{"id":36086,"date":"2022-06-06T15:56:57","date_gmt":"2022-06-06T19:56:57","guid":{"rendered":"https:\/\/mjtsai.com\/blog\/?p=36086"},"modified":"2024-05-03T09:40:04","modified_gmt":"2024-05-03T13:40:04","slug":"apple-m2","status":"publish","type":"post","link":"https:\/\/mjtsai.com\/blog\/2022\/06\/06\/apple-m2\/","title":{"rendered":"Apple M2"},"content":{"rendered":"<p><a href=\"https:\/\/www.apple.com\/newsroom\/2022\/06\/apple-unveils-m2-with-breakthrough-performance-and-capabilities\/\">Apple<\/a> (<a href=\"https:\/\/www.macrumors.com\/2022\/06\/06\/apple-announces-m2-chip-with-support-for-up-to-24gb-memory\/\">MacRumors<\/a>, <a href=\"https:\/\/news.ycombinator.com\/item?id=31643610\">Hacker News<\/a>):<\/p>\n<blockquote cite=\"https:\/\/www.apple.com\/newsroom\/2022\/06\/apple-unveils-m2-with-breakthrough-performance-and-capabilities\/\">\n<p>Built using second-generation 5-nanometer technology, M2 takes the industry-leading performance per watt of M1 even further with an 18 percent faster CPU, a 35 percent more powerful GPU, and a 40 percent faster Neural Engine. It also delivers 50 percent more memory bandwidth compared to M1, and up to 24GB of fast unified memory.<\/p>\n<p>[&#8230;]<\/p>\n<p>The media engine includes a higher-bandwidth video decoder, supporting 8K H.264 and HEVC video.<\/p>\n<p>Apple&rsquo;s powerful ProRes video engine enables playback of multiple streams of both 4K and 8K video.<\/p>\n<\/blockquote>\n\n<p>Previously:<\/p>\n<ul>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2022\/06\/06\/13-inch-macbook-pro-2022\/\">13-inch MacBook Pro 2022<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2022\/06\/06\/macbook-air-2022\/\">MacBook Air 2022<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2022\/03\/08\/apple-m1-ultra\/\">Apple M1 Ultra<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2021\/10\/18\/apple-m1-pro-and-m1-max\/\">Apple M1 Pro and M1 Max<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2020\/11\/11\/the-apple-silicon-m1\/\">The Apple Silicon M1<\/a><\/li>\n<\/ul>\n\n<p id=\"apple-m2-update-2022-06-10\">Update (2022-06-10): <a href=\"https:\/\/semianalysis.substack.com\/p\/apple-m2-die-shot-and-architecture?s=r\">Dylan Patel<\/a>:<\/p>\n<blockquote cite=\"https:\/\/semianalysis.substack.com\/p\/apple-m2-die-shot-and-architecture?s=r\"><p>M2, codenamed Staten, is generally based on the same IP blocks as A15, codenamed Ellis. The codenames being based on some of New York&rsquo;s most well-known islands which should be a hint to how closely related these architectures are. A lot of the disappointment in performance uplift comes from weak gen-on-gen gains given the nearly 2 yearlong gap versus M1.<\/p><p>[&#8230;]<\/p><p>We <a href=\"https:\/\/semianalysis.com\/apple-cpu-gains-grind-to-a-halt-and-the-future-looks-dim-as-the-cpu-engineer-exodus-to-nuvia-and-rivos-impact-starts-to-bleed-in\/\">discussed this in the past<\/a>, but a lot of the slow down stems from Apple losing leagues of amazing engineers to firms such as <a href=\"https:\/\/semianalysis.com\/apple-cpu-gains-grind-to-a-halt-and-the-future-looks-dim-as-the-cpu-engineer-exodus-to-nuvia-and-rivos-impact-starts-to-bleed-in\/\">Nuvia and Rivos<\/a>.<\/p>\n<p>[&#8230;]<\/p>\n<p>The funkiness of Apple&rsquo;s marketing image does mean there is an error window of about 3% after the die was scaled in size.<\/p>\n<p>[&#8230;]<\/p>\n<p>The [P] core itself is 21% larger than in M1, and 7% larger than A15. The big area of gen-on-gen growth is with the shared L2 cache which has gone from 12MB to 16MB compared to both M1 and A15.<\/p>\n<p>[&#8230;]<\/p>\n<p>One very interesting change is that the ROB appears smaller in the Avalanche core that is found in A15 and M2 versus the Firestorm core found in M1 and A14.<\/p>\n<p>[&#8230;]<\/p>\n<p>The E-Core was the main unit of change from a CPU perspective from the A14 to A15 and that holds true here.<\/p>\n<p>[&#8230;]<\/p>\n<p>The combo of minor wafer price increases, larger dies from 118.91mm2  to 155.25mm2, and more expensive memory hurts [costs] a lot.<\/p><\/blockquote>\n\n<p id=\"apple-m2-update-2022-06-16\">Update (2022-06-16): See also: <a href=\"https:\/\/news.ycombinator.com\/item?id=31689366\">Hacker News<\/a>.<\/p>\n\n<p id=\"apple-m2-update-2024-05-03\">Update (2024-05-03): See also: <a href=\"https:\/\/eclecticlight.co\/2024\/01\/15\/why-the-m2-is-more-advanced-that-it-seemed\/\">Howard Oakley<\/a> (<a href=\"https:\/\/news.ycombinator.com\/item?id=38998313\">Hacker News<\/a>).<\/p>","protected":false},"excerpt":{"rendered":"<p>Apple (MacRumors, Hacker News): Built using second-generation 5-nanometer technology, M2 takes the industry-leading performance per watt of M1 even further with an 18 percent faster CPU, a 35 percent more powerful GPU, and a 40 percent faster Neural Engine. It also delivers 50 percent more memory bandwidth compared to M1, and up to 24GB of [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"apple_news_api_created_at":"2022-06-06T19:56:59Z","apple_news_api_id":"f98c55e8-6970-4552-abe0-130faa27781a","apple_news_api_modified_at":"2024-05-03T13:40:08Z","apple_news_api_revision":"AAAAAAAAAAAAAAAAAAAABA==","apple_news_api_share_url":"https:\/\/apple.news\/A-YxV6GlwRVKr4BMPqid4Gg","apple_news_coverimage":0,"apple_news_coverimage_caption":"","apple_news_is_hidden":false,"apple_news_is_paid":false,"apple_news_is_preview":false,"apple_news_is_sponsored":false,"apple_news_maturity_rating":"","apple_news_metadata":"\"\"","apple_news_pullquote":"","apple_news_pullquote_position":"","apple_news_slug":"","apple_news_sections":"\"\"","apple_news_suppress_video_url":false,"apple_news_use_image_component":false,"footnotes":""},"categories":[2],"tags":[1750,2307,2221,1533,30,260,1221],"class_list":["post-36086","post","type-post","status-publish","format-standard","hentry","category-technology","tag-apple-event","tag-apple-hardware-announcement","tag-apple-m2","tag-h-265hevc","tag-mac","tag-processors","tag-wwdc"],"apple_news_notices":[],"_links":{"self":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/36086","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/comments?post=36086"}],"version-history":[{"count":5,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/36086\/revisions"}],"predecessor-version":[{"id":43079,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/36086\/revisions\/43079"}],"wp:attachment":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/media?parent=36086"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/categories?post=36086"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/tags?post=36086"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}