{"id":28363,"date":"2017-01-05T15:20:28","date_gmt":"2017-01-05T14:20:28","guid":{"rendered":"http:\/\/www.planet3dnow.de\/cms\/?p=28363"},"modified":"2017-01-05T15:20:28","modified_gmt":"2017-01-05T14:20:28","slug":"amd-stellt-vega-architektur-auf-ces-vor","status":"publish","type":"post","link":"https:\/\/www.planet3dnow.de\/cms\/28363-amd-stellt-vega-architektur-auf-ces-vor\/","title":{"rendered":"<span class=\"caps\">AMD<\/span> stellt Vega-Architektur auf <span class=\"caps\">CES<\/span>&nbsp;vor"},"content":{"rendered":"<p><b><span class=\"caps\">SUNNYVALE<\/span>, Calif. \u2014 Jan. 5, 2017 \u2014<\/b> Today <a href=\"http:\/\/www.amd.com\"><span class=\"caps\">AMD<\/span><\/a> (<span class=\"caps\">NASDAQ<\/span>: <span class=\"caps\">AMD<\/span>) unvei\u00adled preli\u00admi\u00adna\u00adry details of its forth\u00adco\u00adming <span class=\"caps\">GPU<\/span> archi\u00adtec\u00adtu\u00adre, Vega. Con\u00adcei\u00adved and exe\u00adcu\u00adted over 5 years, Vega archi\u00adtec\u00adtu\u00adre enables new pos\u00adsi\u00adbi\u00adli\u00adties in <span class=\"caps\">PC<\/span> gam\u00ading, pro\u00adfes\u00adsio\u00adnal design and machi\u00adne intel\u00adli\u00adgence that tra\u00addi\u00adtio\u00adnal <span class=\"caps\">GPU<\/span> archi\u00adtec\u00adtures have not been able to address effec\u00adtively. Data-inten\u00adsi\u00adve workloads are beco\u00adming the new nor\u00admal, and the par\u00adal\u00adlel natu\u00adre of the <span class=\"caps\">GPU<\/span> lends its\u00adelf ide\u00adal\u00adly to tack\u00adling them. Howe\u00adver, pro\u00adces\u00adsing the\u00adse huge new data\u00adsets requi\u00adres fast access to mas\u00adsi\u00adve amounts of memo\u00adry. The Vega architecture\u2019s revo\u00adlu\u00adtio\u00adna\u00adry memo\u00adry sub\u00adsys\u00adtem enables GPUs to address very lar\u00adge data sets spread across a mix of memo\u00adry types. The high-band\u00adwidth cache con\u00adtrol\u00adler in Vega-based GPUs can access on-packa\u00adge cache and off-packa\u00adge memo\u00adries in a fle\u00adxi\u00adble, pro\u00adgramma\u00adble fashion using fine-grai\u00adned data movement.<\/p>\n<p><span class=\"dquo\">\u201c<\/span>It is incre\u00addi\u00adble to see GPUs being used to sol\u00adve giga\u00adbyte-sca\u00adle data pro\u00adblems in gam\u00ading to exa\u00adbyte-sca\u00adle data pro\u00adblems in machi\u00adne intel\u00adli\u00adgence. We desi\u00adgned the Vega archi\u00adtec\u00adtu\u00adre to build on this abili\u00adty, with the fle\u00adxi\u00adbi\u00adli\u00adty to address the extra\u00ador\u00addi\u00adna\u00adry breadth of pro\u00adblems GPUs will be sol\u00adving not only today but also five years from now. Our high-band\u00adwidth cache is a pivo\u00adtal dis\u00adrup\u00adti\u00adon that has the poten\u00adti\u00adal to impact the who\u00adle <span class=\"caps\">GPU<\/span> mar\u00adket,\u201d said Raja Kodu\u00adri, seni\u00ador vice pre\u00adsi\u00addent and chief archi\u00adtect, Rade\u00adon Tech\u00adno\u00adlo\u00adgies Group, <span class=\"caps\">AMD<\/span>.<\/p>\n<p>High\u00adlights of the Vega <span class=\"caps\">GPU<\/span> architecture\u2019s advance\u00adments include:<\/p>\n<ul>\n<li><b>The world\u2019s most advan\u00adced <span class=\"caps\">GPU<\/span> memo\u00adry archi\u00adtec\u00adtu\u00adre:<\/b> The Vega archi\u00adtec\u00adtu\u00adre enables a new memo\u00adry hier\u00adar\u00adchy for GPUs. This radi\u00adcal new approach comes in the form of a new high-band\u00adwidth cache and its con\u00adtrol\u00adler. The cache fea\u00adtures lea\u00adding-edge <span class=\"caps\">HBM2<\/span> tech\u00adno\u00adlo\u00adgy which is capa\u00adble of trans\u00adfer\u00adring tera\u00adbytes of data every second, doubling the band\u00adwidth-per-pin over the pre\u00advious gene\u00adra\u00adti\u00adon <span class=\"caps\">HBM<\/span> tech\u00adno\u00adlo\u00adgy. <span class=\"caps\">HBM2<\/span> also enables much grea\u00adter capa\u00adci\u00adty at less than half the foot\u00adprint of <span class=\"caps\">GDDR5<\/span> memo\u00adry. Vega archi\u00adtec\u00adtu\u00adre is opti\u00admi\u00adzed for strea\u00adming very lar\u00adge data\u00adsets and can work with a varie\u00adty of memo\u00adry types with up to <span class=\"caps\">512TB<\/span> of vir\u00adtu\u00adal address space.<\/li>\n<\/ul>\n<ul>\n<li><b>Next-gene\u00adra\u00adti\u00adon geo\u00adme\u00adtry pipe\u00adline:<\/b> Today\u2019s games and pro\u00adfes\u00adsio\u00adnal appli\u00adca\u00adti\u00adons make use of incre\u00addi\u00adbly com\u00adplex geo\u00adme\u00adtry enab\u00adled by the extra\u00ador\u00addi\u00adna\u00adry increase in the reso\u00adlu\u00adti\u00adons of data acqui\u00adsi\u00adti\u00adon devices.&nbsp; The hundreds of mil\u00adli\u00adons of poly\u00adgons in any given frame have mes\u00adhes so den\u00adse that the\u00adre are often many poly\u00adgons being ren\u00adde\u00adred per pixel. Vega\u2019s next-gene\u00adra\u00adti\u00adon geo\u00adme\u00adtry pipe\u00adline enables the pro\u00adgramm\u00ader to extra\u00adct incre\u00addi\u00adble effi\u00adci\u00aden\u00adcy in pro\u00adces\u00adsing this com\u00adplex geo\u00adme\u00adtry, while also deli\u00adve\u00adring more than 200% of the through\u00adput-per-clock over pre\u00advious Rade\u00adon archi\u00adtec\u00adtures.<a>[i]<\/a> It also fea\u00adtures impro\u00adved load-balan\u00adcing with an intel\u00adli\u00adgent workload dis\u00adtri\u00adbu\u00adtor to deli\u00adver con\u00adsis\u00adtent performance.<\/li>\n<\/ul>\n<ul>\n<li><b>Next-gene\u00adra\u00adti\u00adon com\u00adpu\u00adte engi\u00adne:<\/b> At the core of the Vega archi\u00adtec\u00adtu\u00adre is a new, next-gene\u00adra\u00adti\u00adon com\u00adpu\u00adte engi\u00adne built on fle\u00adxi\u00adble com\u00adpu\u00adte units that can natively pro\u00adcess 8\u2011bit, 16-bit, 32-bit or 64-bit ope\u00adra\u00adti\u00adons in each clock cycle.<a>[ii]<\/a> The\u00adse com\u00adpu\u00adte units are opti\u00admi\u00adzed to attain signi\u00adfi\u00adcant\u00adly hig\u00adher fre\u00adquen\u00adci\u00ades than pre\u00advious gene\u00adra\u00adti\u00adons and their sup\u00adport of varia\u00adble data\u00adty\u00adpes makes the archi\u00adtec\u00adtu\u00adre high\u00adly ver\u00adsa\u00adti\u00adle across workloads.<\/li>\n<\/ul>\n<ul>\n<li><b>Advan\u00adced pixel engi\u00adne:<\/b> The new Vega pixel engi\u00adne employs a Draw Stream Bin\u00adning Ras\u00adte\u00adri\u00adzer, desi\u00adgned to impro\u00adve per\u00adfor\u00admance and power effi\u00adci\u00aden\u00adcy. It allows for \u201cfetch once, sha\u00adde once\u201d of pixels through the use of a smart on-chip bin cache and ear\u00adly cul\u00adling of pixels invi\u00adsi\u00adble in a final sce\u00adne. Vega\u2019s pixel engi\u00adne is now a cli\u00adent of the onboard <span class=\"caps\">L2<\/span> cache, enab\u00adling con\u00adsidera\u00adble over\u00adhead reduc\u00adtion for gra\u00adphics workloads which per\u00adform fre\u00adquent read-after-wri\u00adte operations.<\/li>\n<\/ul>\n<p><span class=\"caps\">GPU<\/span> pro\u00adducts based on the Vega archi\u00adtec\u00adtu\u00adre are expec\u00adted to ship in the first half of&nbsp;2017.<\/p>\n<p><b>Sup\u00adport\u00ading Resources<\/b><\/p>\n<ul>\n<li>Check out the <a href=\"https:\/\/www.youtube.com\/watch?v=9R8F-aN6W4g&amp;feature=youtu.be\">Vega Pre\u00adview Cine\u00adma\u00adtic Trailer<\/a><\/li>\n<li>Check out <a href=\"http:\/\/www.ve.ga\">http:\/\/ve.ga<\/a>, the Vega archi\u00adtec\u00adtu\u00adre pre\u00adview portal<\/li>\n<li>Beco\u00adme a fan of&nbsp;<a href=\"http:\/\/www.facebook.com\/radeon\">Rade\u00adon<\/a> on Facebook<\/li>\n<li>Fol\u00adlow <a href=\"https:\/\/twitter.com\/radeon\">@Radeon<\/a> on Twitter<\/li>\n<li>Fol\u00adlow <a href=\"https:\/\/twitter.com\/radeonpro\">@RadeonPro<\/a> on Twitter<\/li>\n<li>Fol\u00adlow <a href=\"https:\/\/twitter.com\/radeoninstinct\">@RadeonInstinct<\/a> on Twitter&nbsp;<\/li>\n<\/ul>\n<p><b>About <span class=\"caps\">AMD<\/span><\/b><\/p>\n<p>For more than 45 years <span class=\"caps\">AMD<\/span> has dri\u00adven inno\u00adva\u00adti\u00adon in high-per\u00adfor\u00admance com\u00adpu\u00adting, gra\u00adphics, and visua\u00adliza\u00adti\u00adon tech\u00adno\u00adlo\u00adgies \u2015 the buil\u00adding blocks for gam\u00ading, immersi\u00adve plat\u00adforms, and the dat\u00ada\u00adcen\u00adter. Hundreds of mil\u00adli\u00adons of con\u00adsu\u00admers, lea\u00adding For\u00adtu\u00adne 500 busi\u00adnesses, and cut\u00adting-edge sci\u00aden\u00adti\u00adfic rese\u00adarch faci\u00adli\u00adties around the world rely on <span class=\"caps\">AMD<\/span> tech\u00adno\u00adlo\u00adgy dai\u00adly to impro\u00adve how they live, work, and play. <span class=\"caps\">AMD<\/span> employees around the world are focu\u00adsed on buil\u00adding gre\u00adat pro\u00adducts that push the boun\u00adda\u00adries of what is pos\u00adsi\u00adble. For more infor\u00adma\u00adti\u00adon about how <span class=\"caps\">AMD<\/span> is enab\u00adling today and inspi\u00adring tomor\u00adrow, visit the <span class=\"caps\">AMD<\/span> (<span class=\"caps\">NASDAQ<\/span>: <span class=\"caps\">AMD<\/span>) <a href=\"http:\/\/www.amd.com\/\">web\u00adsite<\/a>, <a href=\"http:\/\/community.amd.com\/welcome\">blog<\/a>, <a href=\"https:\/\/www.facebook.com\/AMD\">Face\u00adbook<\/a> and <a href=\"https:\/\/twitter.com\/amd\">Twit\u00adter<\/a> pages.<\/p>\n<p><b><span class=\"caps\">AMD<\/span>, the <span class=\"caps\">AMD<\/span> Arrow logo, Rade\u00adon and com\u00adbi\u00adna\u00adti\u00adons the\u00adreof, are trade\u00admarks of Advan\u00adced Micro Devices, Inc. Other names are for infor\u00adma\u00adtio\u00adnal pur\u00adpo\u00adses only and may be trade\u00admarks of their respec\u00adti\u00adve owners.<\/b><\/p>\n<p>Cau\u00adtio\u00adna\u00adry Statement<\/p>\n<p>This press release con\u00adta\u00adins for\u00adward-loo\u00adking state\u00adments con\u00adcer\u00adning&nbsp;Advan\u00adced Micro Devices, Inc.&nbsp;(<span class=\"caps\">AMD<\/span>) inclu\u00adding the fea\u00adtures, func\u00adtion\u00ada\u00adli\u00adty and expec\u00adta\u00adti\u00adons regar\u00adding <span class=\"caps\">AMD<\/span>\u2019s Vega <span class=\"caps\">GPU<\/span> archi\u00adtec\u00adtu\u00adre and the timing and avai\u00adla\u00adbi\u00adli\u00adty of <span class=\"caps\">GPU<\/span> pro\u00adducts based on <span class=\"caps\">AMD<\/span>\u2019s Vega archi\u00adtec\u00adtu\u00adre, which are made pur\u00adsu\u00adant to the Safe Har\u00adbor pro\u00advi\u00adsi\u00adons of the Pri\u00adva\u00adte Secu\u00adri\u00adties Liti\u00adga\u00adti\u00adon Reform Act of 1995. For\u00adward-loo\u00adking state\u00adments are com\u00admon\u00adly iden\u00adti\u00adfied by words such as \u201cwould,\u201d \u201cmay,\u201d \u201cexpects,\u201d \u201cbelie\u00adves,\u201d \u201cplans,\u201d \u201cintends,\u201d \u201cpro\u00adjects\u201d and other terms with simi\u00adlar mea\u00adning. Inves\u00adtors are cau\u00adtio\u00adned that the for\u00adward-loo\u00adking state\u00adments in this docu\u00adment are based on cur\u00adrent beliefs, assump\u00adti\u00adons and expec\u00adta\u00adti\u00adons, speak only as of the date of this press release and invol\u00adve risks and uncer\u00adtain\u00adties that could cau\u00adse actu\u00adal results to dif\u00adfer mate\u00adri\u00adal\u00adly from cur\u00adrent expec\u00adta\u00adti\u00adons. Such state\u00adments are sub\u00adject to cer\u00adtain known and unknown risks and uncer\u00adtain\u00adties, many of which are dif\u00adfi\u00adcult to pre\u00addict and gene\u00adral\u00adly bey\u00adond <span class=\"caps\">AMD<\/span>\u2019s con\u00adtrol, that could cau\u00adse actu\u00adal results and other future events to dif\u00adfer mate\u00adri\u00adal\u00adly from tho\u00adse expres\u00adsed in, or impli\u00aded or pro\u00adjec\u00adted by, the for\u00adward-loo\u00adking infor\u00adma\u00adti\u00adon and state\u00adments. Mate\u00adri\u00adal fac\u00adtors that could cau\u00adse actu\u00adal results to dif\u00adfer mate\u00adri\u00adal\u00adly from cur\u00adrent expec\u00adta\u00adti\u00adons include, wit\u00adhout limi\u00adta\u00adti\u00adon, the fol\u00adlo\u00adwing:&nbsp;Intel Corporation\u2019s domi\u00adnan\u00adce of the micro\u00adpro\u00adces\u00adsor mar\u00adket and its aggres\u00adsi\u00adve busi\u00adness prac\u00adti\u00adces may limit <span class=\"caps\">AMD<\/span>\u2019s abili\u00adty to com\u00adpe\u00adte effec\u00adtively; <span class=\"caps\">AMD<\/span> is par\u00adty to a wafer sup\u00adp\u00adly agree\u00adment with <span class=\"caps\">GLOBALFOUNDRIES<\/span> Inc. (<span class=\"caps\">GF<\/span>) with obli\u00adga\u00adti\u00adons to manu\u00adfac\u00adtu\u00adre pro\u00adducts at <span class=\"caps\">GF<\/span> with cer\u00adtain excep\u00adti\u00adons. If <span class=\"caps\">GF<\/span> is not able to satis\u00adfy <span class=\"caps\">AMD<\/span>\u2019s manu\u00adfac\u00adtu\u00adring requi\u00adre\u00adments, its busi\u00adness could be adver\u00adse\u00adly impac\u00adted; <span class=\"caps\">AMD<\/span> reli\u00ades on third par\u00adties to manu\u00adfac\u00adtu\u00adre its pro\u00adducts, and if they are unable to do so on a time\u00adly basis in suf\u00adfi\u00adci\u00adent quan\u00adti\u00adties and using com\u00adpe\u00adti\u00adti\u00adve tech\u00adno\u00adlo\u00adgies, <span class=\"caps\">AMD<\/span>\u2019s busi\u00adness could be mate\u00adri\u00adal\u00adly adver\u00adse\u00adly affec\u00adted; fail\u00adure to achie\u00adve expec\u00adted manu\u00adfac\u00adtu\u00adring yields for <span class=\"caps\">AMD<\/span>\u2019s pro\u00adducts could nega\u00adtively impact its finan\u00adcial results; the suc\u00adcess of <span class=\"caps\">AMD<\/span>\u2019s busi\u00adness is depen\u00addent upon its abili\u00adty to intro\u00addu\u00adce pro\u00adducts on a time\u00adly basis with fea\u00adtures and per\u00adfor\u00admance levels that pro\u00advi\u00adde value to its cus\u00adto\u00admers while sup\u00adport\u00ading and coin\u00adci\u00adding with signi\u00adfi\u00adcant indus\u00adtry tran\u00adsi\u00adti\u00adons; if <span class=\"caps\">AMD<\/span> can\u00adnot gene\u00adra\u00adte suf\u00adfi\u00adci\u00adent reve\u00adnue and ope\u00adra\u00adting cash flow or obtain exter\u00adnal finan\u00adcing, it may face a cash short\u00adfall and be unable to make all of its plan\u00adned invest\u00adments in rese\u00adarch and deve\u00adlo\u00adp\u00adment or other stra\u00adte\u00adgic invest\u00adments; the loss of a signi\u00adfi\u00adcant cus\u00adto\u00admer may have a mate\u00adri\u00adal adver\u00adse effect on <span class=\"caps\">AMD<\/span>; <span class=\"caps\">AMD<\/span>\u2019s receipt of reve\u00adnue from its semi-cus\u00adtom SoC pro\u00adducts is depen\u00addent upon its tech\u00adno\u00adlo\u00adgy being desi\u00adgned into third-par\u00adty pro\u00adducts and the suc\u00adcess of tho\u00adse pro\u00adducts; glo\u00adbal eco\u00adno\u00admic uncer\u00adtain\u00adty may adver\u00adse\u00adly impact <span class=\"caps\">AMD<\/span>\u2019s busi\u00adness and ope\u00adra\u00adting results; the mar\u00adkets in which <span class=\"caps\">AMD<\/span>\u2019s pro\u00adducts are sold are high\u00adly com\u00adpe\u00adti\u00adti\u00adve; <span class=\"caps\">AMD<\/span> may not be able to gene\u00adra\u00adte suf\u00adfi\u00adci\u00adent cash to ser\u00advice its debt obli\u00adga\u00adti\u00adons or meet its working capi\u00adtal requi\u00adre\u00adments; <span class=\"caps\">AMD<\/span> has a sub\u00adstan\u00adti\u00adal amount of indeb\u00adted\u00adness which could adver\u00adse\u00adly affect its finan\u00adcial posi\u00adti\u00adon and pre\u00advent it from imple\u00admen\u00adting its stra\u00adtegy or ful\u00adfil\u00adling its con\u00adtrac\u00adtu\u00adal obli\u00adga\u00adti\u00adons; the agree\u00adments gover\u00adning <span class=\"caps\">AMD<\/span>\u2019s notes and the secu\u00adred revol\u00adving line of cre\u00addit (Secu\u00adred Revol\u00adving Line of Cre\u00addit) impo\u00adse rest\u00adric\u00adtions on <span class=\"caps\">AMD<\/span> that may adver\u00adse\u00adly affect its abili\u00adty to ope\u00adra\u00adte its busi\u00adness; uncer\u00adtain\u00adties invol\u00adving the orde\u00adring and ship\u00adment of <span class=\"caps\">AMD<\/span>\u2019s pro\u00adducts could mate\u00adri\u00adal\u00adly adver\u00adse\u00adly affect it; the demand for <span class=\"caps\">AMD<\/span>\u2019s pro\u00adducts depends in part on the mar\u00adket con\u00addi\u00adti\u00adons in the indus\u00adtries into which they are sold. Fluc\u00adtua\u00adtions in demand for <span class=\"caps\">AMD<\/span>\u2019s pro\u00adducts or a mar\u00adket decli\u00adne in any of the\u00adse indus\u00adtries could have a mate\u00adri\u00adal adver\u00adse effect on its results of ope\u00adra\u00adti\u00adons; <span class=\"caps\">AMD<\/span>\u2019s abili\u00adty to design and intro\u00addu\u00adce new pro\u00adducts in a time\u00adly man\u00adner is depen\u00addent upon third-par\u00adty intellec\u00adtu\u00adal pro\u00adper\u00adty; <span class=\"caps\">AMD<\/span> depends on third-par\u00adty com\u00adpa\u00adnies for the design, manu\u00adfac\u00adtu\u00adre and sup\u00adp\u00adly of mother\u00adboards, soft\u00adware and other com\u00adpu\u00adter plat\u00adform com\u00adpon\u00adents to sup\u00adport its busi\u00adness; if <span class=\"caps\">AMD<\/span> loses Micro\u00adsoft Corporation\u2019s sup\u00adport for its pro\u00adducts or other soft\u00adware ven\u00addors do not design and deve\u00adlop soft\u00adware to run on <span class=\"caps\">AMD<\/span>\u2019s pro\u00adducts, its abili\u00adty to sell its pro\u00adducts could be mate\u00adri\u00adal\u00adly adver\u00adse\u00adly affec\u00adted; and <span class=\"caps\">AMD<\/span>\u2019s reli\u00adance on third-par\u00adty dis\u00adtri\u00adbu\u00adtors and Add-in-Board part\u00adners sub\u00adjects it to cer\u00adtain risks. Inves\u00adtors are urged to review in detail the risks and uncer\u00adtain\u00adties in <span class=\"caps\">AMD<\/span>\u2019s&nbsp;Secu\u00adri\u00adties and Exch\u00adan\u00adge Com\u00admis\u00adsi\u00adon&nbsp;filings, inclu\u00adding but not limi\u00adt\u00aded to <span class=\"caps\">AMD<\/span>\u2019s Quar\u00adter\u00adly Report on Form 10\u2011Q for the quar\u00adter ended Sep\u00adtem\u00adber 24,&nbsp;2016.<\/p>\n<p><a>[i]<\/a> Data based on <span class=\"caps\">AMD<\/span> Engi\u00adnee\u00adring design of Vega.&nbsp; Rade\u00adon <span class=\"caps\">R9<\/span> Fury X has 4 geo\u00adme\u00adtry engi\u00adnes and a peak of 4 poly\u00adgons per clock. Vega is desi\u00adgned to hand\u00adle up to 11 poly\u00adgons per clock with 4 geo\u00adme\u00adtry engi\u00adnes.&nbsp; This repres\u00adents an increase of 2.6x.&nbsp; <span class=\"caps\">VG<\/span>\u20113<\/p>\n<p><a>[ii]<\/a> Dis\u00adcrete <span class=\"caps\">AMD<\/span> Rade\u00adon\u2122 and Fire\u00adPro\u2122 GPUs based on the Gra\u00adphics Core Next archi\u00adtec\u00adtu\u00adre con\u00adsist of mul\u00adti\u00adple dis\u00adcrete exe\u00adcu\u00adti\u00adon engi\u00adnes known as a Com\u00adpu\u00adte Unit (\u201c<span class=\"caps\">CU<\/span>\u201d). Each <span class=\"caps\">CU<\/span> con\u00adta\u00adins 64 shaders (\u201cStream Pro\u00adces\u00adsors\u201d) working tog\u00ade\u00adther.&nbsp;<span class=\"caps\">GD-78<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>ega: <span class=\"caps\">AMD<\/span>\u2019s New Gra\u00adphics Archi\u00adtec\u00adtu\u00adre for Vir\u00adtual\u00adly Unli\u00admi\u00adt\u00aded Workloads<\/p>\n<p>Brand new high per\u00adfor\u00admance <span class=\"caps\">GPU<\/span> archi\u00adtec\u00adtu\u00adre remo\u00adves many tra\u00addi\u00adtio\u00adnal cons\u00adtraints from<\/p>\n<p>Gam\u00ading, <span class=\"caps\">VR<\/span>, Pro\u00adfes\u00adsio\u00adnal Design and Machi\u00adne Intel\u00adli\u00adgence are\u00adnas (\u2026) <a class=\"moretag\" href=\"https:\/\/www.planet3dnow.de\/cms\/28363-amd-stellt-vega-architektur-auf-ces-vor\/\">Wei\u00adter\u00adle\u00adsen&nbsp;\u00bb<\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"wp_typography_post_enhancements_disabled":false,"ngg_post_thumbnail":0,"footnotes":""},"categories":[22],"tags":[1102],"class_list":["post-28363","post","type-post","status-publish","format-standard","hentry","category-pressemitteilungen","tag-vega","entry"],"share_on_mastodon":{"url":"","error":""},"_links":{"self":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/28363","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/comments?post=28363"}],"version-history":[{"count":1,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/28363\/revisions"}],"predecessor-version":[{"id":28364,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/28363\/revisions\/28364"}],"wp:attachment":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/media?parent=28363"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/categories?post=28363"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/tags?post=28363"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}