this post was submitted on 08 Jun 2024
355 points (96.6% liked)
Technology
59111 readers
3324 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Personally I'm an AMD guy, I don't like the proprietary approach Nvidia takes to everything.
But I have to admit, Nvidia has been on the ball for 30 years now, and it's very impressive what they have achieved.
I think the rest of the industry needs to pool together around an open standard, if they want to have a chance to compete against the near monopoly Nvidia has because of CUDA.
Is there anything fundamentally superior about Cuda over open CL?
Yes: market share. And Nvidia has the top performing cards on the market, so there's no reason to go with a competitor.
And inertia. Same reason x86/64 is still the king. Nobody wants to update their software to a new architecture
Exactly. People will do it if there's a big enough incentive, but that just doesn't exist for openCL.
I am not an AI programmer so I can't really say. But CUDA had a head start and was some years ago allegedly the best combo with Nvidia hardware for AI programming. Over a period of time a lot of companies/projects have come to use CUDA, and so it has an advantage both for compatibility and know how among many AI programmers.
It's kind of like how X86 has maintained a market lead on desktops and servers, despite ARM being very competitive. The change of API is disruptive and costly, so people stay with what already works.