Misplaced Pages

#59940

39-714: NVidia introduced the Video Processing Engine or VPE with the GeForce 4 MX. It is a feature of nVidia's GeForce graphics processor line that offers dedicated hardware to offload parts of the MPEG2 decoding and encoding. The GeForce Go FX 5700 rolled out the VPE 3.0. The VPE later developed into nVidia's PureVideo . The VPE SIP core needs to be supported by the device driver . The device driver provides one or multiple interfaces , like e.g. VDPAU , VAAPI or DXVA . One of this interfaces

78-693: A free device driver is available, which also supports the PureVideo hardware. Support for PureVideo has been available in Nvidia's proprietary driver version 180 since October 2008 through VDPAU . Since April 2013 nouveau also supports PureVideo hardware and provides access to it through VDPAU and partly through XvMC . Microsoft's Windows Media Player , Windows Media Center and modern video players support PureVideo. Nvidia also sells PureVideo decoder software which can be used with media players which use DirectShow. Systems with dual GPU's either need to configure

117-494: A GPU microarchitecture developed by Nvidia , and released in 2006, as the successor to Curie microarchitecture. It was named after the pioneering electrical engineer Nikola Tesla . As Nvidia's first microarchitecture to implement unified shaders, it was used with GeForce 8 series , GeForce 9 series , GeForce 100 series , GeForce 200 series , and GeForce 300 series of GPUs, collectively manufactured in 90 nm , 80 nm , 65 nm , 55 nm , and 40 nm . It

156-471: A considerable customer confusion. The first generation PureVideo GPUs (GeForce 6 series) spanned a wide range of capabilities. On the low-end of GeForce 6 series (6200), PureVideo was limited to standard-definition content (720×576). The mainstream and high-end of the GeForce 6 series was split between older products (6800 GT) which did not accelerate H.264/VC-1 at all, and newer products (6600 GT) with added VC-1/H.264 offloading capability. In 2006, PureVideo HD

195-456: A graphics card with SP count [ n ] and shader frequency [ f , GHz], the formula is: FLOPS sp+sfu = 3 × n × f . However leveraging dual-issue performance like MAD+MUL is problematic: For these reasons, in order to estimate the performance of real-world workloads, it may be more helpful to ignore the SFU and to assume only 1 MAD (2 operations) per SP per cycle. In this case the formula to calculate

234-496: A homogeneous collection of universal floating point processors (called "stream processors") that can perform a more universal set of tasks. GeForce 8's unified shader architecture consists of a number of stream processors (SPs). Unlike the vector processing approach taken with older shader units, each SP is scalar and thus can operate only on one component at a time. This makes them less complex to build while still being quite flexible and universal. Scalar shader units also have

273-539: A maximum of 8192 macroblocks (8190 for VC-1/WMV9). Partial acceleration means that VLD (bitstream) decoding is performed on the CPU , with the GPU only performing IDCT , motion compensation and deblocking . Complete acceleration means that the GPU performs all of VLD, IDCT, motion compensation and deblocking. Qualcomm Tesla (microarchitecture) Tesla is the codename for

312-461: A similar design. Tesla was followed by Fermi . Tesla is Nvidia's first microarchitecture implementing the unified shader model . The driver supports Direct3D 10 Shader Model 4.0 / OpenGL 2.1 (later drivers have OpenGL 3.3 support) architecture. The design is a major shift for NVIDIA in GPU functionality and capability, the most obvious change being the move from the separate functional units (pixel shaders, vertex shaders) within previous GPUs to

351-438: A single MAD instruction. Each SFU can fulfill up to four operations per clock: four MUL (Multiply) instructions. So one SM as a whole can execute 8 MADs (16 operations) and 8 MULs (8 operations) per clock, or 24 operations per clock, which is (relatively speaking) 3 times the number of SPs. Therefore, to calculate the theoretical dual-issue MAD+MUL performance in floating point operations per second [ FLOPS sp+sfu , GFLOPS ] of

390-432: A sufficiently fast host CPU can play Blu-ray without any hardware assistance whatsoever. (April 2009 for the 8400 GS Rev. 3 ) Nvidia VDPAU Feature Sets are different hardware generations of Nvidia GPU's supporting different levels of hardware decoding capabilities. For feature sets A, B and C, the maximum video width and height are 2048 pixels , minimum width and height 48 pixels, and all codecs are currently limited to

429-404: Is also capable of decoding 2160p 4K Ultra-High Definition (UHD) resolution videos at 3840 × 2160 pixels (doubling the 1080p Full High Definition standard in both the vertical and horizontal dimensions) and, depending on the driver and the used codec, higher resolutions of up to 4032 × 4080 pixels. The fifth generation PureVideo HD is sometimes called "PureVideo HD 5" or "VP5", although this

SECTION 10

#1733085305060

468-441: Is also capable of decoding Digital Cinema Initiatives (DCI) 4K resolution videos at 4096 × 2160 pixels and, depending on the driver and the used codec, higher resolutions of up to 4096 × 4096 pixels. GPUs with Feature Set E support an enhanced error concealment mode which provides more robust error handling when decoding corrupted video streams. It supports partial hardware decoding for H.265 FHD. The sixth generation PureVideo HD

507-1272: Is equipped with much more texture filtering arithmetic ability than the GeForce 7 series. This allows high-quality filtering with a much smaller performance hit than previously. NVIDIA has also introduced new polygon edge anti-aliasing methods, including the ability of the GPU's ROPs to perform both Multisample anti-aliasing (MSAA) and HDR lighting at the same time, correcting various limitations of previous generations. GeForce 8 can perform MSAA with both FP16 and FP32 texture formats. GeForce 8 supports 128-bit HDR rendering , an increase from prior cards' 64-bit support. The chip's new anti-aliasing technology, called coverage sampling AA (CSAA), uses Z, color, and coverage information to determine final pixel color. This technique of color optimization allows 16X CSAA to look crisp and sharp. The claimed theoretical single-precision processing power for Tesla-based cards given in FLOPS may be hard to reach in real-world workloads. In G80/G90/GT200, each Streaming Multiprocessor (SM) contains 8 Shader Processors (SP, or Unified Shader, or CUDA Core) and 2 Special Function Units (SFU). Each SP can fulfill up to two single-precision operations per clock: 1 Multiply and 1 Add, using

546-576: Is not an official Nvidia designation. This generation of PureVideo HD corresponds to Nvidia Feature Set D (or " VDPAU Feature Set D"). The sixth generation of PureVideo HD, introduced with the Maxwell (microarchitecture) , e.g. in the GeForce GTX 750/GTX 750 Ti (GM107) and also included in the Nvidia GeForce 900 (Maxwell) series GPUs has significantly improved performance when decoding H.264 and MPEG-2. It

585-596: Is not an official Nvidia designation. This generation of PureVideo HD corresponds to Nvidia Feature Set H (or " VDPAU Feature Set H"). The ninth generation of PureVideo HD, introduced with the NVIDIA TITAN V, a Volta (microarchitecture) GPU. The ninth generation PureVideo HD is sometimes called "PureVideo HD 9" or "VP9", although this is not an official Nvidia designation. This generation of PureVideo HD corresponds to Nvidia Feature Set I (or " VDPAU Feature Set I"). The tenth generation of PureVideo HD, introduced with

624-509: Is sometimes called "PureVideo HD 1" or VP1, although this is not an official Nvidia designation. Starting with the G84/G86 GPUs ( Tesla (microarchitecture) ) (sold as the GeForce 8400/8500/8600 series ), Nvidia substantially re-designed the H.264 decoding block inside its GPUs. The second generation PureVideo HD added a dedicated bitstream processor (BSP) and enhanced video processor, which enabled

663-418: Is sometimes called "PureVideo HD 11" or "VP11", although this is not an official Nvidia designation. This generation of PureVideo HD corresponds to Nvidia Feature Set K (or " VDPAU Feature Set K"). Because the introduction and subsequent rollout of PureVideo technology was not synchronized with Nvidia's GPU release schedule, the exact capabilities of PureVideo technology and their supported Nvidia GPUs led to

702-481: Is sometimes called "PureVideo HD 4" or VP4, although this is not an official Nvidia designation. It corresponds to Nvidia Feature Set C (or " VDPAU Feature Set C"). The fifth generation of PureVideo HD, introduced with the GeForce GT 520 ( Fermi (microarchitecture) ) and also included in the Nvidia GeForce 600/700 ( Kepler (microarchitecture) ) series GPUs has significantly improved performance when decoding H.264. It

741-436: Is sometimes called "PureVideo HD 6" or "VP6", although this is not an official Nvidia designation. This generation of PureVideo HD corresponds to Nvidia Feature Set E (or " VDPAU Feature Set E"). The seventh generation of PureVideo HD, introduced with the GeForce GTX 960 and GTX 950, a second generation Maxwell (microarchitecture) GPU (GM206), adds full hardware-decode of H.265 HEVC Version 1 (Main and Main 10 profiles) to

780-460: Is sometimes called "PureVideo HD 7" or "VP7", although this is not an official Nvidia designation. This generation of PureVideo HD corresponds to Nvidia Feature Set F (or " VDPAU Feature Set F"). The eighth generation of PureVideo HD, introduced with the GeForce GTX 1080, GTX 1070, GTX 1060, GTX 1050 Ti & GTX 1050, GT 1030 & GT 1010, a Pascal (microarchitecture) GPU, adds full hardware-decode of HEVC Version 2 Main 12 profile, and increases

819-432: Is then used by end-user software, like e.g. VLC media player or GStreamer , to access the VPE hardware and make use of it. Nvidia's proprietary device driver is available for multiple operating systems and support for VPE has been added to it. Additionally, a free device driver named nouveau is available. This driver also supports the VPE hardware. PureVideo The PureVideo SIP core needs to be supported by

SECTION 20

#1733085305060

858-409: The device driver , which provides one or more interfaces such as NVDEC , VDPAU , VAAPI or DXVA . One of these interfaces is then used by end-user software, for example VLC media player or GStreamer , to access the PureVideo hardware and make use of it. Nvidia's proprietary device driver is available for multiple operating systems and support for PureVideo has been added to it. Additionally,

897-562: The G98 GPU (sold as GeForce 8400GS), as well as additional minor enhancements for the MPEG-2 decoding block. The functionality of the H.264-decoding pipeline was left unchanged. In essence, VP3 offers complete hardware-decoding for all 3 video codecs of the Blu-ray Disc format: MPEG-2, VC-1, and H.264. All third generation PureVideo hardware (G98, MCP77, MCP78, MCP79MX, MCP7A) cannot decode H.264 for

936-415: The GPU to completely offload the H.264-decoding pipeline. VC-1 acceleration was also improved, with PureVideo HD now able to offload more of VC-1-decoding pipeline's backend (inverse discrete cosine transform (iDCT) and motion compensation stages). The frontend (bitstream) pipeline is still decoded by the host CPU. The second generation PureVideo HD enabled mainstream PCs to play HD DVD and Blu-ray movies, as

975-457: The GPU's video-engine. Feature Set F hardware decoder also supports full fixed function VP9 (video codec) hardware decoding. Previous Maxwell GPUs implemented HEVC playback using a hybrid decoding solution, which involved both the host-CPU and the GPU's GPGPU array. The hybrid implementation is significantly slower than the dedicated hardware in VP7's video-engine. The seventh generation PureVideo HD

1014-643: The GT215, GT216 and GT218 GPUs (sold as GeForce GT 240, GeForce GT 220 and GeForce 210/G210, respectively). The H.264-decoder no longer suffers the framesize restrictions of VP3, and adds hardware-acceleration for MVC , a H.264 extension used on 3D Blu-ray discs. MVC acceleration is OS dependent: it is fully supported in Microsoft Windows through the Microsoft DXVA and Nvidia CUDA APIs, but is not supported through Nvidia's VDPAU API. The fourth generation PureVideo HD

1053-639: The NVIDIA GeForce RTX 2080 Ti, RTX 2080, RTX 2070, RTX 2060, GTX 1660 Ti, GTX 1660 & GTX 1650, a Turing (microarchitecture) GPU, adds full hardware-decoding for three additional HEVC Version 2 profiles (Main 4:4:4, Main 4:4:4 10 and Main 4:4:4 12) to the GPU's video-engine. The tenth generation PureVideo HD is sometimes called "PureVideo HD 10" or "VP10", although this is not an official Nvidia designation. This generation of PureVideo HD corresponds to Nvidia Feature Set J (or " VDPAU Feature Set J"). The eleventh generation of PureVideo HD, introduced with

1092-425: The NVIDIA GeForce RTX 3090, RTX 3080 Ti, RTX 3080, RTX 3070 Ti, RTX 3070, RTX 3060 Ti, RTX 3060, RTX 3050 Ti and RTX 3050, an Ampere (microarchitecture) GPU, with fifth generation NVDEC introduces 8K@60 hardware-decoding capability for AV1 Main profile (4:0:0 and 4:2:0 chroma subsampling with 8 or 10-bit depth) with resolution of up to 8192 x 8192 pixels to the GPU's video-engine. The eleventh generation PureVideo HD

1131-460: The advantage of being more efficient in a number of cases as compared to previous generation vector shader units that rely on ideal instruction mixture and ordering to reach peak throughput. The lower maximum throughput of these scalar processors is compensated for by efficiency and by running them at a high clock speed (made possible by their simplicity). GeForce 8 runs the various parts of its core at differing clock speeds (clock domains), similar to

1170-481: The codec or run the application on the Nvidia GPU to utilize PureVideo. Media players which use LAV, ffdshow or Microsoft Media Foundation codecs are able to utilize PureVideo capabilities. OS X was sold with Nvidia hardware, so support is probably available. PureVideo HD (see "naming confusions" below) is a label which identifies Nvidia graphics boards certified for HD DVD and Blu-ray Disc playback, to comply with

1209-526: The following horizontal resolutions: 769–784, 849–864, 929–944, 1009–1024, 1793–1808, 1873–1888, 1953–1968 and 2033–2048 pixels. The third generation PureVideo HD is sometimes called "PureVideo HD 3" or VP3, although this is not an official Nvidia designation. It corresponds to Nvidia Feature Set B (or " VDPAU Feature Set B"). This implementation of PureVideo HD, VP4 added hardware to offload MPEG-4 Advanced Simple Profile (the compression format implemented by original DivX and Xvid ) bitstream decoding with

Video Processing Engine - Misplaced Pages Continue

1248-519: The majority of the processing-intensive video-decoding was now offloaded to the GPU. The second generation PureVideo HD is sometimes called "PureVideo HD 2" or VP2, although this is not an official Nvidia designation. It corresponds to Nvidia Feature Set A (or " VDPAU Feature Set A"). This is the earliest generation that Adobe Flash Player supports for hardware acceleration of H.264 video on Windows. This implementation of PureVideo HD, VP3 added entropy hardware to offload VC-1 bitstream decoding with

1287-466: The newer VP2 based cores (Geforce 8500 GT/8600 GT/8600 GTS/8800 GT) and other older PureVideo HD 1 based cores (Geforce 7900/G80). Nvidia claims that all GPUs carrying the PureVideo HD label fully support Blu-ray/HD DVD playback with the proper system components. For H.264/AVC content, VP1 offers markedly inferior acceleration compared to newer GPUs, placing a much greater burden on the host CPU. However,

1326-575: The operation of the previous GeForce 7 series GPUs . For example, the stream processors of GeForce 8800 GTX operate at a 1.35 GHz clock rate while the rest of the chip is operating at 575 MHz. GeForce 8 performs significantly better texture filtering than its predecessors that used various optimizations and visual tricks to speed up rendering without impairing filtering quality. The GeForce 8 line correctly renders an angle-independent anisotropic filtering algorithm along with full trilinear texture filtering . G80, though not its smaller brethren,

1365-601: The release of the GeForce 6600, PureVideo added hardware acceleration for VC-1 and H.264 video, though the level of acceleration is limited when benchmarked side by side with MPEG-2 video. VPE (and PureVideo) offloads the MPEG-2 pipeline starting from the inverse discrete cosine transform leaving the CPU to perform the initial run-length decoding, variable-length decoding, and inverse quantization; whereas first-generation PureVideo offered limited VC-1 assistance (motion compensation and post processing). The first generation PureVideo HD

1404-698: The requirements for playing Blu-ray/HD DVDs on PC: The original PureVideo engine was introduced with the GeForce 6 series . Based on the GeForce FX 's video-engine (VPE), PureVideo re-used the MPEG-1/MPEG-2 decoding pipeline, and improved the quality of deinterlacing and overlay-resizing. Compatibility with DirectX 9's VMR9 renderer was also improved. Other VPE features, such as the MPEG-1/MPEG-2 decoding pipeline were left unchanged. Nvidia's press material cited hardware acceleration for VC-1 and H.264 video, but these features were not present at launch. Starting with

1443-502: The resolution for VP9 and HEVC decoding to 8K , including 8K UHDTV and up to 8K fulldome 8192x8192. Previous Maxwell GM200/GM204 GPUs implemented HEVC playback using a hybrid decoding solution, which involved both the host-CPU and the GPU's GPGPU array. The hybrid implementation is significantly slower than the dedicated hardware in VP8's video-engine. The eighth generation PureVideo HD is sometimes called "PureVideo HD 8" or "VP8", although this

1482-496: Was also in the GeForce 405 and in the Quadro FX, Quadro x000, Quadro NVS series, and Nvidia Tesla computing modules. Tesla replaced the old fixed-pipeline microarchitectures, represented at the time of introduction by the GeForce 7 series . It competed directly with AMD's first unified shader microarchitecture named TeraScale , a development of ATI's work on the Xbox 360 which used

1521-548: Was formally introduced with the launch of the GeForce 7900, which had the first generation PureVideo HD. In 2007, when the second generation PureVideo HD (VP2) hardware launched with the Geforce 8500 GT/8600 GT/8600 GTS, Nvidia expanded Purevideo HD to include both the first generation (retroactively called "PureVideo HD 1" or VP1) GPUs (Geforce 7900/8800 GTX) and newer VP2 GPUs. This led to a confusing product portfolio containing GPUs from two distinctly different generational capabilities:

#59940