NVLink is a connection between the CPUs and GPUs , so between sockets. The Infinity Fabric is many things more as it's build within the CPU/GPU, provides a link between dies and across sockets. Infinity Fabric isn't a kind of hypertransport but a superset of it. NVLink 是 CPU 和 GPU之间的连接,也是插槽之间的连接。 Infinity Fabric (AMD) 具有更多功能,因为它构建在 CPU/GPU 内,提供芯片之间和跨插槽的链接。 Infinity Fabric 不是一种超传输,而是它的超集
@limitli1117 Жыл бұрын
Twitter有人推荐。看完感觉太厉害了。知识量强大。讲述清晰。❤
@yifter4043 Жыл бұрын
太讚了,等這個主題等好久,謝謝你
@kevinlantw Жыл бұрын
其實有點可惜沒有講到關於應用上MI300有多大的門檻要跨這件事。 看新聞,就知道所有在做AI的大公司都瘋狂的在搶NVIDIA的AI運算硬體,我都開玩笑說NVIDIA的產量限制了整個人類的進步XD 那為麼有更好的硬體不去用,還要跟人去搶NVIDIA的產品? 有原因的嘛~ 真的光是硬體設計夠優秀是沒有用的,沒辦法把軟體開發環境等整個生態系建立起來,搞得大家用起來門檻很高很麻煩,沒辦法“It just works",那就是失敗。大部份會去做AI Training的人剛開始入門的時候用就是學的某個框架,之後要大量使用的時候,也都會直覺得待在這個生態系。因為我只是要training model,專注的是思考新的訓練的方法,參數怎麼調等等,不太想花時間在轉換生態系這件事上面。舉個例子,大家用Windows,是生態系的關係,不是因為Windows有多好。Linux即使再好,再安全,再開放而且都能客製化還免費,這跟「一般使用者」沒有什麼關係,他們還是不想花時間在轉換生態系這件事上。再舉個例子,寫程式不就是有個基本的文字編輯器(notepad或vi)跟terminal就好了嗎?幹嘛要用IDE還被綁住? 如果今天是學術機構(不像企業有那麼強的時間跟競爭壓力),或有天才型工程師,能不受框架限制把所有硬體都運用自如,那很好啊?!就可以去用MI300或其它的硬體,沒必要被NVIDIA綁架。不過很可惜的是,真正需要大量AI硬體的大企業,他們有時間跟競爭的壓力,他們就是那個會被生態系綁架的那個「一般使用者」。
@stonk5603 Жыл бұрын
你終於回來了 等你好久
@張元儒 Жыл бұрын
您回來啦!!!!!!!!!
@Tech4AllYall Жыл бұрын
原來是連爺爺的部分啊
@petercandylee Жыл бұрын
From Tom’s Hardware The MI300 3D design allows for incredible data throughput between the CPU, GPU and memory dies while also allowing the CPU and GPU to work on the same data in memory simultaneously (zero-copy), which saves power, boosts performance, and simplifies programming.
Actually, in LLM, higher memory is way more important. If you have to sync intermediate values, it's a lot slower. So if the chip can hold the entire model, that would be the fastest, with data sharding only.
@amia0328 Жыл бұрын
終於更新了
@LightnessRevant Жыл бұрын
極端的例外: Crisis初代就是直接用未上市的G80晶片做開發平台
@tp27273529 Жыл бұрын
!!!!想說ig跟yt都沒有更新是不是不做了竟然又有影片了!!!
@Tech4AllYall Жыл бұрын
說真的,我即使是之前還有固定在更新影片的時候也都懶得更新ig哈哈哈😆
@sjcabbw Жыл бұрын
SOC, system on chip, 系統一直在被集成一個單一晶片. 所以根本無所謂 系統重要或晶片重要 , 因為今天的系統可能就是明天的晶片.
@張硯棠 Жыл бұрын
非常感謝解說如此清楚😀 最近IBM New Analogue Chip看來是很前瞻的設計,是否能講解一下😂 存算合一使是否才是打破馮諾依曼瓶頸?
There are a couple of reasons why MI300 is not selling 1. It is not ready - it won't be ready until next year 2024. 2. The older versions (MI250, MI100) are not selling well because the supporting software is not mature. But this will change because large software houses Microsoft, Pytorch, and Hugging Face are helping AMD to optimize its software. Large tech companies want to have a second source.
@watergod420 Жыл бұрын
挖賽,這支影片讓我茅塞頓開。不然我就是發佈會台下的那些華爾街笨蛋XD
@madebyaigeng2 ай бұрын
请问这些知识是什么书上可以学到呢
@ryoushousou Жыл бұрын
終於回來了。我都懷疑您是不是在美國遭遇槍擊案了🤣
@Tech4AllYall Жыл бұрын
I’m the one who knocks 😎
@WenRenChen-y5s Жыл бұрын
這頻道很專業 加油
@此名稱無法顯示14 күн бұрын
有人知道這個頻道還活著嗎?
@mikkeymask36111 ай бұрын
现在正式发布了,能不能发一期更新?谢谢!
@petercandylee Жыл бұрын
MI300 GPU chiplets share the unified memory. Can they not communicate with each other using the shared memory?