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

131–140 of 160 posts

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

#131

Post by pjmlp »

xiphias2 wrote: post #129
pjmlp wrote: post #90

Earlier quoted context omitted.

Does HIP support all the programming languages that are able to target CUDA, like Julia, Numba, .NET, Java, Haskell, Fortran, C++? Khronos did a big mistake to keep pushing C as the only compute language for so long, and it remains to be seen how much adoption SPIR-V is able to actually take from PTX. So unless HIP actually matches PTX, it is a non-starter.

In theory HIP is a modified LLVM, but as far as I know Julia uses a modified LLVM as well, so unless they are upstreamed, we can't use them together :( I guess I'm staying with NVIDIA with developer laptops for a long time, and maybe using AMD for ultrabook.

Except that some of the languages that target CUDA do so via PTX, not by migrating their compiler backends into LLVM.

So if HIP will only work with LLVM, that is also a non-starter.

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

#132

Post by wruza »

Another issues with AMD are power, cooling and deadlines. Our local term for Vega 56/64 is electro-chargrill, which is not far from true. Those who bought them report that PSU and tower-cooling costs are above normal. AMD can do that again, blow dust in their eyes and roll out a card that could melt your ssd and sound like a jet turbine. Also they are known for “soon” marketing, so that you wait for a year, postponing games that you could play right now with a decent nvidia card.

I think they have their own vision of high-end, while frametime enthusiasts still struggle with making ryzen chips to not stutter three times a second. Measures include carefully choosing a motherboard, a memory kit, finding right timings, right cooling curves, etc. And still stock ring-bused 8700 beats easily any infinity-glued cpu in 0.1% low by a margin. Streamers love ryzen though, as it allows to stream from additional cores and microstutters are irrelevant on youtube.

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

#133

Post by ls612 »

SCdF wrote: post #67
_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 w…

Since both next-gen consoles have realtime ray tracing support my guess is that adoption of ray tracing will massively increase in games next year. In fact I'd bet that at some point in the first couple years of this next generation we will see a game where ray tracing is used to make lighting a game mechanic in itself as opposed to merely eye candy.

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

#134

Post by Dylan16807 »

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.

Per core performance matters on a desktop. Per GPU performance doesn't really matter for doing giant machine learning jobs.

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

#135

Post by Shorel »

perceptronas wrote: post #11
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.

Agree, I dropped Linux due bad graphics drivers (AMD)

They are good now.

I am writing this comment in a laptop with Radeon Vega 8 graphics and Ryzen 5 CPU running Ubuntu 19.10.

I am playing Audiosurf2 in the second workspace.

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

#136

Post by Dylan16807 »

SCdF wrote: post #111
hnuser123456 wrote: post #73

Earlier quoted context omitted.

>Secondly, at least with the current generation of RTX, the performance hit you take is criminal. We're talking 40%. I never really understood this argument. If you really need tons of frames for a competitive game, just turn it off. Otherwise, the games that implement it correctly show a marked visual improvement, that can't be computed any faster as far as we know. It's like saying 4k renders 4x slower than 1080p,…

> I never really understood this argument. If you really need tons of frames for a competitive game, just turn it off. I think "if you need tons of frames" may be where your misunderstanding is coming from: most of us don't have tons of frames to give (especially in brand new AAA games that are the only ones implementing this technology). For most people (and you can see this in sales data and hardware surveys), if t…

> most of us don't have tons of frames to give (especially in brand new AAA games that are the only ones implementing this technology).

Especially because it's probably first person and over-the-shoulder games that probably get the best benefit from RTX, but those are the same games where a high frame rate improves playability the most. Not 'tons' of frames to be 'competitive', but 144Hz to be able to perform the actions you intend to perform without frustration. So at that framerate, in a pretty game, maybe you could run RTX at 720p? But resolution is pretty nice too, so the performance hit really is a big deal.

The kind of game where you'd get 300Hz and can burn frames on a whim isn't the kind of game that uses RTX, at least so far. Or you'd have to drop the other settings to low, which kind of defeats the point of improved visuals.

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

#137

Post by dnautics »

melbourne_mat wrote: post #68
dnautics wrote: post #58

Earlier quoted context omitted.

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.

Cool, thanks!! I'll take a look at it

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

#138

Post by philjohn »

dannyw wrote: post #64
jdc wrote: post #10

Earlier quoted context omitted.

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.

Huh, launch day 5700 XT and zero issues ... then again, I don't play older titles which seems to have the most issues.

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

#139

Post by WWLink »

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.

They do, but it's hard to get a replacement for my 1070ti. :( The rx580s are reasonably priced and have a good rep for being reliable! But compared to a 1070ti they are less capable. A vega 56/64 would be perfect, but they're hard to find new now. The 5700xts seem to be a disaster.

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

#140

Post by CountSessine »

ksec wrote: post #116
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…

Did they mention it will ever be supported on Navi? It seems to be AMD is on its way to have specialise Architecture for each segment. Navi and Navi Refresh and Gaming GPU without Ray Tracing, so basically low end to middle segment. Navi 2 support Ray Tracing and aiming at higher quality possible. Arcturus; the uArch name for Vega successor ( also known as Vega 30 ), was suppose to be double the size of VEAG VII, wit…

It doesn’t make sense at all. An enormous number of people who work on GPGPU will develop on consumer hardware before they move up to cloud computing or a Quadro or something. Trying to segment the market like this is based on a misunderstanding of developer needs and preferences. Which is pretty typical of ATI/AMD unfortunately.
Post reply on HN