Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

CUDA Tile Open Sourced

github.com

Post reply on HN
Print view View original

31–40 of 111 posts

Re: CUDA Tile Open Sourced

#31

Post by xmorse »

bigyabai wrote: post #18
xmorse wrote: post #10

Writing this in Mojo would have been so much easier

Use-cases like this are why Mojo isn't used in production, ever. What does Nvidia gain from switching to a proprietary frontend for a compiler backend they're already using? It's a legal headache. Second-rate libraries like OpenCL had industry buy-in because they were open . They went through standards committees and cooperated with the rest of the industry (even Nvidia) to hear-out everyone's needs. Lattner gave up…

Kernels now written in Mojo were all in hand written in MLIR like in this repo. They made a full language because that's not scalable, a sane language is totally worth it. Nvidia will probably end up buying them in a few years.

Re: CUDA Tile Open Sourced

#32

Post by itsthecourier »

bigyabai wrote: post #18
xmorse wrote: post #10

Writing this in Mojo would have been so much easier

Use-cases like this are why Mojo isn't used in production, ever. What does Nvidia gain from switching to a proprietary frontend for a compiler backend they're already using? It's a legal headache. Second-rate libraries like OpenCL had industry buy-in because they were open . They went through standards committees and cooperated with the rest of the industry (even Nvidia) to hear-out everyone's needs. Lattner gave up…

what about a fourty feet pole? would it be viable?

Re: CUDA Tile Open Sourced

#33

Post by llmslave2 »

xmorse wrote: post #10

Writing this in Mojo would have been so much easier

I really want Mojo to take off. Maybe in a few years. The lack of an stdlib holds it back more than they think, and since their focus is narrow atm it's not useful for the vast majority of work.

Re: CUDA Tile Open Sourced

#34

Post by reactordev »

fragmede wrote: post #22
reactordev wrote: post #12

Earlier quoted context omitted.

In this day and age, asking questions about what something is is a minefield of “just ask AI” and “You should know this”. Let’s stop putting down people who ask questions and root out those that have shitty answers.

I get why it feels frustrating when someone snaps "just google it." Nobody likes feeling dumb. That said, there’s a meaningful difference between asking a genuine question and demanding that every discussion be padded to accommodate readers who won’t even type four letters into a search bar. Expecting complete spoon-feeding in technical threads isn’t curiosity; it’s a refusal to engage. Learning requires participatio…

Easy, if that’s how you feel, skip the comment and don’t engage.

Telling people who want to have that participation and discussion to “RTFM” is not a good response.

Often you’ll come across the authors on these posts that can shed direct, 1st person evidence, of what we’re talking about.

So please, when someone asks “what is that?” Don’t respond with “RTFM”.

Re: CUDA Tile Open Sourced

#35

Post by VTimofeenko »

fragmede wrote: post #22
reactordev wrote: post #12

Earlier quoted context omitted.

In this day and age, asking questions about what something is is a minefield of “just ask AI” and “You should know this”. Let’s stop putting down people who ask questions and root out those that have shitty answers.

I get why it feels frustrating when someone snaps "just google it." Nobody likes feeling dumb. That said, there’s a meaningful difference between asking a genuine question and demanding that every discussion be padded to accommodate readers who won’t even type four letters into a search bar. Expecting complete spoon-feeding in technical threads isn’t curiosity; it’s a refusal to engage. Learning requires participatio…

> Learning requires participation

I won't argue, but there is a middle ground between articles consisting of pure JAFAs and this:

> accommodate readers who won’t even type four letters into a search bar

I think it helps if acronyms are expanded at least once or in a footnote so that the potential new reader can follow along and does not need to guess what ACMV^ means.

^: Awesome Combobulating Method by VTimofeenko, patent pending.

Re: CUDA Tile Open Sourced

#36

Post by bigyabai »

xmorse wrote: post #31
bigyabai wrote: post #18

Earlier quoted context omitted.

Use-cases like this are why Mojo isn't used in production, ever. What does Nvidia gain from switching to a proprietary frontend for a compiler backend they're already using? It's a legal headache. Second-rate libraries like OpenCL had industry buy-in because they were open . They went through standards committees and cooperated with the rest of the industry (even Nvidia) to hear-out everyone's needs. Lattner gave up…

Kernels now written in Mojo were all in hand written in MLIR like in this repo. They made a full language because that's not scalable, a sane language is totally worth it. Nvidia will probably end up buying them in a few years.

I don't think Nvidia would acquire Mojo when the Triton compiler is open source, optimized for Nvidia hardware and considered a industry standard.

Re: CUDA Tile Open Sourced

#38

Post by boredatoms »

3abiton wrote: post #11
xmorse wrote: post #10

Writing this in Mojo would have been so much easier

It's barely gaining adoption though. The lack of buzz is a chicken and egg issue for Mojo. I fiddled shortly with it (mainly to get it working some of my pythong scripts), and it was suprisingly easy. It'll shoot up one day for sure if Latner doesn't give up early on it.

I feel like its in AMD/Intel/G’s interest to pile a load of effort into (an open source) mojo

Re: CUDA Tile Open Sourced

#40

Post by Conscat »

Q6T46nT668w6i3m wrote: post #8
pjmlp wrote: post #5

Earlier quoted context omitted.

For NVidia it suffices this is a Python JIT allowing programming CUDA compute kernels directly in Python instead of C++, yet another way how Intel and AMD, alongside Khronos APIs, lag behind in great developer experiences for GPU compute programming. Ah, and Nsight debugging also supports Python CUDA Tiles debugging. https://developer.nvidia.com/blog/simplify-gpu-programming-w...

Slang is a fantastic developer experience.

I work at Nvidia, and my team is using Slang for all of our (numerous and non-trivial) kernels because its automatic differentiation type system is so nice.
Post reply on HN