{"id":35588,"date":"2019-10-31T22:05:12","date_gmt":"2019-10-31T19:05:12","guid":{"rendered":"https:\/\/prohoster.info\/blog\/intel-gotovit-unifitsirovannuyu-model-programmirovaniya-one-api-dlya-cpu-gpu-fpga-i-npu\/"},"modified":"2019-10-31T22:05:12","modified_gmt":"2019-10-31T19:05:12","slug":"intel-gotovit-unifitsirovannuyu-model-programmirovaniya-one-api-dlya-cpu-gpu-fpga-i-npu","status":"publish","type":"post","link":"https:\/\/prohoster.info\/fr\/blog\/news\/intel-gotovit-unifitsirovannuyu-model-programmirovaniya-one-api-dlya-cpu-gpu-fpga-i-npu","title":{"rendered":"Intel pr\u00e9pare un mod\u00e8le de programmation unifi\u00e9 \u00ab One API \u00bb pour CPU, GPU, FPGA et NPU.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>Il y a \u00e0 peine cinq ans, Intel \u00e9tait fier de proposer un mod\u00e8le de programmation unique et traditionnel bas\u00e9 sur des instructions compatibles x86. Ce mod\u00e8le englobe des syst\u00e8mes mobiles sur SoC Atom, des acc\u00e9l\u00e9rateurs de calcul Xeon Phi (une architecture graphiques \u00e0 l'origine connue sous le nom de Larrabee) et des processeurs. Aujourd'hui, l'affirmation \u00ab x86, c'est tout pour nous \u00bb n'est plus d'actualit\u00e9 pour l'entreprise. Intel va bient\u00f4t disposer d'architectures graphiques discr\u00e8tes uniques et a d\u00e9j\u00e0 lanc\u00e9 des processeurs destin\u00e9s \u00e0 travailler avec des r\u00e9seaux de neurones. Pour programmer sur ces nouvelles plateformes et frameworks, Intel requiert un nouveau mod\u00e8le de programmation qui doit \u00e9galement \u00eatre unifi\u00e9.<\/p>\n<p><img decoding=\"async\" alt=\"Intel pr\u00e9pare un mod\u00e8le de programmation unifi\u00e9 \u00ab One API \u00bb pour CPU, GPU, FPGA et NPU.\" src=\"\/wp-content\/uploads\/52c88eb437140c8b01f86fa410f4c40a.png\" style=\"display:block;margin: 0 auto;\" \/><\/p>\n<p>R\u00e9cemment \u00e0 Londres, lors de l'\u00e9v\u00e9nement Intel Software Technology, la soci\u00e9t\u00e9 <noindex><a rel=\"nofollow\" href=\"https:\/\/newsroom.intel.com\/news\/intels-one-api-project-delivers-unified-programming-model-across-diverse-architectures\/?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+IntelNewsroom+%28Intel+Newsroom%29#gs.k4c3a6\">pr\u00e9sent\u00e9e<\/a><\/noindex> Ce mod\u00e8le. Le nouveau mod\u00e8le de programmation unifi\u00e9 se d\u00e9veloppe dans le cadre du projet \u00ab One API \u00bb. Selon ce projet, programmer pour l'ensemble des solutions et plateformes Intel sera simplifi\u00e9, quel que soit le choix de la plateforme. Comme l'a d\u00e9clar\u00e9 Bill Savage, vice-pr\u00e9sident d'Intel et directeur g\u00e9n\u00e9ral du d\u00e9partement des produits pour d\u00e9veloppeurs en performances de calcul : \u00ab L'objectif du projet \u2018One API\u2019 est de fournir aux d\u00e9veloppeurs un ensemble d'outils qui offrent un mod\u00e8le de programmation unifi\u00e9 et simplifient la cr\u00e9ation de charges de travail pour diff\u00e9rentes architectures. \u00c0 mesure que nos capacit\u00e9s de calcul \u00e9voluent, incluant d\u00e9sormais des acc\u00e9l\u00e9rateurs sp\u00e9cialis\u00e9s, Intel proposera des solutions logicielles permettant aux d\u00e9veloppeurs d'obtenir des performances maximales de leur mat\u00e9riel \u00bb.<\/p>\n<p>Un exemple r\u00e9cent de possibilit\u00e9s de travail avec diff\u00e9rentes architectures est fourni par les outils de d\u00e9veloppement Intel Distribution of OpenVINO Toolkit. Nous avons maintes fois <noindex><a rel=\"nofollow\" href=\"https:\/\/servernews.ru\/985088\">ont racont\u00e9<\/a><\/noindex> \u00c0 propos de cet outil qui offre des capacit\u00e9s optimis\u00e9es unifi\u00e9es pour l'apprentissage profond sur toutes les architectures Intel SVMS (scalaire, vectorielle, matrice, spatiale). Cela signifie qu'OpenVINO permet de cr\u00e9er des programmes pour des processeurs traditionnels, graphiques, neuronaux et FPGA. Le projet One API permettra de faire de m\u00eame avec une programmation directe et via une API, mais dans un volume \u00e9largi et un peu plus simplement, ce qui se traduira, par exemple, par la suppression de la n\u00e9cessit\u00e9 de maintenir des bases de code source distinctes, diff\u00e9rents langages de programmation, ainsi que divers outils et flux de travail.<\/p>\n<p>\u00ab Programmation directe : le projet One API comprend un nouveau langage de programmation directe, Data Parallel C++ (DPC++), qui propose une alternative ouverte et standardis\u00e9e aux langages de programmation propri\u00e9taires pour des architectures sp\u00e9cifiques. DPC++ est bas\u00e9 sur C++, utilisant le mod\u00e8le SYCL* du Khronos Group. En outre, il int\u00e8gre le support des extensions de langage d\u00e9velopp\u00e9es au sein de la communaut\u00e9 ouverte \u00bb.<\/p>\n<p><center><\/center><\/p>\n<p>La programmation en utilisant l'API offrira des biblioth\u00e8ques uniques pour diff\u00e9rents types de charges de travail avec prise en charge de l'acc\u00e9l\u00e9ration mat\u00e9rielle. Les fonctionnalit\u00e9s de biblioth\u00e8que sont d\u00e9velopp\u00e9es pour chaque architecture cible. Des versions avanc\u00e9es des outils avec support de DPC++ et des architectures SVMS sont cr\u00e9\u00e9es pour l'analyse et le d\u00e9bogage. \u00c0 noter, une version b\u00eata des outils pour d\u00e9veloppeurs et des d\u00e9tails suppl\u00e9mentaires sur le projet One API sont attendus au quatri\u00e8me trimestre 2019.<\/p>\n<p><center><\/p>\n<p><\/center><\/p>\n<p>\t\t\t\t<center><br \/>\n\t\t\t\t\t\t\t\t<\/center><br \/>Source : <a content=\"nofollow\" rel=\"nofollow\" href=\"http:\/\/www.3dnews.ru\/989619\">3dnews.ru<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u0412\u0441\u0435\u0433\u043e \u043a\u0430\u043a\u0438\u0445-\u0442\u043e \u043f\u044f\u0442\u044c \u043b\u0435\u0442 \u043d\u0430\u0437\u0430\u0434 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Intel \u0431\u044b\u043b\u0430 \u0433\u043e\u0440\u0434\u0430 \u0442\u0435\u043c, \u0447\u0442\u043e \u043c\u043e\u0433\u043b\u0430 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0438\u0442\u044c \u0435\u0434\u0438\u043d\u0443\u044e \u0438 \u0442\u0440\u0430\u0434\u0438\u0446\u0438\u043e\u043d\u043d\u0443\u044e \u0434\u043b\u044f \u043e\u0442\u0440\u0430\u0441\u043b\u0438 \u043c\u043e\u0434\u0435\u043b\u044c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u043d\u0430 \u0431\u0430\u0437\u0435 x86-\u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043c\u044b\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0439. \u042d\u0442\u0430 \u043c\u043e\u0434\u0435\u043b\u044c \u043e\u0445\u0432\u0430\u0442\u044b\u0432\u0430\u043b\u0430 \u043c\u043e\u0431\u0438\u043b\u044c\u043d\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043d\u0430 SoC Atom, \u0443\u0441\u043a\u043e\u0440\u0438\u0442\u0435\u043b\u0438 \u0440\u0430\u0441\u0447\u0451\u0442\u043e\u0432 Xeon Phi (\u0443\u0441\u043b\u043e\u0432\u043d\u043e \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0430\u044f \u0430\u0440\u0445\u0438\u0442\u0435\u043a\u0442\u0443\u0440\u0430 \u2015 \u0432 \u0434\u0435\u0432\u0438\u0447\u0435\u0441\u0442\u0432\u0435 Larrabee) \u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u044b. \u0421\u0435\u0433\u043e\u0434\u043d\u044f \u0442\u0435\u0437\u0438\u0441 &laquo;x86 \u2015 \u044d\u0442\u043e \u043d\u0430\u0448\u0435 \u0432\u0441\u0451&raquo; \u0434\u043b\u044f \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438 \u043f\u0435\u0440\u0435\u0441\u0442\u0430\u043b [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-35588","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.2.1 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u0412\u0441\u0435\u0433\u043e \u043a\u0430\u043a\u0438\u0445-\u0442\u043e \u043f\u044f\u0442\u044c \u043b\u0435\u0442 \u043d\u0430\u0437\u0430\u0434 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Intel \u0431\u044b\u043b\u0430 \u0433\u043e\u0440\u0434\u0430 \u0442\u0435\u043c, \u0447\u0442\u043e \u043c\u043e\u0433\u043b\u0430 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0438\u0442\u044c \u0435\u0434\u0438\u043d\u0443\u044e \u0438 \u0442\u0440\u0430\u0434\u0438\u0446\u0438\u043e\u043d\u043d\u0443\u044e \u0434\u043b\u044f \u043e\u0442\u0440\u0430\u0441\u043b\u0438 \u043c\u043e\u0434\u0435\u043b\u044c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u043d\u0430 \u0431\u0430\u0437\u0435 x86-\u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043c\u044b\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0439.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/fr\/blog\/news\/intel-gotovit-unifitsirovannuyu-model-programmirovaniya-one-api-dlya-cpu-gpu-fpga-i-npu\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.2.1\" \/>\n\t\t<meta property=\"og:locale\" content=\"fr_FR\" \/>\n\t\t<meta property=\"og:site_name\" content=\"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\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47Intel \u0433\u043e\u0442\u043e\u0432\u0438\u0442 \u0443\u043d\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u00abOne API\u00bb \u0434\u043b\u044f CPU, GPU, FPGA \u0438 NPU | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u0412\u0441\u0435\u0433\u043e \u043a\u0430\u043a\u0438\u0445-\u0442\u043e \u043f\u044f\u0442\u044c \u043b\u0435\u0442 \u043d\u0430\u0437\u0430\u0434 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Intel \u0431\u044b\u043b\u0430 \u0433\u043e\u0440\u0434\u0430 \u0442\u0435\u043c, \u0447\u0442\u043e \u043c\u043e\u0433\u043b\u0430 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0438\u0442\u044c \u0435\u0434\u0438\u043d\u0443\u044e \u0438 \u0442\u0440\u0430\u0434\u0438\u0446\u0438\u043e\u043d\u043d\u0443\u044e \u0434\u043b\u044f \u043e\u0442\u0440\u0430\u0441\u043b\u0438 \u043c\u043e\u0434\u0435\u043b\u044c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u043d\u0430 \u0431\u0430\u0437\u0435 x86-\u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043c\u044b\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0439.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/fr\/blog\/news\/intel-gotovit-unifitsirovannuyu-model-programmirovaniya-one-api-dlya-cpu-gpu-fpga-i-npu\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2019-10-31T19:05:12+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2019-10-31T19:05:12+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Intel pr\u00e9pare un mod\u00e8le de programmation unifi\u00e9 \u00ab One API \u00bb pour CPU, GPU, FPGA et NPU | ProHoster","description":"Il y a seulement cinq ans, Intel \u00e9tait fi\u00e8re de pouvoir offrir un mod\u00e8le de programmation unifi\u00e9 et traditionnel bas\u00e9 sur des instructions compatibles x86.","canonical_url":"https:\/\/prohoster.info\/fr\/blog\/news\/intel-gotovit-unifitsirovannuyu-model-programmirovaniya-one-api-dlya-cpu-gpu-fpga-i-npu","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"fr_FR","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\udd47Intel \u0433\u043e\u0442\u043e\u0432\u0438\u0442 \u0443\u043d\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u00abOne API\u00bb \u0434\u043b\u044f CPU, GPU, FPGA \u0438 NPU | ProHoster","og:description":"\u0412\u0441\u0435\u0433\u043e \u043a\u0430\u043a\u0438\u0445-\u0442\u043e \u043f\u044f\u0442\u044c \u043b\u0435\u0442 \u043d\u0430\u0437\u0430\u0434 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Intel \u0431\u044b\u043b\u0430 \u0433\u043e\u0440\u0434\u0430 \u0442\u0435\u043c, \u0447\u0442\u043e \u043c\u043e\u0433\u043b\u0430 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0438\u0442\u044c \u0435\u0434\u0438\u043d\u0443\u044e \u0438 \u0442\u0440\u0430\u0434\u0438\u0446\u0438\u043e\u043d\u043d\u0443\u044e \u0434\u043b\u044f \u043e\u0442\u0440\u0430\u0441\u043b\u0438 \u043c\u043e\u0434\u0435\u043b\u044c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u043d\u0430 \u0431\u0430\u0437\u0435 x86-\u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043c\u044b\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0439.","og:url":"https:\/\/prohoster.info\/fr\/blog\/news\/intel-gotovit-unifitsirovannuyu-model-programmirovaniya-one-api-dlya-cpu-gpu-fpga-i-npu","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":"2019-10-31T19:05:12+00:00","article:modified_time":"2019-10-31T19:05:12+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"35588","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-21 23:53:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 01:59:36","updated":"2026-01-21 23:53:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/posts\/35588","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/comments?post=35588"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/posts\/35588\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/media?parent=35588"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/categories?post=35588"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/tags?post=35588"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}