{"id":13329,"date":"2014-11-18T14:51:17","date_gmt":"2014-11-18T13:51:17","guid":{"rendered":"http:\/\/www.planet3dnow.de\/cms\/?p=13329"},"modified":"2014-11-18T14:51:17","modified_gmt":"2014-11-18T13:51:17","slug":"amd-and-pathscale-join-the-openacc-standards-group","status":"publish","type":"post","link":"https:\/\/www.planet3dnow.de\/cms\/13329-amd-and-pathscale-join-the-openacc-standards-group\/","title":{"rendered":"<span class=\"caps\">AMD<\/span> and PathScale Join the OpenACC Standards Group"},"content":{"rendered":"<p><span class=\"caps\">NEW<\/span> <span class=\"caps\">ORLEANS<\/span>, La., Nov. 17 \u2014&nbsp;The Open\u00adACC stan\u00addards group today announ\u00adced that Advan\u00adced Micro Devices (<span class=\"caps\">AMD<\/span>) and PathSca\u00adle, Inc.,&nbsp;have joi\u00adn\u00aded the orga\u00adniza\u00adti\u00adon, alig\u00adning with 18 other mem\u00adbers and sup\u00adport\u00aders world\u00adwi\u00adde to dri\u00adve the deve\u00adlo\u00adp\u00adment of appli\u00adca\u00adti\u00adons for acce\u00adle\u00adra\u00adtor-enab\u00adled super\u00adcom\u00adpu\u00adters, clus\u00adters and other high per\u00adfor\u00admance com\u00adpu\u00adting (<span class=\"caps\">HPC<\/span>) systems.<\/p>\n<p>Open\u00adACC pro\u00advi\u00addes an effi\u00adci\u00adent and per\u00adfor\u00admance-por\u00adta\u00adble path for deve\u00adlo\u00adping mas\u00adsi\u00adve\u00adly par\u00adal\u00adlel pro\u00adgrams across a wide ran\u00adge of acce\u00adle\u00adra\u00adtors, inclu\u00adding GPUs, many core copro\u00adces\u00adsors and mul\u00adti-core CPUs. By joi\u00adning the Open\u00adACC stan\u00addards group, <span class=\"caps\">AMD<\/span> and PathSca\u00adle bring con\u00adsidera\u00adble exper\u00adti\u00adse in high per\u00adfor\u00admance com\u00adpu\u00adting tech\u00adno\u00adlo\u00adgy and pro\u00adgramming capa\u00adbi\u00adli\u00adties, pro\u00advi\u00adding deve\u00adlo\u00adpers with more diver\u00adsi\u00adty and choice in com\u00adpu\u00adting archi\u00adtec\u00adtures and soft\u00adware tools, and pro\u00admi\u00adsing to extend the reach of Open\u00adACC-sup\u00adport\u00aded solu\u00adti\u00adons to new and exis\u00adting users worldwide.<\/p>\n<p>Expert Open\u00adACC mem\u00adbers will be on hand at the Super\u00adcom\u00adpu\u00adting Con\u00adfe\u00adrence (<span class=\"caps\">SC14<\/span>) in New Orleans, Loui\u00adsia\u00adna <span class=\"caps\">USA<\/span> this week, to ans\u00adwer Open\u00adACC pro\u00adgramming ques\u00adti\u00adons, dis\u00adcuss the latest deve\u00adlo\u00adp\u00adments, and pro\u00advi\u00adde tech\u00adno\u00adlo\u00adgy demos. For more infor\u00adma\u00adti\u00adon visit the Open\u00adACC booth (#657) or the Open\u00adACC web\u00adsite:&nbsp;<a href=\"http:\/\/www.openacc.org\/SC14\">http:\/\/www.openacc.org\/<span class=\"caps\">SC14<\/span><\/a>.<\/p>\n<p><strong>Open\u00adACC Sim\u00adpli\u00adfies Appli\u00adca\u00adti\u00adons Acce\u00adle\u00adra\u00adti\u00adon on <span class=\"caps\">AMD<\/span>&nbsp;APUs<\/strong><\/p>\n<p>Advan\u00adced Micro Devices is a lea\u00adding mul\u00adti\u00adna\u00adtio\u00adnal semi\u00adcon\u00adduc\u00adtor com\u00adpa\u00adny with vast expe\u00adri\u00adence in ener\u00adgy-effi\u00adci\u00adent high-per\u00adfor\u00admance com\u00adpu\u00adting. The Open\u00adACC stan\u00addard helps pro\u00adgramm\u00aders take full advan\u00adta\u00adge of <span class=\"caps\">AMD<\/span>\u2019s high-per\u00adfor\u00admance Acce\u00adle\u00adra\u00adted Pro\u00adces\u00adsing Units (APUs).<\/p>\n<p><span class=\"dquo\">\u201c<\/span>The <span class=\"caps\">HPC<\/span> com\u00admu\u00adni\u00adty is dri\u00adving the need for rich hete\u00adro\u00adge\u00adneous com\u00adpu\u00adting solu\u00adti\u00adons to bet\u00adter meet cus\u00adto\u00admer per\u00adfor\u00admance and power needs.&nbsp;With this tran\u00adsi\u00adti\u00adon the\u00adre is a strong need for a rich, sim\u00adpli\u00adfied pro\u00adg\u00adra\u00adming model to sup\u00adport new hete\u00adro\u00adge\u00adneous appli\u00adca\u00adti\u00adon deve\u00adlo\u00adp\u00adment and pull in lega\u00adcy C\/C++\/Fortran appli\u00adca\u00adti\u00adons,\u201c &nbsp;said Greg Stoner,&nbsp; seni\u00ador direc\u00adtor of Deve\u00adlo\u00adper Tech\u00adno\u00adlo\u00adgy, Pro\u00adfes\u00adsio\u00adnal Gra\u00adphics, <span class=\"caps\">AMD<\/span>, and new\u00adly appoin\u00adted mem\u00adber of the Open\u00adACC board of direc\u00adtors.&nbsp;\u201cOpen\u00adACC 2.0 via its sin\u00adgle source direc\u00adti\u00adves-based pro\u00adgramming model puts in place a solid foun\u00adda\u00adti\u00adon to dri\u00adve key bene\u00adfits of a hete\u00adro\u00adge\u00adneous hard\u00adware plat\u00adform.&nbsp;<span class=\"caps\">AMD<\/span> is loo\u00adking for\u00adward to working with the Open\u00adACC orga\u00adniza\u00adti\u00adon&nbsp;to help it to con\u00adti\u00adnue to evol\u00adve this important pro\u00adgramming standard.<\/p>\n<p><strong>PathSca\u00adle Joins OpenACC<\/strong><\/p>\n<p>PathSca\u00adle is the deve\u00adlo\u00adper of inno\u00adva\u00adti\u00adve <span class=\"caps\">ENZO<\/span> 2014 com\u00adpi\u00adlers that enhan\u00adce the per\u00adfor\u00admance and ener\u00adgy effi\u00adci\u00aden\u00adcy of acce\u00adle\u00adra\u00adted Linux <span class=\"caps\">HPC<\/span> clus\u00adters and sys\u00adtems. By sup\u00adport\u00ading the Open\u00adACC stan\u00addard, PathSca\u00adle pro\u00advi\u00addes users with more opti\u00adons and fle\u00adxi\u00adbi\u00adli\u00adty to choo\u00adse the ide\u00adal com\u00adpi\u00adler solu\u00adti\u00adon that fits their indi\u00advi\u00addu\u00adal&nbsp;needs.<\/p>\n<p><span class=\"dquo\">\u201c<\/span>It is important in any <span class=\"caps\">HPC<\/span> deve\u00adlo\u00adp\u00adment envi\u00adron\u00adment to have access to a varie\u00adty of com\u00adpi\u00adlers,\u201d noted Oscar Her\u00adnan\u00addez, prin\u00adci\u00adple inves\u00adti\u00adga\u00adtor at Oak Ridge Natio\u00adnal Labo\u00adra\u00adto\u00adry. \u201cSome\u00adti\u00admes one com\u00adpi\u00adler will exhi\u00adbit bet\u00adter per\u00adfor\u00admance on a par\u00adti\u00adcu\u00adlar code than ano\u00adther, or behave in a more desi\u00adra\u00adble way. We ful\u00adly intend to make PathSca\u00adle available to deve\u00adlo\u00adpers crea\u00adting appli\u00adca\u00adti\u00adons for <span class=\"caps\">ORNL<\/span>\u2019s Titan Cray <span class=\"caps\">XK7<\/span> supercomputer.\u201d<\/p>\n<p><strong>Open\u00adACC Events at&nbsp;<span class=\"caps\">SC14<\/span><\/strong><\/p>\n<p>Open\u00adACC mem\u00adbers are par\u00adti\u00adci\u00adpa\u00adting in num\u00adber of pre\u00adsen\u00adta\u00adti\u00adons, talks and dis\u00adcus\u00adsions at <span class=\"caps\">SC14<\/span> on the latest deve\u00adlo\u00adp\u00adments. They will also pro\u00advi\u00adde tech\u00adno\u00adlo\u00adgy demons\u00adtra\u00adti\u00adons in a varie\u00adty of mem\u00adber booths, inclu\u00adding demons\u00adtra\u00adti\u00adons of the latest Open\u00adACC fea\u00adtures as deve\u00adlo\u00adped for the next major release of the popu\u00adlar open-source <span class=\"caps\">GCC<\/span> compiler.<\/p>\n<p>For more infor\u00adma\u00adti\u00adon about Open\u00adACC demons\u00adtra\u00adti\u00adons and events visit&nbsp;<a href=\"http:\/\/www.openacc.org\/SC14\">http:\/\/www.openacc.org\/<span class=\"caps\">SC14<\/span><\/a><\/p>\n<p><strong>Key Open\u00adACC events at <span class=\"caps\">SC14<\/span> include:<\/strong><\/p>\n<ul>\n<li>Work\u00adshop \u2014 \u201cWork\u00adshop on Acce\u00adle\u00adra\u00adtor Pro\u00adgramming Using Direc\u00adti\u00adves\u201d \u2014&nbsp;<span data-term=\"goog_588846617\">Mon\u00adday, Nov. 17, 2014, 8am to 5pm<\/span>&nbsp;in Rooms 276 and&nbsp;277.<\/li>\n<li>Tuto\u00adri\u00adal \u2014 \u201cOpen\u00adACC: Pro\u00adduct, Por\u00adta\u00adble Per\u00adfor\u00admance on Hybrid Sys\u00adtems using High Level Com\u00adpi\u00adlers and Tools\u201d \u2014 Mon\u00adday, Nov. 17, 8am to 5pm in Room&nbsp;396.<\/li>\n<li>Open\u00adACC Birds of a Fea\u00adther (BoF) ses\u00adsi\u00adon\u2014 \u201cOpen\u00adACC <span class=\"caps\">API<\/span> User Expe\u00adri\u00adence, Ven\u00addor Reac\u00adtion, Rele\u00advan\u00adce and Road\u00admap\u201d \u2014&nbsp;<span data-term=\"goog_588846619\">Wed\u00adnes\u00adday, Nov. 19, 2014 at 5:30pm<\/span>&nbsp;in Rooms 275\/276\/277. BoF high\u00adlights will include reports on the recent hacka\u00adthon at <span class=\"caps\">ORNL<\/span>, the first Open\u00adACC Seis\u00admic work\u00adshop at the Uni\u00adver\u00adsi\u00adty of Hous\u00adton, and recent pro\u00adgress in imple\u00admen\u00adting and enhan\u00adcing the Open\u00adACC standard.<\/li>\n<\/ul>\n<p>The Open\u00adACC stan\u00addard sim\u00adpli\u00adfies the pro\u00adgramming of acce\u00adle\u00adra\u00adted-com\u00adpu\u00adting sys\u00adtems through the use of direc\u00adti\u00adves, enab\u00adling appli\u00adca\u00adti\u00adon deve\u00adlo\u00adpers world\u00adwi\u00adde to easi\u00adly take advan\u00adta\u00adge of the trans\u00adfor\u00adma\u00adti\u00adve power of the\u00adse sys\u00adtems to dri\u00adve advan\u00adces in sci\u00adence, engi\u00adnee\u00adring and indus\u00adtry.&nbsp;&nbsp;It is now available in com\u00adpi\u00adler pro\u00adducts from many lea\u00adding com\u00adpi\u00adler ven\u00addors and is sup\u00adport\u00aded in a wide ran\u00adge of debug\u00adgers, pro\u00adfi\u00adlers and other pro\u00adgramming tools.<\/p>\n<p><span style=\"font-size: 8pt;\"><strong>About the Open\u00adACC Stan\u00addards&nbsp;Group<\/strong><\/span><\/p>\n<p><span style=\"font-size: 8pt;\">Open\u00adACC is a non-pro\u00adfit cor\u00adpo\u00adra\u00adti\u00adon that crea\u00adted and fos\u00adters a cross-plat\u00adform <span class=\"caps\">API<\/span> which allows any sci\u00aden\u00adtist or pro\u00adgramm\u00ader to more easi\u00adly acce\u00adle\u00adra\u00adte appli\u00adca\u00adti\u00adons on modern many-core and mul\u00adti-core pro\u00adces\u00adsors. Open\u00adACC direc\u00adti\u00adves iden\u00adti\u00adfy com\u00adpu\u00adte-inten\u00adsi\u00adve code to a com\u00adpi\u00adler for acce\u00adle\u00adra\u00adti\u00adon or off\u00adload, while pre\u00adser\u00adving&nbsp;a sin\u00adgle&nbsp;code base and cross-plat\u00adform por\u00adta\u00adbi\u00adli\u00adty. Open\u00adACC is com\u00adple\u00admen\u00adta\u00adry to and inter\u00adope\u00adra\u00adble with exis\u00adting pro\u00adgramming models, inclu\u00adding OpenMP, <span class=\"caps\">MPI<\/span>, <span class=\"caps\">CUDA<\/span> and Open\u00adCL. Orga\u00adniza\u00adti\u00adons actively invol\u00adved in high-per\u00adfor\u00admance hete\u00adro\u00adge\u00adneous com\u00adpu\u00adting are encou\u00adra\u00adged to par\u00adti\u00adci\u00adpa\u00adte. Plea\u00adse visit&nbsp;<a href=\"http:\/\/www.openacc.org\/\">http:\/\/www.openacc.org<\/a>&nbsp;for more information.<\/span><\/p>\n<p><span style=\"font-size: 8pt;\"><strong>About <span class=\"caps\">AMD<\/span><\/strong><\/span><\/p>\n<p><span style=\"font-size: 8pt;\"><span class=\"caps\">AMD<\/span> is a semi\u00adcon\u00adduc\u00adtor design inno\u00adva\u00adtor lea\u00adding the next era of vivid digi\u00adtal expe\u00adri\u00aden\u00adces with its ground\u00adbrea\u00adking <span class=\"caps\">AMD<\/span> Acce\u00adle\u00adra\u00adted Pro\u00adces\u00adsing Units (APUs) that power a wide ran\u00adge of com\u00adpu\u00adting devices. <span class=\"caps\">AMD<\/span>\u2019s ser\u00adver com\u00adpu\u00adting pro\u00adducts are focu\u00adsed on dri\u00adving indus\u00adtry-lea\u00adding cloud com\u00adpu\u00adting and vir\u00adtua\u00adliza\u00adti\u00adon envi\u00adron\u00adments. <span class=\"caps\">AMD<\/span>\u2019s supe\u00adri\u00ador gra\u00adphics tech\u00adno\u00adlo\u00adgies are found in a varie\u00adty of solu\u00adti\u00adons ran\u00adging from game con\u00adso\u00adles, PCs to super\u00adcom\u00adpu\u00adters. For more infor\u00adma\u00adti\u00adon, visit&nbsp;<a href=\"http:\/\/www.amd.com\/\">www.amd.com<\/a>.<\/span><\/p>\n<p><span style=\"font-size: 8pt;\"><strong>About PathSca\u00adle<\/strong><\/span><\/p>\n<p><span style=\"font-size: 8pt;\">PathSca\u00adle Inc. has deve\u00adlo\u00adped indus\u00adtry lea\u00adding high per\u00adfor\u00admance&nbsp;For\u00adtran, C and C++ com\u00adpi\u00adler pro\u00adducts for <span class=\"caps\">AMD<\/span>, Intel and <span class=\"caps\">NVIDIA<\/span> pro\u00adces\u00adsors. The PathSca\u00adle com\u00adpi\u00adler tech\u00adno\u00adlo\u00adgy has the world\u2019s most advan\u00adced opti\u00admiza\u00adti\u00adon infra\u00adstruc\u00adtu\u00adre and can ful\u00adly exploit the poten\u00adti\u00adals of many-core and hete\u00adro\u00adge\u00adneous archi\u00adtec\u00adtures. The company\u2019s goal is to deli\u00adver robust and high per\u00adfor\u00admance com\u00adpi\u00adlers tail\u00ado\u00adred to clus\u00adte\u00adred, <span class=\"caps\">GPGPU<\/span> and mul\u00adti-core com\u00adpu\u00adting envi\u00adron\u00adments. More infor\u00adma\u00adti\u00adon about PathSca\u00adle is available on the web at&nbsp;<a href=\"http:\/\/www.pathscale.com\/\">http:\/\/www.pathscale.com<\/a><\/span><\/p>\n<p><span style=\"font-size: 8pt;\"><em>Source: Open\u00adACC Stan\u00addards&nbsp;Group<\/em><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p><span class=\"caps\">NEW<\/span> <span class=\"caps\">ORLEANS<\/span>, La., Nov. 17 \u2014 The Open\u00adACC stan\u00addards group today announ\u00adced that Advan\u00adced Micro Devices (<span class=\"caps\">AMD<\/span>) and PathSca\u00adle, Inc., have joi\u00adn\u00aded the orga\u00adniza\u00adti\u00adon, alig\u00adning with 18 other mem\u00adbers and sup\u00adport\u00aders world\u00adwi\u00adde to dri\u00adve the deve\u00adlo\u00adp\u00adment of appli\u00adca\u00adti\u00adons for acce\u00adle\u00adra\u00adtor-enab\u00adled super\u00adcom\u00adpu\u00adters, clus\u00adters and other high per\u00adfor\u00admance com\u00adpu\u00adting (<span class=\"caps\">HPC<\/span>) sys\u00adtems. (\u2026) <a class=\"moretag\" href=\"https:\/\/www.planet3dnow.de\/cms\/13329-amd-and-pathscale-join-the-openacc-standards-group\/\">Wei\u00adter\u00adle\u00adsen&nbsp;\u00bb<\/a><\/p>\n","protected":false},"author":8,"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":[],"class_list":["post-13329","post","type-post","status-publish","format-standard","hentry","category-pressemitteilungen","entry"],"share_on_mastodon":{"url":"","error":""},"_links":{"self":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/13329","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\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/comments?post=13329"}],"version-history":[{"count":1,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/13329\/revisions"}],"predecessor-version":[{"id":13330,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/posts\/13329\/revisions\/13330"}],"wp:attachment":[{"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/media?parent=13329"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/categories?post=13329"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.planet3dnow.de\/cms\/wp-json\/wp\/v2\/tags?post=13329"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}