ROCm VS tensorflow_macos

Yep, did exactly that. IMO he threw a fit, even though AMD was working with him squashing bugs. https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...

I don't know if they'll ultimately succeed or not, but they at least seem to be putting genuine effort into this. ROCm releases are coming out at a relatively nice clip[1], including a new release just a week or two ago[2].

[1]: https://github.com/RadeonOpenCompute/ROCm/releases

[2]: https://www.phoronix.com/news/AMD-ROCm-5.7-Released

Ok, I wonder what's wrong. maybe it's this? https://stackoverflow.com/questions/4959621/error-1001-in-cl...

Nope. Anything about this on the arch wiki? Nope

This bug report[2] from 2021? Maybe I need to update my groups.

[2]: https://github.com/RadeonOpenCompute/ROCm/issues/1411

    $ ls -la /dev/kfd

HMM is, I believe, a Linux feature.

AMD added HMM support in ROCm 5.0 according to this: https://github.com/RadeonOpenCompute/ROCm/blob/develop/CHANG...

Woot AMD now supports APU? I sold my notebook as i hit a wall when trying rocm [1] Is there a list oft Wirkung apu's ?

[1] https://github.com/RadeonOpenCompute/ROCm/issues/1587

I think geohot is working on that with tinygrad. Activity on the ROCm repo seems to have increased a lot recently:

https://github.com/RadeonOpenCompute/ROCm/graphs/code-freque...

Last I heard he's abandoned working with AMD products.

https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...

[1] links to https://github.com/RadeonOpenCompute/ROCm/issues/2198 which has all the context (driver bugs, vowing to stop using AMD, Lisa Su's response that they're committed to fixing this stuff, a comment that it's fixed)

They're talking about the meltdown he had on stream [1] (in front of the mentioned pirate flag), that ended with him saying he'd stop using AMD hardware [2]. He recanted this two weeks after talking with AMD [3].

Maybe he'll succeed, but this definitely doesn't scream stability to me. I'd be wary of investing money into his ventures (but then I'm not a VC, so what do I know).

[1] https://www.youtube.com/watch?v=Mr0rWJhv9jU

[2] https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...

[3] https://twitter.com/realGeorgeHotz/status/166980346408248934...

He flamed out, then is back after Lisa Su called him (lmao)

https://geohot.github.io/blog/jekyll/update/2023/05/24/the-t...

https://www.youtube.com/watch?v=Mr0rWJhv9jU

https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...

https://geohot.github.io/blog/jekyll/update/2023/06/07/a-div...

On a personal level that youtube doesn't make him come off looking that good... like people are trying to get patches to him and generally soothe him/damage control and he's just being a bit of a manchild. And it sounds like that's the general course of events around a lot of his "efforts".

On the other hand he's not wrong either, having this private build inside AMD and not even validating official, supported configurations for the officially supported non-private builds they show to the world isn't a good look, and that's just the very start of the problems around ROCm. AMD's OpenCL runtime was never stable or good either and every experience I've heard with it was "we spent so much time fighting AMD-specific runtime bugs and specs jank that what we ended up with was essentially vendor-proprietary anyway".

On the other other hand, it sounds like AMD know this is a mess and has some big stability/maturity improvements in the pipeline. It seems clear from some of the smoke coming out of the building that they're cooking on more general ROCm support for RDNA cards, and generally working to patch the maturity and stability issues he's talking about. I hate the "wait for drivers/new software release bro it's gonna fix everything" that surrounds AMD products but in this case I'm at least hopeful they seem to understand the problem, even if it's completely absurdly late.

Some of what he was viewing as "the process happening in secret" was likely people doing rush patches on the latest build to accommodate him, and he comes off as berating them over it. Again, like, that stream just comes off as "mercurial manchild" not coding genius. And everyone knew the driver situation is bad, that's why there's notionally alpha for him to realize here in the first place. He's bumping into moneymakers, and getting mad about it.

https://github.com/apple/tensorflow_macos is no longer needed

Tensorflow has a CoreML enabled version which run on ANE.

https://github.com/apple/tensorflow_macos

Apple did some work to optimize tensorflow for M1, can be found here https://github.com/apple/tensorflow_macos It's alpha, but works fine, I tried it

I was able to install this fairly easily (much more so then the crap they dumped out here - https://github.com/apple/tensorflow_macos. Just take a look at the 200 github issues that were ignored for the most part...)

I also noticed that in my project I got a decent speedup immediately when executing my model, but I have not run any benchmarks.

But, where do you go to file bugs? Ask questions? etc. I am not a big Mac developer, so is there something I don't know?

https://github.com/apple/tensorflow_macos you mean this one?

So the question I have now is which one is faster/better suited for my puropses. M1 got [hyped](https://machinelearning.apple.com/updates/ml-compute-training-on-mac) a lot so I thought the M1 would savage my desktop (and acutally the hype biased my purchase decision), but well its only slightly better (like 1.2-1.5x faster in my cifar10 benchmark) and I wonder if its worth the effective 1-2 GB of RAM left on MacOS vs the \~14 GB on my Linux machine. Further there is Colab and I can't really tell which one will win the race, since Colab limits resources by demand but also allows distributed fit on cloud TPUs, which would introduce some extra coding efforts. Then again I have to say: so does ML on Apple Silicon, which comes with [a handful of limitations](https://github.com/apple/tensorflow_macos#additional-information), a [peculiar MiniConda setup](https://github.com/apple/tensorflow_macos/issues/153), a [lot of issues](https://github.com/apple/tensorflow_macos/issues) (also severe ones, like training errors etc., problems which I would not even recognize) which are actually not really being worked on.

Following this site's instructions, I tried multiple ways of downloading and installing Miniforge, including Homebrew, CI pipeline, and by downloading the shell files from here.

You might be interested in this for your M1 MBA: https://github.com/apple/tensorflow_macos

I did find this thoguh: https://github.com/apple/tensorflow_macos Take this with a grain of salt though. I don't own a M1 (although I do save up for a new laptop and am thinking about it :) ).