SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Technology Stocks : AMD, ARMH, INTC, NVDA
AMD 233.54-1.8%Nov 7 9:30 AM EST
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
From: neolib10/16/2025 2:05:22 PM
of 72186
 
Here is a fascinating example from a 3rd party of the inference d/p split for increased performance:

tomshardware.com

If they can do this with anyone's hardware why the CUDA moat still, at least in inference??

I'd think the Chinese would be very interested in this approach, assuming they aren't already doing so. I see that Huawei has embraced the d/p split with their next generation Ascend chips, if one can believe their PR on the subject. But this should play nicely with the wanna be GPU hordes coming in China.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  

HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News