{"id":17606,"date":"2025-10-19T06:31:36","date_gmt":"2025-10-19T05:31:36","guid":{"rendered":"https:\/\/roglacup.com\/klaus62\/?p=17606"},"modified":"2025-10-19T06:31:37","modified_gmt":"2025-10-19T05:31:37","slug":"how-do-graphics-cards-work-exploring-gpu-architecture","status":"publish","type":"post","link":"https:\/\/roglacup.com\/klaus62\/2025\/10\/19\/how-do-graphics-cards-work-exploring-gpu-architecture\/","title":{"rendered":"How do Graphics Cards Work? Exploring GPU Architecture"},"content":{"rendered":"\n<p>Graphics Cards can run some of the most incredible video games, but how many calculations do they perform every single second? Well, some of the most advanced graphics perform 36 Trillion calculations or more every single second. But how can a single device manage these tens of trillions of calculations? In this video, we explore the architecture inside the 3090 graphics card and the GA102 GPU chip architecture. Note: We chose to feature the 30 series of GPUs because, to create accurate 3D models, we had to tear down a 3090 GPU rather destructively. We typically select a slightly older model because we&#8217;re able to find broken components on eBay. If you&#8217;re wondering, the 4090 can perform 82.58 trillion calculations a second, and then we&#8217;re sure the 5090 will be even more. <\/p>\n\n\n\n<p>Table of Contents:<\/p>\n\n\n\n<p> <a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU\">00:00<\/a> &#8211; How many calculations do Graphics Cards Perform? <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=135s\">02:15<\/a> &#8211; The Difference between GPUs and CPUs? <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=296s\">04:56<\/a> &#8211; GPU GA102 Architecture <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=419s\">06:59<\/a> &#8211; GPU GA102 Manufacturing <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=528s\">08:48<\/a> &#8211; CUDA Core Design <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=669s\">11:09<\/a> &#8211; Graphics Cards Components <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=724s\">12:04<\/a> &#8211; Graphics Memory GDDR6X GDDR7 <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=911s\">15:11<\/a> &#8211; All about Micron <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=1011s\">16:51<\/a> &#8211; Single Instruction Multiple Data Architecture <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=1069s\">17:49<\/a> &#8211; Why GPUs run Video Game Graphics, Object Transformations <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=1253s\">20:53<\/a> &#8211; Thread Architecture<\/p>\n\n\n\n<p> <a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=1411s\">23:31<\/a> &#8211; Help Branch Education Out! <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=1469s\">24:29<\/a> &#8211; Bitcoin Mining <\/p>\n\n\n\n<p><a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=1610s\">26:50<\/a> &#8211; Tensor Cores<\/p>\n\n\n\n<p> <a href=\"https:\/\/www.youtube.com\/watch?v=h9Z4oGN89MU&amp;t=1678s\">27:58<\/a> &#8211; Outro<\/p>\n\n\n\n<p>Posted from: <a href=\"https:\/\/blogs.nvidia.com\/blog\/nvidia-oracle-accelerate-enterprise-ai-data-processing\/\">Branch Education Website: <\/a><a href=\"https:\/\/www.youtube.com\/redirect?event=video_description&amp;redir_token=QUFFLUhqazBVYnZySXl5TlVmQk0tcDY3bGFsckRSWGl1d3xBQ3Jtc0ttTjBJbWNwSjRPRzJ4T0h5a2V6QkNKRUlGYmU3Rkg2czEyLXpaVk82YWxuR3lBRkpCckFPSkQ1azdBWnlqSTk2WWM1TlNFdkYzZksxUUxkZWZScUJKNXc2bmtySXhuWUhqb0tUQTUtWkFUZWt1WWRHNA&amp;q=https%3A%2F%2Fwww.branch.education%2F&amp;v=h9Z4oGN89MU\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/www.branch.education<\/a><\/p>\n\n\n\n<p>More: A TON of information was found in Nvidia&#8217;s white papers. You can find them here: <a href=\"https:\/\/www.youtube.com\/redirect?event=video_description&amp;redir_token=QUFFLUhqbUFGS3Ntcm0xMW1EX3JSV0JSY0xLam51Yy1OQXxBQ3Jtc0tua1RDa1NiVUlQbzB5dGc5RUZKSW14cEM4a1NHdjRURnZHRXRqWGlBWkRveG1Rc2FEcUdTNFAzd013eGpZYzVPZFpJWU5OQ3dnVXBzcGlnRm9hOXBBcDJUQnNQRlhacW5VUHI1RHhKUE1PUzVJY0ZaZw&amp;q=https%3A%2F%2Fresearch.nvidia.com%2Fpublications&amp;v=h9Z4oGN89MU\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/research.nvidia.com\/publications<\/a><\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\"  id=\"_ytid_11794\"  width=\"1200\" height=\"675\"  data-origwidth=\"1200\" data-origheight=\"675\" src=\"https:\/\/www.youtube.com\/embed\/h9Z4oGN89MU?enablejsapi=1&#038;autoplay=0&#038;cc_load_policy=0&#038;cc_lang_pref=&#038;iv_load_policy=1&#038;loop=0&#038;rel=1&#038;fs=1&#038;playsinline=0&#038;autohide=2&#038;theme=dark&#038;color=red&#038;controls=1&#038;disablekb=0&#038;\" class=\"__youtube_prefs__  epyt-is-override  no-lazyload\" title=\"YouTube player\"  allow=\"fullscreen; accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen data-no-lazy=\"1\" data-skipgform_ajax_framebjll=\"\"><\/iframe>\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Graphics Cards can run some of the most incredible video games, but how many calculations do they perform every single second? Well, some of the most advanced graphics perform 36 Trillion calculations or more every single second. But how can a single device manage these tens of trillions of calculations? In this video, we explore&hellip;&nbsp;<a href=\"https:\/\/roglacup.com\/klaus62\/2025\/10\/19\/how-do-graphics-cards-work-exploring-gpu-architecture\/\" class=\"\" rel=\"bookmark\">Read More &raquo;<span class=\"screen-reader-text\">How do Graphics Cards Work? Exploring GPU Architecture<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":17607,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"categories":[812,35],"tags":[],"class_list":["post-17606","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","category-oracle"],"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts\/17606","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/comments?post=17606"}],"version-history":[{"count":1,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts\/17606\/revisions"}],"predecessor-version":[{"id":17608,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/posts\/17606\/revisions\/17608"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/media\/17607"}],"wp:attachment":[{"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/media?parent=17606"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/categories?post=17606"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/roglacup.com\/klaus62\/wp-json\/wp\/v2\/tags?post=17606"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}