Jump to content
Search In
  • More options...
Find results that contain...
Find results in...


  • Content Count

  • Joined

  • Last visited


This user doesn't have any awards

About DoTr

  • Title
  1. Nobody knows yet except AMD, also remember that TSMC cannot pump out enough Ryzen 5000 so I don't think AMD will release them anytime soon.
  2. Yeah, but for DL and a lot of other compute task, CUDA is still the standard as it works better than anything else.
  3. I wish ROCm or any open-source standard will beat Nvidia CUDA and be the industry standard, as that is the only reason a lot of ppl uses their card/accelerator
  4. It's like Nvidia desperately trying to beat AMD as they fear this gen will be one of the last gen of their dominance, as AMD starts to produce MCM GPUs, they will lose
  5. I don't think that this will become a reality till the end of this decade, as Intel haven't even made a prototype chip yet, like photonics
  6. So what if you buy something by a bot and after 2-3 years you decide to sell it ?
  7. Actually, you can try these in Google's Colaboratory so it is kind of useless to buy a physical card assume that the training time of your model is less than 12 hrs.
  8. How about a video about cold computer,Linus
  9. do a watercooling loop with Nitrogen for evaporating and a pump and then use a cryocooler to cool them off.