Editing Graphics processing unit (section)

==Computational functions==
Modern GPUs have traditionally used most of their [[transistor]]s to do calculations related to [[3D computer graphics]]. In addition to the 3D hardware, today's GPUs include basic 2D acceleration and [[framebuffer]] capabilities (usually with a VGA compatibility mode). Newer cards such as AMD/ATI HD5000–HD7000 lack dedicated 2D acceleration; it is emulated by 3D hardware. GPUs were initially used to accelerate the memory-intensive work of [[texture mapping]] and [[Rendering (computer graphics)|rendering]] polygons. Later, dedicated hardware was added to accelerate [[geometry|geometric]] calculations such as the [[rotation]] and [[Translation (geometry)|translation]] of [[vertex (geometry)|vertices]] into different [[coordinate system]]s. Recent developments in GPUs include support for [[programmable shader]]s which can manipulate vertices and textures with many of the same operations that are supported by [[Central processing unit|CPUs]], [[oversampling]] and [[interpolation]] techniques to reduce [[aliasing]], and very high-precision [[color space]]s.

{{anchor|Compute unit|Streaming multiprocessor}}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 [[CPU cache|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 discrete 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.<ref>{{cite web | url = https://www.extremetech.com/gaming/269335-how-graphics-cards-work | title = How Do Graphics Cards Work? | first = Joel | last = Hruska | date = February 10, 2021 | access-date = July 17, 2021 | work = [[Extreme Tech]] }}</ref>

===GPU accelerated video decoding and encoding===
[[Image:AMD HD5470 GPU.JPG|thumb|The ATI HD5470 GPU (above, with copper [[heatpipe]] attached) features [[UVD]] 2.1 which enables it to decode AVC and VC-1 video formats.]]
Most GPUs made since 1995 support the [[YUV]] [[color space]] and [[hardware overlay]]s, important for [[digital video]] playback, and many GPUs made since 2000 also support [[MPEG]] primitives such as [[motion compensation]] and [[inverse discrete cosine transform|iDCT]]. This hardware-accelerated video decoding, in which portions of the [[video decoding]] process and [[video post-processing]] are offloaded to the GPU hardware, is commonly referred to as "GPU accelerated video decoding", "GPU assisted video decoding", "GPU hardware accelerated video decoding", or "GPU hardware assisted video decoding".

Recent graphics cards decode [[high-definition video]] on the card, offloading the central processing unit. The most common [[API]]s for GPU accelerated video decoding are [[DirectX Video Acceleration|DxVA]] for [[Microsoft Windows]] operating systems and [[VDPAU]], [[vaAPI|VAAPI]], [[X-Video Motion Compensation|XvMC]], and [[X-Video Bitstream Acceleration|XvBA]] for Linux-based and UNIX-like operating systems. All except XvMC are capable of decoding videos encoded with [[MPEG-1]], [[MPEG-2]], [[MPEG-4 Part 2|MPEG-4 ASP (MPEG-4 Part 2)]], [[MPEG-4 AVC]] (H.264 / DivX 6), [[VC-1]], [[WMV3]]/[[WMV9]], [[Xvid]] / OpenDivX (DivX 4), and [[DivX]] 5 [[codec]]s, while XvMC is only capable of decoding MPEG-1 and MPEG-2.

There are several [[:Category:Video compression and decompression ASIC|dedicated hardware video decoding and encoding solutions]].

====Video decoding processes that can be accelerated====
Video decoding processes that can be accelerated by modern GPU hardware are:
* [[Motion compensation|Motion compensation (mocomp)]]
* [[Inverse discrete cosine transform|Inverse discrete cosine transform (iDCT)]]
** [[Inverse telecine]] 3:2 and 2:2 pull-down correction
* Inverse [[modified discrete cosine transform]] (iMDCT)
* In-loop [[deblocking filter (video)|deblocking filter]]
* Intra-frame prediction
* Inverse [[Quantization (image processing)|quantization]] (IQ)
* [[Huffman coding|Variable-length decoding (VLD)]], more commonly known as slice-level acceleration
* Spatial-temporal [[deinterlacing]] and automatic [[Interlaced video|interlace]]/[[progressive scan|progressive]] source detection
* Bitstream processing ([[Context-adaptive variable-length coding]]/[[Context-adaptive binary arithmetic coding]]) and perfect pixel positioning

These operations also have applications in video editing, encoding, and transcoding.

===2D graphics APIs===
An earlier GPU may support one or more 2D graphics API for 2D acceleration, such as [[Graphics Device Interface|GDI]] and [[DirectDraw]].<ref>{{citation |url=https://theretroweb.com/chip/documentation/cl-gd5446-smol-645654db1ae03286068933.pdf |title=CL-GD5446 64-bit VisualMedia Accelerator Preliminary Data Book |publisher=Cirrus Logic |date=November 1996 |access-date=30 January 2024 |via=The Datasheet Archive}}</ref>

=== 3D graphics APIs ===
A GPU can support one or more 3D graphics API, such as [[DirectX]], [[Metal (API)|Metal]], [[OpenGL]], [[OpenGL ES]], [[Vulkan]].