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

AMD reckons it can win the high-end GPU battle

techradar.com

Post reply on HN
Print view View original

61–70 of 160 posts

Re: AMD reckons it can win the high-end GPU battle

#61

Post by jchw »

atq2119 wrote: post #43
jamesblonde wrote: post #30

The big problem right now is that ROCm, AMD's equivalent to Cuda for deep learning, is not supported for the consumer Radeon Navi cards. I had hoped it would be supported in ROCm 3.0 when that was released - but there has been no official word, which is worrying. If AMD are to compete in the GPU/DeepLearning space, it will be because they have hardware that is competitive (not even as good as Nvidia), low cost, and d…

I agree that the lack of (official) Navi support is just bad strategy on AMD's part, but I disagree with your numbers. Their goal needs to be performance parity or dominance, and then perhaps offer a slight discount. That's how they're succeeding with Zen on CPUs. Offering the kind of steep discount you write about is just bad business.

From a consumer perspective Ryzen certainly feels like a steep discount. Was there a comparable price/perf to 3900X/3950X in the Intel world? Last I looked it seemed like you had to hop ship to Xeon with more expensive boards and really expensive CPUs to get something similar on paper.

It looks like the 10980XE is the best answer. But in fairness, I believe it and its pricing was exactly an answer to Ryzen 9.

Re: AMD reckons it can win the high-end GPU battle

#63

Post by proverbialbunny »

omegabravo wrote: post #29
chao- wrote: post #12

Earlier quoted context omitted.

Same with a 580. Linux, many monitors, work, light gaming. Drivers are the first time I've ever not had issues with Linux graphics. Three years in I'm still waiting for the other shoe to drop. Where are the driver issues? I'm certain it was like a law of physics in Linux, but somehow, not this time, not for me?

I have 2x 24" monitors on Ubuntu 18.04.03 with a Radeon RX 580 I can't watch a video on Youtube without substantial tearing on Firefox or Chrome. I've followed close to 20 guides and tried a number of drivers which all fail provide any benefit. Running glxgears will run at 7400FPS, with minor tearing. My monitors don't have FreeSync or whatever it's called since they're pretty old (over 10 years). Since most guides a…

My condolences. On Nvidia there is a Full Composition Pipeline option in Nvidia driver settings which gets rid of vsync issues. It's odd it's not on by default.

Re: AMD reckons it can win the high-end GPU battle

#64

Post by dannyw »

jdc wrote: post #10
AmVess wrote: post #3

They aren't going to win anything until they fix their laughably bad drivers and keep them fixed. I have several Ryzens, but there's no way I'd go anywhere near their graphics cards.

I'm running an RX 570 on Linux and it works fine for my purposes (work, Steam games & Blizzard games under wine).

The driver issues are for the 5500, 5600, and 5700 cards. Your card is a gen out of date, so it's fine.

Re: AMD reckons it can win the high-end GPU battle

#65

Post by llukas »

pixelpoet wrote: post #20

AMD's rather old Radeon VII can really smash a 2080 Ti if you're doing relatively simple streaming computation, like say video processing. That 1TB/s HBM is no joke, and there's 16GB of it, at ~half the price of the 2080 Ti with 11GB. Nvidia's memory compression is very impressive and allows them to do better with a narrower memory bus in many situations (such as games), however if your data is not so compressible (o…

Did you manage to achieve 1TB/s?

https://www.sisoftware.co.uk/2019/08/01/amd-vega2-gpgpu/ BW test over there shows 627GB/s of actual BW.

Re: AMD reckons it can win the high-end GPU battle

#66

Post by ubercow13 »

omegabravo wrote: post #29
chao- wrote: post #12

Earlier quoted context omitted.

Same with a 580. Linux, many monitors, work, light gaming. Drivers are the first time I've ever not had issues with Linux graphics. Three years in I'm still waiting for the other shoe to drop. Where are the driver issues? I'm certain it was like a law of physics in Linux, but somehow, not this time, not for me?

I have 2x 24" monitors on Ubuntu 18.04.03 with a Radeon RX 580 I can't watch a video on Youtube without substantial tearing on Firefox or Chrome. I've followed close to 20 guides and tried a number of drivers which all fail provide any benefit. Running glxgears will run at 7400FPS, with minor tearing. My monitors don't have FreeSync or whatever it's called since they're pretty old (over 10 years). Since most guides a…

I have a 580. Have you tried turning on the in-driver vsync option? AMD's implementation of it seems the best to me out of cards I've tried. You can turn it on while X is running easily using xrandr to see if it helps:

https://wiki.archlinux.org/index.php/AMDGPU#Tear_free_render...

Re: AMD reckons it can win the high-end GPU battle

#67

Post by SCdF »

_bxg1 wrote: post #49

AMD cards don't yet have any raytracing support, right? I know it's a young technology, but they shouldn't be dragging their feet on it if they want to make a serious push for the top.

Real time ray tracing hardware is in a funny place right now.

Firstly, it's not really as impressive as it sounds. You aren't going to be playing a game where you explore a house of mirrors any time soon. Control is a really good implementation, and it's so good it makes it really clear how quickly it falls over.

Better than not ray tracing, but nowhere near non-real time traditional ray tracing.

Secondly, at least with the current generation of RTX, the performance hit you take is criminal. We're talking 40%. If you're most people, who buy a graphics card to a budget based on your requirements (say 1440p/60, or 1080p/144, or whatever), supporting ray tracing means you either need to massively over spend (in my calculations about 6 months ago, I would have had to double my budget), or drop your quality presumptions in resolution and framerate drastically.

Which brings us to third: support. RTX has been out for over a year, and there is really only 2-3 games where RTX makes any kind of interesting visual difference, and really only 1 (Control) that you're actually going to actively notice after playing for more than 5 minutes.

AFAICT then, RTX is useful as a fun demo to play around with for a few minutes, before disabling it and getting your framerate back so you can actually play the game, and for absurdly rich people (which is convenient for nVidia, because absurdly rich streamers have normalised 1080p gaming on 2080tis for awhile now).

I am looking forward to seeing the shape real time ray tracing takes on consoles, because I presume that will determine the true shape for the next decade or so.

Re: AMD reckons it can win the high-end GPU battle

#68

Post by melbourne_mat »

dnautics wrote: post #58
jamesblonde wrote: post #52

Earlier quoted context omitted.

Cuda is a proprietary Nvidia framework. You don't need cuda support to train deep learning models on TensorFlow. ROCm also works - and is built by AMD and is open-source.

Have you tried installing rocm? Last I checked two months ago you had to run a Ubuntu 16.04 container on Ubuntu 18.04 because the amd drivers were only compiled for bionic and the rocm software was only compiled for xenial.

I've been running rocm directly on Ubuntu 19.04 for a while now. I didn't have to build from source either. It's odd that they haven't updated their docs about this yet.

Re: AMD reckons it can win the high-end GPU battle

#69

Post by Kliment »

amerine wrote: post #33
nyjah wrote: post #32

AMD cards also work with hackintosh builds. Some of the cards work seamlessly, others take minor config, but much better than the nVidia support these days.

Any recent hackintosh build guide recommendations?

Not used it, but this was posted on HN a few days ago https://infinitediaries.net/my-2020-hackintosh-hardware-spec...

Re: AMD reckons it can win the high-end GPU battle

#70

Post by melbourne_mat »

unnouinceput wrote: post #19

And when that day comes, I will buy it. But for now I will go with nVidia. Also I badly need same CUDA codebase/documentation on AMD part as well to make such a move. ML is such a breeze when you throw CUDA at it these days.

AMD has something called HIP which is a portable version of CUDA (compiles to either nvidia or amd hardware). They made a tool called HIPPIFY which can auto translate CUDA source to HIP. Haven't used it myself so I can't comment on it's effectiveness.
Post reply on HN