic video acceleration and power management, and up to R500, have at least 'basic' (up to OpenGL 1.5 feature set, GLSL is still a work in progress) 3D accel

eration. On R600/700, 3D is still very much experimental, and Evergreen support has barely started due to lack of documentation  WD  passport for Mac(320GB/500GB) .

ATI does not support its proprietary fglrx driver on FreeBSD, it has been partly ported by a third party as of January 2007. This is in contrast to its main rival, NVIDIA, which has periodically released its proprietary driver for FreeBSD since November 2002 (64-bit beta driver available as of December 3, 2009). In the meantime, the release is similar to Linux  WD  passport for Mac(640GB/1TB) .

MidnightBSD

MidnightBSD supports 2D and 3D acceleration for Radeon R100, R200, and R300 chipsets. This support is similar to FreeBSD and Linux       My book essential 4 generation  (640GB/1TB) .

AmigaOS

Since the introduction of AmigaOS 4 users gained partial support for R100/R200 Radeon cards   (Radeon 8500/9100 have no 3D support). Currently, RadeonHD R700 Amiga OS4 driver is under development by 3rd party developer. The AmigaOne X1000, slated for release in 2010, will include an R700 based GPU      WD  My book essential 4 generation( 1.5TB/2TB) .

BeOS

Although ATI does not provide its own drivers for BeOS, it provides hardware and technical documentation to the Haiku Project who provide drivers with full 2D and video in/out support. They are the sole graphics manufacturer in any way still supporting BeOS  WD  My book elite( 1TB/1.5TB) .

MorphOS

MorphOS supports 2D and 3D acceleration for Radeon R100 and R200 chipsets .

FOSS drivers

On September 12, 2007, AMD released documentation without an NDA for the RV630 (Radeon HD 2600 PRO and Radeon HD 2600 XT) and M56 (Radeon Mobility X1600) chips for open source driver development, for its strategic open source driver development initiative        WD  My book studio(1TB/2TB) .

This initial documentation released sufficient programming information for a skeleton display detection and modesetting driver to be released. This was version 1.0.0 of the radeonhd driver, developed in cooperation with Novell      WD  My book essential 4 generation( 1.5TB/2TB) .

The register reference guides for M76 (Mobility Radeon HD 2600/2700/3600/3800 series) and RS690 (AMD 690 chipset series) were also released on January 4, 2008.

Most of the work is shared with the existing Xorg radeon driver that also supports older Radeon architectures  WD  My book elite(640GB/2TB) .

Conceptually, radeonhd initially tried to directly hit a card's register to perform its operations, while Xorg's driver radeon makes use of AtomBIOS (an abstraction layer created by Ati to ease the programming of new video card drivers) when available   Seagate  expansion portable (320GB/500GB) .

Since AtomBIOS headers have been made public by AMD and are kept up to date, the argument went rather moot.

As of December 2009, the DRM part of the radeon driver is now included in the mainstream Linux kernel, the first version appearing in kernel version 2.6.32, used by default on several GNU/Linux distributions   Seagate  expansion (1.5TB/2TB) .

Partager cet article

Repost 0
Published by batterys - dans Laptop Battery
commenter cet article

commentaires