{"id":113552,"date":"2024-02-12T22:02:43","date_gmt":"2024-02-12T20:02:45","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/opublikovan-instrumentarij-zluda-pozvolyayushhij-zapuskat-cuda-prilozheniya-na-gpu-amd"},"modified":"2024-02-12T22:02:43","modified_gmt":"2024-02-12T20:02:45","slug":"opublikovan-instrumentarij-zluda-pozvolyayushhij-zapuskat-cuda-prilozheniya-na-gpu-amd","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hu\/blog\/news\/opublikovan-instrumentarij-zluda-pozvolyayushhij-zapuskat-cuda-prilozheniya-na-gpu-amd","title":{"rendered":"Megjelent a ZLUDA eszk\u00f6zk\u00e9szlete, amely lehet\u0151v\u00e9 teszi a CUDA-alkalmaz\u00e1sok futtat\u00e1s\u00e1t AMD GPU-n.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

A ZLUDA projekt elk\u00e9sz\u00edtette az AMD GPU-kra optimaliz\u00e1lt CUDA technol\u00f3gia ny\u00edlt megval\u00f3s\u00edt\u00e1s\u00e1t, amely lehet\u0151v\u00e9 teszi a m\u00f3dos\u00edtatlan CUDA-alkalmaz\u00e1sok futtat\u00e1s\u00e1t olyan teljes\u00edtm\u00e9nnyel, amely k\u00f6zel \u00e1ll a r\u00e9teg n\u00e9lk\u00fcli futtat\u00e1sok teljes\u00edtm\u00e9ny\u00e9hez. A k\u00f6zz\u00e9tett eszk\u00f6zk\u00e9szlet biztos\u00edtja a bin\u00e1ris kompatibilit\u00e1st a megl\u00e9v\u0151 CUDA-alkalmaz\u00e1sokkal, amelyeket NVIDIA GPU-hoz k\u00e9sz\u00fclt CUDA ford\u00edt\u00f3val \u00e1ll\u00edtottak \u00f6ssze. A megval\u00f3s\u00edt\u00e1s az AMD \u00e1ltal fejlesztett ROCm stackre \u00e9s a HIP (Heterogeneous-computing Interface for Portability) futtat\u00f3k\u00f6rnyezetre \u00e9p\u00fcl. A projekt k\u00f3dja Rust nyelven \u00edr\u00f3dott, \u00e9s MIT valamint Apache 2.0 licenc alatt terjesztik. T\u00e1mogatott a Linux \u00e9s Windows m\u0171k\u00f6d\u00e9s. <\/p>\n

A CUDA m\u0171k\u00f6d\u00e9s\u00e9nek megszervez\u00e9se AMD GPU-s rendszereken az utols\u00f3 k\u00e9t \u00e9vben fejleszt\u00e9s alatt \u00e1llt, de a projekt kor\u00e1bbi \u00e9vtizedeinek t\u00f6rt\u00e9nete van, \u00e9s eredetileg az Intel GPU-k sz\u00e1m\u00e1ra lett kifejlesztve. A GPU-k t\u00e1mogat\u00e1s\u00e1ra vonatkoz\u00f3 politika v\u00e1ltoz\u00e1sa az\u00e9rt t\u00f6rt\u00e9nt, mert kezdetben a ZLUDA fejleszt\u0151je az Intel munkat\u00e1rsa volt, de 2021-ben a c\u00e9g \u00fagy d\u00f6nt\u00f6tt, hogy a CUDA-alkalmaz\u00e1sok Intel GPU-n val\u00f3 futtat\u00e1s\u00e1nak lehet\u0151s\u00e9ge nem jelent \u00fczleti \u00e9rdekeket, \u00e9s nem s\u00fcrgeti a kezdem\u00e9nyez\u00e9s fejleszt\u00e9s\u00e9t. <\/p>\n

2022 elej\u00e9n a fejleszt\u0151 elhagyta az Intel-t, \u00e9s szerz\u0151d\u00e9st k\u00f6t\u00f6tt az AMD-vel a CUDA kompatibilit\u00e1s\u00e9rt felel\u0151s r\u00e9teg fejleszt\u00e9s\u00e9re. Az AMD arra k\u00e9rte a fejleszt\u00e9st, hogy ne hirdess\u00e9k az AMD projekt ir\u00e1nti \u00e9rdekl\u0151d\u00e9s\u00e9t, \u00e9s ne v\u00e9gezzenek k\u00f6zz\u00e9t\u00e9telt a ZLUDA nyilv\u00e1nos rep\u00f3j\u00e1ban. K\u00e9t \u00e9v eltelt\u00e9vel az AMD \u00fagy d\u00f6nt\u00f6tt, hogy a CUDA-alkalmaz\u00e1sok AMD GPU-n val\u00f3 futtat\u00e1sa nem k\u00e9pvisel \u00fczleti \u00e9rdekeket, ami a szerz\u0151d\u00e9s felt\u00e9telei alapj\u00e1n lehet\u0151v\u00e9 tette a fejleszt\u0151 sz\u00e1m\u00e1ra, hogy felfedje munk\u00e1j\u00e1t. Mivel a GPU gy\u00e1rt\u00f3k le\u00e1ll\u00edtott\u00e1k a projekt finansz\u00edroz\u00e1s\u00e1t, a projektek j\u00f6v\u0151je most a k\u00f6z\u00f6ss\u00e9g \u00e9rdekl\u0151d\u00e9s\u00e9t\u0151l \u00e9s m\u00e1s c\u00e9gekt\u0151l \u00e9rkez\u0151 egy\u00fcttm\u0171k\u00f6d\u00e9si aj\u00e1nlatokt\u00f3l f\u00fcgg. K\u00fcls\u0151 t\u00e1mogat\u00e1s n\u00e9lk\u00fcl a projekt csak olyan ir\u00e1nyokban fejl\u0151dhet, amelyek egyed\u00fcl a szerz\u0151t \u00e9rdeklik, mint p\u00e9ld\u00e1ul a DLSS (Deep Learning Super Sampling). <\/p>\n

A jelenlegi form\u00e1j\u00e1ban a megval\u00f3s\u00edt\u00e1s min\u0151s\u00e9ge alfa-verzi\u00f3k\u00e9nt van \u00e9rt\u00e9kelve. Eddig a ZLUDA m\u00e1r sz\u00e1mos CUDA-alkalmaz\u00e1s futtat\u00e1s\u00e1ra haszn\u00e1lhat\u00f3, bele\u00e9rtve a Geekbench-t, a 3DF Zephyr-t, a Blendert, a Reality Capture-t, a LAMMPS-t, a NAMD-t, a waifu2x-t, az OpenFOAM-ot \u00e9s az Arnold-ot. Minim\u00e1lis t\u00e1mogat\u00e1st ny\u00fajt a cuDNN, cuBLAS, cuSPARSE, cuFFT, NCCL \u00e9s NVML primit\u00edvek \u00e9s k\u00f6nyvt\u00e1rak sz\u00e1m\u00e1ra. <\/p>\n

A CUDA-alkalmaz\u00e1sok els\u0151 ind\u00edt\u00e1sa ZLUDA alatt jelent\u0151s k\u00e9s\u00e9sekkel t\u00f6rt\u00e9nik, mivel a ZLUDA GPU-k\u00f3dot ford\u00edt. A k\u00e9s\u00e9s a k\u00f6vetkez\u0151 ind\u00edt\u00e1sokn\u00e1l nem tapasztalhat\u00f3, mivel a leford\u00edtott k\u00f3d a gyors\u00edt\u00f3t\u00e1rban t\u00e1rol\u00f3dik. A leford\u00edtott k\u00f3d v\u00e9grehajt\u00e1sa sor\u00e1n a teljes\u00edtm\u00e9ny k\u00f6zel van a nat\u00edvhoz. A Geekbench csomag futtat\u00e1sa sor\u00e1n az AMD Radeon 6800 XT GPU-n a ZLUDA \u00e1ltal kezelt CUDA tesztsorozat jelent\u0151sen magasabb teljes\u00edtm\u00e9nyt mutatott, mint az OpenCL-alap\u00fa v\u00e1ltozat.

\"Megjelent<\/center> <\/p>\n

A ZLUDA t\u00e1mogatja az hivatalos CUDA Driver API-t \u00e9s a visszafejt\u00e9ssel felfedezett, r\u00e9szben dokument\u00e1latlan CUDA API-t is a h\u00edv\u00e1sok AMD HIP runtime-ra t\u00f6rt\u00e9n\u0151 \u00e1tkonvert\u00e1l\u00e1s\u00e1val, amely nagym\u00e9rt\u00e9kben hasonl\u00edt a CUDA-ra. P\u00e9ld\u00e1ul a cuDeviceGetAttribute() f\u00fcggv\u00e9ny helyett a hipDeviceGetAttribute() ker\u00fcl alkalmaz\u00e1sra. Hasonl\u00f3 m\u00f3don biztos\u00edtjuk a kompatibilit\u00e1st az NVIDIA k\u00f6nyvt\u00e1rakkal, mint p\u00e9ld\u00e1ul a NVML, cuBLAS \u00e9s cuSPARSE. Az ilyen k\u00f6nyvt\u00e1rak sz\u00e1m\u00e1ra a ZLUDA azonos n\u00e9vvel \u00e9s azonos funkci\u00f3s k\u00e9szlettel rendelkez\u0151 transzform\u00e1l\u00f3 k\u00f6nyvt\u00e1rakat biztos\u00edt a hasonl\u00f3 AMD k\u00f6nyvt\u00e1rak f\u00f6l\u00e9 \u00e9p\u00edtkezve. <\/p>\n

A PTX (Parallel Thread Execution) form\u00e1tumra ford\u00edtott alkalmaz\u00e1sok GPU-k\u00f3dja egy speci\u00e1lis ford\u00edt\u00f3val el\u0151sz\u00f6r LLVM IR k\u00f6ztes form\u00e1tumra, majd pedig az AMD GPU-hoz megfelel\u0151 bin\u00e1ris k\u00f3dra gener\u00e1l\u00f3dik.

\"Megjelent<\/center>
\n
Forr\u00e1s: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041f\u0440\u043e\u0435\u043a\u0442 ZLUDA \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u0438\u043b \u043e\u0442\u043a\u0440\u044b\u0442\u0443\u044e \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u044e \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 CUDA \u0434\u043b\u044f GPU AMD, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0443\u044e \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0442\u044c \u043d\u0435\u043c\u043e\u0434\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0435 CUDA-\u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f \u0441 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c\u044e, \u0431\u043b\u0438\u0437\u043a\u043e\u0439 \u043a \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u0439, \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u043c\u044b\u0445 \u0431\u0435\u0437 \u043f\u0440\u043e\u0441\u043b\u043e\u0435\u043a. \u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d\u043d\u044b\u0439 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0431\u0438\u043d\u0430\u0440\u043d\u0443\u044e \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u0438\u043c\u043e\u0441\u0442\u044c \u0441 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0449\u0438\u043c\u0438 CUDA-\u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f\u043c\u0438, \u0441\u043e\u0431\u0440\u0430\u043d\u043d\u044b\u043c\u0438 \u043f\u0440\u0438 \u043f\u043e\u043c\u043e\u0449\u0438 \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0442\u043e\u0440\u0430 CUDA \u0434\u043b\u044f GPU NVIDIA. \u0420\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u044f \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u043f\u043e\u0432\u0435\u0440\u0445 \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u0435\u043c\u043e\u0433\u043e \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0435\u0439 AMD \u0441\u0442\u0435\u043a\u0430 ROCm \u0438 runtime HIP (Heterogeneous-computing Interface for Portability). \u041a\u043e\u0434 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":113553,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-113552","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47Megjelent a ZLUDA eszk\u00f6zk\u00e9szlet, amely lehet\u0151v\u00e9 teszi a CUDA-alkalmaz\u00e1sok futtat\u00e1s\u00e1t AMD GPU-n | ProHoster","description":"A ZLUDA projekt egy ny\u00edlt implement\u00e1ci\u00f3t k\u00e9sz\u00edtett a CUDA technol\u00f3gi\u00e1b\u00f3l AMD GPU-kra, lehet\u0151v\u00e9 t\u00e9ve a m\u00f3dos\u00edt\u00e1s n\u00e9lk\u00fcli CUDA-alkalmaz\u00e1sok futtat\u00e1s\u00e1t, a nat\u00edv futtat\u00e1s\u00e9hoz k\u00f6zeli teljes\u00edtm\u00e9nnyel.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/opublikovan-instrumentarij-zluda-pozvolyayushhij-zapuskat-cuda-prilozheniya-na-gpu-amd","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hu_HU","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 ZLUDA, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0439 \u0437\u0430\u043f\u0443\u0441\u043a\u0430\u0442\u044c CUDA-\u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f \u043d\u0430 GPU AMD | ProHoster","og:description":"\u041f\u0440\u043e\u0435\u043a\u0442 ZLUDA \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u0438\u043b \u043e\u0442\u043a\u0440\u044b\u0442\u0443\u044e \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u044e \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 CUDA \u0434\u043b\u044f GPU AMD, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0443\u044e \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0442\u044c \u043d\u0435\u043c\u043e\u0434\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0435 CUDA-\u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f \u0441 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c\u044e, \u0431\u043b\u0438\u0437\u043a\u043e\u0439 \u043a \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u0439, \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u043c\u044b\u0445 \u0431\u0435\u0437.","og:url":"https:\/\/prohoster.info\/hu\/blog\/news\/opublikovan-instrumentarij-zluda-pozvolyayushhij-zapuskat-cuda-prilozheniya-na-gpu-amd","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2024-02-12T20:02:45+00:00","article:modified_time":"2024-02-12T20:02:45+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/113552","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/comments?post=113552"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/113552\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media\/113553"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=113552"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=113552"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=113552"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}