Graphics processing unit

The components of a GPU.

A graphics processing unit (GPU) is a specialized electronic circuit designed for digital image
processing and to accelerate computer graphics, being present either as a component on a discrete
graphics card or embedded on motherboards, mobile phones, personal computers, workstations, and game
consoles. GPUs are increasingly being used for artificial intelligence (AI) processing due to linear algebra
acceleration, which is also used extensively in graphics processing.

Although there is no single definition of the term, and it may be used to describe any video display
system, in modern use a GPU includes the ability to internally perform the calculations needed for
various graphics tasks, like rotating and scaling 3D images, and often the additional ability to run custom
programs known as shaders. This contrasts with earlier graphics controllers known as video display
controllers which had no internal calculation capabilities, or blitters, which performed only basic memory
movement operations. The modern GPU emerged during the 1990s, adding the ability to perform
operations like drawing lines and text without CPU help, and later adding 3D functionality.
Graphics functions are generally independent and this lends these tasks to being implemented on separate
calculation engines. Modern GPUs include hundreds, or thousands, of calculation units. This made them
useful for non-graphic calculations involving embarrassingly parallel problems due to their parallel
structure. The ability of GPUs to rapidly perform vast numbers of calculations has led to their adoption in
diverse fields including artificial intelligence (AI) where they excel at handling data-intensive and
computationally demanding tasks. Other non-graphical uses include the training of neural networks and
cryptocurrency mining.

History

1960s – 1970s
Dedicated 3D graphics hardware dates back to graphic
terminals such as the Adage AGT-30 from 1968 with matrix
processors. Ikonas made graphics systems with 8- and 24-bit
graphics and 3D acceleration in the late 70s.[1]

Arcade system boards have used specialized 2D graphics

circuits since the 1970s. In early video game hardware, RAM
for frame buffers was expensive, so video chips composited
data together as the display was being scanned out on the
monitor.[2]

A specialized barrel shifter circuit helped the CPU animate

Adage Graphics terminal from 1968
the framebuffer graphics for various 1970s arcade video
brochure
games from Midway and Taito, such as Gun Fight (1975),
Sea Wolf (1976), and Space Invaders (1978).[3] The Namco
Galaxian arcade system in 1979 used specialized graphics hardware that supported RGB color, multi-
colored sprites, and tilemap backgrounds.[4] The Galaxian hardware was widely used during the golden
age of arcade video games, by game companies such as Namco, Centuri, Gremlin, Irem, Konami,
Midway, Nichibutsu, Sega, and Taito.[5]

The Atari 2600 in 1977 used a video shifter called the

Television Interface Adaptor.[6] Atari 8-bit computers
(1979) had ANTIC, a video processor which
interpreted instructions describing a "display list"—
the way the scan lines map to specific bitmapped or
character modes and where the memory is stored (so
there did not need to be a contiguous frame buffer).[7]
6502 machine code subroutines could be triggered on Atari ANTIC microprocessor on an Atari 130XE
scan lines by setting a bit on a display list motherboard
instruction.[8] ANTIC also supported smooth vertical
and horizontal scrolling independent of the CPU.[9]
1980s
In the 1980s significant advancements were made in
professional 3D graphics hardware. Perhaps most impactful
was the 1981 development of the Geometry Engine, a VLSI
vector processor ASIC designed by Jim Clark and Marc
Hannah at Stanford University. This processor is the
forerunner of modern tensor cores and other similar
processors marketed for graphics and AI. The Geometry
Engine went on to be used in Silicon Graphics workstations
for many years. Silicon Graphics's first product, shipped in
November 1983, was the IRIS 1000, a terminal with
hardware-accelerated 3D graphics based on the Geometry Geometry Engine integrated circuit
Engine.[1] The Geometry Engine was capable of
approximately 6 million operations per second.[10]

The NEC μPD7220 was the first implementation of a

personal computer graphics display processor as a
single large-scale integration (LSI) integrated circuit
chip. This enabled the design of low-cost, high-
performance video graphics cards such as those from
Number Nine Visual Technology. It became the best-
known GPU until the mid-1980s.[11] It was the first
fully integrated VLSI (very large-scale integration)
metal–oxide–semiconductor (NMOS) graphics NEC μPD7220A
display processor for PCs, supported up to 1024×1024
resolution, and laid the foundations for the PC
graphics market. It was used in a number of graphics cards and was licensed for clones such as the Intel
82720, the first of Intel's graphics processing units.[12] The Williams Electronics arcade games Robotron:
2084, Joust, Sinistar, and Bubbles, all released in 1982, contain custom blitter chips for operating on 16-
color bitmaps.[13][14]

In 1984, Hitachi released the ARTC HD63484, the first major CMOS graphics processor for personal
computers. The ARTC could display up to 4K resolution when in monochrome mode. It was used in a
number of graphics cards and terminals during the late 1980s.[15]

In 1985, the Amiga was released with a custom

graphics chip called Agnus including a blitter for
bitmap manipulation, line drawing, and area fill. It
also included a coprocessor with its own simple
instruction set, that was capable of manipulating
graphics hardware registers in sync with the video
beam (e.g. for per-scanline palette switches, sprite
multiplexing, and hardware windowing), or driving
the blitter.
MOS 8367R0 – Agnus
Also in 1985, IBM released the Professional Graphics Controller which was a rudimentary 3D card with
640 × 480 256-color graphics which used a dedicated CPU to draw graphics independently of the main
system. It was cloned by a number of makers (including Matrox).[1]

In 1986, Texas Instruments released the TMS34010, the first fully programmable graphics processor.[16]
It could run general-purpose code but also had a graphics-oriented instruction set. During 1990–1992, this
chip became the basis of the Texas Instruments Graphics Architecture ("TIGA") Windows accelerator
cards.

Following in 1987, the IBM 8514 graphics system

was released. It was one of the first video cards for
IBM PC compatibles that implemented fixed-function
2D primitives in electronic hardware. Sharp's
X68000, released in 1987, used a custom graphics
chipset[17] with a 65,536 color palette and hardware
support for sprites, scrolling, and multiple
playfields.[18] It served as a development machine for
Capcom's CP System arcade board. Fujitsu's FM The IBM 8514 Micro Channel adapter, with
Towns computer, released in 1989, had support for a memory add-on
16,777,216 color palette.[19]

For context, IBM also introduced its Video Graphics

Array (VGA) display system in 1987, with a
maximum resolution of 640 × 480 pixels. Unlike
8514/A, VGA had no hardware acceleration features.
In November 1988, NEC Home Electronics
announced its creation of the Video Electronics
Standards Association (VESA) to develop and
promote a Super VGA (SVGA) computer display
standard as a successor to VGA. Super VGA enabled
graphics display resolutions up to 800 × 600 pixels, a
56% increase.[20]
VGA section on the motherboard in IBM PS/55
In 1988 SGI sold IRIS workstation graphics with 10-
12 Geometry Engines and introduced the IrisVision
add-in board for IBM MicroChannel bus (RS/6000) based on the Geometry Engine as well.[1]

In 1988 as well, the first dedicated polygonal 3D graphics boards in arcade machines were introduced
with the Namco System 21[21] and Taito Air System.[22]

1990s
The 1990s again saw considerable advancements in professional workstation 3D graphics hardware from
Sun Microsystems, SGI, and others. The introduction of OpenGL by SGI in 1992 paved the way for
standard hardware-independent 3D programming interfaces.[23][24] However by the mid and late 90s,
professional hardware was being slowly eclipsed by consumer products which offered similar or even
better performance, especially in regards to texture mapping, at a lower cost and on platforms familiar to
end users.[24][25]
In 1991, S3 Graphics introduced the S3 86C911,
which its designers named after the Porsche 911 as an
indication of the performance increase it promised.[26]
The 86C911 spawned a variety of imitators: by 1995,
all major PC graphics chip makers had added 2D
acceleration support to their chips.[27] Fixed-function
Windows accelerators surpassed expensive general-
purpose graphics coprocessors in Windows
Tseng Labs ET4000/W32p
performance, and such coprocessors faded from the
PC market.

In the early- and mid-1990s, real-time 3D graphics

became increasingly common in arcade, computer,
and console games, which led to increasing public
demand for hardware-accelerated 3D graphics. Early
examples of mass-market 3D graphics hardware can
be found in arcade system boards such as the Sega
Model 1, Namco System 22, and Sega Model 2, and
the fifth-generation video game consoles such as the
Saturn, PlayStation, and Nintendo 64. Arcade systems
such as the Sega Model 2 and SGI Onyx-based S3 Graphics ViRGE
Namco Magic Edge Hornet Simulator in 1993 were
capable of hardware T&L (transform, clipping, and
lighting) years before appearing in consumer graphics
cards.[28][29] Another early example is the Super FX
chip, a RISC-based on-cartridge graphics chip used in
some SNES games, notably Doom and Star Fox.
Some systems used DSPs to accelerate
transformations. Fujitsu, which worked on the Sega
Model 2 arcade system,[30] began working on
integrating T&L into a single LSI solution for use in
home computers in 1995;[31] the Fujitsu Pinolite, the
first 3D geometry processor for personal computers,
announced in 1997.[32] The first hardware T&L GPU Voodoo3 2000 AGP card
on home video game consoles was the Nintendo 64's
Reality Coprocessor, released in 1996.[33] In 1997,
Mitsubishi released the 3Dpro/2MP, a GPU capable of transformation and lighting, for workstations and
Windows NT desktops;[34] ATi used it for its FireGL 4000 graphics card, released in 1997.[35]

The term "GPU" was coined by Sony in reference to the 32-bit Sony GPU (designed by Toshiba) in the
PlayStation video game console, released in 1994.[36]

2000s
In October 2002, with the introduction of the ATI Radeon 9700 (also known as R300), the world's first
Direct3D 9.0 accelerator, pixel and vertex shaders could implement looping and lengthy floating point
math, and were quickly becoming as flexible as CPUs, yet orders of magnitude faster for image-array
operations. Pixel shading is often used for bump mapping, which adds texture to make an object look
shiny, dull, rough, or even round or extruded.[37]

With the introduction of the Nvidia GeForce 8 series and new generic stream processing units, GPUs
became more generalized computing devices. Parallel GPUs are making computational inroads against
the CPU, and a subfield of research, dubbed GPU computing or GPGPU for general purpose computing
on GPU, has found applications in fields as diverse as machine learning,[38] oil exploration, scientific
image processing, linear algebra,[39] statistics,[40] 3D reconstruction, and stock options pricing. GPGPUs
were the precursors to what is now called a compute shader (e.g. CUDA, OpenCL, DirectCompute) and
actually abused the hardware to a degree by treating the data passed to algorithms as texture maps and
executing algorithms by drawing a triangle or quad with an appropriate pixel shader. This entails some
overheads since units like the scan converter are involved where they are not needed (nor are triangle
manipulations even a concern—except to invoke the pixel shader).

Nvidia's CUDA platform, first introduced in 2007,[41] was the earliest widely adopted programming
model for GPU computing. OpenCL is an open standard defined by the Khronos Group that allows for
the development of code for both GPUs and CPUs with an emphasis on portability.[42] OpenCL solutions
are supported by Intel, AMD, Nvidia, and ARM, and according to a report in 2011 by Evans Data,
OpenCL had become the second most popular HPC tool.[43]

2010s
In 2010, Nvidia partnered with Audi to power their cars' dashboards, using the Tegra GPU to provide
increased functionality to cars' navigation and entertainment systems.[44] Advances in GPU technology in
cars helped advance self-driving technology.[45] AMD's Radeon HD 6000 series cards were released in
2010, and in 2011 AMD released its 6000M Series discrete GPUs for mobile devices.[46] The Kepler line
of graphics cards by Nvidia were released in 2012 and were used in the Nvidia 600 and 700 series cards.
A feature in this GPU microarchitecture included GPU boost, a technology that adjusts the clock-speed of
a video card to increase or decrease according to its power draw.[47] Kepler also introduced NVENC
video encoding acceleration technology.

The PS4 and Xbox One were released in 2013; they both used GPUs based on AMD's Radeon HD 7850
and 7790.[48] Nvidia's Kepler line of GPUs was followed by the Maxwell line, manufactured on the same
process. Nvidia's 28 nm chips were manufactured by TSMC in Taiwan using the 28 nm process.
Compared to the 40 nm technology from the past, this manufacturing process allowed a 20 percent boost
in performance while drawing less power.[49][50] Virtual reality headsets have high system requirements;
manufacturers recommended the GTX 970 and the R9 290X or better at the time of their release.[51][52]
Cards based on the Pascal microarchitecture were released in 2016. The GeForce 10 series of cards are of
this generation of graphics cards. They are made using the 16 nm manufacturing process which improves
upon previous microarchitectures.[53]

In 2018, Nvidia launched the RTX 20 series GPUs that added ray tracing cores to GPUs, allowing real
time ray tracing to be performant on mass market hardware.[54] Polaris 11 and Polaris 10 GPUs from
AMD are fabricated by a 14 nm process. Their release resulted in a substantial increase in the
performance per watt of AMD video cards.[55] AMD also released the Vega GPU series for the high end
market as a competitor to Nvidia's high end Pascal cards, also featuring HBM2 like the Titan V.
In 2019, AMD released the successor to their Graphics Core Next (GCN) microarchitecture/instruction
set. Dubbed RDNA, the first product featuring it was the Radeon RX 5000 series of video cards.[56] The
company announced that the successor to the RDNA microarchitecture would be incremental (a
"refresh"). AMD unveiled the Radeon RX 6000 series, its RDNA 2 graphics cards with support for
hardware-accelerated ray tracing.[57] The product series, launched in late 2020, consisted of the RX 6800,
RX 6800 XT, and RX 6900 XT.[58][59] The RX 6700 XT, which is based on Navi 22, was launched in
early 2021.[60]

The PlayStation 5 and Xbox Series X and Series S were released in 2020; they both use GPUs based on
the RDNA 2 microarchitecture with incremental improvements and different GPU configurations in each
system's implementation.[61][62][63]

2020s
In the 2020s, GPUs have been increasingly used for calculations involving embarrassingly parallel
problems, such as training of neural networks on enormous datasets that are needed for artificial
intelligence large language models. Specialized processing cores on most modern GPUs that are
dedicated to deep learning provide significant FLOPS performance increases, using 4×4 matrix
multiplication and division. Early implementations, such as Nvidia's Volta microarchitecture, released in
2017[64], saw results of up to 128 TFLOPS in some applications.[65]

Since then, AI Acceleration cores have been a widely adopted feature in consumer and workstation
microarchitectures starting with Nvidia's Turing microarchitecture in 2018[54], named Tensor cores.
Originally used for Deep Learning Super Sampling to enhance gaming performance and improve image
quality, they have since been used in Nvidia's Broadcast ([Link]
ing/broadcast-app/) software to provide many AI powered effects such as voice filtering and video noise
removal.

AMD originally implemented their equivalent "Matrix" Cores for consumers in their RDNA 3
architecture, while Intel has implemented their equivalent "XMX" Cores in all of their Arc GPUs, starting
with the Alchemist microarchitecture.

GPU companies
Many companies have produced GPUs under a number of brand names. In 2009, Intel, Nvidia, and
AMD/ATI were the market share leaders, with 49.4%, 27.8%, and 20.6% market share respectively. In
addition, Matrox[66] produces GPUs. Chinese companies such as Jingjia Micro have also produced GPUs
for the domestic market although in terms of worldwide sales, they lag behind market leaders.[67]

Computational functions
Several factors of GPU construction affect the performance of the card for real-time rendering, such as
the size of the connector pathways in the semiconductor device fabrication, the clock signal frequency,
and the number and size of various on-chip memory caches. Performance is also affected by the number
of streaming multiprocessors (SM) for NVidia GPUs, or compute units (CU) for AMD GPUs, or Xe cores
for Intel Xe based GPUs, which describe the number of on-silicon processor core units within the GPU
chip that perform the core calculations, typically working in parallel with other SM/CUs on the GPU.
GPU performance is typically measured in floating point operations per second (FLOPS); GPUs in the
2010s and 2020s typically deliver performance measured in teraflops (TFLOPS). This is an estimated
performance measure, as other factors can affect the actual display rate.[68]

2D graphics APIs
An earlier GPU may support one or more 2D graphics APIs
for 2D acceleration, such as GDI and DirectDraw.[69]

GPU forms

Terminology The ATI HD5470 GPU (above, with

copper heatpipe attached) features UVD
In the 1970s, the term "GPU" originally stood for graphics
2.1 which enables it to decode AVC and
processor unit and described a programmable processing unit VC-1 video formats.
working independently from the CPU that was responsible for
graphics manipulation and output.[70][71] In 1994, Sony used
the term (with the meaning graphics processing unit) in reference to the PlayStation console's Toshiba-
designed Sony GPU.[36] The term was popularized by Nvidia in 1999, who marketed the GeForce 256 as
"the world's first GPU".[72] It was presented as a "single-chip processor with integrated transform,
lighting, triangle setup/clipping, and rendering engines".[73] Rival ATI Technologies coined the term
"visual processing unit" (VPU) with the release of the Radeon 9700 in 2002.[74] The AMD Alveo
MA35D features dual VPUs, each using the 5 nm process in 2023.[75]

In personal computers, there are two main forms of GPUs: dedicated graphics (also called discrete
graphics) and integrated graphics (also called shared graphics solutions, integrated graphics processors
(IGP), or unified memory architecture (UMA)).[76]

Dedicated graphics processing unit

Dedicated graphics processing units use RAM that is dedicated to the GPU rather than relying on the
computer's main system memory. This RAM is usually specially selected for the expected serial workload
of the graphics card, such as GDDR SDRAM. Sometimes systems with dedicated discrete GPUs were
called "DIS" systems as opposed to "UMA" systems.[77]

Technologies such as Scan-Line Interleave by 3dfx, Scalable Link Interface (SLI) and NVLink by Nvidia
and CrossFire by AMD allow multiple GPUs to draw images simultaneously for a single screen,
increasing the processing power available for graphics. These technologies, however, are increasingly
uncommon; most games do not fully use multiple GPUs, as most users cannot afford them.[78][79][80]
Multiple GPUs are still used on supercomputers (such as in Summit); on workstations to accelerate video
(processing multiple videos at once)[81][82][83] and 3D rendering;[84] for visual effects (VFX);[85] general
purpose graphics processing unit (GPGPU) workloads and for simulations,[86] and in AI to expedite
training, as is the case with Nvidia's lineup of DGX workstations and servers, Tesla GPUs, and Intel's
Ponte Vecchio GPUs.
Integrated graphics processing unit

The position of an integrated GPU in a

northbridge/southbridge system layout.

An ASRock motherboard with integrated

graphics, which has HDMI, VGA and DVI-
out ports.

Integrated graphics processing units (IGPU), also called integrated graphics, shared graphics solutions,
integrated graphics processors (IGP), or unified memory architectures (UMA) use a portion of a
computer's system RAM rather than dedicated graphics memory. IGPs can be integrated onto a
motherboard as part of its northbridge chipset,[87] or on the same die (integrated circuit) with the CPU,
such as Accelerated Processing Unit (AMD APU) or Intel HD Graphics. On certain motherboards,[88]
AMD's IGPs can use dedicated sideport memory: a separate fixed block of high performance memory
that is dedicated for use by the GPU. As of early 2007, computers with integrated graphics account for
about 90% of all PC shipments.[89] They are less costly to implement than dedicated graphics processing,
but tend to be less capable. Historically, integrated processing was considered unfit for 3D games or
graphically intensive programs but could run less intensive programs such as Adobe Flash. Examples of
such IGPs would be offerings from SiS and VIA circa 2004.[90] However, modern integrated graphics
processors such as AMD Accelerated Processing Unit and Intel Graphics Technology, such as HD, UHD,
Iris, Iris Pro, Iris Plus, and Xe-LP, can handle 2D graphics or low-stress 3D graphics.

Because GPU computations are memory-intensive, integrated processing may compete with the CPU for
relatively slow system RAM, as it has minimal or no dedicated video memory. IGPs use system memory
with bandwidth up to a current maximum of 128 gigabytes per second, whereas a discrete graphics card
may have a bandwidth[91] of more than 1000 gigabytes per second between its video random access
memory (VRAM) and GPU core. This memory bus bandwidth can limit the performance of the GPU,
though multi-channel memory can mitigate this deficiency.[92] Older integrated graphics chipsets lacked
hardware transform and lighting, but newer ones include it.[93][94]

On systems with "Unified Memory Architecture" (UMA), including modern AMD processors with
integrated graphics,[95] modern Intel processors with integrated graphics,[96] Apple processors, the PS5
and Xbox Series (among others), the CPU cores and the GPU block share the same pool of RAM and
memory address space.

Stream processing and general purpose GPUs (GPGPU)

It is common to use a general purpose graphics processing unit (GPGPU) as a modified form of stream
processor or a vector processor, running compute kernels. This turns the massive computational power of
a modern graphics accelerator's shader pipeline into general-purpose computing power. In certain
applications requiring massive vector operations, this can yield several orders of magnitude higher
performance than a conventional CPU. The two largest discrete GPU designers, AMD and Nvidia, are
pursuing this approach with an array of applications. Nvidia and AMD collaborated with Stanford
University to create a GPU-based client for the Folding@home distributed computing project for protein
folding calculations. In certain circumstances, the GPU calculates forty times faster than the CPUs
traditionally used by such applications.[97][98]

GPU-based high performance computers play a significant role in large-scale modelling. Three of the ten
most powerful supercomputers in the world take advantage of GPU acceleration.[99]

Since 2005 there has been interest in using the performance offered by GPUs for evolutionary
computation in general, and for accelerating the fitness evaluation in genetic programming in particular.
Most approaches compile linear or tree programs on the host PC and transfer the executable to the GPU
to be run. Typically a performance advantage is only obtained by running the single active program
simultaneously on many example problems in parallel, using the GPU's single instruction, multiple data
(SIMD) architecture.[100] Substantial acceleration can also be obtained by not compiling the programs,
and instead transferring them to the GPU, to be interpreted there.[101]

External GPU (eGPU)

A GPU can be attached to some external bus of a notebook. PCI Express is the only bus used for this
purpose. The port may be, for example, an ExpressCard or mPCIe port (PCIe ×1, up to 5 or 2.5 gigabits
per second respectively), a Thunderbolt 1, 2, or 3 port (PCIe ×4, up to 10, 20, or 40 gigabits per second
respectively), a USB4 port with Thunderbolt compatibility, or an OCuLink port. Those ports are only
available on certain notebook systems.[102] eGPU enclosures include their own power supply (PSU),
because powerful GPUs can consume hundreds of watts.[103]
Energy efficiency
Graphics processing units (GPU) have continued to increase in energy usage, while CPUs designers have
recently focused on improving performance per watt. High performance GPUs may draw large amount of
power, therefore intelligent techniques are required to manage GPU power consumption. Measures like
3DMark2006 score per watt can help identify more efficient GPUs.[104] However that may not
adequately incorporate efficiency in typical use, where much time is spent doing less demanding
tasks.[105]

With modern GPUs, energy usage is an important constraint on the maximum computational capabilities
that can be achieved. GPU designs are usually highly scalable, allowing the manufacturer to put multiple
chips on the same video card, or to use multiple video cards that work in parallel. Peak performance of
any system is essentially limited by the amount of power it can draw and the amount of heat it can
dissipate. Consequently, performance per watt of a GPU design translates directly into peak performance
of a system that uses that design.

Since GPUs may also be used for some general purpose computation, sometimes their performance is
measured in terms also applied to CPUs, such as FLOPS per watt.

Sales
In 2013, 438.3 million GPUs were shipped globally and the forecast for 2014 was 414.2 million.
However, by the third quarter of 2022, shipments of PC GPUs totaled around 75.5 million units, down
19% year-over-year.[106][107]

See also
UALink
Texture mapping unit (TMU)
Render output unit (ROP)
Brute force attack
Computer hardware
Computer monitor
GPU cache
GPU virtualization
Manycore processor
Physics processing unit (PPU)
Tensor processing unit (TPU)
Ray-tracing hardware
Single instruction, multiple threads (SIMT)
Software rendering
Vision processing unit (VPU)
Vector processor
 Video card
Video display controller
Video game console
AI accelerator
GPU Vector Processor internal features

Hardware
List of AMD graphics processing units
List of Nvidia graphics processing units
List of Intel graphics processing units
List of discrete and integrated graphics processing units
Intel GMA
Larrabee
Nvidia PureVideo – the bit-stream technology from Nvidia used in their graphics chips to
accelerate video decoding on hardware GPU with DXVA.
SoC
UVD (Unified Video Decoder) – the video decoding bit-stream technology from ATI to
support hardware (GPU) decode with DXVA

APIs
OpenGL API
OpenCL API
OpenVX API
TensorFlow Lite
Mantle (API)
Metal (API)
Core ML
Vulkan (API)
Direct3D
DirectX Video Acceleration (DxVA) API for Microsoft Windows operating-system.
DirectML
Direct2D
DirectDraw
DirectWrite
Video Acceleration API (VA API)
VDPAU (Video Decode and Presentation API for Unix)
X-Video Bitstream Acceleration (XvBA), the X11 equivalent of DXVA for MPEG-2, H.264,
and VC-1
X-Video Motion Compensation – the X11 equivalent for MPEG-2 video codec only

Applications
GPU cluster
Mathematica – includes built-in support for CUDA and OpenCL GPU execution
 Molecular modeling on GPU
Deeplearning4j – open-source, distributed deep learning for Java

References
1. Jon Peddie (2022). The History of the GPU - Steps to Invention (1st ed.). Springer. p. 424.
ISBN 978-3031109676.
2. Hague, James (September 10, 2013). "Why Do Dedicated Game Consoles Exist?" (https://
[Link]/web/20150504042057/[Link] Programming
in the 21st Century. Archived from the original ([Link] on
May 4, 2015. Retrieved November 11, 2015.
3. "mame/8080bw.c at master 路mamedev/mame 路
GitHub" ([Link]
ame/tree/master/src/mame/drivers/8080bw.c). GitHub.

"mame/mw8080bw.c at master 路
mamedev/mame 路GitHub" ([Link]
dev/mame/tree/master/src/mame/drivers/mw8080bw.c). GitHub.
"Arcade/SpaceInvaders – Computer Archeology" ([Link]
080838/[Link]
[Link]. Archived from the original ([Link]
om/wiki/wiki/Arcade/SpaceInvaders) on 2014-09-13.
4. "mame/galaxian.c at master 路 mamedev/mame 路 GitHub" ([Link]
ame/tree/master/src/mame/video/galaxian.c). GitHub.
5. "mame/galaxian.c at master 路 mamedev/mame 路 GitHub" ([Link]
ame/tree/master/src/mame/drivers/galaxian.c). GitHub.
"MAME – src/mame/drivers/galdrvr.c" ([Link]
ps://[Link]/source/src/mame/drivers/[Link]). Archived from the original (ht
tps://[Link]/source/src/mame/drivers/[Link]) on 3 January 2014.
6. Springmann, Alessondra. "Atari 2600 Teardown: What?s Inside Your Old Console?" (https://
[Link]/wp-dyn/content/article/2010/09/01/[Link]). The
Washington Post. Archived ([Link]
[Link]/wp-dyn/content/article/2010/09/01/[Link]) from the
original on July 14, 2015. Retrieved July 14, 2015.
7. "What are the 6502, ANTIC, CTIA/GTIA, POKEY, and FREDDIE chips?" ([Link]
[Link]/web/20160305010645/[Link] [Link]. Archived from the
original ([Link] on 2016-03-05.
8. Wiegers, Karl E. (April 1984). "Atari Display List Interrupts" ([Link]
m/compute/issue47/153_1_Atari_Display_List_Interrupts.php). Compute! (47): 161.
Archived ([Link]
mpute/issue47/153_1_Atari_Display_List_Interrupts.php) from the original on 2016-03-04.
9. Wiegers, Karl E. (December 1985). "Atari Fine Scrolling" ([Link]
ompute/issue67/338_1_Atari_Fine_Scrolling.php). Compute! (67): 110. Archived ([Link]
[Link]/web/20060216181611/[Link]
_1_Atari_Fine_Scrolling.php) from the original on 2006-02-16.
10. James H. Clark (1982). "The Geometry Engine:A VLSI Geometry System for Graphics" (http
s://[Link]/courses/cs148-10-summer/docs/1982--clark--geometry_engine.pd
f) (PDF). Palo Alto: Stanford University.
11. Hopgood, F. Robert A.; Hubbold, Roger J.; Duce, David A., eds. (1986). Advances in
Computer Graphics II ([Link]
Springer. p. 169. ISBN 9783540169109. "Perhaps the best known one is the NEC 7220."
12. Anderson, Marian (2018-07-18). "Famous Graphics Chips: NEC μPD7220 Graphics Display
Controller" ([Link]
s-chips/). IEEE Computer Society. Retrieved 2023-10-17.
13. Riddle, Sean. "Blitter Information" ([Link] Archived ([Link]
[Link]/web/20151222155908/[Link] from the original on
2015-12-22.
14. Wolf, Mark J. P. (June 2012). Before the Crash: Early Video Game History ([Link]
[Link]/books?id=oK3D4i5ldKgC). Wayne State University Press. p. 185. ISBN 978-
0814337226.
15. Anderson, Marian (2018-10-07). "GPU History: Hitachi ARTC HD63484" ([Link]
[Link]/publications/tech-news/chasing-pixels/gpu-history-hitachi-artc-hd63484/). IEEE
Computer Society. Retrieved 2023-10-17.
16. "Famous Graphics Chips: TI TMS34010 and VRAM. The first programmable graphics
processor chip | IEEE Computer Society" ([Link]
chasing-pixels/Famous-Graphics-Chips-IBMs-professional-graphics-the-PGC-and-8514A/Fa
mous-Graphics-Chips-TI-TMS34010-and-VRAM). 10 January 2019.
17. "X68000" ([Link] Archived ([Link]
0903010307/[Link] from the original on 2014-09-03. Retrieved
2014-09-12.
18. "museum ~ Sharp X68000" ([Link]
[Link]/museum/[Link]?st=1&c=298). [Link]. Archived from the
original ([Link] on 2015-02-
19. Retrieved 2015-01-28.
19. "Hardcore Gaming 101: Retro Japanese Computers: Gaming's Final Frontier" ([Link]
[Link]/JPNcomputers/[Link]). [Link].
Archived ([Link]
t/JPNcomputers/[Link]) from the original on 2011-01-13.
20. Brownstein, Mark (November 14, 1988). "NEC Forms Video Standards Group" ([Link]
[Link]/books?id=wTsEAAAAMBAJ&pg=PT2). InfoWorld. Vol. 10, no. 46. p. 3.
ISSN 0199-6649 ([Link] Retrieved May 27, 2016.
21. "System 16 – Namco System 21 Hardware (Namco)" ([Link]
php?id=536). [Link]. Archived ([Link]
s://[Link]/[Link]?id=536) from the original on 2015-05-18.
22. "System 16 – Taito Air System Hardware (Taito)" ([Link]
id=656). [Link]. Archived ([Link]
[Link]/[Link]?id=656) from the original on 2015-03-16.
23. [Link]
24. Cal Jeffrey (November 10, 2022). "Silicon Graphics: Gone But Not Forgotten" ([Link]
[Link]/article/2142-silicon-graphics/). Techspot.
25. "What Happened to the Silicon Graphics Company?" ([Link]
ppened-to-the-silicon-graphics-company/). Quantum Zeitgeist. July 5, 2024.
26. "S3 Video Boards" ([Link]
g=PA62). InfoWorld. 14 (20): 62. May 18, 1992. Archived ([Link]
1122191720/[Link]
11&hl=en&sa=X&ved=0CBwQ6AEwAGoVChMI85bTh7XYxgIVyyeUCh3Z_wYp#v=onepage
&q=S3%2086C911&f=false) from the original on November 22, 2017. Retrieved July 13,
2015.
27. "What the numbers mean" ([Link]
PC Magazine. 12: 128. 23 February 1993. Archived ([Link]
72653/[Link] from the original on
11 April 2017. Retrieved 29 March 2016.
Singer, Graham. "The History of the Modern Graphics Processor" ([Link]
com/article/650-history-of-the-gpu/). Techspot. Archived ([Link]
60329140009/[Link] from the original
on 29 March 2016. Retrieved 29 March 2016.
28. "System 16 – Namco Magic Edge Hornet Simulator Hardware (Namco)" ([Link]
[Link]/[Link]?id=832). [Link]. Archived ([Link]
40912000953/[Link] from the original on 2014-
09-12.
29. "MAME – src/mame/video/model2.c" ([Link]
[Link]/source/src/mame/video/[Link]). Archived from the original ([Link]
[Link]/source/src/mame/video/[Link]) on 4 January 2013.
30. "System 16 – Sega Model 2 Hardware (Sega)" ([Link]
=713). [Link]. Archived ([Link]
[Link]/[Link]?id=713) from the original on 2010-12-21.
31. "3D Graphics Processor Chip Set" ([Link]
[Link]/wp-content/uploads/hc_archives/hc07/3_Tue/HC7.S5/[Link]) (PDF).
Archived from the original ([Link]
_Tue/HC7.S5/[Link]) (PDF) on 2016-10-11. Retrieved 2016-08-08.
"3D-CG System with Video Texturing for Personal Computers" ([Link]
eb/20140906132147/[Link]
(PDF). Archived from the original ([Link]
[Link]) (PDF) on 2014-09-06. Retrieved 2016-08-08.
32. "Fujitsu Develops World's First Three Dimensional Geometry Processor" ([Link]
m/jp/news/1997/Jul/[Link]). [Link]. Archived ([Link]
4938/[Link] from the original on 2014-09-12.
33. "The Nintendo 64 is one of the greatest gaming devices of all time" ([Link]
web/20151118044413/[Link]
g-devices-o-1722364688). xenol. Archived from the original ([Link]
endo-64-is-one-of-the-greatest-gaming-devices-o-1722364688) on 2015-11-18.
34. "Mitsubishi's 3DPro/2mp Chipset Sets New Records for Fastest 3D Graphics Accelerator for
Windows NT Systems; 3DPro/2mp grabs Viewperf performance lead; other high-end
benchmark tests clearly show that 3DPro's performance outdistances all Windows NT
competitors" ([Link]
Mitsubishi%27s+3DPro%2f2mp+Chipset+Sets+New+Records+for+Fastest+3D...-a0194651
88). Archived from the original ([Link]
Chipset+Sets+New+Records+for+Fastest+3D...-a019465188) on 2018-11-15. Retrieved
2022-02-18.
35. Vlask. "VGA Legacy MKIII – Diamond Fire GL 4000 (Mitsubishi 3DPro/2mp)" ([Link]
[Link]/[Link]/component/k2/item/547-diamond-fire-gl-4000-mitsubishi-3dpro-2mp).
Archived ([Link]
omponent/k2/item/547-diamond-fire-gl-4000-mitsubishi-3dpro-2mp) from the original on
2015-11-18.
36. "Is it Time to Rename the GPU? | IEEE Computer Society" ([Link]
ations/tech-news/chasing-pixels/is-it-time-to-rename-the-gpu). 17 July 2018.
37. Dreijer, Søren. "Bump Mapping Using CG (3rd Edition)" ([Link]
120195901/[Link]
hp). Archived from the original ([Link]
mapping_using_cg.php) on 2010-01-20. Retrieved 2007-05-30.
38. Raina, Rajat; Madhavan, Anand; Ng, Andrew Y. (2009-06-14). "Large-scale deep
unsupervised learning using graphics processors". Proceedings of the 26th Annual
International Conference on Machine Learning – ICML '09. [Link]. pp. 1–8.
doi:10.1145/1553374.1553486 ([Link]
ISBN 9781605585161. S2CID 392458 ([Link]
39. "Linear algebra operators for GPU implementation of numerical algorithms" ([Link]
[Link]/viewdoc/download?doi=[Link].1988&rep=rep1&type=pdf), Kruger and
Westermann, International Conference on Computer Graphics and Interactive Techniques,
2005
40. Liepe; et al. (2010). "ABC-SysBio—approximate Bayesian computation in Python with GPU
support" ([Link]
org/content/26/14/[Link]). Bioinformatics. 26 (14): 1797–1799.
doi:10.1093/bioinformatics/btq278 ([Link]
PMC 2894518 ([Link] PMID 20591907
([Link] Archived from the original ([Link]
[Link]/content/26/14/[Link]) on 2015-11-05. Retrieved 2010-10-15.
41. Sanders, Jason; Kandrot, Edward (2010-07-19). CUDA by Example: An Introduction to
General-Purpose GPU Programming, Portable Documents ([Link]
s?id=49OmnOmTEtQC). Addison-Wesley Professional. ISBN 9780132180139. Archived (htt
ps://[Link]/web/20170412034641/[Link]
TEtQC) from the original on 2017-04-12.
42. "OpenCL – The open standard for parallel programming of heterogeneous systems" (https://
[Link]/opencl/). [Link]. Archived ([Link]
3233/[Link] from the original on 2011-08-09.
43. Handy, Alex (2011-09-28). "AMD helps OpenCL gain ground in HPC space" ([Link]
com/amd/amd-helps-opencl-gain-ground-in-hpc-space/). SD Times. Retrieved 2023-06-04.
44. Teglet, Traian (8 January 2010). "NVIDIA Tegra Inside Every Audi 2010 Vehicle" ([Link]
[Link]/news/[Link]).
Archived ([Link]
[Link]) from the original on 2016-10-
04. Retrieved 2016-08-03.
45. "School's in session – Nvidia's driverless system learns by watching" ([Link]
[Link]/cars/nvidia-gpu-driverless-car/). 2016-04-30. Archived ([Link]
20160501203712/[Link] from the
original on 2016-05-01. Retrieved 2016-08-03.
46. "AMD Radeon HD 6000M series – don't call it ATI!" ([Link]
n-hd-6000m-series-dont-call-it-ati/). CNET. Archived ([Link]
195008/[Link] from the
original on 2016-10-11. Retrieved 2016-08-03.
47. "Nvidia GeForce GTX 680 2GB Review" ([Link]
a-geforce-gtx-680-2gb-review/4). Archived ([Link]
tps://[Link]/hardware/2012/03/22/nvidia-geforce-gtx-680-2gb-review/4) from the
original on 2016-09-11. Retrieved 2016-08-03.
48. "Xbox One vs. PlayStation 4: Which game console is best?" ([Link]
gaming/156273-xbox-720-vs-ps4-vs-pc-how-the-hardware-specs-compare). ExtremeTech.
20 November 2015. Retrieved 2019-05-13.
49. "Kepler TM GK110" ([Link]
[Link]) (PDF). NVIDIA Corporation. 2012. Archived ([Link]
g/web/20161011194501/[Link]
[Link]) (PDF) from the original on October 11, 2016. Retrieved
August 3, 2016.
50. "Taiwan Semiconductor Manufacturing Company Limited" ([Link]
dicatedFoundry/technology/[Link]). [Link]. Archived ([Link]
eb/20160810092021/[Link]
m) from the original on 2016-08-10. Retrieved 2016-08-03.
51. "Building a PC for the HTC Vive" ([Link] 2016-06-
16. Archived ([Link]
ding-a-vive-pc/) from the original on 2016-07-29. Retrieved 2016-08-03.
52. "VIVE Ready Computers" ([Link] Vive. Archived ([Link]
org/web/20160224182407/[Link] from the original
on 2016-02-24. Retrieved 2021-07-30.
53. "Nvidia's monstrous Pascal GPU is packed with cutting-edge tech and 15 billion transistors"
([Link]
[Link]). 5 April 2016. Archived
([Link]
mponents-graphics/nvidias-monstrous-pascal-gpu-is-packed-with-cutting-edge-tech-and-15-
[Link]) from the original on 2016-07-31. Retrieved 2016-08-03.
54. Sarkar, Samit (20 August 2018). "Nvidia RTX 2070, RTX 2080, RTX 2080 Ti GPUs revealed:
specs, price, release date" ([Link]
x-2080-ti-2070-specs-release-date-price-turing). Polygon. Retrieved 11 September 2019.
55. "AMD RX 480, 470 & 460 Polaris GPUs To Deliver The 'Most Revolutionary Jump In
Performance' Yet" ([Link] 2016-01-16.
Archived ([Link]
olaris-11-10-gpu/) from the original on 2016-08-01. Retrieved 2016-08-03.
56. AMD press release: "AMD Announces Next-Generation Leadership Products at Computex
2019 Keynote" ([Link]
generation-leadership-products-computex-2019-keynote). AMD. Retrieved October 5, 2019.
57. "AMD to Introduce New Next-Gen RDNA GPUs in 2020, Not a Typical 'Refresh' of Navi" (htt
ps://[Link]/news/amds-navi-to-be-refreshed-with-next-gen-rdna-architectu
re-in-2020). Tom's Hardware. 2020-01-29. Retrieved 2020-02-08.
Garreffa, Anthony (September 9, 2020). "AMD to reveal next-gen Big Navi RDNA 2
graphics cards on October 28" ([Link]
next-gen-big-navi-rdna-2-graphics-cards-on-october-28/[Link]). TweakTown.
Retrieved September 9, 2020.
Lyles, Taylor (September 9, 2020). "AMD's next-generation Zen 3 CPUs and Radeon RX
6000 'Big Navi' GPU will be revealed next month" ([Link]
1429127/amd-zen-3-cpu-big-navi-gpu-events-october). The Verge. Retrieved
September 10, 2020.
58. "AMD Teases Radeon RX 6000 Card Performance Numbers: Aiming For 3080?" ([Link]
[Link]/web/20201008200930/[Link]
adeon-rx-6000-card-performance-numbers-aiming-for-3080). AnandTech. 2020-10-08.
Archived from the original ([Link]
6000-card-performance-numbers-aiming-for-3080) on 2020-10-08. Retrieved 2020-10-25.
"AMD Announces Ryzen 'Zen 3' and Radeon 'RDNA2' Presentations for October: A New
Journey Begins" ([Link]
om/show/16077/amd-announces-ryzen-zen-3-and-radeon-rdna2-presentations-for-octob
er-a-new-journey-begins). AnandTech. 2020-09-09. Archived from the original ([Link]
[Link]/show/16077/amd-announces-ryzen-zen-3-and-radeon-rdna2-presen
tations-for-october-a-new-journey-begins) on 2020-09-10. Retrieved 2020-10-25.
59. Judd, Will (October 28, 2020). "AMD unveils three Radeon 6000 graphics cards with ray
tracing and RTX-beating performance" ([Link]
20-10-28-amd-unveils-three-radeon-6000-graphics-cards-with-ray-tracing-and-impressive-p
erformance). Eurogamer. Retrieved October 28, 2020.
60. Mujtaba, Hassan (2020-11-30). "AMD Radeon RX 6700 XT 'Navi 22 GPU' Custom Models
Reportedly Boost Up To 2.95 GHz" ([Link]
odels-boost-up-to-2-95-ghz-220w-tgp/). Wccftech. Retrieved 2020-12-03.
Tyson, Mark (December 3, 2020). "AMD CEO keynote scheduled for CES 2020 on 12th
January" ([Link]
2020-12th-january/). HEXUS. Retrieved 2020-12-03.
Cutress, Ian (January 12, 2021). "AMD to Launch Mid-Range RDNA 2 Desktop Graphics
in First Half 2021" ([Link]
[Link]/show/16402/amd-to-launch-midrange-rdna-2-desktop-graphics-in-first-half-2021).
AnandTech. Archived from the original ([Link]
launch-midrange-rdna-2-desktop-graphics-in-first-half-2021) on January 12, 2021.
Retrieved January 4, 2021.
61. Funk, Ben (December 12, 2020). "Sony PS5 Gets A Full Teardown Detailing Its RDNA 2
Guts And Glory" ([Link]
ws/sony-playstation-5-independent-teardown-ifixit). Hot Hardware. Archived from the
original ([Link] on
December 12, 2020. Retrieved January 3, 2021.
62. Gartenberg, Chaim (March 18, 2020). "Sony reveals full PS5 hardware specifications" (http
s://[Link]/2020/3/18/21183181/sony-ps5-playstation-5-specs-details-hardware-
processor-8k-ray-tracing). The Verge. Retrieved January 3, 2021.
63. Smith, Ryan. "Microsoft Drops More Xbox Series X Tech Specs: Zen 2 + RDNA 2, 12
TFLOPs GPU, HDMI 2.1, & a Custom SSD" ([Link]
[Link]
n-2-rdna-2-12-tflops-gpu-hdmi-21-a-custom-ssd). AnandTech. Archived from the original (htt
ps://[Link]/show/15546/microsoft-drops-more-xbox-series-x-tech-specs-zen-
2-rdna-2-12-tflops-gpu-hdmi-21-a-custom-ssd) on February 24, 2020. Retrieved
2020-03-19.
64. "NVIDIA Volta AI Architecture" ([Link]
ure/). NVIDIA. Retrieved 2026-03-03.
65. Smith, Ryan. "NVIDIA Volta Unveiled: GV100 GPU and Tesla V100 Accelerator Announced"
([Link]
a-volta-unveiled-gv100-gpu-and-tesla-v100-accelerator-announced). AnandTech. Archived
from the original ([Link]
and-tesla-v100-accelerator-announced) on May 11, 2017. Retrieved 16 August 2018.
66. "Matrox Graphics – Products – Graphics Cards" ([Link]
cts/graphics_cards). [Link]. Archived ([Link]
tps://[Link]/graphics/en/products/graphics_cards/) from the original on 2014-02-
05. Retrieved 2014-01-21.
67. Pan, Che (31 July 2023). "Blacklisted Jingjia Micro to develop GPUs in Wuxi in latest chip
self sufficiency move" ([Link]
ctioned-chip-maker-jingjia-micro-develop-gpus-wuxi-latest-sign-chinas-self). South China
Morning Post. Retrieved 20 January 2025.
68. Hruska, Joel (February 10, 2021). "How Do Graphics Cards Work?" ([Link]
[Link]/gaming/269335-how-graphics-cards-work). Extreme Tech. Retrieved July 17, 2021.
69. CL-GD5446 64-bit VisualMedia Accelerator Preliminary Data Book ([Link]
chip/documentation/[Link]) (PDF), Cirrus Logic,
November 1996, retrieved 30 January 2024 – via The Datasheet Archive
70. Barron, E. T.; Glorioso, R. M. (September 1973). "A micro controlled peripheral processor".
Conference record of the 6th annual workshop on Microprogramming – MICRO 6. pp. 122–
128. doi:10.1145/800203.806247 ([Link]
ISBN 9781450377836. S2CID 36942876 ([Link]
76).
71. Levine, Ken (August 1978). "Core standard graphic package for the VGI 3400" ([Link]
[Link]/doi/abs/10.1145/965139.807405). ACM SIGGRAPH Computer Graphics. 12 (3): 298–
300. doi:10.1145/965139.807405 ([Link]
72. "NVIDIA Launches the World's First Graphics Processing Unit: GeForce 256" ([Link]
[Link]/object/IO_20020111_5424.html). Nvidia. 31 August 1999. Archived ([Link]
[Link]/web/20160412035751/[Link]
from the original on 12 April 2016. Retrieved 28 March 2016.
73. "Graphics Processing Unit (GPU)" ([Link] Nvidia. 16
December 2009. Archived ([Link]
[Link]/object/[Link]) from the original on 8 April 2016. Retrieved 29 March 2016.
74. Pabst, Thomas (18 July 2002). "ATi Takes Over 3D Technology Leadership With Radeon
9700" ([Link]
700,[Link]). Tom's Hardware. Retrieved 29 March 2016.
75. Child, J. (6 April 2023). "AMD Rolls Out 5 nm ASIC-based Accelerator for the Interactive
Streaming Era" ([Link]
erator-for-the-interactive-streaming-era). EETech Media. Retrieved 24 December 2023.
76. "Help Me Choose: Video Cards" ([Link]
video-card-inspiron-lt). Dell. Retrieved 2016-09-17.
77. "Nvidia Optimus documentation for Linux device driver" ([Link]
[Link]). freedesktop. 13 November 2023. Retrieved 24 December 2023.
78. Abazovic, F. (3 July 2015). "Crossfire and SLI market is just 300.000 units" ([Link]
[Link]/news/graphics/38134-crossfire-and-sli-market-is-just-300-000-units). fudzilla.
Retrieved 24 December 2023.
79. "Is Multi-GPU Dead?" ([Link] 7 January 2018.
80. "Nvidia SLI and AMD CrossFire is dead – but should we mourn multi-GPU gaming? |
TechRadar" ([Link]
d-we-mourn-multi-gpu-gaming). 24 August 2019.
81. "NVIDIA FFmpeg Transcoding Guide" ([Link]
g-guide/). 24 July 2019.
82. "Hardware Selection and Configuration Guide DaVinci Resolve 15" ([Link]
[Link]/ConfigGuides/DaVinci_Resolve_15_Mac_Configuration_Guide.pdf)
(PDF). BlackMagic Design. 2018. Retrieved 31 May 2022.
83. "Recommended System: Recommended Systems for DaVinci Resolve" ([Link]
[Link]/recommended/Recommended-Systems-for-DaVinci-Resolve-187/Hardware-Re
commendations). Puget Systems.
"GPU Accelerated Rendering and Hardware Encoding" ([Link]
ctkb/multi/[Link]).
84. "V-Ray Next Multi-GPU Performance Scaling" ([Link]
V-Ray-Next-Multi-GPU-Performance-Scaling-1559/). 20 August 2019.
"FAQ | GPU-accelerated 3D rendering software | Redshift" ([Link]
20200411151101/[Link] Archived from the original (htt
ps://[Link]/support/faq) on 2020-04-11. Retrieved 2020-03-03.
"OctaneRender 2020™ Preview is here!" ([Link]
aqs/). Otoy.
"Exploring Performance with Autodesk's Arnold Renderer GPU Beta" ([Link]
om/article/autodesk-arnold-render-gpu-beta-performance/). 8 April 2019.
"GPU Rendering – Blender Manual" ([Link]
cles/gpu_rendering.html).
85. "V-Ray for Nuke – Ray Traced Rendering for Compositors | Chaos Group" ([Link]
[Link]/vray/nuke).
"System Requirements | Nuke | Foundry" ([Link]
ements).
86. "What about multi-GPU support? – Folding@home" ([Link]
mmon/frequently-asked-questions-common-ati-nvidia-gpu2-clients-2/multi-gpu-support/).
87. "Evolution of Intel Graphics: I740 to Iris Pro" ([Link]
[Link]). 4 February 2017.
88. "GA-890GPA-UD3H overview" ([Link]
[Link]/products/[Link]?pid=3785#ov). GIGABYTE. Archived from the
original ([Link] on 2015-04-
15. Retrieved 2015-04-15.
89. Key, Gary. "AnandTech – μATX Part 2: Intel G33 Performance Review" ([Link]
org/web/20080531045027/[Link]
[Link]. Archived from the original ([Link]
=3111&p=23) on 2008-05-31.
90. Tscheblockov, Tim. "Xbit Labs: Roundup of 7 Contemporary Integrated Graphics Chipsets
for Socket 478 and Socket A Platforms" ([Link]
s://[Link]/articles/chipsets/display/[Link]). X-bit labs.
Archived from the original ([Link]
[Link]) on 2007-05-26. Retrieved 2007-06-03.
91. "GPU Memory Bandwidth Evolution 2007-2025: NVIDIA AMD Intel" ([Link]
[Link]/memory-bandwidth-statistics). Axiom Gaming. Retrieved 17 August 2025.
92. Coelho, Rafael (18 January 2016). "Does dual-channel memory make difference on
integrated video performance?" ([Link]
ake-difference-integrated-video-performance/). Hardware Secrets. Retrieved 4 January
2019.
93. Sanford, Bradley. "Integrated Graphics Solutions for Graphics-Intensive Applications" (http
s://[Link]/us-en/assets/content_type/white_papers_and_tech_docs/Integrated_Gra
phics_Solutions_white_paper_rev61.pdf) (PDF). AMD. Archived ([Link]
b/20071128165723/[Link]
h_docs/Integrated_Graphics_Solutions_white_paper_rev61.pdf) (PDF) from the original on
2007-11-28. Retrieved 2007-09-02.
 94. Sanford, Bradley. "Integrated Graphics Solutions for Graphics-Intensive Applications" (http
s://[Link]/news/46773-amd-announces-radeon-hd-7970-claims-fastest-gpu-titl
[Link]). TechSpot. Archived ([Link]
[Link]/news/[Link]) from
the original on 2012-01-07. Retrieved 2007-09-02.
95. Shimpi, Anand Lal. "AMD Outlines HSA Roadmap: Unified Memory for CPU/GPU in 2013,
HSA GPUs in 2014" ([Link]
om/show/5493/amd-outlines-hsa-roadmap-unified-memory-for-cpugpu-in-2013-hsa-gpus-in-
2014). [Link]. Archived from the original ([Link]
493/amd-outlines-hsa-roadmap-unified-memory-for-cpugpu-in-2013-hsa-gpus-in-2014) on
February 4, 2012. Retrieved 2024-01-08.
96. Lake, Adam T. "Getting the Most from OpenCL™ 1.2: How to Increase Performance by..." (h
ttps://[Link]/content/www/us/en/developer/articles/training/getting-the-most-from-op
encl-12-how-to-increase-performance-by-minimizing-buffer-copies-on-intel-processor-graphi
[Link]) Intel. Retrieved 2024-01-08.
97. Murph, Darren (29 September 2006). "Stanford University tailors Folding@home to GPUs"
([Link]
Archived ([Link]
9/29/stanford-university-tailors-folding-home-to-gpus/) from the original on 2007-10-12.
Retrieved 2007-10-04.
98. Houston, Mike. "Folding@Home – GPGPU" ([Link]
Archived ([Link]
uston/) from the original on 2007-10-27. Retrieved 2007-10-04.
99. "Top500 List – June 2012 | TOP500 Supercomputer Sites" ([Link]
40113044747/[Link] [Link]. Archived from the
original ([Link] on 2014-01-13. Retrieved 2014-01-21.
100. Nickolls, John (July 2008). "Stanford Lecture: Scalable Parallel Programming with CUDA on
Manycore GPUs" ([Link] YouTube. Archived
([Link]
OpbE) from the original on 2016-10-11.
Harding, S.; Banzhaf, W. "Fast genetic programming on GPUs" ([Link]
[Link]/~wbl/biblio/gp-html/eurogp07_harding.html). Archived ([Link]
20080609231021/[Link]
l) from the original on 2008-06-09. Retrieved 2008-05-01.
101. Langdon, W.; Banzhaf, W. "A SIMD interpreter for Genetic Programming on GPU Graphics
Cards" ([Link]
Archived ([Link]
lio/gp-html/langdon_2008_eurogp.html) from the original on 2008-06-09. Retrieved
2008-05-01.
V. Garcia and E. Debreuve and M. Barlaud. Fast k nearest neighbor search using GPU.
In Proceedings of the CVPR Workshop on Computer Vision on GPU, Anchorage,
Alaska, June 2008.
102. Mohr, Neil. "How to make an external laptop graphics adaptor" ([Link]
ews/computing-components/graphics-cards/how-to-make-an-external-laptop-graphics-adapt
or-915616). TechRadar. Archived ([Link]
[Link]/news/computing-components/graphics-cards/how-to-make-an-external-lapt
op-graphics-adaptor-915616) from the original on 2017-06-26.
103. "Best External Graphics Card 2020 (EGPU) [The Complete Guide]" ([Link]
[Link]/best-external-graphics-card/). 16 March 2020.
104. Atwood, Jeff (2006-08-18). "Video Card Power Consumption" ([Link]
0080908060043/[Link] Archived from the
original ([Link] on 8 September 2008.
Retrieved 26 March 2008.
105. "Video card power consumption" ([Link]
[Link]/articles/video/display/[Link]). Xbit Labs. Archived from the original
([Link] on 2011-09-04.
106. "GPU Q3'22 biggest quarter-to-quarter drop since the 2009 recession" ([Link]
[Link]/news/q322-biggest-qtr-to-qtr-drop-since-the-2009-recession/). Jon Peddie Research.
2022-11-20. Retrieved 2023-06-06.
107. "Graphics chips market is showing some life" ([Link]
aphics-chips-market-is-showing-some-life). TG Daily. August 20, 2014. Archived ([Link]
[Link]/web/20140826115733/[Link]
ps-market-is-showing-some-life) from the original on August 26, 2014. Retrieved August 22,
2014.

Sources
Peddie, Jon (1 January 2023). The History of the GPU – New Developments ([Link]
[Link]/books?id=vfKkEAAAQBAJ). Springer Nature. ISBN 978-3-03-114047-1.
OCLC 1356877844 ([Link]

External links
NVIDIA – What is GPU computing? ([Link]
tml)
The GPU Gems book series ([Link]
[Link]/content/gpu-gems)
– A Graphics Hardware History ([Link] Archived (https://
[Link]/web/20220331004621/[Link] 2022-03-
31 at the Wayback Machine
How GPUs work ([Link]
~gfx/papers/[Link]?paper_id=59)
GPU Caps Viewer – Video card information utility ([Link]
er/)
ARM Mali GPUs Overview ([Link]
[Link]/learn-about-mali/about-mali/arm-mali-gpus/)

Retrieved from "[Link]