AMD to Launch Radeon R7 470 and R9 480 at Computex

[medi01]

The final nail in Fiji's coffin?

Fiji replacement, Vega, is expected in Q1 2017.
Anyway, what's wrong with Fury Nano, that costs roughly as 980 yet is faster, smaller?

Except HD5850, HD6950 and HD7850/7950, there really weren't any great priced graphic cards from AMD...

4850 was.

...driver complexity issues of CF..

AMD is pushing for "multi-gpu aware" game development. As far as I understand, it would mean devs to keep in mind "multi-gpu"-ness, which would also simplify drivers (no need to present 2 cards as single one)

 

[Parn]

Wow, a big come back for AMD in terms of power efficiency if those figures hold true.

 

[SonicZap]

This would be awesome if true. If I upgraded from my HD 7850 to a R9 480, I'd get 2.5 times more performance for the same power draw. No need for upgrading the PSU.

The lower power draw should also help AMD get market share in the high margin gaming laptops (assuming it's not far behind Pascal in power efficiency). Currently nearly all gaming laptops are Intel / Nvidia, so AMD really needs better power efficiency to compete there.

I think most people are hoping for more performance, not necessarily more efficiency. Unless they price the r9 480 on par with the current 390 offerings and replace them I don't see a point in such an SKU.

Not everyone is looking for a power-hungry and very expensive high end GPU, or already owns a high-end GPU. The GTX 970 didn't give much better performance than the GTX 780 Ti, yet it sold like hotcakes.

 

[Parn]

Not everyone is looking for a power-hungry and very expensive high end GPU, or already owns a high-end GPU. The GTX 970 didn't give much better performance than the GTX 780 Ti, yet it sold like hotcakes.

Agree. The power-hungry expensive high-end GPU is the niche market. It's actually the mid-tier power efficient GPUs that most users would like to buy.

 

[RejZoR]

Fiji replacement, Vega, is expected in Q1 2017.
Anyway, what's wrong with Fury Nano, that costs roughly as 980 yet is faster, smaller?


4850 was.


AMD is pushing for "multi-gpu aware" game development. As far as I understand, it would mean devs to keep in mind "multi-gpu"-ness, which would also simplify drivers (no need to present 2 cards as single one)

HD5850 delivered twice the performance of HD4870 iirc. It made one of the biggest performance leaps of all times. HD6900 was interesting because of EQAA anti-aliasing not found on any older/lower graphic cards and HD7950, well, it was the first generation of GCN cards that still beat today in many systems and still run games at quite high details (1080p). It was certainly a great value, because you can still use it today at its full capacity (since it's even DX12 capable).

 

[bug]

one 290X handles 1440P, the 295x2 decimates everything, even at 4K if the drivers work.

Nope, it doesn't:
http://www.techpowerup.com/reviews/AMD/R9_295_X2/17.html
http://www.techpowerup.com/reviews/AMD/R9_295_X2/13.html

It's "playable", if you're comfortable with the price of that and a return of 26FPS in Crysis3, but it definitely doesn't "decimate".

The 480 looks to be on par with a 290X, so good up to 1440P, IF the 490 is a double 480 it will be in the vicinity of the 295x2, and able to handle 4K without the added complexity of CF

Based on what?

We need more power for 4k, that much is clear. If the manufacturers decide to throw us 10-20% better performance and put everything else in cutting power consumption, 4k gaming will be a no-go for one more generation. Which isn't a terrible loss, because there aren't many affordable, good 4k monitors on the market anyway.

 

[Brusfantomet]

If the 490 is a double 480, it will still have all the driver complexity issues of CF. Unless you mean, 490 as being double the power in a single GPU.

And what 490?

Polaris 10 rumored to have 4096 stream processors add higher clocks and the performance should be close to double that of VEGA 10. This makes it double, (double number of stream processors, like 380X against 370 as in double the recourses and therefore a potential double performance. NOT a dual card like the 295x2

With the naming here its quite obvious that there will be a 490 in the future.

Nope, it doesn't:
http://www.techpowerup.com/reviews/AMD/R9_295_X2/17.html
http://www.techpowerup.com/reviews/AMD/R9_295_X2/13.html

It's "playable", if you're comfortable with the price of that and a return of 26FPS in Crysis3, but it definitely doesn't "decimate".



Based on what?

We need more power for 4k, that much is clear. If the manufacturers decide to throw us 10-20% better performance and put everything else in cutting power consumption, 4k gaming will be a no-go for one more generation. Which isn't a terrible loss, because there aren't many affordable, good 4k monitors on the market anyway.

With "decimate" i mean beat every other card out there by a large margin, not every other game out there, 26 FPS in Crysis3 is actuality decimate if the next best thing gets 14 FPS.

IF the 480 has 2304 stream processors and a higher clock ( say 1250 MHz) the compute power will be on pair with the 290X (2816 stream processors at 1 GHz). Add in that the 290X is GCN 1.1 and the rumored 480 is GCN 1.3 there is a good possibility for it to match the 290X.

We can at least agree on the need for more power, but, remember that the name 480 indicates that it is a replacement for the 380, and that card is noticeably weaker than a 290X (the 380 is approximately 60% of the performance of a 290X according to This review)

 

[rruff]

Agree. The power-hungry expensive high-end GPU is the niche market. It's actually the mid-tier power efficient GPUs that most users would like to buy.

Or lower than mid-tier. Anyone seen actual sales figures? I think the great majority of dGPU sales ($) must be in the <$150 range.

 

[JMccovery]

Polaris 10 rumored to have 4096 stream processors add higher clocks and the performance should be close to double that of VEGA 10. This makes it double, (double number of stream processors, like 380X against 370 as in double the recourses and therefore a potential double performance. NOT a dual card like the 295x2

With the naming here its quite obvious that there will be a 490 in the future.

I think you meant that Vega 10 is rumored to have 4096sp, while Polaris 10 will have 2560.

 

[SKD007]

I would be more interested in 490x or higher that can allow me play games at 60fps 4K.. Maxed out..

 

[efikkan]

If AMD ever is going to make a profit again, they'll need to give Nvidia decent competition in the $200-550 segment, so AMD will need to compete with the whole range of GP104 chips...

 

[Brusfantomet]

I think you meant that Vega 10 is rumored to have 4096sp, while Polaris 10 will have 2560.

Yes, i ment Vega 10.

 

[badtaylorx]

I don't remember the last time AMD gave us new silicon this far down the product line...

6870/6850???

 

[Kanan]

I don't remember the last time AMD gave us new silicon this far down the product line...

6870/6850???

Yeah, that's why I'm speculating on a R9 490/490X that will be semi big sized and released before Vega, and Vega itself will just be the replacement to Fury X -> Fury X2, so a maximized big chip (600mm²+). But that's maybe just a wish or dream that I have. To me at the moment it seems like, small/mid (Polaris 11/10) sized and big (Vega), nothing in between, which isn't optimal to say the least. I can't imagine R9 480 comparing to GTX 1080, I think 1080 will be a decent highend GPU, at least as fast as GTX 980 Ti, so the R9 480 has basically no chance against it - that's why AMD desperately needs a bigger chip than that, a semi big chip at least (the R9 490(X). The R9 290/390(X) were also semi big in size).

 

[$ReaPeR$]

If AMD ever is going to make a profit again, they'll need to give Nvidia decent competition in the $200-550 segment, so AMD will need to compete with the whole range of GP104 chips...

*If AMD is ever going to make a profit again, they'll need to close some OEM deals.

this looks very promising, but with no reviews speculating is a bit pointless.

 

[rruff]

If AMD ever is going to make a profit again, they'll need to give Nvidia decent competition in the $200-550 segment

Nah, they could ignore that boutique market entirely. Besides if all they did was GPUs I think they'd be making money now. It's in CPUs where they've really been hurting, and it's no mystery why.

If the R7 470 really performs better than the R7 370 while consuming <50W, they can sell loads of them to budget gamers and laptop manufacturers.

 

[prtskg]

AMD already showed Polaris 10 playing Hitman @60 fps (1440p) in dx12 at ultra settings. Assuming this is full Polaris 10 i.e. 480X, we have this mid tier gpu playing dx12 game better than furyX or 980ti. I think this is good progress.

 

[the54thvoid]

AMD already showed Polaris 10 playing Hitman @60 fps in dx12 at ultra settings. Assuming this is full Polaris 10 i.e. 480X, we have this mid tier gpu playing dx12 game better than furyX or 980ti. I think this is good progress.

I don't think that's entirely accurate. Nobody got to see the card, just the outputs. I think the overall view is Polaris 10 is mainstream card with excellent efficiency but NOT Fury X performance level.
I'd likewise be surprised if the upcoming Pascal card is faster than the 980ti.

 

[Xzibit]

I don't think that's entirely accurate. Nobody got to see the card, just the outputs. I think the overall view is Polaris 10 is mainstream card with excellent efficiency but NOT Fury X performance level.
I'd likewise be surprised if the upcoming Pascal card is faster than the 980ti.

Doesnt the 390X equal or beat the 980TI in most of the Hitman DX12 1440p benchmarks? If Polaris 10 replaces the 390s they should come with a performance boost in that segment.

 

[HD64G]

AMD already showed Polaris 10 playing Hitman @60 fps in dx12 at ultra settings. Assuming this is full Polaris 10 i.e. 480X, we have this mid tier gpu playing dx12 game better than furyX or 980ti. I think this is good progress.

We all should hope that's true imo, since it would be a big factor to help lower the price of all the now existing GPUs and give to all much more FPS/$. It is viable for sure, so lets be patient for another month or 2 to see what's up with the next gen GPUs.

 

[the54thvoid]

Doesnt the 390X equal or beat the 980TI in most of the Hitman DX12 1440p benchmarks? If Polaris 10 replaces the 390s they should come with a performance boost in that segment.

Worryingly, the 390X beats Fury X at DX12 in Hitman (at 4k).

http://www.guru3d.com/articles_pages/hitman_2016_pc_graphics_performance_benchmark_review,7.html

I think DX12 is not really polished enough to demonstrate tangible benefits (10% for 390X and only 5% for Fury X in the above link). Obviously the Async agnostic Maxwell gets zero lift.

Like I said and I always say - we'll need to wait. The games will make a difference to each camp so cherry picking titles never helps (and let's not argue that in showpiece demo's the vendor will choose what suits their marketing best). We need a good spread of neutral and sponsored to see who's fiddled what.

I just hope if AMD come up trumps, they let AIB's release custom's because I don't like stock cards (coil whine, coolers etc).

EDIT:

Found this tidbit. AMD are shoving Async hard because they know Nvidia will not keep up. Funny, Nvidia used to do that with tesselation.

http://www.gamersnexus.net/news-pc/2309-amd-hitman-dx12-ace-workload-management

Hitman aims to utilize the ACEs on AMD GPUs (Asynchronous Compute Engines) to better manage intense workloads

“With on-staff game developers, source code and effects, the AMD Gaming Evolved program helps developers to bring the best out of a GPU. And now in 2016, Hitman gets the same PC-focused treatment with AMD and IO Interactive to ensure that the series’ newest title represents another great showcase for PC gaming!”

It's going to be like I said ages ago - the games will be chosen by AMD and Nvidia and hobbled accordingly. Welcome to the same future. At least now AMD can hobble back.

But we all lose.

 

[efikkan]

We'll have to wait a year or so until we got a selection of decent Direct3D 12 games to actually see how the hardware handles it.

Most likely we will never see a game which does two complete optimized pipelines, so comparisons between Direct3D 11 and 12 within a game wouldn't reflect the API itself.

 

[HumanSmoke]

Found this tidbit. AMD are shoving Async hard because they know Nvidia will not keep up. Funny, Nvidia used to do that with tesselation. It's going to be like I said ages ago - the games will be chosen by AMD and Nvidia and hobbled accordingly. Welcome to the same future. At least now AMD can hobble back.

But we all lose.

You also will see this with conservative rasterization. Like async compute it has positive workload reduction facets. Likewise they are fairly minor unless you move down the tech segment food chain, but Just Cause 3's limited use of CR was enough to crater performance on AMD hardware. I doubt that it hasn't gone unnoticed, or will be an isolated occurrence. Sales and marketing might just come down to which vendor handles the penalties of unsupported features best

The other worrying part of the equation is that the sheer amount of work a game developer now has to take onto themselves just to get a DX12 feature rich game out the door and working correctly. As the Hitman dev says:

Several DirectX 12 games are out now, but the first outlook isn’t nearly as positive as Microsoft stated (up to 20% more performance from the GPU and up to 50% more performance from the CPU). Do you think that it’s just a matter of time before developers learn how to use the new API, or perhaps the performance benefits have been somewhat overestimated?
I think it will take a bit of time, and the drivers & games need to mature and do the right things. Just reaching parity with DX11 is a lot of work. 50% performance from CPU is possible, but it depends a lot on your game, the driver, and how well they work together. Improving performance by 20% when GPU bound will be very hard, especially when you have a DX11 driver team trying to improve performance on platform as well. It’s worth mentioning we did only a straight port, once we start using some of the new features of dx12, it will open up a lot of new possibilities – and then the gains will definitely be possible. We probably won’t start on those features until we can ditch DX11, since a lot of them require fundamental changes to our render code.

Given the reluctance of a large section of people to move to Win10, it doesn't auger well that devs can continue to use the need for a DX11 codepath as an excuse for sloppy DX12 programming.

Tangental (at best) to this, I found this quote fairly amusing

Another low level API has been recently released: Vulkan. What do you think of it in terms of performance and features? Do you have any plans to add Vulkan support to HITMAN?
Vulkan is a graphics programmer’s wet dream: A high performance API, like d3d12, for all platforms. With that said, we don’t have any plans to add Vulkan support to Hitman. Also, unfortunately it looks like Vulkan won’t be supported on all platforms.

Developers wet dream - but no we won't be using it
Vulkan an API for all platforms...that looks like it won't be supported on all platforms !?!

 

[the54thvoid]

Developers wet dream - but no we won't be using it
Vulkan an API for all platforms...that looks like it won't be supported on all platforms !?!

Do I smell MS waving the big stick here or are dev's too reluctant to move away from DX 'whatever'?

 

[G33k2Fr34k]

It's highly unlikely that Polaris 10 cards will perform worse than the 390/390X cards, despite having less SPs.
The number of FP32/FP64 units in this chip are likely better utilized than the previous generations of their GCN chips, which didn't change much since its release in 2012.
Spending 4 years or so to find and eliminate bottlenecks in their GCN microarchitecture and make architectural improvements over the original GCN designs should pay off well with these chips.

Also, back when they announced Polaris, they mentioned that Polaris chips will get some form of memory compression to improve memory performance. This in a way implies that they're already hitting the bandwidth limits of GDDR5 with their Polaris 10 cards, which the GTX980 didn't hit even when over clocked.

I predict that the 470 will replace the 390X and that the 480 will replace FuryX performance wise.