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

Documentation for the AMD 7900XTX

github.com

Post reply on HN
Print view View original

51–60 of 154 posts

Re: Documentation for the AMD 7900XTX

#51

Post by llm_trw »

andrewmcwatters wrote: post #50
roenxi wrote: post #8

So for reference, this geohot is George Hotz who has a company Tiny Corp [0] in the space. Among a long list of things, he had a moment in the spotlight recently for a long rant [1] where he "gave up on AMD" because their drivers sucked more than he expected. The situation is reasonably complex - AMD have some programmers working on ROCm who seemed to be operating at standard fare when that is really not what AMD nee…

It was particularly hard to listen to himself admit that he basically became unpaid QA for AMD. Like, dude, you’re making the same junior mistake people writing apps for the App Store make. It’s not your platform.

If the AMD code makes it into the kernel, like their graphics drivers did, then we've won because it will just work on every kernel update.

Compared to now where AMD drivers just don't work and NVidia drivers only work with the right blobs installed I'd be willing to take a paycut for 6 months to have 10 years of painless development.

That said I jumped ship to NVidia since I need to work and not spend all my time trying to get servers to the point that they can work.

Re: Documentation for the AMD 7900XTX

#52

Post by threeseed »

andrewmcwatters wrote: post #50
roenxi wrote: post #8

So for reference, this geohot is George Hotz who has a company Tiny Corp [0] in the space. Among a long list of things, he had a moment in the spotlight recently for a long rant [1] where he "gave up on AMD" because their drivers sucked more than he expected. The situation is reasonably complex - AMD have some programmers working on ROCm who seemed to be operating at standard fare when that is really not what AMD nee…

It was particularly hard to listen to himself admit that he basically became unpaid QA for AMD. Like, dude, you’re making the same junior mistake people writing apps for the App Store make. It’s not your platform.

As a developer you're always building on top of something you don't control.

At least with the App Store you make pretty good money.

It's worse when you have companies who have APIs you need that you know they don't care about.

Re: Documentation for the AMD 7900XTX

#53

Post by lannisterstark »

roenxi wrote: post #8

So for reference, this geohot is George Hotz who has a company Tiny Corp [0] in the space. Among a long list of things, he had a moment in the spotlight recently for a long rant [1] where he "gave up on AMD" because their drivers sucked more than he expected. The situation is reasonably complex - AMD have some programmers working on ROCm who seemed to be operating at standard fare when that is really not what AMD nee…

>I'm cheering him on, even though his complaints were a little melodramatic.

I've really soured on him when he literally went "I'm going to fix twitter search, hire me elon" and then went to public saying "Hey, want an internship? Fix it, and then MIT license your code(so he could use it lol), and maybe we can talk - oh btw I have no real authority to give anyone an internship."

He might be a brilliant programmer and problem solver, but that incident left a very sour "Grifter" vibes.

Re: Documentation for the AMD 7900XTX

#54

Post by shard972 »

glimshe wrote: post #44

I used to be an AMD diehard fan. Bought their processors and GPUs for close to 20 years until I simply couldn't take it anymore - 5 years ago I started buying NVIDIA GPUs with Intel CPUs and honestly never looked back. Sure I pay more, but it's worth paying more for reliability and software support. Anything else and I'm losing money out of ideology to give to a business that doesn't have its act together.

As someone who basicially grew up with Intel/Nvidia but now running AMD/AMD, while i could agree with you on the GPU side that AMD still has more work to do, I would hard disagree on the CPU side.

Especially with the X3D line, AMD cpus can absolute smoke intel and at worst, come within a single percentage of performance in usually single thread bound scenarios.

Re: Documentation for the AMD 7900XTX

#55

Post by llm_trw »

jimbob45 wrote: post #41
georgehotz wrote: post #32

Earlier quoted context omitted.

I have had multiple replies from Lisa Su on both Twitter and by e-mail. It doesn't help. AMD is structurally incapable of fixing these issues. They don't even have a 7900XTX in CI. Crashing the firmware is so trivial there's no way anyone fuzzed anything. They debug by the application, adding mitigations at many layers of the stack to make it work. While this strategy is fine for the 20 mainstream games that come out…

They don't even have a 7900XTX in CI. You read stories in the glory days of Microsoft where they would bend over backwards to ensure backwards compatibility [0]. Going from that to what you say is depressing. It’s actually hard for me to accept your statement because such a failure would not only require QA/the PM to be totally ignorant of current testing best practices, but also require HR to have catastrophically m…

The shocking thing about AMD in the last 5 years isn't that they got Ryzen to work, it's that they didn't screw it up within two releases. There are no other technology companies in the world who have a will to fail so ingrained in their corporate DNA as does AMD.

Re: Documentation for the AMD 7900XTX

#56

Post by llm_trw »

AnthonyMouse wrote: post #38
sashank_1509 wrote: post #36

Earlier quoted context omitted.

Nope, they basically open sourced their api which is kind of a worthless proposition. You would think this is malicious, trying to pretend as open source, but the whole thing is done so ineptly, it is just incompetence. Likely management has no idea what open source means and thinks releasing api code means open source and is good enough for customers to use your GPU. More concretely, what they open sourced calls clo…

> More concretely, what they open sourced calls closed source functions that run on the GPU which is where all the bugs are, and causes all the crashes. In particular, what they did was open source the drivers but not the firmware , and then when the firmware has bugs nobody outside the company can fix it because it's not open source.

Worth noting that is a step up from NVidia who moved their driver to the GPU and open sourced a configuration file.

Re: Documentation for the AMD 7900XTX

#58

Post by threeseed »

ein0p wrote: post #35
wmf wrote: post #30

Earlier quoted context omitted.

Making GPUs work properly requires years of effort so she needs a time machine to go back and start earlier.

[flagged]

> have him fix it to his liking

Like when he strolled into Twitter, acted like he knew better than everyone, delivered nothing and then left.

There is far more to achieving things in large companies than simply having great technical skills.

Re: Documentation for the AMD 7900XTX

#60

Post by atq2119 »

AnthonyMouse wrote: post #38
sashank_1509 wrote: post #36

Earlier quoted context omitted.

Nope, they basically open sourced their api which is kind of a worthless proposition. You would think this is malicious, trying to pretend as open source, but the whole thing is done so ineptly, it is just incompetence. Likely management has no idea what open source means and thinks releasing api code means open source and is good enough for customers to use your GPU. More concretely, what they open sourced calls clo…

> More concretely, what they open sourced calls closed source functions that run on the GPU which is where all the bugs are, and causes all the crashes. In particular, what they did was open source the drivers but not the firmware , and then when the firmware has bugs nobody outside the company can fix it because it's not open source.

Yes, that's a problem, but it's also a bit of an unfair dunk.

After all, your CPU almost certainly runs firmware with all the same issues. Not to mention all other GPUs from all other vendors.

Despite all of the noise-making, I don't think anybody has really convincingly made the case that the firmware quality is the main issue here, as opposed to the quality of the rest of the stack.

Post reply on HN