{"id":3181,"date":"2023-05-18T16:56:54","date_gmt":"2023-05-18T08:56:54","guid":{"rendered":"https:\/\/blog.adlinktech.com\/?p=3181"},"modified":"2024-06-05T13:55:29","modified_gmt":"2024-06-05T05:55:29","slug":"intel-deep-link-technology","status":"publish","type":"post","link":"https:\/\/blog.adlinktech.com\/fr\/2023\/05\/18\/intel-deep-link-technology\/","title":{"rendered":"Technologie Intel\u00ae Deep Link : Transformer l'interaction CPU-GPU pour des performances am\u00e9lior\u00e9es"},"content":{"rendered":"

Intel\u00ae<\/sup> La technologie Deep Link est une innovation r\u00e9volutionnaire qui transforme l'interaction entre le processeur (CPU) et le processeur graphique (GPU) d'un syst\u00e8me. Disponible sur plusieurs modules Intel, Deep Link combine la puissance de calcul d'un GPU d\u00e9di\u00e9 (dGPU) \u00e0 celle d'un GPU int\u00e9gr\u00e9 (iGPU) performant, simplifiant ainsi le d\u00e9veloppement et r\u00e9duisant l'effort global. Gr\u00e2ce \u00e0 un haut degr\u00e9 de r\u00e9utilisation du code, Deep Link permet la construction de charges de travail et de pipelines complexes, ce qui se traduit par des gains significatifs en termes de performances et d'efficacit\u00e9, et renforce les capacit\u00e9s fonctionnelles d'une application.<\/p>\n\n\n

\n
\"\"
Le MXM-AXe d'ADLINK est l'un des modules prenant en charge la technologie Deep Link<\/figcaption><\/figure>\n<\/div>\n\n\n

Le partitionnement des \u00e9l\u00e9ments de calcul en segments logiques permet aux GPU Deep Link de partager \u00e9quitablement la charge de travail, chaque dGPU et iGPU travaillant ind\u00e9pendamment et simultan\u00e9ment avec l'autre. Intel\u00ae Iris\u00ae Xe <\/sup><\/em>peuvent \u00eatre utilis\u00e9s ensemble pour diviser les t\u00e2ches, ce qui r\u00e9duit de moiti\u00e9 le temps d'ex\u00e9cution de la charge de travail.<\/p>\n\n\n\n

En combinant la puissance de calcul de plusieurs GPU aux caract\u00e9ristiques similaires, Deep Link permet aux composants informatiques d'Intel de fonctionner ensemble \u00e0 un niveau de vitesse et d'efficacit\u00e9 sans pr\u00e9c\u00e9dent, avec peu de surcharge suppl\u00e9mentaire lors du partitionnement des t\u00e2ches entre les deux processeurs graphiques. <\/p>\n\n\n\n

Solutions ADLINK prenant en charge la technologie Intel\u00ae Deep Link\u00a0: Module GPU MXM-AXe<\/a>, Kit de d\u00e9veloppement MXM-AXe<\/a>, Express-RLP<\/a>, Express-ADP<\/a>.<\/p>\n\n\n\n

\n
\n
\"Alex<\/figure>\n<\/div>\n\n\n\n
\n

Alex Wang<\/h2>\n\n\n\n

Chef de Produit, BU Ordinateurs sur Modules ADLINK, ADLINK<\/p>\n\n\n\n

\n
Visitez ADLINK<\/a><\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"

Intel\u00ae Deep Link Technology is a game-changing innovation that transforms the interaction between a systems’s Central Processing Unit (CPU) and Graphics Processing Units (GPUs). Available on several Intel-based modules, Deep Link combines the computing power of a discrete GPU (dGPU) with that of a powerful integrated GPU (iGPU), simplifying code development and reducing overall effort. […]<\/p>\n","protected":false},"author":188103281,"featured_media":3187,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_stc_notifier_status":"sent","_stc_notifier_sent_time":"2023-05-18 17:49:58","_stc_notifier_request":false,"_stc_notifier_prevent":false,"_stc_subscriber_keywords":"","_stc_subscriber_search_areas":"","_coblocks_attr":"","_coblocks_dimensions":"","_coblocks_responsive_height":"","_coblocks_accordion_ie_support":"","_crdt_document":"","jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"_wpas_customize_per_network":false},"categories":[1,702134936],"tags":[8146977,702134903],"class_list":{"0":"post-3181","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","6":"hentry","7":"category-uncategorized","8":"category-japanese","9":"tag-edge-computing","10":"tag-featured","12":"fallback-thumbnail"},"jetpack_publicize_connections":[],"jetpack_featured_media_url":"https:\/\/i0.wp.com\/blog.adlinktech.com\/wp-content\/uploads\/2023\/05\/adlink_intel-deep-link-technology.png?fit=1200%2C675&ssl=1","jetpack_likes_enabled":true,"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/pc6JDC-Pj","_links":{"self":[{"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/posts\/3181","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/users\/188103281"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/comments?post=3181"}],"version-history":[{"count":9,"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/posts\/3181\/revisions"}],"predecessor-version":[{"id":3567,"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/posts\/3181\/revisions\/3567"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/media\/3187"}],"wp:attachment":[{"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/media?parent=3181"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/categories?post=3181"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.adlinktech.com\/fr\/wp-json\/wp\/v2\/tags?post=3181"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}