{"id":9707,"date":"2022-04-15T11:45:52","date_gmt":"2022-04-15T09:45:52","guid":{"rendered":"https:\/\/www.generationrobots.com\/blog\/?p=9707"},"modified":"2024-06-27T10:18:35","modified_gmt":"2024-06-27T08:18:35","slug":"nvidia-jetson-orin-notre-comparatif-avec-la-nvidia-jetson-xavier","status":"publish","type":"post","link":"https:\/\/www.generationrobots.com\/blog\/fr\/nvidia-jetson-orin-notre-comparatif-avec-la-nvidia-jetson-xavier\/","title":{"rendered":"NVIDIA Jetson Orin : notre comparatif avec la NVIDIA Jetson Xavier"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"9707\" class=\"elementor elementor-9707\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-6116e5b0 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"6116e5b0\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-3afa75e7\" data-id=\"3afa75e7\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-109ac660 elementor-widget elementor-widget-text-editor\" data-id=\"109ac660\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\n<p>Les syst\u00e8mes ultra compacts <strong><a class=\"catalogue\" title=\"Processeurs NVIDIA Jetson\" href=\"\/fr\/463-processeurs-nvidia-jetson\">NDIVIA Jetson<\/a><\/strong> sont depuis longtemps r\u00e9put\u00e9s pour \u00eatre parmi les plus performants du monde pour les machines autonomes.<\/p>\n\n<p>Combinant une puissance \u00e9lev\u00e9e et un rendement \u00e9nerg\u00e9tique in\u00e9dit, ils constituent la solution id\u00e9ale pour la <strong>robotique embarqu\u00e9e<\/strong> et le domaine du <strong>edge computing<\/strong>. Il est difficile de pouvoir penser qu&rsquo;il est possible de faire mieux, pourtant, NVIDIA a une fois de plus su relever le d\u00e9fi pour proposer une <strong>nouvelle g\u00e9n\u00e9ration de modules<\/strong> proposant une performance jusqu&rsquo;\u00e0 8 fois sup\u00e9rieure \u00e0 la pr\u00e9c\u00e9dente : la gamme <strong>NVIDIA Jetson Orin<\/strong>.<\/p>\n\n<h2 class=\"wp-block-heading\" id=\"h-qu-est-ce-que-la-gamme-nvidia-jetson-orin\"><strong>Qu&rsquo;est-ce-que la gamme NVIDIA Jetson Orin ?<\/strong><\/h2>\n\n<p>Les <a class=\"catalogue\" title=\"Kit de d\u00e9veloppement Nvidia Jetson AGX Orin\" href=\"\/fr\/403969-kit-de-developpement-nvidia-jetson-agx-orin.html\"><strong>modules NVIDIA Jetson Orin<\/strong><\/a> offrent un parfait \u00e9quilibre entre <strong>puissance<\/strong>, performance et <strong>basse consommation<\/strong> pour d\u00e9velopper les produits de demain gr\u00e2ce aux machines autonomes. Ils offrent une puissance pouvant atteindre <strong>275 TOPs<\/strong> et des performances in\u00e9dites jusqu&rsquo;\u00e0 <strong>8 fois sup\u00e9rieures<\/strong> \u00e0 celles des modules Jetson Xavier. Les syst\u00e8mes NVIDIA Jeston AGX Orin offrent des niveaux de performance et de rendement \u00e9nerg\u00e9tique n\u00e9cessaires pour impl\u00e9menter des machines autonomes sur l&rsquo;Edge.<\/p>\n\n<p>Le kit de d\u00e9veloppement Jetson AGX Orin permet notamment de d\u00e9ployer plus facilement et plus rapidement des applications de robotique de pointe dans des domaines comme le d\u00e9veloppement de <strong>smart cities<\/strong>, la <strong>distribution<\/strong>, l&rsquo;<strong>agriculture<\/strong>, la logistique, la production industrielle, la sant\u00e9, etc\u2026<\/p>\n\n<h2 class=\"wp-block-heading\"><strong>Qu&rsquo;est-ce-que le Edge Computing ?<\/strong><\/h2>\n\n<p>Le Edge Computing permet de <strong>traiter des donn\u00e9es directement par le p\u00e9riph\u00e9rique qui les produit<\/strong>, ou par un <strong>ordinateur local<\/strong>. Les donn\u00e9es ne sont pas transmises \u00e0 un datacenter distant pour \u00eatre analys\u00e9es. On gagne en rapidit\u00e9, surtout lorsqu\u2019il s\u2019agit de traiter des donn\u00e9es lourdes, comme des vid\u00e9os, de l\u2019audio, etc.\u00a0<\/p>\n\n<p>Ce traitement des donn\u00e9es en temps r\u00e9el permet de gagner en rapidit\u00e9, d\u2019<strong>\u00e9liminer les niveaux de latence<\/strong>, qui, dans le cas de la robotique et particuli\u00e8rement des v\u00e9hicules autonomes et connect\u00e9s, sont dangereux.<\/p>\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><a href=\"https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/edge-computer-nvidia-jetson-orin-1-1.jpg\"><img fetchpriority=\"high\" decoding=\"async\" width=\"1024\" height=\"614\" class=\"wp-image-9718\" src=\"https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/edge-computer-nvidia-jetson-orin-1-1-1024x614.jpg\" alt=\"Qu'est-ce-que le Edge Computing ?\" srcset=\"https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/edge-computer-nvidia-jetson-orin-1-1-1024x614.jpg 1024w, https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/edge-computer-nvidia-jetson-orin-1-1-300x180.jpg 300w, https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/edge-computer-nvidia-jetson-orin-1-1-768x461.jpg 768w, https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/edge-computer-nvidia-jetson-orin-1-1.jpg 1140w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/a><\/figure>\n<\/div>\n\n<h2 class=\"wp-block-heading\" id=\"h-les-principales-evolutions-de-la-gamme-orin-par-rapport-a-la-gamme-xavier\"><strong>Les principales \u00e9volutions de la gamme Orin par rapport \u00e0 la gamme Xavier<\/strong><\/h2>\n\n<p>Les modules <strong>Jetson AGX Orin<\/strong> fournissent des performances d&rsquo;IA pouvant atteindre jusqu&rsquo;\u00e0 275 TOPs avec une capacit\u00e9 de m\u00e9moire allant jusqu&rsquo;\u00e0 64 Go, contre 30 TOPs pour une capacit\u00e9 de 32 Go maximum pour la s\u00e9rie Jetson Xavier. La consommation des modules Jetson Orin se trouve l\u00e0 aussi plus optimis\u00e9e que jamais avec une consommation d&rsquo;\u00e9nergie maximale de <strong>60 W contre 40 W<\/strong> maximum pour les modules Jetson Xavier.<\/p>\n\n<p><strong>Cela en fait l&rsquo;ordinateur d&rsquo;IA le plus puissant au monde pour les machines autonomes, tout en gardant une consommation basse et ultra optimis\u00e9e.<\/strong><\/p>\n\n<p>Il permet d&rsquo;atteindre des performances nouvelle g\u00e9n\u00e9ration jusqu&rsquo;\u00e0 8 fois sup\u00e9rieures \u00e0 celles de la gamme Jetson Xavier, afin de g\u00e9rer un plus grand nombre de pipelines simultan\u00e9ment. Aussi, il offre une prise en charge optimale des interfaces gr\u00e2ce \u00e0 de multiples capteurs, dans l&rsquo;optique de toujours mieux r\u00e9pondre aux tendances du domaine de la robotique embarqu\u00e9e nouvelle g\u00e9n\u00e9ration.<\/p>\n\n<p>La mise en r\u00e9seau, qui s&rsquo;effectuait uniquement par Ethernet classique avec les modules Jetson Xavier, est dor\u00e9navant possible avec Gigabit Ethernet pour les modules Jetson Orin. La transmission de donn\u00e9es peut ainsi s&rsquo;effectuer beaucoup plus rapidement qu&rsquo;auparavant.<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-12271f98 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"12271f98\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-665e108c\" data-id=\"665e108c\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6d9f72f1 elementor-widget elementor-widget-heading\" data-id=\"6d9f72f1\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Kit de d\u00e9veloppement Nvidia Jetson AGX Orin<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-55de7976 elementor-widget elementor-widget-text-editor\" data-id=\"55de7976\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: center;\">3 598,80 \u20ac TTC<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3b1d44a0 elementor-widget elementor-widget-image\" data-id=\"3b1d44a0\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"450\" height=\"450\" src=\"https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/nvidia-jetson-orin-module-de-developpement.jpg\" class=\"attachment-large size-large wp-image-9907\" alt=\"Kit de d\u00e9veloppement Nvidia Jetson AGX Orin\" srcset=\"https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/nvidia-jetson-orin-module-de-developpement.jpg 450w, https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/nvidia-jetson-orin-module-de-developpement-300x300.jpg 300w, https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/nvidia-jetson-orin-module-de-developpement-150x150.jpg 150w, https:\/\/www.generationrobots.com\/blog\/wp-content\/uploads\/2022\/04\/nvidia-jetson-orin-module-de-developpement-140x140.jpg 140w\" sizes=\"(max-width: 450px) 100vw, 450px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3fdb2964 elementor-widget elementor-widget-text-editor\" data-id=\"3fdb2964\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<ul>\n<li><strong>8x plus performant<\/strong> que la AGX Xavier<\/li>\n<li>D\u00e9veloppement d&rsquo;applications en <strong>Edge Computing<\/strong><\/li>\n<li><strong>Eco-conception<\/strong> (entre 15 et 60 W)<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2a39294b elementor-align-center elementor-widget elementor-widget-button\" data-id=\"2a39294b\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"\/fr\/403969-kit-de-developpement-nvidia-jetson-agx-orin.html\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Commandez<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-66469aa elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"66469aa\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-6d369e6\" data-id=\"6d369e6\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-8033491 elementor-widget elementor-widget-text-editor\" data-id=\"8033491\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\n<h2 class=\"wp-block-heading\" id=\"h-tableau-comparatif-des-nvidia-jetson-xavier-avec-les-nvidia-jetson-orin\">Tableau comparatif des NVIDIA Jetson Xavier avec les NVIDIA Jetson Orin<\/h2>\n\n<figure class=\"wp-block-table is-style-stripes\" style=\"font-size: 16px;\">\n<table>\n<tbody>\n<tr>\n<td>\u00a0<\/td>\n<td><strong>Jetson Xavier NX 16 Go<\/strong><\/td>\n<td><strong>Jetson Xavier NX<\/strong><\/td>\n<td><strong>Jetson AGX Xavier 64 Go<\/strong><\/td>\n<td><strong>Jetson AGX Xavier<\/strong><\/td>\n<td><strong>Jetson Orin NX 8 Go<\/strong><\/td>\n<td><strong>Jetson Orin NX 16 Go<\/strong><\/td>\n<td><strong>Jetson Orin AGX 32 Go<\/strong><\/td>\n<td><strong>Jetson Orin AGX 64 Go<\/strong><\/td>\n<\/tr>\n<tr>\n<td><strong>Performances d\u2019IA<\/strong><\/td>\n<td>21 TOPs<\/td>\n<td>21 TOPs<\/td>\n<td>32 TOPs<\/td>\n<td>32 TOPs<\/td>\n<td>70 TOPs<\/td>\n<td>100 TOPs<\/td>\n<td>200 TOPs<\/td>\n<td>275 TOPs<\/td>\n<\/tr>\n<tr>\n<td><strong>GPU<\/strong><\/td>\n<td>GPU NVIDIA Volta\u2122 \u00e0 384 c\u0153urs (avec 48 c\u0153urs Tensor)<\/td>\n<td>GPU NVIDIA Volta\u2122 \u00e0 384 c\u0153urs (avec 48 c\u0153urs Tensor)<\/td>\n<td>GPU NVIDIA Volta \u00e0 512 c\u0153urs (avec 64 c\u0153urs Tensor)<\/td>\n<td>GPU NVIDIA Volta \u00e0 512 c\u0153urs (avec 64 c\u0153urs Tensor)<\/td>\n<td>GPU NVIDIA Ampere \u00e0 1024\u00a0c\u0153urs (avec 32\u00a0c\u0153urs Tensor)<\/td>\n<td>GPU NVIDIA Ampere \u00e0 1024\u00a0c\u0153urs (avec 32\u00a0c\u0153urs Tensor)<\/td>\n<td>GPU NVIDIA Ampere \u00e0 1792 c\u0153urs (avec 56 c\u0153urs Tensor)<\/td>\n<td>GPU NVIDIA Ampere \u00e0 2048 c\u0153urs (avec 64 c\u0153urs Tensor)<\/td>\n<\/tr>\n<tr>\n<td><strong>CPU<\/strong><\/td>\n<td>CPU NVIDIA Carmel ARM\u00ae 6 c\u0153urs v8.2 64 bits 6 Mo L2 + 4 Mo L3<\/td>\n<td>CPU NVIDIA Carmel ARM\u00ae 6 c\u0153urs v8.2 64 bits 6 Mo L2 + 4 Mo L3<\/td>\n<td>CPU NVIDIA Carmel ARM\u00ae 8 c\u0153urs v8.2 64 bits 8 Mo L2 + 4 Mo L3<\/td>\n<td>CPU NVIDIA Carmel ARM\u00ae 8 c\u0153urs v8.2 64 bits 8 Mo L2 + 4 Mo L3<\/td>\n<td>CPU Arm\u00ae Cortex\u00ae-A78AE v8.2 64 bits \u00e0 6 c\u0153urs, 2 Mo L2 + 4 Mo L3<\/td>\n<td>CPU NVIDIA Arm\u00ae Cortex\u00ae-A78AE v8.2 64 bits \u00e0 8 c\u0153urs 1,5 Mo L2 + 4 Mo L3<\/td>\n<td>CPU Arm\u00ae Cortex\u00ae-A78AE v8.2 64 bits \u00e0 8 c\u0153urs 2 Mo L2 + 4 Mo L3<\/td>\n<td>CPU Arm\u00ae Cortex\u00ae-A78AE v8.2 64 bits \u00e0 12 c\u0153urs 3 Mo L2 + 6 Mo L3<\/td>\n<\/tr>\n<tr>\n<td><strong>Acc\u00e9l\u00e9rateur DL<\/strong><\/td>\n<td>2x NVDLA<\/td>\n<td>2x NVDLA<\/td>\n<td>2x NVDLA<\/td>\n<td>2x NVDLA<\/td>\n<td>1x NVDLA v2<\/td>\n<td>2x NVDLA v2<\/td>\n<td>2x NVDLA v2<\/td>\n<td>2x NVDLA v2<\/td>\n<\/tr>\n<tr>\n<td><strong>Acc\u00e9l\u00e9rateur Vision<\/strong><\/td>\n<td>2x PVA<\/td>\n<td>2x PVA<\/td>\n<td>2x PVA<\/td>\n<td>2x PVA<\/td>\n<td>1x PVA v2<\/td>\n<td>1x PVA v2<\/td>\n<td>1x PVA v2<\/td>\n<td>1x PVA v2<\/td>\n<\/tr>\n<tr>\n<td><strong>M\u00e9moire<\/strong><\/td>\n<td>16 Go 128 bits LPDDR4x 59,7 Go\/s<\/td>\n<td>8 Go 128 bits LPDDR4x 59,7 Go\/s<\/td>\n<td>64 Go 256 bits LPDDR4x 136,5 Go\/s<\/td>\n<td>32 Go 256 bits LPDDR4x 136,5 Go\/s<\/td>\n<td>8 Go 128 bits LPDDR5 102,4 Go\/s<\/td>\n<td>16 Go 128 bits LPDDR5 102,4 Go\/s<\/td>\n<td>32 Go 256 bits LPDDR5 204,8 Go\/s<\/td>\n<td>64 Go 256 bits LPDDR5 204,8 Go\/s<\/td>\n<\/tr>\n<tr>\n<td><strong>Stockage<\/strong><\/td>\n<td>16 Go eMMC 5.1<\/td>\n<td>16 Go eMMC 5.1<\/td>\n<td>32 Go eMMC 5.1<\/td>\n<td>32 Go eMMC 5.1<\/td>\n<td>(Compatibilit\u00e9 NVMe externe)<\/td>\n<td>(Compatibilit\u00e9 NVMe externe)<\/td>\n<td>64 Go eMMC 5.1<\/td>\n<td>64 Go eMMC 5.1<\/td>\n<\/tr>\n<tr>\n<td><strong>Cam\u00e9ra<\/strong><\/td>\n<td>Jusqu\u2019\u00e0 6 cam\u00e9ras<br \/>(24 via des cha\u00eenes virtuelles)<br \/>14 canaux MIPI CSI-2<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 30 Gbit\/s)<\/td>\n<td>Jusqu\u2019\u00e0 6 cam\u00e9ras<br \/>(24 via des cha\u00eenes virtuelles)<br \/>14 canaux MIPI CSI-2<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 30 Gbit\/s)<\/td>\n<td>Jusqu\u2019\u00e0 6 cam\u00e9ras<br \/>(36 via des cha\u00eenes virtuelles)<br \/>16 canaux MIPI CSI-2 | 8 canaux SLVS-EC<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 40 Gbit\/s)<br \/>C-PHY 1.1 (jusqu\u2019\u00e0 62 Gbit\/s)<\/td>\n<td>Jusqu\u2019\u00e0 6 cam\u00e9ras<br \/>(36 via des cha\u00eenes virtuelles)<br \/>16 canaux MIPI CSI-2 | 8 canaux SLVS-EC<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 40 Gbit\/s)<br \/>C-PHY 1.1 (jusqu\u2019\u00e0 62 Gbit\/s)<\/td>\n<td>Jusqu\u2019\u00e0 4 cam\u00e9ras (8 via des cha\u00eenes virtuelles*)<br \/>8 canaux MIPI CSI-2<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 20 Gbit\/s)<\/td>\n<td>Jusqu\u2019\u00e0 4 cam\u00e9ras (8 via des cha\u00eenes virtuelles*)<br \/>8 canaux MIPI CSI-2<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 20 Gbit\/s)<\/td>\n<td>Jusqu\u2019\u00e0 6 cam\u00e9ras (16 via des cha\u00eenes virtuelles*)<br \/>16 canaux MIPI CSI-2<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 40 Gbit\/s) | C-PHY 1.1 (jusqu\u2019\u00e0 164 Gbit\/s)<\/td>\n<td>Jusqu\u2019\u00e0 6 cam\u00e9ras (16 via des cha\u00eenes virtuelles*)<br \/>16 canaux MIPI CSI-2<br \/>D-PHY 1.2 (jusqu\u2019\u00e0 40 Gbit\/s) | C-PHY 1.1 (jusqu\u2019\u00e0 164 Gbit\/s)<\/td>\n<\/tr>\n<tr>\n<td><strong>Encodage vid\u00e9o<\/strong><\/td>\n<td>2x 4K @ 60 (H.265)<br \/>10x 1080p @ 60 (H.265)<br \/>22x 1080p @ 30 (H.265)<\/td>\n<td>2x 4K @ 60 (H.265)<br \/>10x 1080p @ 60 (H.265)<br \/>22x 1080p @ 30 (H.265)<\/td>\n<td>4x 4K @ 60 (H.265)<br \/>16x 1080p @ 60 (H.265)<br \/>32x 1080p @ 30 (H.265)<\/td>\n<td>4x 4K @ 60 (H.265)<br \/>16x 1080p @ 60 (H.265)<br \/>32x 1080p @ 30 (H.265)<\/td>\n<td>1x 4K @ 60 (H.265)<br \/>3x 4K @ 30 (H.265)<br \/>6x 1080p @ 60 (H.265)<br \/>12x 1080p @ 30 (H.265)<\/td>\n<td>1x 4K @ 60 (H.265)<br \/>3x 4K @ 30 (H.265)<br \/>6x 1080p @ 60 (H.265)<br \/>12x 1080p @ 30 (H.265)<\/td>\n<td>1x 4K @ 60 (H.265)<br \/>3x 4K @ 30 (H.265)<br \/>6x 1080p @ 60 (H.265)<br \/>12x 1080p @ 30 (H.265)<\/td>\n<td>2x 4K @ 60 (H.265)<br \/>4x 4K @ 30 (H.265)<br \/>8x 1080p @ 60 (H.265)<br \/>16x 1080p @ 30 (H.265)<\/td>\n<\/tr>\n<tr>\n<td><strong>D\u00e9codage vid\u00e9o<\/strong><\/td>\n<td>2x 8K @ 30 (H.265)<br \/>6x 4K @ 60 (H.265)<br \/>22x 1080p @ 60 (H.265)<br \/>44x 1080p @ 30 (H.265)<\/td>\n<td>2x 8K @ 30 (H.265)<br \/>6x 4K @ 60 (H.265)<br \/>22x 1080p @ 60 (H.265)<br \/>44x 1080p @ 30 (H.265)<\/td>\n<td>2x 8K @ 30 (H.265)<br \/>6x 4K @ 60 (H.265)<br \/>26x 1080p @ 60 (H.265)<br \/>52x 1080p @ 30 (H.265)<\/td>\n<td>2x 8K @ 30 (H.265)<br \/>6x 4K @ 60 (H.265)<br \/>26x 1080p @ 60 (H.265)<br \/>52x 1080p @ 30 (H.265)<\/td>\n<td>1x 8K @ 30 (H.265)<br \/>2x 4K @ 60 (H.265)<br \/>4x 4K @ 30 (H.265)<br \/>9x 1080p @ 60 (H.265)<br \/>18x 1080p @ 30 (H.265)<\/td>\n<td>1x 8K @ 30 (H.265)<br \/>2x 4K @ 60 (H.265)<br \/>4x 4K @ 30 (H.265)<br \/>9x 1080p @ 60 (H.265)<br \/>18x 1080p @ 30 (H.265)<\/td>\n<td>1x 8K @ 30 (H.265)<br \/>2x 4K @ 60 (H.265)<br \/>4x 4K @ 30 (H.265)<br \/>9x 1080p @ 60 (H.265)<br \/>18x 1080p @ 30 (H.265)<\/td>\n<td>1x 8K @ 30 (H.265)<br \/>3x 4K @ 60 (H.265)<br \/>7x 4K @ 30 (H.265)<br \/>11x 1080p @ 60 (H.265)<br \/>22x 1080p @ 30 (H.265)<\/td>\n<\/tr>\n<tr>\n<td><strong>PCIe<\/strong><\/td>\n<td>1 x1 (PCIe Gen3) + 1 x4<br \/>(PCIe Gen4)<\/td>\n<td>1 x1 (PCIe Gen3) + 1 x4<br \/>(PCIe Gen4)<\/td>\n<td>1 x8 + 1 x4 + 1 x2 + 2 x1<br \/>(PCIe Gen4, Root Port et Endpoint)<\/td>\n<td>1 x8 + 1 x4 + 1 x2 + 2 x1<br \/>(PCIe Gen4, Root Port et Endpoint)<\/td>\n<td>1 x4 + 3 x1<br \/>(PCIe Gen4, Root Port et Endpoint)<\/td>\n<td>1 x4 + 3 x1<br \/>(PCIe Gen4, Root Port et Endpoint)<\/td>\n<td>Jusqu\u2019\u00e0 2 x8 + 2 x4 + 2 x1<br \/>(PCIe Gen4, Root Port et Endpoint)<\/td>\n<td>Jusqu\u2019\u00e0 2 x8 + 2 x4 + 2 x1<br \/>(PCIe Gen4, Root Port et Endpoint)<\/td>\n<\/tr>\n<tr>\n<td><strong>Mise en r\u00e9seau<\/strong><\/td>\n<td>Ethernet 10\/100\/1000BASE-T<\/td>\n<td>Ethernet 10\/100\/1000BASE-T<\/td>\n<td>Ethernet 10\/100\/1000BASE-T<\/td>\n<td>Ethernet 10\/100\/1000BASE-T<\/td>\n<td>1x GbE<\/td>\n<td>1x GbE<\/td>\n<td>1x GbE<br \/>4x 10GbE<\/td>\n<td>1x GbE<br \/>4x 10GbE<\/td>\n<\/tr>\n<tr>\n<td><strong>Affichage<\/strong><\/td>\n<td>2 multi-modes DP 1.4\/eDP 1.4\/HDMI 2.0<br \/>Pas de support DSI<\/td>\n<td>2 multi-modes DP 1.4\/eDP 1.4\/HDMI 2.0<br \/>Pas de support DSI<\/td>\n<td>3x multi-modes DP 1.4\/eDP 1.4\/HDMI 2.0<br \/>Pas de support DSI<\/td>\n<td>3x multi-modes DP 1.4\/eDP 1.4\/HDMI 2.0<br \/>Pas de support DSI<\/td>\n<td>1x multi-modes 8K @ 60 DP 1.4a (+MST)\/eDP 1.4a\/HDMI 2.1<\/td>\n<td>1x multi-modes 8K @ 60 DP 1.4a (+MST)\/eDP 1.4a\/HDMI 2.1<\/td>\n<td>1x multi-modes 8K @ 60 DP 1.4a (+MST)\/eDP 1.4a\/HDMI 2.1<\/td>\n<td>1x multi-modes 8K @ 60 DP 1.4a (+MST)\/eDP 1.4a\/HDMI 2.1<\/td>\n<\/tr>\n<tr>\n<td><strong>Consommation<\/strong><\/td>\n<td>10 W | 15 W | 20 W<\/td>\n<td>10 W | 15 W | 20 W<\/td>\n<td>10 W | 15 W | 30 W<\/td>\n<td>10 W | 15 W | 30 W<\/td>\n<td>10 W | 15 W | 20 W<\/td>\n<td>10 W | 15 W | 25 W<\/td>\n<td>15 W | 20 W | 50 W<\/td>\n<td>15\u00a0W | 30\u00a0W | 60\u00a0W<\/td>\n<\/tr>\n<tr>\n<td><strong>Sp\u00e9cifications m\u00e9caniques<\/strong><\/td>\n<td>69,6 mm x 45 mm<br \/>Connecteur SO-DIMM \u00e0 260 broches<\/td>\n<td>69,6 mm x 45 mm<br \/>Connecteur SO-DIMM \u00e0 260 broches<\/td>\n<td>100 mm x 87 mm<br \/>Connecteur \u00e0 699 broches<br \/>Plaque int\u00e9gr\u00e9e de transfert thermique<\/td>\n<td>100 mm x 87 mm<br \/>Connecteur \u00e0 699 broches<br \/>Plaque int\u00e9gr\u00e9e de transfert thermique<\/td>\n<td>69,6 mm x 45 mm<br \/>Connecteur SO-DIMM \u00e0 260 broches<\/td>\n<td>69,6 mm x 45 mm<br \/>Connecteur SO-DIMM \u00e0 260 broches<\/td>\n<td>100 mm x 87 mm<br \/>Connecteur 699 broches Molex Mirror Mezz<br \/>Plaque int\u00e9gr\u00e9e de transfert thermique<\/td>\n<td>100 mm x 87 mm<br \/>Connecteur 699 broches Molex Mirror Mezz<br \/>Plaque int\u00e9gr\u00e9e de transfert thermique<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/figure>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Les syst\u00e8mes ultra compacts NDIVIA Jetson sont depuis longtemps r\u00e9put\u00e9s pour \u00eatre parmi les plus performants du monde pour les machines autonomes. Combinant une puissance \u00e9lev\u00e9e et un rendement \u00e9nerg\u00e9tique in\u00e9dit, ils constituent la solution id\u00e9ale pour la robotique embarqu\u00e9e et le domaine du edge computing. Il est difficile de pouvoir penser qu&rsquo;il est possible[&#8230;]<br \/> <a class=\"button\" href=\"https:\/\/www.generationrobots.com\/blog\/fr\/nvidia-jetson-orin-notre-comparatif-avec-la-nvidia-jetson-xavier\/\" style=\"float:right;\">Read this article &gt;&gt;<\/a><\/p>\n","protected":false},"author":188,"featured_media":9716,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10523],"tags":[],"class_list":["post-9707","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-comparatifs-et-tests-produits"],"_links":{"self":[{"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/posts\/9707","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/users\/188"}],"replies":[{"embeddable":true,"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/comments?post=9707"}],"version-history":[{"count":34,"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/posts\/9707\/revisions"}],"predecessor-version":[{"id":18328,"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/posts\/9707\/revisions\/18328"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/media\/9716"}],"wp:attachment":[{"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/media?parent=9707"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/categories?post=9707"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.generationrobots.com\/blog\/wp-json\/wp\/v2\/tags?post=9707"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}