this is my next card!

Available 29th aswell?

Caring1I believe DX12 games allow the use of different cards in Crossfire.

Not CrossFire. DirectX 12 native multi-GPU.

Nice pricing, gpus have been price gouged for the longest time.

ShamalamadingdongI'd assume no one would buy a card solely for DX12 Explicit (Unlinked) Multi Adapter. That would be a ridiculous prospect. No one should buy a product around a single (supposedly) niche technology. I think it's safe to assume that most who will use this are people looking to get some extra performance through integrated graphics. I think there is better value in selling your old card for money than keeping it in hopes of using it for extra performance in the few games that are likely to support it. Ashes of the Singularity is the only game I know of that has implemented this multi GPU mode.


It won't work like that. Well, or if it does, the scaling/performance would probably be bad.

Crossfire/SLI implementations are very driver dependent meaning that a lot of the work is put in the hands of AMD and Nvidia. Yet not all games support multi GPU.
With DX12, we get three modes of multi GPU and two of them, including the one we're discussing here, is all in the hands of the developer. How likely are we to see developers with the skill and time to implement this properly and then there's budget constraints to go along with it. I just don't see it happening. If they couldn't do it before, how could they do it now?

DX12 also has a mode called Implicit Multi Adapter. The idea is similar to Crossfire/SLI and will also be driver dependent. I'm guessing most developers who will implement multi GPU support will use this to save time and effort by putting the ball in the court of hardware vendors.

Im not going to claim to be any expert in the area, but "If they couldn't do it before, how could they do it now?".

There are a lot of things that we could not do before that we can now or that has gotten a lot easier with time and progress.
DX12 is new and different right? the idea that was sold to us was that if there are components that can render graphics etc, those components would help out.
So yeah unless indeed its all in the hands of the drivers which constantly change and update...
I thought DX12 would be a bit like that Lucid Hydra chip...although that has not taken off really...maybe for a reason, a well, idk I guess, but it sure would be nice to look back at this in 2 - 3 years and see proper DX12 multi gpu of whatever variety support :)

If its that close in cores, it almost sounds like its supposed to be a cut down version of the RX 480...That would be interesting because it would then mean there are no X designations this generation from AMD.

Very curious...

ZoneDymoIm not going to claim to be any expert in the area, but "If they couldn't do it before, how could they do it now?".

There are a lot of things that we could not do before that we can now or that has gotten a lot easier with time and progress.
DX12 is new and different right? the idea that was sold to us was that if there are components that can render graphics etc, those components would help out.
So yeah unless indeed its all in the hands of the drivers which constantly change and update...
I thought DX12 would be a bit like that Lucid Hydra chip...although that has not taken off really...maybe for a reason, a well, idk I guess, but it sure would be nice to look back at this in 2 - 3 years and see proper DX12 multi gpu of whatever variety support :)

The DX12 feature we're discussing relies entirely on the developer.
That makes things much harder since they can't off-load the work to someone else and there isn't (as far as I know) a tool to do the work for them. And even if there was, it's not certain they'd use it.

Intel (and a consortium of other companies) has created an open source tool (OpenMP) to easily make multi-threaded software including games. Developers refuse to use it even though it's a great tool that allows great scaling.

But to remain on-topic:
Of course the features in DX12 are advertised even if they aren't used because the capability is there for anyone to use but it's not a requirement nor an automatic process.

I'm thinking that DX12 might make integrating some multi GPU features (specifically Implicit Multi Adapter) easier than SLI or Crossfire ever was because it's built-in and perhaps the documentation is better but it probably ends there. Implementing the ability to use any mix of GPUs will be hard to implement and harder to implement well.

Making things more complicated never makes things easier, so just because it's possible now doesn't mean it's because it's easier. It just means the tools are available if you have the resources to use it.

If you think about it: things have become easier for the end-user but harder for the developer. And that even goes beyond IT-related products.

night.foxyou cant different chips.

Agreed! Only same chips, one full with the cut out, as 7970-7950, 290X-290, etc.

GhostRyderIf its that close in cores, it almost sounds like its supposed to be a cut down version of the RX 480...That would be interesting because it would then mean there are no X designations this generation from AMD.

Very curious...

Or maybe yields are so bad that AMD is selling two levels of cut Polaris 10 chips (480 and 470), and that a 480x is still likely in the future? They must have a lot of the 470 chips to price it that attractively, since the 480 should only be ~15% faster.

RaviSSI think that RX 470 will have 1792 cores..... 2048 cores will be too close to RX 480 and will make it redundant if 470 is indeed priced at $149. On the other hand 460 with 1024 cores will be much weaker and again would be a much worse value for money at $100.

So in summary:

RX 480 - 2304 cores - 1266 MHz - 8Gbps 256-bit - $199
RX 470 - 1792 cores - 1150-1200 MHz - 6-6.5Gbps 256-bit - $149
RX 460 - 1024 cores - 1200-1250 MHz - 8Gbps 128-bit - $99

But then again, 7950 and 7970 had only 256SP difference. So it's not farfetched to see 470rx with 2048sps and maybe a lower clock (1Ghz base ?)

What more interesting is this is pretty much the "end-all-be-all" for phenomenal 1080p. Pretty much what AMD with the 7770Ghz and up 1680 x 1050 gaming back in the day. You won't necessarily need more (of yea it you 144Hz) for most game to play almost always maxed out and still provide a truly full immersive experience. I'm mean once the 7770Ghz came out all the talk and reviews of 1680 x 1050 where extraneous, now it's 1080p sunset, and we can move to 1440p.

Heck the RX 460 should offer great 1080p (aka 960/380) at a $100 price point and no 6-pin, however I understood that would be a Polaris 11 (smaller) part compared to the Polaris 10 of the RX470/480.

geon2k2I think they wanted to say that you can have decent 1080p performance with 150$ which is great.
I wonder if this would crossfire with older R9 380(x) though. That would be interesting, especially as I have one of those, with 4GB memory just like the RX 470.

CrossFire will not be possible between two different chips & different generation cards.
But you can Crossfire two of theses for ~300. :peace:

It would be nice if AMD would leg sweep nVidia at the mid-range, and put a check on NV prices. (4GB gtx 960 with 1024 cores and 128-bit vram isn't a $250 product!)

pidginthis is my next card!

Available 29th aswell?

As far as I know, only the 480 will be released on the 29th


I think that AMD is doing the smart thing with only having 4 chips in development. In the past they would have used 1 GPU per product stack (Tahiti for 7970/7950, Pitcairn for 7870/7850) now we're seeing them using 1 chip for 2 product stacks (Polaris 10 for 480 and 470).

It's a smart way for using their limited resources and once they get better yields and higher binned chips they can offer X versions with increased clockspeed (think 480X = 480@ >1.5Ghz)

GhostRyderIf its that close in cores, it almost sounds like its supposed to be a cut down version of the RX 480...That would be interesting because it would then mean there are no X designations this generation from AMD.

Very curious...

My thinking is that if there are 'X' versions, they may be using GDDR5X. There's little doubting that the RX 480 could benefit from more memory bandwidth and rumors have long held that Polaris has GDDR5X capability.

Still, this may well be something that will be unannounced until Vega's release - sort of a mid-cycle refresh.

BoyGeniusCrossFire will not be possible between two different chips & different generation cards.

Why not? They support "kinda cross fire" with APUs GPU + discrete.

medi01Why not? They support "kinda cross fire" with APUs GPU + discrete.

The technical reason: Different driver code-paths are in use which prevents splitting game graphics queues between multiple cards efficiently enough to be worthwhile.

Layman's terms: Polaris is just too different from what came before to work together with older video cards in crossfire.

DX12 solution: permit multiple game-managed graphics queues and compute queues which allows completely different GPUs to work together more or less seamlessly.

I think some you guys need to read up on Explicit Multi-Adapter (EMA) under Dx12.

"One of the most exciting parts of Microsoft's DirectX 12 API is the ability to pair graphics cards of varying generations, performance, or even manufacturers together in a single PC, to pool their resources and thus make games and applications run better."

arstechnica.com/gaming/2016/02/directx-12-amd-and-nvidia-gpus-finally-work-together-but-amd-still-has-the-lead/

A 750ti has a typical board power of 70w and does not need power supply input. The 470 will have 110w typical board power and will need at least a 6pin of power supply input.

If they are trying to gain the market share of the 750ti, this won't do it. It will be faster than a 750ti by probably at least 50% though.

james888The 470 will have 110w typical board power and will need at least a 6pin of power supply input.

That's what the RX 460 2Gb (No 6-pin <75W) will be for at the $100 price... while rumors place it above the reference 960 performance.

james888A 750ti has a typical board power of 70w and does not need power supply input. The 470 will have 110w typical board power and will need at least a 6pin of power supply input.

If they are trying to gain the market share of the 750ti, this won't do it. It will be faster than a 750ti by probably at least 50% though.

That's what the RX 460 is for... 60W typical board power. Much faster than a 750 Ti. Cheaper too.

hojnikbBut then again, 7950 and 7970 had only 256SP difference. So it's not farfetched to see 470rx with 2048sps and maybe a lower clock (1Ghz base ?)

Yes... It's possible, but...

1. 7950 was closer to 7970 in terms of price (82%) than what 470 at $149 would be (75%), so there ought to be more separation between 470 and 480.

2. As 14nm is a new process, the probability of a more cut down version is always higher in order to maximize yields.

So I would agree with you that there is a possibility for 2048 cores, since 2048@1-1.05GHz would give roughly same performance as 1792@1.15-1.2Ghz, it's just that I think the latter is more probable.

Man screw this, when are the big boys coming????????

CasecutterThat's what the RX 460 2Gb (No 6-pin <75W) will be for at the $100 price... while rumors place it above the reference 960 performance.

I sincerely doubt it. It should be close to or slightly above950 performance. Even AMD slides a few months back showed Polaris 11(460) and 950 neck-to-neck in performance.

Looking at it another way, 950 was 5-10% faster than 370. Now 460 will have the same core count as 370 (1024 cores) and will feature a higher clock... So it should be around 10-12% faster. Thus effectively it should be 2-5% faster than 950.

So the newer cards hierarchy is looking like:

RX 460: Good 1080p performance (Firestrike score ~6k)
RX 470: Excellent 1080p performance (Firestrike score ~9k)
RX 480: Outstanding 1080p performance (Firestrike score ~12k)
or Good 1440p performance (Firestrike Extreme Score ~6k)

GTX 1070: Excellent 1440p performance (Firestrike Extreme Score ~8K)

$150 for 970 performance? Why not?

RX 460 is very interesting too, I'm pretty positive that it'll touch 960's performance, for $100, I think it would be my next card for my second PC.

xorbeIt would be nice if AMD would leg sweep nVidia at the mid-range, and put a check on NV prices. (4GB gtx 960 with 1024 cores and 128-bit vram isn't a $250 product!)

Well technically AMD has always offered competition in price/performance against Nvidia, but my main concern/hope is whether they can do it at a good margin of profit! For example last round AMD pretty much lost against nvidia in the mid-end segment because it was selling much bigger chips at the cost of smaller/cheaper nvidia chips like tonga(r9 380/380x) vs gtx 960. The tonga chip was a decent in size 366mm2 chip while the gtx 960 was a 226mm2 chip, yet they performed on par. Being that nvidia was on a less complex smaller chip their power consumption was less, and by default the circuit design not as complex in general making manufacturing a gtx960 far cheaper than a tonga solution

Same thing happened with gtx980 at around 400mm2 die size vs hawaii(r9 390x) at 440mm2, amd in this case is somewhat more competitive than tonga was because hawaii is a newer revision of gcn so with only 10% extra die space they competed, however the power consumption was far greater on amds side.

With all this being said I would also like to make a suggestion for reviews to focus a bit on this aspect of not only performance/watt and performance/dollar, but also performance/mm2 of die size. Because that in my opinion is a clear indication on who has the superior architecture or the better business model, and basically in other words who can achieve higher performance with better cost efficiency