{"id":117,"date":"2015-03-01T21:57:17","date_gmt":"2015-03-01T20:57:17","guid":{"rendered":"https:\/\/project.inria.fr\/granit\/?page_id=117"},"modified":"2015-03-16T14:15:06","modified_gmt":"2015-03-16T13:15:06","slug":"fixed-point-arithmetic","status":"publish","type":"page","link":"https:\/\/www-granit.irisa.fr\/fr\/fixed-point-arithmetic\/","title":{"rendered":"Arithm\u00e9tique en virgule fixe"},"content":{"rendered":"<p>Les architectures bas\u00e9es sur l\u2019arithm\u00e9tique virgule fixe utilisent des donn\u00e9es de tailles relativement faibles, ce qui pr\u00e9sente l\u2019avantage de r\u00e9duire la surface, la latence et la puissance consomm\u00e9e des syst\u00e8mes embarqu\u00e9s.\u00a0Cependant, l\u2019arithm\u00e9tique virgule fixe g\u00e9n\u00e8re des bruits de quantification qui modifient les calculs et peuvent d\u00e9grader la qualit\u00e9 de l\u2019application. Notre approche consiste \u00e0 \u00e9tudier la pr\u00e9cision des syst\u00e8mes en virgule fixe en privil\u00e9giant des m\u00e9thodes analytiques. Ces derni\u00e8res r\u00e9duisent \u00e9norm\u00e9ment le temps de conversion en virgule fixe par rapport aux m\u00e9thodes utilisant l\u2019arithm\u00e9tique virgule flottante.<\/p>\n<p>Nos \u00e9tudes concernent\u00a0:<\/p>\n<ul>\n<li>Implantation efficace d\u2019algorithmes d\u2019\u00e9galisation et de synchronisation pour des applications de communications<\/li>\n<li>Modifier la taille des donn\u00e9es de mani\u00e8re dynamique en fonction du canal de transmission.<\/li>\n<li>Implantation multi-contraintes d\u2019applications de communications num\u00e9riques: (multi pr\u00e9cisions, et\/ou latence, et\/ou co\u00fbt&#8230; )<\/li>\n<li>Effets de la fr\u00e9quence d\u2019\u00e9chantillonnage sur la qualit\u00e9 des calculs<\/li>\n<li>Etude de nouvelles arithm\u00e9tiques (calculs approximatif, quantification vectorielle&#8230;)<\/li>\n<\/ul>\n<p><\/p>","protected":false},"excerpt":{"rendered":"<p>Les architectures bas\u00e9es sur l\u2019arithm\u00e9tique virgule fixe utilisent des donn\u00e9es de tailles relativement faibles, ce qui pr\u00e9sente l\u2019avantage de r\u00e9duire la surface, la latence et la puissance consomm\u00e9e des syst\u00e8mes embarqu\u00e9s.\u00a0Cependant, l\u2019arithm\u00e9tique virgule fixe g\u00e9n\u00e8re des bruits de quantification qui modifient les calculs et peuvent d\u00e9grader la qualit\u00e9 de l\u2019application.\u2026<\/p>\n<p class=\"continue-reading-button\"> <a class=\"continue-reading-link\" href=\"https:\/\/www-granit.irisa.fr\/fr\/fixed-point-arithmetic\/\">Lire la suite<i class=\"crycon-right-dir\"><\/i><\/a><\/p>\n","protected":false},"author":683,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-117","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/pages\/117","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/users\/683"}],"replies":[{"embeddable":true,"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/comments?post=117"}],"version-history":[{"count":4,"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/pages\/117\/revisions"}],"predecessor-version":[{"id":260,"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/pages\/117\/revisions\/260"}],"wp:attachment":[{"href":"https:\/\/www-granit.irisa.fr\/fr\/wp-json\/wp\/v2\/media?parent=117"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}