{"id":41490,"date":"2018-11-07T10:27:01","date_gmt":"2018-11-07T09:27:01","guid":{"rendered":"https:\/\/www.planet3dnow.de\/cms\/?p=41490"},"modified":"2018-11-07T10:27:01","modified_gmt":"2018-11-07T09:27:01","slug":"amd-unveils-worlds-first-7nm-datacenter-gpus","status":"publish","type":"post","link":"https:\/\/www.planet3dnow.de\/cms\/41490-amd-unveils-worlds-first-7nm-datacenter-gpus\/","title":{"rendered":"<span class=\"caps\">AMD<\/span> Unveils World\u2019s First 7nm Datacenter GPUs"},"content":{"rendered":"<div class=\"field field--name-field-nir-news-title field--type-string field--label-hidden\">\n<div class=\"field__item\">\u2013 Powe\u00adring the Next Era of Arti\u00adfi\u00adci\u00adal Intel\u00adli\u00adgence, Cloud Com\u00adpu\u00adting and High Per\u00adfor\u00admance Com\u00adpu\u00adting (<span class=\"caps\">HPC<\/span>)<\/div>\n<div>&nbsp;<\/div>\n<\/div>\n<div class=\"field field--name-field-subheading field--type-text-long field--label-hidden field__item\">\n<p><em>\u2014 <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> and <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtors with&nbsp;<\/em><em>super\u00adchar\u00adged com\u00adpu\u00adte per\u00adfor\u00admance, high-speed con\u00adnec\u00adti\u00advi\u00adty, fast memo\u00adry band\u00adwidth and&nbsp;<\/em><em>updated ROCm open soft\u00adware plat\u00adform&nbsp;<\/em><em>power the most deman\u00adding deep lear\u00adning, <span class=\"caps\">HPC<\/span>, cloud and ren\u00adde\u00adring appli\u00adca\u00adti\u00adons&nbsp;<\/em><em>\u2014<\/em><\/p>\n<\/div>\n<div class=\"location-date\">\n<div class=\"field field--name-field-location field--type-string field--label-hidden field__item\">San Fran\u00adcis\u00adco, Calif.&nbsp;<time datetime=\"2018-11-06T12:00:00Z\">11\/06\/2018<\/time><\/div>\n<div>&nbsp;<\/div>\n<\/div>\n<div class=\"field field--name-body field--type-text-with-summary field--label-hidden field__item\">\n<p><a href=\"http:\/\/www.amd.com\/\"><span class=\"caps\">AMD<\/span><\/a>&nbsp;(<span class=\"caps\">NASDAQ<\/span>: <span class=\"caps\">AMD<\/span>) today announ\u00adced the <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> and <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtors, the world\u2019s first 7nm dat\u00ada\u00adcen\u00adter GPUs, desi\u00adgned to deli\u00adver the com\u00adpu\u00adte per\u00adfor\u00admance requi\u00adred for next-gene\u00adra\u00adti\u00adon deep lear\u00adning, <span class=\"caps\">HPC<\/span>, cloud com\u00adpu\u00adting and ren\u00adde\u00adring appli\u00adca\u00adti\u00adons. Rese\u00adar\u00adchers, sci\u00aden\u00adtists and deve\u00adlo\u00adpers will use <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 acce\u00adle\u00adra\u00adtors to sol\u00adve tough and inte\u00adres\u00adt\u00ading chal\u00adlenges, inclu\u00adding lar\u00adge-sca\u00adle simu\u00adla\u00adti\u00adons, cli\u00adma\u00adte chan\u00adge, com\u00adpu\u00adta\u00adtio\u00adnal bio\u00adlo\u00adgy, dise\u00ada\u00adse pre\u00adven\u00adti\u00adon and&nbsp;more.<\/p>\n<p><span class=\"dquo\">\u201c<\/span>Lega\u00adcy <span class=\"caps\">GPU<\/span> archi\u00adtec\u00adtures limit <span class=\"caps\">IT<\/span> mana\u00adgers from effec\u00adtively addres\u00adsing the con\u00adstant\u00adly evol\u00adving demands of pro\u00adces\u00adsing and ana\u00adly\u00adzing huge data\u00adsets for modern cloud dat\u00ada\u00adcen\u00adter workloads,\u201d said David Wang, seni\u00ador vice pre\u00adsi\u00addent of engi\u00adnee\u00adring, Rade\u00adon Tech\u00adno\u00adlo\u00adgies Group at <span class=\"caps\">AMD<\/span>. \u201cCom\u00adbi\u00adning world-class per\u00adfor\u00admance and a fle\u00adxi\u00adble archi\u00adtec\u00adtu\u00adre with a robust soft\u00adware plat\u00adform and the industry\u2019s lea\u00adding-edge ROCm open soft\u00adware eco\u00adsys\u00adtem, the new <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 acce\u00adle\u00adra\u00adtors pro\u00advi\u00adde the cri\u00adti\u00adcal com\u00adpon\u00adents nee\u00added to sol\u00adve the most dif\u00adfi\u00adcult cloud com\u00adpu\u00adting chal\u00adlenges today and into the future.\u201d<\/p>\n<p>The <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> and <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtors fea\u00adture fle\u00adxi\u00adble mixed-pre\u00adcis\u00adi\u00adon capa\u00adbi\u00adli\u00adties, powered by high-per\u00adfor\u00admance com\u00adpu\u00adte units that expand the types of workloads the\u00adse acce\u00adle\u00adra\u00adtors can address, inclu\u00adding a ran\u00adge of <span class=\"caps\">HPC<\/span> and deep lear\u00adning appli\u00adca\u00adti\u00adons. The new <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> and <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtors were desi\u00adgned to effi\u00adci\u00adent\u00adly pro\u00adcess workloads such as rapidly trai\u00adning com\u00adplex neu\u00adral net\u00adworks, deli\u00adve\u00adring hig\u00adher levels of floa\u00adting-point per\u00adfor\u00admance, grea\u00adter effi\u00adci\u00aden\u00adci\u00ades and new fea\u00adtures for dat\u00ada\u00adcen\u00adter and depart\u00adment\u00adal deploy\u00adments<sup>1<\/sup>.<\/p>\n<p>The <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> and <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtors pro\u00advi\u00adde ultra-fast floa\u00adting-point per\u00adfor\u00adman\u00adceand hyper-fast <span class=\"caps\">HBM2<\/span> (second-gene\u00adra\u00adti\u00adon High-Band\u00adwidth Memo\u00adry) with up to 1 <span class=\"caps\">TB<\/span>\/s memo\u00adry band\u00adwidth speeds. They are also the first GPUs capa\u00adble of sup\u00adport\u00ading next-gene\u00adra\u00adti\u00adon PCIe\u00ae 4.0<sup>2<\/sup>&nbsp;inter\u00adcon\u00adnect, which is up to <span class=\"caps\">2X<\/span> fas\u00adter than other x86 CPU-to-GPU inter\u00adcon\u00adnect tech\u00adno\u00adlo\u00adgies<sup>3<\/sup>, and fea\u00adture <span class=\"caps\">AMD<\/span> Infi\u00adni\u00adty Fabric\u2122 Link <span class=\"caps\">GPU<\/span> inter\u00adcon\u00adnect tech\u00adno\u00adlo\u00adgy that enables GPU-to-GPU com\u00admu\u00adni\u00adca\u00adti\u00adons that are up to <span class=\"caps\">6X<\/span> fas\u00adter than PCIe\u00ae Gen 3 inter\u00adcon\u00adnect speeds<sup>4<\/sup>.<\/p>\n<p><span class=\"caps\">AMD<\/span> also announ\u00adced a new ver\u00adsi\u00adon of the ROCm open soft\u00adware plat\u00adform for acce\u00adle\u00adra\u00adted com\u00adpu\u00adting that sup\u00adports the archi\u00adtec\u00adtu\u00adral fea\u00adtures of the new acce\u00adle\u00adra\u00adtors, inclu\u00adding opti\u00admi\u00adzed deep lear\u00adning ope\u00adra\u00adti\u00adons (<span class=\"caps\">DLOPS<\/span>) and the <span class=\"caps\">AMD<\/span> Infi\u00adni\u00adty Fabric\u2122 Link <span class=\"caps\">GPU<\/span> inter\u00adcon\u00adnect tech\u00adno\u00adlo\u00adgy. Desi\u00adgned for sca\u00adle, ROCm allows cus\u00adto\u00admers to deploy high-per\u00adfor\u00admance, ener\u00adgy-effi\u00adci\u00adent hete\u00adro\u00adge\u00adneous com\u00adpu\u00adting sys\u00adtems in an open environment.<\/p>\n<p><span class=\"dquo\">\u201c<\/span>Goog\u00adle belie\u00adves that open source is good for ever\u00adyo\u00adne,\u201d said Rajat Mon\u00adga, engi\u00adnee\u00adring direc\u00adtor, Ten\u00adsor\u00adFlow, Goog\u00adle. \u201cWe\u2019\u00adve seen how hel\u00adpful it can be to open source machi\u00adne lear\u00adning tech\u00adno\u00adlo\u00adgy, and we\u2019re glad to see <span class=\"caps\">AMD<\/span> embra\u00adcing it. With the ROCm open soft\u00adware plat\u00adform, Ten\u00adsor\u00adFlow users will bene\u00adfit from <span class=\"caps\">GPU<\/span> acce\u00adle\u00adra\u00adti\u00adon and a more robust open source machi\u00adne lear\u00adning ecosystem.\u201d<\/p>\n<p>Key fea\u00adtures of the <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> and <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtors include:<\/p>\n<ul>\n<li><strong>Opti\u00admi\u00adzed Deep Lear\u00adning Ope\u00adra\u00adti\u00adons:&nbsp;<\/strong>Pro\u00advi\u00addes fle\u00adxi\u00adble mixed-pre\u00adcis\u00adi\u00adon <span class=\"caps\">FP16<\/span>, <span class=\"caps\">FP32<\/span> and <span class=\"caps\">INT4<\/span>\/<span class=\"caps\">INT8<\/span> capa\u00adbi\u00adli\u00adties to meet gro\u00adwing demand for dyna\u00admic and ever-chan\u00adging workloads, from trai\u00adning com\u00adplex neu\u00adral net\u00adworks to run\u00adning infe\u00adrence against tho\u00adse trai\u00adned networks.<\/li>\n<li><strong>World\u2019s Fas\u00adtest Dou\u00adble Pre\u00adcis\u00adi\u00adon PCIe\u00ae<sup>2<\/sup>&nbsp;Acce\u00adle\u00adra\u00adtor<sup>5<\/sup>:&nbsp;<\/strong>The <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> is the world\u2019s fas\u00adtest dou\u00adble pre\u00adcis\u00adi\u00adon PCIe 4.0 capa\u00adble acce\u00adle\u00adra\u00adtor, deli\u00adve\u00adring up to 7.4 <span class=\"caps\">TFLOPS<\/span> peak <span class=\"caps\">FP64<\/span> per\u00adfor\u00admance<sup>5<\/sup>&nbsp;allo\u00adwing sci\u00aden\u00adtists and rese\u00adar\u00adchers to more effi\u00adci\u00adent\u00adly pro\u00adcess <span class=\"caps\">HPC<\/span> appli\u00adca\u00adti\u00adons across a ran\u00adge of indus\u00adtries inclu\u00adding life sci\u00aden\u00adces, ener\u00adgy, finan\u00adce, auto\u00admo\u00adti\u00adve, aero\u00adspace, aca\u00adde\u00admics, govern\u00adment, defen\u00adse and more. The <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI50<\/span> deli\u00advers up to 6.7 <span class=\"caps\">TFLOPS<\/span> <span class=\"caps\">FP64<\/span> peak per\u00adfor\u00admance<sup>1<\/sup>, while pro\u00advi\u00adding an effi\u00adci\u00adent, cost-effec\u00adti\u00adve solu\u00adti\u00adon for a varie\u00adty of deep lear\u00adning workloads, as well as enab\u00adling high reu\u00adse in Vir\u00adtu\u00adal Desk\u00adtop Infra\u00adstruc\u00adtu\u00adre (<span class=\"caps\">VDI<\/span>), Desk\u00adtop-as-a-Ser\u00advice (DaaS) and cloud environments.<\/li>\n<li><strong>Up to <span class=\"caps\">6X<\/span> Fas\u00adter Data Trans\u00adfer:&nbsp;<\/strong>Two Infi\u00adni\u00adty Fabric\u2122 Links per <span class=\"caps\">GPU<\/span> deli\u00adver up to 200 <span class=\"caps\">GB<\/span>\/s of peer-to-peer band\u00adwidth \u2013 up to <span class=\"caps\">6X<\/span> fas\u00adter than PCIe 3.0 alo\u00adne<sup>4<\/sup>&nbsp;\u2013 and enable the con\u00adnec\u00adtion of up to 4 GPUs in a hive ring con\u00adfi\u00adgu\u00adra\u00adti\u00adon (2 hives in 8 <span class=\"caps\">GPU<\/span> servers).<\/li>\n<li><strong>Ultra-Fast <span class=\"caps\">HBM2<\/span> Memo\u00adry<\/strong>: The <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> pro\u00advi\u00addes <span class=\"caps\">32GB<\/span> of <span class=\"caps\">HBM2<\/span> Error-cor\u00adrec\u00adting code (<span class=\"caps\">ECC<\/span>) memo\u00adry<sup>6<\/sup>, and the Rade\u00adon Instinct\u2122 <span class=\"caps\">MI50<\/span> pro\u00advi\u00addes <span class=\"caps\">16GB<\/span> of <span class=\"caps\">HBM2<\/span> <span class=\"caps\">ECC<\/span> memo\u00adry. Both GPUs pro\u00advi\u00adde full-chip <span class=\"caps\">ECC<\/span> and Relia\u00adbi\u00adli\u00adty, Acces\u00adsi\u00adbi\u00adli\u00adty and Ser\u00advicea\u00adbi\u00adli\u00adty (<span class=\"caps\">RAS<\/span>)<sup>7<\/sup>&nbsp;tech\u00adno\u00adlo\u00adgies, which are cri\u00adti\u00adcal to deli\u00adver more accu\u00adra\u00adte com\u00adpu\u00adte results for lar\u00adge-sca\u00adle <span class=\"caps\">HPC<\/span> deployments.<\/li>\n<li><strong>Secu\u00adre Vir\u00adtua\u00adli\u00adzed Workload Sup\u00adport:<\/strong>&nbsp;<a href=\"https:\/\/pro.radeon.com\/en\/solutions\/vdi\/\"><span class=\"caps\">AMD<\/span> MxG\u00adPU Tech\u00adno\u00adlo\u00adgy<\/a>, the industry\u2019s only hard\u00adware-based <span class=\"caps\">GPU<\/span> vir\u00adtua\u00adliza\u00adti\u00adon solu\u00adti\u00adon, which is based on the indus\u00adtry-stan\u00addard <span class=\"caps\">SR-IOV<\/span> (Sin\u00adgle Root I\/O Vir\u00adtua\u00adliza\u00adti\u00adon) tech\u00adno\u00adlo\u00adgy, makes it dif\u00adfi\u00adcult for hackers to attack at the hard\u00adware level, hel\u00adping pro\u00advi\u00adde secu\u00adri\u00adty for vir\u00adtua\u00adli\u00adzed cloud deployments.<\/li>\n<\/ul>\n<h3>Updated ROCm Open Software Platform<\/h3>\n<p><span class=\"caps\">AMD<\/span> today also announ\u00adced a new ver\u00adsi\u00adon of its&nbsp;<a>ROCm open soft\u00adware plat\u00adform&nbsp;<\/a>desi\u00adgned to speed deve\u00adlo\u00adp\u00adment of high-per\u00adfor\u00admance, ener\u00adgy-effi\u00adci\u00adent hete\u00adro\u00adge\u00adneous com\u00adpu\u00adting sys\u00adtems. In addi\u00adti\u00adon to sup\u00adport for the new Rade\u00adon Instinct\u2122 acce\u00adle\u00adra\u00adtors, ROCm soft\u00adware ver\u00adsi\u00adon 2.0 pro\u00advi\u00addes updated math libra\u00adri\u00ades for the new <span class=\"caps\">DLOPS<\/span>; sup\u00adport for 64-bit Linux ope\u00adra\u00adting sys\u00adtems inclu\u00adding Cent\u00adOS, <span class=\"caps\">RHEL<\/span> and Ubun\u00adtu; opti\u00admiza\u00adti\u00adons of exis\u00adting com\u00adpon\u00adents; and sup\u00adport for the latest ver\u00adsi\u00adons of the most popu\u00adlar deep lear\u00adning frame\u00adworks, inclu\u00adding Ten\u00adsor\u00adFlow 1.11, PyTorch (Caffe2) and others. Learn more about ROCm 2.0 soft\u00adware&nbsp;<a href=\"https:\/\/community.amd.com\/community\/radeon-instinct-accelerators\/blog\/2018\/11\/06\/rocm-software-enables-the-worlds-first-7nm-gpu\">here<\/a>.<\/p>\n<h3>Availability<\/h3>\n<p>The <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> acce\u00adle\u00adra\u00adtor is expec\u00adted to ship to dat\u00ada\u00adcen\u00adter cus\u00adto\u00admers by the end of 2018. The <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtor is expec\u00adted to begin ship\u00adping to data cen\u00adter cus\u00adto\u00admers by the end of <span class=\"caps\">Q1<\/span> 2019. The ROCm 2.0 open soft\u00adware plat\u00adform is expec\u00adted to be available by the end of&nbsp;2018.<\/p>\n<h3>Supporting Resources<\/h3>\n<ul>\n<li>Visit the <span class=\"caps\">AMD<\/span>&nbsp;<a href=\"https:\/\/www.amd.com\/en\/events\/next-horizon\">Next Hori\u00adzon event web\u00adpage<\/a>&nbsp;to get the event materials<\/li>\n<li>Learn more about <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122&nbsp;<a href=\"http:\/\/www.amd.com\/mi60\"><span class=\"caps\">MI60<\/span><\/a>&nbsp;and&nbsp;<a href=\"http:\/\/www.amd.com\/mi50\"><span class=\"caps\">MI50<\/span><\/a>&nbsp;accelerators<\/li>\n<li>Learn more about <span class=\"caps\">AMD<\/span> 7nm tech\u00adno\u00adlo\u00adgy&nbsp;<a href=\"http:\/\/www.amd.com\/vega7nm\">here<\/a><\/li>\n<li>Learn more about the ROCm 2.0 open soft\u00adware plat\u00adform&nbsp;<a href=\"https:\/\/community.amd.com\/community\/radeon-instinct-accelerators\/blog\/2018\/11\/06\/rocm-software-enables-the-worlds-first-7nm-gpu\">here<\/a><\/li>\n<li>Learn more about ROCm <span class=\"amp\">&amp;<\/span> MIO\u00adpen Docker Hub&nbsp;<a href=\"https:\/\/hub.docker.com\/u\/rocm\" target=\"_blank\" rel=\"noopener\">here<\/a><\/li>\n<li>Beco\u00adme a fan of <span class=\"caps\">AMD<\/span> on&nbsp;<a href=\"http:\/\/www.facebook.com\/AMD\" target=\"_blank\" rel=\"noopener\">Face\u00adbook<\/a><\/li>\n<li>Fol\u00adlow <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct on&nbsp;<a href=\"https:\/\/twitter.com\/RadeonInstinct\" target=\"_blank\" rel=\"noopener\">Twit\u00adter<\/a><\/li>\n<\/ul>\n<h3>About <span class=\"caps\">AMD<\/span><\/h3>\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>)&nbsp;<a href=\"https:\/\/www.amd.com\/\">web\u00adsite<\/a>,&nbsp;<a href=\"http:\/\/community.amd.com\/welcome\">blog<\/a>,&nbsp;<a href=\"https:\/\/www.facebook.com\/AMD\" target=\"_blank\" rel=\"noopener\">Face\u00adbook<\/a>&nbsp;and&nbsp;<a href=\"https:\/\/twitter.com\/amd\" target=\"_blank\" rel=\"noopener\">Twit\u00adter<\/a>&nbsp;pages.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u2013 Powe\u00adring the Next Era of Arti\u00adfi\u00adci\u00adal Intel\u00adli\u00adgence, Cloud Com\u00adpu\u00adting and High Per\u00adfor\u00admance Com\u00adpu\u00adting (<span class=\"caps\">HPC<\/span>) &nbsp; \u2014 <span class=\"caps\">AMD<\/span> Rade\u00adon Instinct\u2122 <span class=\"caps\">MI60<\/span> and <span class=\"caps\">MI50<\/span> acce\u00adle\u00adra\u00adtors with&nbsp;super\u00adchar\u00adged com\u00adpu\u00adte per\u00adfor\u00admance, high-speed con\u00adnec\u00adti\u00advi\u00adty, fast memo\u00adry band\u00adwidth and&nbsp;updated ROCm open soft\u00adware plat\u00adform&nbsp;power the most deman\u00adding deep lear\u00adning, <span class=\"caps\">HPC<\/span>, cloud and ren\u00adde\u00adring appli\u00adca\u00adti\u00adons&nbsp;\u2014 San Fran\u00adcis\u00adco, Calif.&nbsp;11\/06\/2018 &nbsp; <span class=\"caps\">AMD<\/span>&nbsp;(<span class=\"caps\">NASDAQ<\/span>: <span class=\"caps\">AMD<\/span>) today announ\u00adced (\u2026) <a class=\"moretag\" href=\"https:\/\/www.planet3dnow.de\/cms\/41490-amd-unveils-worlds-first-7nm-datacenter-gpus\/\">Wei\u00adter\u00adle\u00adsen&nbsp;\u00bb<\/a><\/p>\n","protected":false},"author":593,"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":[12,22],"tags":[1445,966,1620,1619,1579],"class_list":["post-41490","post","type-post","status-publish","format-standard","hentry","category-aktuelles","category-pressemitteilungen","tag-7nm","tag-amd","tag-mi50","tag-mi60","tag-radeon-instinct","entry"],"share_on_mastodon":{"url":"","error":""},"_links":{"self":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/41490","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\/593"}],"replies":[{"embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/comments?post=41490"}],"version-history":[{"count":1,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/41490\/revisions"}],"predecessor-version":[{"id":41794,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/41490\/revisions\/41794"}],"wp:attachment":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/media?parent=41490"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/categories?post=41490"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/tags?post=41490"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}