随手摸下B200 (148SM)。Vector性能相比H100的提升比较常规(+25%)。全局原子CAS延迟是H100的2x，达到200ns，这大概就是MCM的代价。有意思的点在于wmma发生明显倒退，每SM性能回到了图形卡水平。本代大概只有tcgen05.mma可以跑出纸面tensor吞吐，这标志着计算卡重心逐渐转向类似NPU的TMEM？

David's random thoughts

随手摸下B200 (148SM)。Vector性能相比H100的提升比较常规(+25%)。全局原子CAS延迟是H100的2x，达到200ns，这大概就是MCM的代价。

有意思的点在于wmma发生明显倒退，每SM性能回到了图形卡水平。本代大概只有tcgen05.mma可以跑出纸面tensor吞吐，这标志着计算卡重心逐渐转向类似NPU的TMEM？

www.tg-me.com/tw/David& 39;s random thoughts/com.david_random/567

2.2K viewsApr 24 at 10:42

tg-me.com/david_random/567

Create: 2025-04-24
Last Update: 2025-06-01 08:58:18

BY David's random thoughts

Share with your friend now:
tg-me.com/david_random/567

David& 39;s random thoughts Telegram | DID YOU KNOW?

A Telegram spokesman declined to comment on the bond issue or the amount of the debt the company has due. The spokesman said Telegram’s equipment and bandwidth costs are growing because it has consistently posted more than 40% year-to-year growth in users.

Tata Power whose core business is to generate, transmit and distribute electricity has made no money to investors in the last one decade. That is a big blunder considering it is one of the largest power generation companies in the country. One of the reasons is the company's huge debt levels which stood at ₹43,559 crore at the end of March 2021 compared to the company’s market capitalisation of ₹44,447 crore.