{"id":233181,"date":"2016-04-06T08:25:00","date_gmt":"2016-04-06T06:25:00","guid":{"rendered":"https:\/\/cms.galaxiemedia.fr\/tomshardware\/2016\/04\/06\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/"},"modified":"2023-09-20T14:07:55","modified_gmt":"2023-09-20T12:07:55","slug":"larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu","status":"publish","type":"post","link":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/","title":{"rendered":"L’architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU"},"content":{"rendered":"

\"ImageL’architecture Pascal (GP100)<\/span><\/span><\/span><\/span><\/span><\/p>\n\n

<\/p>\n\n

Apr\u00e8s sa conf\u00e9rence de presse pr\u00e9sentant la premi\u00e8re puce Pascal, la Tesla P100<\/a>, NVIDIA a donn\u00e9 plus de d\u00e9tail sur son architecture. Parmi les nouveaut\u00e9s, on notera que la nouvelle finesse de gravure permet d\u2019accro\u00eetre le nombre de Stream Multiprocessors (SM) disponibles. Chaque SM regroupe 64 coeurs CUDA et quatre unit\u00e9s de textures. L\u2019architecture peut monter jusqu\u2019\u00e0 3 840 coeurs CUDA et 240 unit\u00e9s de texture, soit un total de 60 SM.<\/p>\n\n

<\/p>\n\n

– Comparatif : les cartes graphiques du moment au banc d\u2019essai<\/a>

\"Image<\/span><\/td>\"Image<\/span><\/td><\/tr><\/table><\/div><\/span><\/p>\n\n

<\/p>\n\n

Priorit\u00e9 aux applications GPGPU<\/h4>\n\n

<\/p>\n\n

Chaque SM a moins de coeurs CUDA et d\u2019unit\u00e9s de texture que sur les Kepler, mais le ratio FP64\/FP32 est nettement sup\u00e9rieur. Concr\u00e8tement, cela signifie que la puce privil\u00e9gie les applications GPGPU. L\u2019autre grande nouveaut\u00e9 est la priorit\u00e9 donn\u00e9e \u00e0 la m\u00e9moire. La puce Pascal a deux fois moins de coeurs CUDA que la puce Maxwell GM200, mais on retrouve la m\u00eame taille de bancs de registre par SM. Comme Pascal a nettement plus de SM, on se retrouve avec une puce ayant des bancs de registre plus grands et une plus grande m\u00e9moire partag\u00e9e, ce qui sera int\u00e9ressant lorsque l\u2019on traite une tr\u00e8s grande quantit\u00e9 de donn\u00e9es \u00e0 la fois. Bref, le GP100 est clairement tourn\u00e9 vers l\u2019apprentissage automatique, l\u2019intelligence artificielle et les op\u00e9rations GPGPU. NVIDIA estime que l\u2019augmentation du nombre de SM sera suffisante pour apporter un gain de performance acceptable dans les jeux. La r\u00e9ponse devrait arriver avec les GeForce GTX 1080, qui pourrait aussi embarquer une puce l\u00e9g\u00e8rement modifi\u00e9e pour les jeux.<\/p>\n\n

<\/p>\n\n

Caract\u00e9ristiques<\/th> \tTesla K40<\/th> \tTesla M40<\/th> \tTesla P100<\/th><\/tr><\/tbody>
GPU<\/th> \tGK110 (Kepler)<\/td> \tGM200 (Kepler)<\/td> \tGP100 (Pascal)<\/td><\/tr>
Finesse<\/th> \t28 nm<\/td> \t28 nm<\/td> \t16 nm<\/td><\/tr>
Transistors<\/th> \t7,1 milliards<\/td> \t8 milliards<\/td> \t15,3 milliards<\/td><\/tr>
Taille du die<\/th> \t551 mm2<\/sup><\/td> \t601 mm2<\/sup><\/td> \t610 mm2<\/sup><\/td><\/tr>
Stream Multiprocessors (SM)<\/th> \t15<\/td> \t24<\/td> \t56<\/td><\/tr>
Coeur CUDA \/ SM<\/th> \t192<\/td> \t128<\/td> \t64<\/td><\/tr>
Unit\u00e9s de texture \/ SM<\/th> \t16<\/td> \t8<\/td> \t4<\/td><\/tr>
FP32 Cores CUDA \/ GPU<\/th> \t2 880<\/td> \t3 072<\/td> \t3 584<\/td><\/tr>
Ratio FP64\/FP32<\/th> \t1\/3<\/td> \t1\/32<\/td> \t1\/2<\/td><\/tr>
Fr\u00e9quences de base<\/th> \t745 MHz<\/td> \t948 MHz<\/td> \t1 328 MHz<\/td><\/tr>
Fr\u00e9quence boost<\/th> \t875 MHz<\/td> \t1 114 MHz<\/td> \t1 480 MHz<\/td><\/tr>
Puissance en double pr\u00e9cision (FP64) en TFLOPS<\/th> \t1,680<\/td> \t0,192<\/td> \t5,304<\/td><\/tr>
Bus m\u00e9moire<\/th> \t384 bits GDDR5<\/td> \t384 bits GDRR5<\/td> \t4 096 bits HBM2<\/td><\/tr>
M\u00e9moire<\/th> \tJusqu\u2019\u00e0 12 Go<\/td> \tJusqu\u2019\u00e0 24 Go<\/td> \t16 Go<\/td><\/tr>
Cache L2<\/th> \t1,5 Mo<\/td> \t3 Mo<\/td> \t4 Mo<\/td><\/tr>
Taille des bancs de registre<\/th> \t4 Mo<\/td> \t6 Mo<\/td> \t14 Mo<\/td><\/tr>
TDP<\/th> \t235 W<\/td> \t250 W<\/td> \t300 W<\/td><\/tr><\/tbody><\/table><\/div>\n\n<\/p>\n\n

\n\n\n

<\/p>\n\n

<\/div> ","protected":false},"excerpt":{"rendered":"

Si l\u2019on se penche sur l\u2019architecture Pascal pr\u00e9sent\u00e9e aujourd\u2019hui pour le Tesla P100, on remarque qu\u2019elle donne la priorit\u00e9 aux applications GPGPU au d\u00e9triment des jeux et du grand public.<\/p>","protected":false},"author":8,"featured_media":233182,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[487,4072],"tags":[538],"hubs":[],"class_list":["post-233181","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-actualite","category-cartes-graphiques","tag-nvidia"],"acf":{"post_show_excerpt":true,"post_source":{"title":"Tom's Hardware FR","url":"https:\/\/www.tomshardware.fr\/","target":""}},"yoast_head":"\nL'architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU<\/title>\n<meta name=\"description\" content=\"Si l\u2019on se penche sur l\u2019architecture Pascal pr\u00e9sent\u00e9e aujourd\u2019hui pour le Tesla P100, on remarque qu\u2019elle donne la priorit\u00e9 aux applications GPGPU au d\u00e9triment des jeux et du grand public.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"L'architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU\" \/>\n<meta property=\"og:description\" content=\"Si l\u2019on se penche sur l\u2019architecture Pascal pr\u00e9sent\u00e9e aujourd\u2019hui pour le Tesla P100, on remarque qu\u2019elle donne la priorit\u00e9 aux applications GPGPU au d\u00e9triment des jeux et du grand public.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/\" \/>\n<meta property=\"og:site_name\" content=\"Tom\u2019s Hardware\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/TomsHardwareFrance\/\" \/>\n<meta property=\"article:published_time\" content=\"2016-04-06T06:25:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-09-20T12:07:55+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png\" \/>\n\t<meta property=\"og:image:width\" content=\"624\" \/>\n\t<meta property=\"og:image:height\" content=\"368\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"David Civera\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@https:\/\/twitter.com\/DavidCivera\" \/>\n<meta name=\"twitter:site\" content=\"@tomshardware_fr\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/\"},\"author\":{\"name\":\"David Civera\",\"@id\":\"https:\/\/www.tomshardware.fr\/#\/schema\/person\/746509d2b13ec667acdb5f6a67b8cfdb\"},\"headline\":\"L’architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU\",\"datePublished\":\"2016-04-06T06:25:00+00:00\",\"dateModified\":\"2023-09-20T12:07:55+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/\"},\"wordCount\":396,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.tomshardware.fr\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png\",\"keywords\":[\"NVIDIA\"],\"articleSection\":[\"Actualit\u00e9\",\"Cartes graphiques\"],\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/\",\"url\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/\",\"name\":\"L'architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU\",\"isPartOf\":{\"@id\":\"https:\/\/www.tomshardware.fr\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png\",\"datePublished\":\"2016-04-06T06:25:00+00:00\",\"dateModified\":\"2023-09-20T12:07:55+00:00\",\"description\":\"Si l\u2019on se penche sur l\u2019architecture Pascal pr\u00e9sent\u00e9e aujourd\u2019hui pour le Tesla P100, on remarque qu\u2019elle donne la priorit\u00e9 aux applications GPGPU au d\u00e9triment des jeux et du grand public.\",\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage\",\"url\":\"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png\",\"contentUrl\":\"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png\",\"width\":624,\"height\":368},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.tomshardware.fr\/#website\",\"url\":\"https:\/\/www.tomshardware.fr\/\",\"name\":\"Tom\u2019s Hardware\",\"description\":\"Toute l'info hardware et gaming !\",\"publisher\":{\"@id\":\"https:\/\/www.tomshardware.fr\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.tomshardware.fr\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.tomshardware.fr\/#organization\",\"name\":\"Tom\u2019s Hardware\",\"url\":\"https:\/\/www.tomshardware.fr\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/www.tomshardware.fr\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2023\/06\/th.png\",\"contentUrl\":\"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2023\/06\/th.png\",\"width\":1000,\"height\":1000,\"caption\":\"Tom\u2019s Hardware\"},\"image\":{\"@id\":\"https:\/\/www.tomshardware.fr\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/TomsHardwareFrance\/\",\"https:\/\/x.com\/tomshardware_fr\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.tomshardware.fr\/#\/schema\/person\/746509d2b13ec667acdb5f6a67b8cfdb\",\"name\":\"David Civera\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/www.tomshardware.fr\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/a08bb358c2a9fc36265e8f3225c5de08?s=64&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/a08bb358c2a9fc36265e8f3225c5de08?s=64&d=mm&r=g\",\"caption\":\"David Civera\"},\"description\":\"N\u00e9 aux \u00c9tats-Unis, \u00e9lev\u00e9 en France et \u00e0 Singapour, adopt\u00e9 par les Philippines, et maintenant pos\u00e9 au Canada (pour l'instant), son amour du monde n'a d'\u00e9gal que sa passion pour les micro-architectures, les derni\u00e8res trouvailles des labos ou les jeux sur consoles. R\u00e9dacteur Tom's Hardware France (anciennement Pr\u00e9sence-PC) depuis 2005, il reste l'\u00e9ternel \u00e9l\u00e8ve de la communaut\u00e9 des lecteurs.\",\"sameAs\":[\"https:\/\/x.com\/https:\/\/twitter.com\/DavidCivera\"],\"url\":\"https:\/\/www.tomshardware.fr\/author\/david-civera\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"L'architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU","description":"Si l\u2019on se penche sur l\u2019architecture Pascal pr\u00e9sent\u00e9e aujourd\u2019hui pour le Tesla P100, on remarque qu\u2019elle donne la priorit\u00e9 aux applications GPGPU au d\u00e9triment des jeux et du grand public.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/","og_locale":"fr_FR","og_type":"article","og_title":"L'architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU","og_description":"Si l\u2019on se penche sur l\u2019architecture Pascal pr\u00e9sent\u00e9e aujourd\u2019hui pour le Tesla P100, on remarque qu\u2019elle donne la priorit\u00e9 aux applications GPGPU au d\u00e9triment des jeux et du grand public.","og_url":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/","og_site_name":"Tom\u2019s Hardware","article_publisher":"https:\/\/www.facebook.com\/TomsHardwareFrance\/","article_published_time":"2016-04-06T06:25:00+00:00","article_modified_time":"2023-09-20T12:07:55+00:00","og_image":[{"width":624,"height":368,"url":"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png","type":"image\/png"}],"author":"David Civera","twitter_card":"summary_large_image","twitter_creator":"@https:\/\/twitter.com\/DavidCivera","twitter_site":"@tomshardware_fr","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#article","isPartOf":{"@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/"},"author":{"name":"David Civera","@id":"https:\/\/www.tomshardware.fr\/#\/schema\/person\/746509d2b13ec667acdb5f6a67b8cfdb"},"headline":"L’architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU","datePublished":"2016-04-06T06:25:00+00:00","dateModified":"2023-09-20T12:07:55+00:00","mainEntityOfPage":{"@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/"},"wordCount":396,"commentCount":0,"publisher":{"@id":"https:\/\/www.tomshardware.fr\/#organization"},"image":{"@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage"},"thumbnailUrl":"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png","keywords":["NVIDIA"],"articleSection":["Actualit\u00e9","Cartes graphiques"],"inLanguage":"fr-FR","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/","url":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/","name":"L'architecture GPU Pascal en d\u00e9tail : priorit\u00e9 aux applications GPGPU","isPartOf":{"@id":"https:\/\/www.tomshardware.fr\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage"},"image":{"@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage"},"thumbnailUrl":"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png","datePublished":"2016-04-06T06:25:00+00:00","dateModified":"2023-09-20T12:07:55+00:00","description":"Si l\u2019on se penche sur l\u2019architecture Pascal pr\u00e9sent\u00e9e aujourd\u2019hui pour le Tesla P100, on remarque qu\u2019elle donne la priorit\u00e9 aux applications GPGPU au d\u00e9triment des jeux et du grand public.","inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/www.tomshardware.fr\/larchitecture-gpu-pascal-en-detail-priorite-aux-applications-gpgpu\/#primaryimage","url":"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png","contentUrl":"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2016\/04\/gp100-block-diagram-1-624x368.png","width":624,"height":368},{"@type":"WebSite","@id":"https:\/\/www.tomshardware.fr\/#website","url":"https:\/\/www.tomshardware.fr\/","name":"Tom\u2019s Hardware","description":"Toute l'info hardware et gaming !","publisher":{"@id":"https:\/\/www.tomshardware.fr\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.tomshardware.fr\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/www.tomshardware.fr\/#organization","name":"Tom\u2019s Hardware","url":"https:\/\/www.tomshardware.fr\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/www.tomshardware.fr\/#\/schema\/logo\/image\/","url":"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2023\/06\/th.png","contentUrl":"https:\/\/www.tomshardware.fr\/content\/uploads\/sites\/3\/2023\/06\/th.png","width":1000,"height":1000,"caption":"Tom\u2019s Hardware"},"image":{"@id":"https:\/\/www.tomshardware.fr\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/TomsHardwareFrance\/","https:\/\/x.com\/tomshardware_fr"]},{"@type":"Person","@id":"https:\/\/www.tomshardware.fr\/#\/schema\/person\/746509d2b13ec667acdb5f6a67b8cfdb","name":"David Civera","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/www.tomshardware.fr\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/a08bb358c2a9fc36265e8f3225c5de08?s=64&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a08bb358c2a9fc36265e8f3225c5de08?s=64&d=mm&r=g","caption":"David Civera"},"description":"N\u00e9 aux \u00c9tats-Unis, \u00e9lev\u00e9 en France et \u00e0 Singapour, adopt\u00e9 par les Philippines, et maintenant pos\u00e9 au Canada (pour l'instant), son amour du monde n'a d'\u00e9gal que sa passion pour les micro-architectures, les derni\u00e8res trouvailles des labos ou les jeux sur consoles. R\u00e9dacteur Tom's Hardware France (anciennement Pr\u00e9sence-PC) depuis 2005, il reste l'\u00e9ternel \u00e9l\u00e8ve de la communaut\u00e9 des lecteurs.","sameAs":["https:\/\/x.com\/https:\/\/twitter.com\/DavidCivera"],"url":"https:\/\/www.tomshardware.fr\/author\/david-civera\/"}]}},"_links":{"self":[{"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/posts\/233181"}],"collection":[{"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/comments?post=233181"}],"version-history":[{"count":0,"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/posts\/233181\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/media\/233182"}],"wp:attachment":[{"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/media?parent=233181"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/categories?post=233181"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/tags?post=233181"},{"taxonomy":"hubs","embeddable":true,"href":"https:\/\/www.tomshardware.fr\/wp-json\/wp\/v2\/hubs?post=233181"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}