SherbyNet - /page/wikibook/entry.mu

Micron Document

<!DOCTYPE html>

<title>Vision processing unit</title>

</head>

<span id="openzim-page-title" class="mw-page-title-main"><span class="mw-page-title-main">Vision processing unit</span></span>

</h1>

</header>

<p>A <b>vision processing unit</b> (<b>VPU</b>) is (as of 2023) an emerging class of <a href="Microprocessor" title="Microprocessor">microprocessor</a>; it is a specific type of <a href="AI_accelerator" class="mw-redirect" title="AI accelerator">AI accelerator</a>, designed to <a href="Hardware_acceleration" title="Hardware acceleration">accelerate</a> <a href="Machine_vision" title="Machine vision">machine vision</a> tasks.<sup id="cite_ref-1" class="reference"><a href="#cite_note-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-2" class="reference"><a href="#cite_note-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading2"><h2 id="Overview">Overview</h2></div>

<p>Vision processing units are distinct from <a href="Graphics_processing_unit" title="Graphics processing unit">graphics processing units</a> (which are specialised for <a href="Video_codec" title="Video codec">video encoding and decoding</a>) in their suitability for running <a href="Machine_vision" title="Machine vision">machine vision algorithms</a> such as CNN (<a href="Convolutional_neural_network" title="Convolutional neural network">convolutional neural networks</a>), SIFT (<a href="Scale-invariant_feature_transform" title="Scale-invariant feature transform">scale-invariant feature transform</a>) and similar.

</p><p>They may include <a href="Interface_(computing)" title="Interface (computing)">direct interfaces</a> to take data from <a href="Digital_cameras" class="mw-redirect" title="Digital cameras">cameras</a> (bypassing any off chip buffers), and have a greater emphasis on on-chip <a href="Dataflow" title="Dataflow">dataflow</a> between many <a href="Parallel_execution_units" class="mw-redirect" title="Parallel execution units">parallel execution units</a> with <a href="Scratchpad_memory" title="Scratchpad memory">scratchpad memory</a>, like a <a href="Spatial_architecture" title="Spatial architecture">spatial architecture</a> or a <a href="Manycore_processor" title="Manycore processor">manycore</a> <a href="Digital_signal_processor" title="Digital signal processor">DSP</a>. But, like video processing units, they may have a focus on <a href="Low_precision" class="mw-redirect" title="Low precision">low precision</a> <a href="Fixed_point_arithmetic" class="mw-redirect" title="Fixed point arithmetic">fixed point arithmetic</a> for <a href="Image_processing" class="mw-redirect" title="Image processing">image processing</a>.

</p>

<div class="mw-heading mw-heading2"><h2 id="Contrast_with_GPUs">Contrast with GPUs</h2></div>

<p>They are distinct from <a href="GPU" class="mw-redirect" title="GPU">GPUs</a>, which contain specialised hardware for <a href="Rasterization" class="mw-redirect" title="Rasterization">rasterization</a> and <a href="Texture_mapping" title="Texture mapping">texture mapping</a> (for <a href="3D_graphics" class="mw-redirect" title="3D graphics">3D graphics</a>), and whose <a href="Memory_architecture" title="Memory architecture">memory architecture</a> is optimised for manipulating <a href="Bitmap_images" class="mw-redirect" title="Bitmap images">bitmap images</a> in <a href="Off-chip_memory" class="mw-redirect" title="Off-chip memory">off-chip memory</a> (reading <a href="Texture_map" class="mw-redirect" title="Texture map">textures</a>, and modifying <a href="Frame_buffers" class="mw-redirect" title="Frame buffers">frame buffers</a>, with <a href="Locality_of_reference" title="Locality of reference">random access patterns</a>). VPUs are optimized for performance per watt, while GPUs mainly focus on absolute performance.

</p><p>Target markets are <a href="Robotics" title="Robotics">robotics</a>, the <a href="Internet_of_things" title="Internet of things">internet of things</a> (IoT), new classes of <a href="Digital_cameras" class="mw-redirect" title="Digital cameras">digital cameras</a> for <a href="Virtual_reality" title="Virtual reality">virtual reality</a> and <a href="Augmented_reality" title="Augmented reality">augmented reality</a>, <a href="Smart_camera" title="Smart camera">smart cameras</a>, and integrating machine vision acceleration into <a href="Smartphone" title="Smartphone">smartphones</a> and other <a href="Mobile_devices" class="mw-redirect" title="Mobile devices">mobile devices</a>.

</p>

<div class="mw-heading mw-heading2"><h2 id="Examples">Examples</h2></div>

<ul><li><a href="Movidius_Myriad_X" class="mw-redirect" title="Movidius Myriad X">Movidius Myriad X</a>, which is the third-generation vision processing unit in the Myriad VPU line from <a href="Intel" title="Intel">Intel Corporation</a>.<sup id="cite_ref-3" class="reference"><a href="#cite_note-3"><span class="cite-bracket">[</span>3<span class="cite-bracket">]</span></a></sup></li>

<li><a href="Movidius_Myriad_2" class="mw-redirect" title="Movidius Myriad 2">Movidius Myriad 2</a>, which finds use in <a href="Google_Project_Tango" class="mw-redirect" title="Google Project Tango">Google Project Tango</a>,<sup id="cite_ref-RiseOfVPUs_4-0" class="reference"><a href="#cite_note-RiseOfVPUs-4"><span class="cite-bracket">[</span>4<span class="cite-bracket">]</span></a></sup> <a href="Google_Clips" title="Google Clips">Google Clips</a> and DJI drones<sup id="cite_ref-5" class="reference"><a href="#cite_note-5"><span class="cite-bracket">[</span>5<span class="cite-bracket">]</span></a></sup></li>

<li><a href="Pixel_Visual_Core" title="Pixel Visual Core">Pixel Visual Core</a> (PVC), which is a fully programmable <a href="Image_processor" title="Image processor">Image</a>, Vision and <a href="AI_accelerator" class="mw-redirect" title="AI accelerator">AI</a> processor for mobile devices</li>

<li><a href="Microsoft_HoloLens" title="Microsoft HoloLens">Microsoft HoloLens</a>, which includes an accelerator referred to as a <i>holographic processing unit</i> (complementary to its CPU and GPU), aimed at interpreting camera inputs, to accelerate environment tracking and vision for augmented reality applications.<sup id="cite_ref-6" class="reference"><a href="#cite_note-6"><span class="cite-bracket">[</span>6<span class="cite-bracket">]</span></a></sup></li>

<li><a href="Eyeriss" class="mw-redirect" title="Eyeriss">Eyeriss</a>, a <a href="Spatial_architecture" title="Spatial architecture">spatial architecture</a> designed from <a href="MIT" class="mw-redirect" title="MIT">MIT</a> intended for running <a href="Convolutional_neural_network" title="Convolutional neural network">convolutional neural networks</a>.<sup id="cite_ref-7" class="reference"><a href="#cite_note-7"><span class="cite-bracket">[</span>7<span class="cite-bracket">]</span></a></sup></li>

<li>NeuFlow, a design by <a href="Yann_LeCun" title="Yann LeCun">Yann LeCun</a> (implemented in <a href="FPGA" class="mw-redirect" title="FPGA">FPGA</a>) for accelerating <a href="Convolutions" class="mw-redirect" title="Convolutions">convolutions</a>, using a dataflow architecture.</li>

<li>Mobileye EyeQ, by <a href="Mobileye" title="Mobileye">Mobileye</a></li>

<li>Programmable Vision Accelerator (PVA), a 7-way VLIW Vision Processor designed by <a href="Nvidia" title="Nvidia">Nvidia</a>.</li></ul>

<div class="mw-heading mw-heading2"><h2 id="Broader_category">Broader category</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .hatnote{font-style:italic}.mw-parser-output div.hatnote{padding-left:1.6em;margin-bottom:0.5em}.mw-parser-output .hatnote i{font-style:normal}.mw-parser-output .hatnote+link+.hatnote{margin-top:-0.5em}@media print{body.ns-0 .mw-parser-output .hatnote{display:none!important}}

/* end https://en.wikipedia.org/ */

</style><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="AI_accelerator" class="mw-redirect" title="AI accelerator">AI accelerator</a></div>

<p>Some processors are not described as VPUs, but are equally applicable to machine vision tasks. These may form a broader category of <a href="AI_accelerator_(computer_hardware)" class="mw-redirect" title="AI accelerator (computer hardware)">AI accelerators</a> (to which VPUs may also belong), however as of 2016 there is no consensus on the name:

</p>

<ul><li><a href="IBM" title="IBM">IBM</a> <a href="TrueNorth" class="mw-redirect" title="TrueNorth">TrueNorth</a>, a <a href="Neuromorphic" class="mw-redirect" title="Neuromorphic">neuromorphic</a> processor aimed at similar sensor data <a href="Pattern_recognition" title="Pattern recognition">pattern recognition</a> and intelligence tasks, including video/audio.</li>

<li><a href="Qualcomm_Zeroth_Neural_processing_unit" class="mw-redirect" title="Qualcomm Zeroth Neural processing unit">Qualcomm Zeroth Neural processing unit</a>, another entry in the emerging class of sensor/AI oriented chips.<sup id="cite_ref-8" class="reference"><a href="#cite_note-8"><span class="cite-bracket">[</span>8<span class="cite-bracket">]</span></a></sup></li>

<li>All models of Intel <a href="Meteor_Lake" title="Meteor Lake">Meteor Lake</a> processors have a <a href="Versatile_Processor_Unit" class="mw-redirect" title="Versatile Processor Unit">Versatile Processor Unit</a> (VPU) built-in for accelerating <a href="Statistical_inference" title="Statistical inference">inference</a> for computer vision and deep learning.<sup id="cite_ref-9" class="reference"><a href="#cite_note-9"><span class="cite-bracket">[</span>9<span class="cite-bracket">]</span></a></sup></li></ul>

<ul><li><a href="Adapteva_Epiphany" class="mw-redirect" title="Adapteva Epiphany">Adapteva Epiphany</a>, a manycore processor with similar emphasis on on-chip dataflow, focussed on 32-bit floating point performance</li>

<li><a href="CELL" class="mw-redirect" title="CELL">CELL</a>, a multicore processor with features fairly consistent with vision processing units (SIMD instructions & datatypes suitable for video, and on-chip DMA between scratchpad memories)</li>

<li><a href="Coprocessor" title="Coprocessor">Coprocessor</a></li>

<li><a href="Graphics_processing_unit" title="Graphics processing unit">Graphics processing unit</a>, also commonly used to run vision algorithms. NVidia's Pascal architecture includes FP16 support, to provide a better precision/cost tradeoff for AI workloads</li>

<li><a href="MPSoC" class="mw-redirect" title="MPSoC">MPSoC</a></li>

<li><a href="OpenCL" title="OpenCL">OpenCL</a></li>

<li><a href="OpenVX" title="OpenVX">OpenVX</a></li>

<li><a href="Physics_processing_unit" title="Physics processing unit">Physics processing unit</a>, a past attempt to complement the CPU and GPU with a high throughput accelerator</li>

<li><a href="Tensor_Processing_Unit" title="Tensor Processing Unit">Tensor Processing Unit</a>, a chip used internally by Google for accelerating AI calculations</li></ul>

<div class="mw-heading mw-heading2"><h2 id="References">References</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .reflist{margin-bottom:0.5em;list-style-type:decimal}@media screen{.mw-parser-output .reflist{font-size:90%}}.mw-parser-output .reflist .references{font-size:100%;margin-bottom:0;list-style-type:inherit}.mw-parser-output .reflist-columns-2{column-width:30em}.mw-parser-output .reflist-columns-3{column-width:25em}.mw-parser-output .reflist-columns{margin-top:0.3em}.mw-parser-output .reflist-columns ol{margin-top:0}.mw-parser-output .reflist-columns li{page-break-inside:avoid;break-inside:avoid-column}.mw-parser-output .reflist-upper-alpha{list-style-type:upper-alpha}.mw-parser-output .reflist-upper-roman{list-style-type:upper-roman}.mw-parser-output .reflist-lower-alpha{list-style-type:lower-alpha}.mw-parser-output .reflist-lower-greek{list-style-type:lower-greek}.mw-parser-output .reflist-lower-roman{list-style-type:lower-roman}

/* end https://en.wikipedia.org/ */

</style><div class="reflist">

/* start https://en.wikipedia.org/ */

.mw-parser-output cite.citation{font-style:inherit;word-wrap:break-word}.mw-parser-output .citation q{quotes:"\"""\"""'""'"}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}.mw-parser-output .id-lock-free.id-lock-free a{background:url("./mw/Lock-green.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-limited.id-lock-limited a,.mw-parser-output .id-lock-registration.id-lock-registration a{background:url("./mw/Lock-gray-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-subscription.id-lock-subscription a{background:url("./mw/Lock-red-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .cs1-ws-icon a{background:url("./mw/Wikisource-logo.svg")right 0.1em center/12px no-repeat}body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-free a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-limited a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-registration a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-subscription a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .cs1-ws-icon a{background-size:contain;padding:0 1em 0 0}.mw-parser-output .cs1-code{color:inherit;background:inherit;border:none;padding:inherit}.mw-parser-output .cs1-hidden-error{display:none;color:var(--color-error,#d33)}.mw-parser-output .cs1-visible-error{color:var(--color-error,#d33)}.mw-parser-output .cs1-maint{display:none;color:#085;margin-left:0.3em}.mw-parser-output .cs1-kern-left{padding-left:0.2em}.mw-parser-output .cs1-kern-right{padding-right:0.2em}.mw-parser-output .citation .mw-selflink{font-weight:inherit}@media screen{.mw-parser-output .cs1-format{font-size:95%}html.skin-theme-clientpref-night .mw-parser-output .cs1-maint{color:#18911f}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .cs1-maint{color:#18911f}}

/* end https://en.wikipedia.org/ */

</style><cite id="CITEREFSeth_ColanerMatthew_Humrick2016" class="citation web cs1">Seth Colaner; Matthew Humrick (January 3, 2016). <a rel="nofollow" class="external text" href="http://www.tomshardware.com/news/movidiud-myriad2-vpu-vision-processing-vr,30850.html">"A third type of processor for AR/VR: Movidius' Myriad 2 VPU"</a>. <i>Tom's Hardware</i>.</cite></span>

</li>

<li id="cite_note-2"><span class="mw-cite-backlink"><b><a href="#cite_ref-2">^</a></b></span> <span class="reference-text"><cite id="CITEREFPrasid_Banerje2016" class="citation web cs1">Prasid Banerje (March 28, 2016). <a rel="nofollow" class="external text" href="http://www.digit.in/general/the-rise-of-vpus-giving-eyes-to-machines-29561.html">"The rise of VPUs: Giving Eyes to Machines"</a>. <i>Digit.in</i>.</cite></span>

</li>

<li id="cite_note-3"><span class="mw-cite-backlink"><b><a href="#cite_ref-3">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.intel.com/content/www/us/en/products/details/processors/movidius-vpu.html">"Intel® Movidius™ Vision Processing Units (VPUs)"</a>. <i>Intel</i>.</cite></span>

</li>

<li id="cite_note-RiseOfVPUs-4"><span class="mw-cite-backlink"><b><a href="#cite_ref-RiseOfVPUs_4-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFWeckler2016" class="citation web cs1">Weckler, Adrian (14 February 2016). <a rel="nofollow" class="external text" href="http://www.independent.ie/business/technology/news/dublin-tech-firm-movidius-to-power-googles-new-virtual-reality-headset-34449883.html">"Dublin tech firm Movidius to power Google's new virtual reality headset"</a>. <i>Independent.ie</i><span class="reference-accessdate">. Retrieved <span class="nowrap">15 March</span> 2016</span>.</cite></span>

</li>

<li id="cite_note-5"><span class="mw-cite-backlink"><b><a href="#cite_ref-5">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.movidius.com/news/dji-brings-two-new-flagship-drones-to-lineup-featuring-myriad-2-vpus">"DJI Brings Two New Flagship Drones to Lineup Featuring Myriad 2 VPUs - Machine Vision Technology - Movidius"</a>. <i>www.movidius.com</i>.</cite></span>

</li>

<li id="cite_note-6"><span class="mw-cite-backlink"><b><a href="#cite_ref-6">^</a></b></span> <span class="reference-text"><cite id="CITEREFFred_O'Connor2015" class="citation web cs1">Fred O'Connor (May 1, 2015). <a rel="nofollow" class="external text" href="http://www.pcworld.com/article/2917512/microsoft-designed-a-special-processor-to-handle-hololens-data.html">"Microsoft dives deeper into HoloLens details: 'Holographic processor' role revealed"</a>. <i>PCWorld</i>.</cite></span>

</li>

<li id="cite_note-7"><span class="mw-cite-backlink"><b><a href="#cite_ref-7">^</a></b></span> <span class="reference-text"><cite id="CITEREFChen,_Yu-HsinKrishna,_TusharEmer,_JoelSze,_Vivienne2016" class="citation web cs1">Chen, Yu-Hsin; Krishna, Tushar; Emer, Joel & <a href="Vivienne_Sze" title="Vivienne Sze">Sze, Vivienne</a> (2016). <a rel="nofollow" class="external text" href="https://www.mit.edu/~sze/eyeriss.html">"Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks"</a>. <i>IEEE International Solid-State Circuits Conference, ISSCC 2016, Digest of Technical Papers</i>. pp. <span class="nowrap">262–</span>263.</cite></span>

</li>

<li id="cite_note-8"><span class="mw-cite-backlink"><b><a href="#cite_ref-8">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.qualcomm.com/news/onq/2013/10/10/introducing-qualcomm-zeroth-processors-brain-inspired-computing">"Introducing Qualcomm Zeroth Processors: Brain-Inspired Computing"</a>. <i>Qualcomm</i>. October 10, 2013.</cite></span>

</li>

<li id="cite_note-9"><span class="mw-cite-backlink"><b><a href="#cite_ref-9">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.pcmag.com/news/intel-to-bring-a-vpu-processor-unit-to-14th-gen-meteor-lake-chips">"Intel to Bring a 'VPU' Processor Unit to 14th Gen Meteor Lake Chips"</a>. <i>PCMAG</i>. August 2022.</cite></span>

</li>

</ol></div></div>

<div class="mw-heading mw-heading2"><h2 id="External_links">External links</h2></div>

<ul><li><a rel="nofollow" class="external text" href="http://eyeriss.mit.edu">Eyeriss architecture</a></li>

<li><a rel="nofollow" class="external text" href="http://whatis.techtarget.com/definition/holographic-processing-unit-HPU">Holographic processing unit</a></li>

<li><a rel="nofollow" class="external text" href="http://pub.clement.farabet.net/ecvw11.pdf">NeuFlow: A Runtime Reconfigurable Dataflow Processor for Vision</a> <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170505184615/http://pub.clement.farabet.net/ecvw11.pdf">Archived</a> 2017-05-05 at the <a href="Wayback_Machine" title="Wayback Machine">Wayback Machine</a></li></ul>

/* start https://en.wikipedia.org/ */

.mw-parser-output .hlist dl,.mw-parser-output .hlist ol,.mw-parser-output .hlist ul{margin:0;padding:0}.mw-parser-output .hlist dd,.mw-parser-output .hlist dt,.mw-parser-output .hlist li{margin:0;display:inline}.mw-parser-output .hlist.inline,.mw-parser-output .hlist.inline dl,.mw-parser-output .hlist.inline ol,.mw-parser-output .hlist.inline ul,.mw-parser-output .hlist dl dl,.mw-parser-output .hlist dl ol,.mw-parser-output .hlist dl ul,.mw-parser-output .hlist ol dl,.mw-parser-output .hlist ol ol,.mw-parser-output .hlist ol ul,.mw-parser-output .hlist ul dl,.mw-parser-output .hlist ul ol,.mw-parser-output .hlist ul ul{display:inline}.mw-parser-output .hlist .mw-empty-li{display:none}.mw-parser-output .hlist dt::after{content:": "}.mw-parser-output .hlist dd::after,.mw-parser-output .hlist li::after{content:" · ";font-weight:bold}.mw-parser-output .hlist dd:last-child::after,.mw-parser-output .hlist dt:last-child::after,.mw-parser-output .hlist li:last-child::after{content:none}.mw-parser-output .hlist dd dd:first-child::before,.mw-parser-output .hlist dd dt:first-child::before,.mw-parser-output .hlist dd li:first-child::before,.mw-parser-output .hlist dt dd:first-child::before,.mw-parser-output .hlist dt dt:first-child::before,.mw-parser-output .hlist dt li:first-child::before,.mw-parser-output .hlist li dd:first-child::before,.mw-parser-output .hlist li dt:first-child::before,.mw-parser-output .hlist li li:first-child::before{content:" (";font-weight:normal}.mw-parser-output .hlist dd dd:last-child::after,.mw-parser-output .hlist dd dt:last-child::after,.mw-parser-output .hlist dd li:last-child::after,.mw-parser-output .hlist dt dd:last-child::after,.mw-parser-output .hlist dt dt:last-child::after,.mw-parser-output .hlist dt li:last-child::after,.mw-parser-output .hlist li dd:last-child::after,.mw-parser-output .hlist li dt:last-child::after,.mw-parser-output .hlist li li:last-child::after{content:")";font-weight:normal}.mw-parser-output .hlist ol{counter-reset:listitem}.mw-parser-output .hlist ol>li{counter-increment:listitem}.mw-parser-output .hlist ol>li::before{content:" "counter(listitem)"\a0 "}.mw-parser-output .hlist dd ol>li:first-child::before,.mw-parser-output .hlist dt ol>li:first-child::before,.mw-parser-output .hlist li ol>li:first-child::before{content:" ("counter(listitem)"\a0 "}

/* end https://en.wikipedia.org/ */

</style><style data-mw-deduplicate="TemplateStyles:r1236075235">

/* start https://en.wikipedia.org/ */

.mw-parser-output .navbox{box-sizing:border-box;border:1px solid #a2a9b1;width:100%;clear:both;font-size:88%;text-align:center;padding:1px;margin:1em auto 0}.mw-parser-output .navbox .navbox{margin-top:0}.mw-parser-output .navbox+.navbox,.mw-parser-output .navbox+.navbox-styles+.navbox{margin-top:-1px}.mw-parser-output .navbox-inner,.mw-parser-output .navbox-subgroup{width:100%}.mw-parser-output .navbox-group,.mw-parser-output .navbox-title,.mw-parser-output .navbox-abovebelow{padding:0.25em 1em;line-height:1.5em;text-align:center}.mw-parser-output .navbox-group{white-space:nowrap;text-align:right}.mw-parser-output .navbox,.mw-parser-output .navbox-subgroup{background-color:#fdfdfd}.mw-parser-output .navbox-list{line-height:1.5em;border-color:#fdfdfd}.mw-parser-output .navbox-list-with-group{text-align:left;border-left-width:2px;border-left-style:solid}.mw-parser-output tr+tr>.navbox-abovebelow,.mw-parser-output tr+tr>.navbox-group,.mw-parser-output tr+tr>.navbox-image,.mw-parser-output tr+tr>.navbox-list{border-top:2px solid #fdfdfd}.mw-parser-output .navbox-title{background-color:#ccf}.mw-parser-output .navbox-abovebelow,.mw-parser-output .navbox-group,.mw-parser-output .navbox-subgroup .navbox-title{background-color:#ddf}.mw-parser-output .navbox-subgroup .navbox-group,.mw-parser-output .navbox-subgroup .navbox-abovebelow{background-color:#e6e6ff}.mw-parser-output .navbox-even{background-color:#f7f7f7}.mw-parser-output .navbox-odd{background-color:transparent}.mw-parser-output .navbox .hlist td dl,.mw-parser-output .navbox .hlist td ol,.mw-parser-output .navbox .hlist td ul,.mw-parser-output .navbox td.hlist dl,.mw-parser-output .navbox td.hlist ol,.mw-parser-output .navbox td.hlist ul{padding:0.125em 0}.mw-parser-output .navbox .navbar{display:block;font-size:100%}.mw-parser-output .navbox-title .navbar{float:left;text-align:left;margin-right:0.5em}body.skin--responsive .mw-parser-output .navbox-image img{max-width:none!important}@media print{body.ns-0 .mw-parser-output .navbox{display:none!important}}

/* end https://en.wikipedia.org/ */

</style></div><div role="navigation" class="navbox" aria-labelledby="Differentiable_computing254" style="padding:3px"><table class="nowraplinks hlist mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><style data-mw-deduplicate="TemplateStyles:r1239400231">

/* start https://en.wikipedia.org/ */

.mw-parser-output .navbar{display:inline;font-size:88%;font-weight:normal}.mw-parser-output .navbar-collapse{float:left;text-align:left}.mw-parser-output .navbar-boxtext{word-spacing:0}.mw-parser-output .navbar ul{display:inline-block;white-space:nowrap;line-height:inherit}.mw-parser-output .navbar-brackets::before{margin-right:-0.125em;content:"[ "}.mw-parser-output .navbar-brackets::after{margin-left:-0.125em;content:" ]"}.mw-parser-output .navbar li{word-spacing:-0.125em}.mw-parser-output .navbar a>span,.mw-parser-output .navbar a>abbr{text-decoration:inherit}.mw-parser-output .navbar-mini abbr{font-variant:small-caps;border-bottom:none;text-decoration:none;cursor:inherit}.mw-parser-output .navbar-ct-full{font-size:114%;margin:0 7em}.mw-parser-output .navbar-ct-mini{font-size:114%;margin:0 4em}html.skin-theme-clientpref-night .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}@media(prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}}@media print{.mw-parser-output .navbar{display:none!important}}

/* end https://en.wikipedia.org/ */

</style><div id="Differentiable_computing254" style="font-size:114%;margin:0 4em">Differentiable computing</div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Differentiable_function" title="Differentiable function">General</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><b><a href="Differentiable_programming" title="Differentiable programming">Differentiable programming</a></b></li>

<li><a href="Information_geometry" title="Information geometry">Information geometry</a></li>

<li><a href="Statistical_manifold" title="Statistical manifold">Statistical manifold</a></li>

<li><a href="Automatic_differentiation" title="Automatic differentiation">Automatic differentiation</a></li>

<li><a href="Neuromorphic_computing" title="Neuromorphic computing">Neuromorphic computing</a></li>

<li><a href="Pattern_recognition" title="Pattern recognition">Pattern recognition</a></li>

<li><a href="Ricci_calculus" title="Ricci calculus">Ricci calculus</a></li>

<li><a href="Computational_learning_theory" title="Computational learning theory">Computational learning theory</a></li>

<li><a href="Inductive_bias" title="Inductive bias">Inductive bias</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Hardware</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><a href="Memristor" title="Memristor">Memristor</a></li>

<li><a href="SpiNNaker" title="SpiNNaker">SpiNNaker</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Software libraries</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="TensorFlow" title="TensorFlow">TensorFlow</a></li>

<li><a href="PyTorch" title="PyTorch">PyTorch</a></li>

<li><a href="Keras" title="Keras">Keras</a></li>

<li><a href="Scikit-learn" title="Scikit-learn">scikit-learn</a></li>

<li><a href="Theano_(software)" title="Theano (software)">Theano</a></li>

<li><a href="MindSpore" title="MindSpore">MindSpore</a></li></ul>

</div></td></tr><tr><td class="navbox-abovebelow" colspan="2"><div>

<ul><li><span class="noviewer" typeof="mw:File"></span> Portals

<ul><li><a href="Portal%3AComputer_programming" title="Portal:Computer programming">Computer programming</a></li>

<li><a href="Portal%3ATechnology" title="Portal:Technology">Technology</a></li></ul></li></ul>

</div></td></tr></tbody></table></div></div><div><div class="zim-footer">

This article is issued from <a class="external text" title="Last edited on 2025-07-11" href="https://en.wikipedia.org/wiki/?title=Vision_processing_unit&oldid=1299945341">Wikipedia</a>. The text is available under <a class="external text" href="https://creativecommons.org/licenses/by-sa/4.0/deed.en">Creative Commons Attribution-Share Alike 4.0</a> unless otherwise noted. Additional terms may apply for the media files.

</div>

</div></div>

</div>

</main>

</div>

</body></html>