Hacker News Reader

Comment by Zaheer | Hacker News Reader

How does this compare to AMD's latest card?

It doesn't. AMD only has low & mid-range cards ATM. Vega is supposed to be released in the first half of 2017, and working silicon has already been demoed, so it does look likely. Rumours have it at 12TFlops, so should be comparable to this card.

> Rumours have it at 12TFlops, so should be comparable to this card.

Comparable on paper perhaps, but Nvidia architectures tend to get more actual gaming performance per FLOP than AMD architectures do.

i.e. the AMD RX480 (5.8 TFLOPS) is 30% faster than the NV GTX1060 (4.4 TFLOPS) on paper, but in practice they perform more or less the same.

Even in titles where AMD performs especially well the advantage is around 10-15% in favor of the RX480 - still less than the specs would suggest.

Still the 480 is cheaper than the 1060.

Not true. Lowest price for 1060, 180$, lowest for 480, 185$. Granted, that's a 3gb model vs 4gb, but the prices are basically identical.

Newegg has a 4GB RX 480 for $179.99 right now:

https://www.newegg.com/Product/Product.aspx?Item=N82E1681412...

The 3GB 1060 is a cut down version (what the 470 is to 480).

It has nothing to do with that. It's about driver cpu overhead, game optimization and specific driver shader optimization.

It always been about what you stated. Christ, when me and my buddy ran the intel gaming DRG lab in 1997 we were testing all games (this is when SIMD came out, and we proposed stacking cores... but thats a different story) against optimizing (specifically Intel wanted to pay game companies to optimize against SIMD, and would give them $1MM for marketing if it could be proven the game (subjectivly) ran better on their Celeron processors vs AMDs anything... so they were paying devs to opt for the SIMD instructions and then using that as marketing material... it was a fun job.

aside: That was my personal golden age of gaming... Intel had an OC-48 to SC-5 building... so playing UO on 6 machines simultaneously when everyone else was modeming at 56K made us like gods against lag in that game... I still think fondly of that time.

Hmm, that's interesting. I've noticed that with the new 1000 line, NVIDIA has been giving away some games as an incentive. Every single time I've seen it, it's been a ubisoft game. There was probably a similar deal with Ubisoft this gen. Otherwise why would they be promoting those games so much?

It will more than likely demolish it in terms of raw performance; however, AMD's most recent cards are aimed at being more budget-friendly. An RX 480 will only set you back about $200-250 (compared with this $1200 beast of a card). You'll get more "bang for your buck" by going with an AMD card as opposed to a top-of-the-line model such as this one. That may change later this year when AMD releases their Vega architecture, as it's rumored to aim more at the high-end market (which is currently dominated by Nvidia).

And it appears that for titles using Vulkan or DX12 AMD sees a bigger uplift than NVidia cards switching to those APIs for reasons unknown.

NVidia has a killer driver team, which gives them a huge advantage. This advantage is lessened in the "lower-level" DX12 & Vulkan API's.

And on the other hand, Graphics Core Next was initially designed for low level APIs — they actually started the whole "low level API on desktop" trend with Mantle.

Reason are unknown but there are speculation. https://www.youtube.com/watch?v=nIoZB-cnjc0

This is a very good explanation/speculation which deals with the NV driver optimization for DX11 where they break up the draw calls between threads because the scheduler is software based where AMD is hardware based and can't do the same. In DX12 this isn't needed so AMD scheduler being hardware based can be better utilized.

Are there any signs that machine learning libraries and other GPGPU applications will start using the cross platform OpenCL instead of the proprietary Cuda anytime soon? It's a bit of a shame that so many allow themselves to be locked to one vendor, although it's been a while since I used either of them.

There are recent developments but nothing really significant. AMD did say they were working on CUDA compatibility.

AMD should just do it for TensorFlow. They would get a lot of benefit if they could show higher performance per dollar at least on Linux, and it would take just a small team to implement it.

Hopefully they'll catch up when everyone is using Vulkan and SPIR-V?

I read somewhere about some sort of cuda or opencl transpiler, but not sure of the details.

Mind you, nvidia also has the 1060 which preforms either better or worse than a 480 depending on what benchmark you use, it's basically identical in performance in practice, for the same price point.

The 1060 performs clearly not has good when using Vulkan.

Of course that since my foremost interest is computation, then NVIDIA it is. But if you just want to game, AMD gives a better bang for the buck.

Looking so forward to the Vega release, gonna be a really good year for a GPU upgrade. The 1080Ti release already flooded the market with cheap 980ti/1080, if AMD can bring the pain then more of these things will hit the used market, making them even cheaper.

AMD's card are much better supported by free drivers. If you plan to use a modern distribution as a desktop, I strongly recommend going with AMD.

Unless you plan to use Steam, which still has no real support for those drivers. You can find guides to modify the LD_PRELOAD to get some stuff working though.

I'm using Steam with those drivers and nearly everything works fine. The only thing I can remember right now that doesn't is Divinity Original Sin. It is broken and the developer Larian Studios refuses to fix it.

Unless you want to use your desktop for anything else but gaming, then you will have to go NVIDIA.

I'm gaming, and it works fine. I actually had a newer NVIDIA card, and replaced it with my older AMD card, because the AMD one worked better.

Reply on news.ycombinator.com