More Polaris10 and Polaris11 Specifications Revealed

[32257870]

This is interesting; if the 32CU Polaris 10 comes in 'under' 150w with performance similar to Hawaii/Grenada, and the PS4 Neo is rumored to have Polaris-based graphics, I'm wondering if it will have more than 16-20CUs.

PS4 Neo will have as many CUs as it needs to output a minimum 1080p 60fps. However many that is remains to be seen, but we'll have a much clearer picture of it after Polaris 10 benchmarks become prevalent.

 

[32257870]

It seems that it's not going to compete with 1070 or 1080, maybe that'd be Vega on October, but I'm not sure. Polaris, with 32 CU seems to be like a low power 380/X that will have little from the older Antigua (Tonga/Tahiti) GPUs. This is very disappointing, especially when the Power Consumption is the same as 1080/1070 (probably not though). I hope this is not true because this will make people buy the 1080/1070 and the possibilities are AMD new "Vega", or whatever it is can outperform these two, which means we'd have to wait for real competition to come.

However, that 5.5 TFLOPS seems to be quite interesting, but I doubt that with the same number of CU that it'll be faster than Hawaii/Grenada.

Of course Polaris 10 won't compete with Pascal. It never was supposed to. It should compete with the R9 390 in a big way, and if AMD's new insulation technology along with other improvements allow for MUCH higher overclocks, then 32CUs might be all you need to reach near-980ti levels of performance. NEAR-980ti though. Let's not get ahead of ourselves.

 

[Chaitanya]

2015 Midrange = 2016 Low end

2016 Midrange = 2015 Enthusiast

That's what has to happen for any of these releases to make sense. High overclocks on Polaris 10 and performance approaching within 10% of a 980ti at a pricepoint of $300 or less should mean we progress nicely in all ranges of price to performance.

Finally some decent comments compared to nvidia ass kissers comments above. I think more realistic target for Polaris would be 980 level performance at around 250-275$ mark. Its the price bracket in which most gpus tend to sell, even if I can afford higher end gpus I prefer 250$ gpu as I can upgrade these in 2 years instead of 3year cycle.

 

[EarthDog]

Dude.. .please edit your posts instead of double/triple/quadruple posting...

 

[32257870]

To be fair, I'd say releasing a $379 card that outperforms your previous $1000 card isn't so much "just enough" as 'raising the bar'.

I do REALLY want AMD to woo me away from the 370 tho, for their own sake.

Especially since memory bandwidth at 1440p and 4K on the 1070 seems to be lacking in theory, especially in SLI, yet nobody wants to talk about it. Memory bandwidth for the 1070 might be what 3.5GB was tot he 970. I'm going two Polaris 10s for some 4K action, if they get solid frames. If not then it's the 1080 for me, but the 1070... Call me rash or even crazy but I wouldn't trust the 1070 if it payed me to use it.

 

[G33k2Fr34k]

To be fair, I'd say releasing a $379 card that outperforms your previous $1000 card isn't so much "just enough" as 'raising the bar'.

I do REALLY want AMD to woo me away from the 370 tho, for their own sake.

The GTX1070 isn't equipped with GDDR5X, so it's highly unlikely that it outperforms the 980 TI/Titan X at 2K and 4K resolutions.
As for the Polaris 10 cards, we know that these cards will be at least as fast as the 390/390X and will cost a lot less than Nvidia's offerings. Both the 480 and the 480X will most likely outperform the 980 TI/Titan X in existing/upcoming DX12 games since the 390X already does that. All these factors make the 480/480X cards way more appealing to your average PC gamer, especially to those of us who aren't in the US.

 

[bug]

Nope.
449$ for 1070 (plus moar, even moar, for shortages) - cause it's "Founders Edition" (lovely, nVidia, thank you!)
699$ for 1080 (again, "Founder's Edition")

Note we are talking about prices here and now (well, short term). Who knows what will cost what when Xmas comes.

Wth dude? http://www.anandtech.com/show/10304/nvidia-announces-the-geforce-gtx-1080-1070
What "here and now" are you talking about?

 

[Casecutter]

The pic in the article is of a ref 380x clearly.

Yea it's a placeholder, I can't think of a instance of seeing 400 Series shroud design. I'd think it's not holding to that, probably more like a new take on the Nano. And I though read the Polaris 10 was to be a little longer than Nano, while Polaris 11 is just slightly less the Nano perhaps single slot fan with an abbreviated shroud.

 

[EarthDog]

Wth dude? http://www.anandtech.com/show/10304/nvidia-announces-the-geforce-gtx-1080-1070
What "here and now" are you talking about?

He's vomiting crimson colored FUD?

Around Xmas it will likely be cheaper as they have been out for a while and the market settled after both releases.

 

[HumanSmoke]

He's vomiting crimson colored FUD?
Around Xmas it will likely be cheaper as they have been out for a while and the market settled after both releases.

So what happens when the reduced-BoM cards get sold by Newegg at $599 and get snapped up as soon as they are in stock, and start showing up in Pascal owners threads in forums? Does the FUD vomiting go projectile?

 

[EarthDog]

Yes. Please put on your waders.

 

[Kanan]

Not bad, so this means the 480 (non X) features 2048 GCN 4 shaders, that run faster than the 2816 of R9 390(X), at a price point of about 200-300$.
The 480X (40 of 40 CU activated) may then follow, have 2560 shaders and be nearly as fast as 980 Ti or even faster, for about 300-400$, effectively competing against GTX 1070.

Also I think the "Baffin" chip with 896 shaders is a non-X version with deactivated CU's too, so the full version may have 1024 or 1280 shaders and be a lot faster.

The GDDR5 @ 1750 MHz on a 256 bit bus should btw be enough to drive the 480/X, I expect revamped delta compression that is comparable to that of Maxwell or better, effectively increasing bandwidth per bit of GCN 4 cards a lot.

 

[Brusfantomet]

With a TDP of 150 W the polaris 10 would be able to get away with only a 6 pin for power.
GDDR5X at 10 GHz and 256 bit = GDDR5 at 5Ghz and 512 bit (290x ram bandwidth).
two 290x plays everything i have trown at it at 2560 x 1600, one will do the same at 1080p, if these rumors are to be trusted the cards based on polaris 10 will outperform a 290x, at 150W they just need to price it right and you have the new price/performance king. As a fun side note, the 295x2 outperforms anything from nvidia when CF works, IF AMD gets the CP profiles on polaris 10 right two of them have the potential to take on a 1080 GTX.

 

[deu]

Why people think that this GPUs are for competing with the 1080? these GPUs are for low/mid market, things that nvidia hasn't reveal for this generation....

Yeah people are too focused in on GTX1080 and want to compare everything to it. polaris 10 will be the value for money 1080p card for the "low-end" gamer (if you can even call it that.)

I think that some people are missing is that is a seperation in customers requirements being 1080p, VR and 4K (In some games VR will require more that 4K gaming.

There will be released a product from both companies;

1 for 1080p FPS gaming ala GTA V, the witcher / BF4
1 for VR experiences right now in 90FPS / low req 4K gaming
1 30-40FPS+ for 4K

GTX1080 is aiming for highest end polaris is aiming for the low end in this spectre :0

VEGA is aimed to compete with 1080 and to be honest right now 1080 is hitting in a weird spot of nothing; to weak for 4K gaming at 60FPS+ and WAY too powerful for 1080p; 1440p and high-requirements VR-games will benfit from it but right now these games are not made yet and not that many people have 1440p screen. 1080Ti and VEGA 2017 Q1 refresh will be ready for VR maxed out, and 4K 60FPS-ish.

(ofcourse there will be lower-lower-end and entusiast aswell)

 

[Basard]

From the looks of it, I'll be skipping this generation and just keeping my OC'ed GTX 980. I don't want to hear about damn Hawaii 2 frigging generations later. And while GTX 1000 series do seem to deliver based on PR stuff, question is, do I really need it? Doom 2016 runs maxed out butter smooth at 1080p and quite playable at 4K DSR. Returning me to the part where I'm skipping this entire generation, probably even the next one. Might be returning to the graphics scene when AMD's Vega launches. And NVIDIA's GTX 3000 series...

It sure does seem like nothing has really changed since the 2900XT/8800GTX..... They should bring back the rivaTNT, lol... What was up with the "riva"? That card changed my life! Then there was Geforce, that's when the shit really hit the fan... I couldn't afford that at the time though.

Now it's just meh after meh.... Fury is cool as hell, nobody gives it respect though. Still cooler than the 1080, even if it's not as fast.

We need bigger interposers! HEY! The 1930's called, they want their fiberglass back!

 

[EarthDog]

Yeah people are too focused in on GTX1080 and want to compare everything to it. polaris 10 will be the value for money 1080p card for the "low-end" gamer (if you can even call it that.)

I think that some people are missing is that is a seperation in customers requirements being 1080p, VR and 4K (In some games VR will require more that 4K gaming.

There will be released a product from both companies;

1 for 1080p FPS gaming ala GTA V, the witcher / BF4
1 for VR experiences right now in 90FPS / low req 4K gaming
1 30-40FPS+ for 4K

GTX1080 is aiming for highest end polaris is aiming for the low end in this spectre :0

VEGA is aimed to compete with 1080 and to be honest right now 1080 is hitting in a weird spot of nothing; to weak for 4K gaming at 60FPS+ and WAY too powerful for 1080p; 1440p and high-requirements VR-games will benfit from it but right now these games are not made yet and not that many people have 1440p screen. 1080Ti and VEGA 2017 Q1 refresh will be ready for VR maxed out, and 4K 60FPS-ish.

(ofcourse there will be lower-lower-end and entusiast aswell)

If It's 20-25% faster than a 980ti, and a 980ti can get playable fps in many titles with out AA (which none or less is needed anyway), this stands to do better, no? I mean if you are looking for 60fps+ across all titles, no single gpu can do that... just not sure what expectations these are based off of...

 

[jabbadap]

Of course Polaris 10 won't compete with Pascal. It never was supposed to. It should compete with the R9 390 in a big way, and if AMD's new insulation technology along with other improvements allow for MUCH higher overclocks, then 32CUs might be all you need to reach near-980ti levels of performance. NEAR-980ti though. Let's not get ahead of ourselves.

Which pascal are you meaning, gp100, gp104, gp106 or gp107? I would presume it is somewhere between gp104 to gp106 performance. More cutted gp104 might come as 1060ti to compete with polaris 10 xt and full gp106 might have enough juice to compete with polaris 10 pro.

 

[arbiter]

256 bit GDRR5x on the Polaris 10 will be much slower than the 512 bit GDRR5 of the Hawaii.
As of now, the 256 bit GDDR5x of the 1080 is slower than that of the 384 bit 980ti.

GDDR5x on a 1080 does 320GB/s, which is same speed hawaii on 290(x) ran, they overclocked the memory on 390 cards for 380GB/s. 980ti had 336GB/s so if AMD clocks it the same it won't be that much slower plus don't know what Overclocking that memory will be able to take yet .

Of course Polaris 10 won't compete with Pascal. It never was supposed to. It should compete with the R9 390 in a big way,

Depends on how fast it works in games and price, it may not be ment to compete with current 1070/1080 but performance per $ could make it that was.

Finally some decent comments compared to nvidia ass kissers comments above. I think more realistic target for Polaris would be 980 level performance at around 250-275$ mark.

Um i would say it should be more 200$ more, 250/275 seems high given what looks like can get outta 16nm.

The GTX1070 isn't equipped with GDDR5X, so it's highly unlikely that it outperforms the 980 TI/Titan X at 2K and 4K resolutions.

1070 is more of a budget 1080/1440p card. using GDDR5 keeps it cheap since not using new more expensive memory.

 

[G33k2Fr34k]

Depends on how fast it works in games and price, it may not be ment to compete with current 1070/1080 but performance per $ could make it that was.

Well... if the fully enabled Polaris 10 chip is rated at 5.5 TFlops/second, then doing some math can give us a close estimate of the 480X performance.
Assuming that Polairs has delta color compression, which Hawaii lacks, as well as better shader efficiency and Geometry throughput than Hawaii, then This should give Polaris a 25% performance advantage over Hawaii at the same flops rating. So a 480X should have: 5.5/5.2 *1.25 = ~1.3 the performance of the 390X. That is ~FuryX ish performance, which isn't too shabby. The 480 pro should be slightly faster than the 390X in this case.

1070 is more of a budget 1080/1440p card. using GDDR5 keeps it cheap since not using new more expensive memory.

my point still holds; the 1070 at 2K or 4K will lose to the 980 TI/Titan X.

 

[rruff]

Not bad, so this means the 480 (non X) features 2048 GCN 4 shaders, that run faster than the 2816 of R9 390(X), at a price point of about 200-300$.
The 480X (40 of 40 CU activated) may then follow, have 2560 shaders and be nearly as fast as 980 Ti or even faster, for about 300-400$, effectively competing against GTX 1070.

I think you and many others are getting carried away again. The odds are very good that the full chip has 2048 shaders, and cut down versions will fill the space between this and Polaris 11. All indications are that this is a 480x so it will slot in well below the 1070, just as the 380x was well below the 970. So you'll need to wait until the fall before you see the cards that compete with the 1070 and 1080.

This is a smart move by AMD, because most likely their architecture will be inferior to Nvidia's but they will have several months where they have the best and newest midrange cards, since they'll be competing against Nvidia's Maxwell. How long has it been since that was the case?

FPS/$ will be at least as good as Nvidia's 1070. I predict Polaris 10 will match or slightly exceed 390/970 performance for $250 or less. It will be great if you are in that budget range.

 

[wizyy]

I think it's safe to say - opinions about "Polaris" are "polarized"...

 

[Kanan]

I think you and many others are getting carried away again. The odds are very good that the full chip has 2048 shaders, and cut down versions will fill the space between this and Polaris 11. All indications are that this is a 480x so it will slot in well below the 1070, just as the 380x was well below the 970. So you'll need to wait until the fall before you see the cards that compete with the 1070 and 1080.

This is a smart move by AMD, because most likely their architecture will be inferior to Nvidia's but they will have several months where they have the best and newest midrange cards, since they'll be competing against Nvidia's Maxwell. How long has it been since that was the case?

FPS/$ will be at least as good as Nvidia's 1070. I predict Polaris 10 will match or slightly exceed 390/970 performance for $250 or less. It will be great if you are in that budget range.

Has nothing to do with being carried away. My guesses are based on the original numbers that the GPU has 40 CUs, not 32, or at least more than 2048 shaders. You are playing the same game as me.

I don't think the architecture is inferior, when a 2048 shader card will be faster than a 390X, the opposite is true. My predictions are just more optimistic than yours. "Match or slightly exceed 390/970 performance" is a pretty negative guess for a new chip. It must be clearly faster than 390X, everything else would be a catastrophe. Also read the news again, I think you missed the tflops part of it, your guess doesn't make much sense.

Vega will be the more interesting part of this, I expect up to 2 times the CU amount of Polaris 10, meaning between 4096 and 5120 shaders and meaning the GTX 1080 will be easily crushed. After all, the GTX 1080 is only ~25% faster than Titan X, and maybe 5% faster than 980 Ti custom cards. The 1080 custom will maybe be 20% faster than 980 Ti custom, meaning that Pascal isn't as strong as the hype and Nvidia PR makes you believe. Pascal is pretty weak, I expected a lot more from a 16nm chip for 599$+. My hopes are on the Vega GPU of AMD now, this will be a real game changer if my expectations are true, unlike the GTX 1080 which is a small upgrade.

Anyway, we will see.

 

[neliz]

funny how people think this is the 390x replacement in terms of price etc. while everything points to 270/380 range. this is a <150W ~$150-$250 card. People already forget what Fury did with the lineup and naming of AMD's 200/300 series.

 

[medi01]

32CUs

That's a number of CUs on mobile version, to my knowledge.


PS

http://www.amd.com/en-gb/products/graphics/notebook/r9-m200

 

[G33k2Fr34k]

That's a number of CUs on mobile version, to my knowledge.

I don't think there's a mobile version of Polairs 10. AMD is going to have 2 different versions of the Polaris 10 chip. We already know there's one with 36 CUs. I think that's the fully enabled one. The cut down version of Polaris 10 has 32 CUs, which is what this rumors implies.

What matters is the theoretical single precision FP rating and how efficient the micro-architecture is. If the
5.5 TF rating is true, then the Polaris 10 cards are definitely faster than the 390/390X. How much faster depends on how good Polaris is in comparison to Hawaii, which is Vanilla GCN.