Hacker News new | ask | show | jobs
by ieidkeheb 515 days ago
Nope ... IMO AMD cannot compete on software with nvidia. I bought an rx580 to test rocm/tensorflow ... Only for it to be a buggy mess that was discontinued for support in the next version.

AMD needs to invest a Fsck load of money in software... Until then they can have the greatest compute cards in the world.but it will.mean nothing
1 comments
bavell 515 days ago
Isn't rx580 like 4 gens behind now? It was released in 2017. Probably not the right card for anything AI.
link
imtringued 515 days ago
Why would anyone buy a new AMD card if the expectation is that the new one won't work either after support runs out? I use AMD at home and Nvidia A100s at work. There is no need to upgrade an old GPU to a new GPU if all it does is act as a fancy iGPU.
link
KeplerBoy 514 days ago
Because only the new ones are officially supported by AMDs compute stack?
link
gymbeaux 514 days ago
To be fair Nvidia is the de-facto king of “planned obsolescence” and “remove features for no reason other than to force people to pay more $$$”. I think they’re even worse than Apple in this regard.

My favorite one of many examples of this is when Nvidia said “okay, fine, we’ll allow customers to enable G-Sync (adaptive refresh) on any display, but only 1000 series and newer GPUs!” No hardware limitation for this, they just didn’t want to give any 900-series holdouts a reason not to upgrade.

Then there’s the arbitrary lock on using consumer Nvidia GPUs in passthrough on a level 1 hypervisor. Sometimes there are unofficial workarounds but why do I have to go through that hassle at all? Ain’t nobody realistically going to buy consumer grade GPUs to throw in datacenter racks… but even if they were, so what? It’s their hardware, they bought it, let them use it. No reason whatsoever to block passthrough on consumer cards except $$$.

link
ieidkeheb 514 days ago
Yes this was years ago... Pre covid ... I thought the fact I used tensoflow as the target library I thought would flag that for others
link
gymbeaux 514 days ago
I will say AMD seems to have come a long way since 2020/2021. I also messed around with an RX580 and ROCm on Ubuntu Server and while I wasn’t as experienced in the world of ML/Data Science then, I remember encountering a roadblock or two when following the official install guide. I haven’t had an AMD GPU since, but I’ve read and heard many good things. Supposedly Tensorflow and PyTorch work more or less out of the box with the right AMD GPU.
link