(GURU3D RUMOR) AMD Polaris 10 GPU To Offer Near 980 Ti Performance For 299 USD?

[airfathaaaaa]

Yes.

I made my contribution by observing and reporting the historical recurrence of the same posting style as recent AMD product launches. Do you have a problem with that?

If this gets anywhere near 980 performance, let alone 980ti, for $300 and 150w power consumption (have I rounded up all the rumors?) I'll buy one on launch day.

My wallet will be safe.

D: D: D:
great contribution

on other news if polaris 10 is slower than a inferior card on 14nm everyone will suicide

 

[flopper]

980 is 180W.
980 is way overpriced but 970 is $300 for ~10-15% less performance.

Logic has nothing to do with blind faith.
When you check the fps you recive from doubling the price one understands the die shrink cant come to soon.

 

[maddie]

Does it matter if Nvidia launches first, outside of fanboys glee? The cards are in different market segments, so should not directly compete against each other except maybe at the fringes, top Polaris vs bottom GP104.

Remember Koduri said - "We believe we’re several months ahead of this transition, especially for the notebook and the mainstream market"

This is Polaris territory, not GP104. Indeed one could make a strong case for AMD wanting Nvidia to set prices first.

 

[iiiankiii]

If this gets anywhere near 980 performance, let alone 980ti, for $300 and 150w power consumption (have I rounded up all the rumors?) I'll buy one on launch day.

My wallet will be safe.

You mean to tell me a 14nm GPU can't get GTX 980 performance @ 150W? LOL. Considering that Polaris is said to get 2.5x performance/watt over 28nm, it would be a shock if it couldn't get GTX 980 performance @ 150W.

The R9 390x has a TDP of 275W and is basically on par with a GTX 980. At 2.5x per/watt, Polaris should get R9 390x's performance at @110W.

 

[beginner99]

299USD for their most expensive GPU in their 2016 line up? Suuuure.

Maybe the Polaris 10 PRO, but not the XT!
Even the PRO I would imagine around 349 and the XT at 449USD, if they match 980ti performance...

Nvidia will announce their line up first and until then I'm guessing AMD is in stand by to look at their numbers which should beat AMD polaris in performance, and then position their solution as the best value...

Exactly. Either performance is worse or price is higher. If true AMD would be retarded to price it that way. They could sell it for $349 instead and get just as much buyers because still half the price than a 980 Ti.

 

[maddie]

Originally Posted by Phynaz
If this gets anywhere near 980 performance, let alone 980ti, for $300 and 150w power consumption (have I rounded up all the rumors?) I'll buy one on launch day.

My wallet will be safe.

You mean to tell me a 14nm GPU can't get GTX 980 performance @ 150W? LOL. Considering that Polaris is said to get 2.5x performance/watt over 28nm, it would be a shock if it couldn't get GTX 980 performance @ 150W.

The R9 390x has a TDP of 275W and is basically on par with a GTX 980. At 2.5x per/watt, Polaris should get R9 390x's performance at @110W.

He's describing a GTX970 and sarcastically saying a 14nm Polaris can't meet those performance points. I struggle to understand that state of mind.

 

[maddie]

Exactly. Either performance is worse or price is higher. If true AMD would be retarded to price it that way. They could sell it for $349 instead and get just as much buyers because still half the price than a 980 Ti.

I disagree. Buyers at the margin will refuse the offer. Maybe not a huge amount but neither of us know the actual amount.

AMD needs to be profitable and this is is a combination of revenue increases and margins. I have not seen anyone here showing the margins on the present product stack. We assume that margins are very poor, but we don't know for sure and those who claim truth are just guessing.

In addition to a high unit margin/markup, AMD needs revenue (sale volume) and these two factors oppose each other. Optimum is unknown to me as an outsider.

As some have stated, AMD needs a much more attractive perf/$ ratio to lure Nvidia owners to upgrade. This I agree with. No logic, reasoning, etc will work. Nvidia has too much mindshare and the only way to reclaim some sales territory is to be a way more attractive purchase until the mass gamer community start accepting AMD once again.

 

[Phynaz]

We're keeping you to that.

980 is 180W.
980 is way overpriced but 970 is $300 for ~10-15% less performance.

And you honestly think AMD can't do better than that on 14nm? Your bias is blinding you.

What bias? I own more AMD cards than anything else.

 

[Phynaz]

Take off the rumors, what do you believe Polaris 10 performance will be relatively to todays GPUs and at what price ??

I think performance will be improved by a perceptible amount in the mid range at roughly the same msrp. Power consumption should be down considerably.

I don't think they are going to give you 100% performance increases while lowering prices significantly. What's in it for them? Those 14nm transistors are going to very, very expensive.

 

[Phynaz]

You mean to tell me a 14nm GPU can't get GTX 980 performance @ 150W? LOL. Considering that Polaris is said to get 2.5x performance/watt over 28nm, it would be a shock if it couldn't get GTX 980 performance @ 150W.

The R9 390x has a TDP of 275W and is basically on par with a GTX 980. At 2.5x per/watt, Polaris should get R9 390x's performance at @110W.

This is the company that said Carrizo would increase perf per watt by 2.5x. It did not happen.

Why are people so convinced by the marketing slide decks is beyond me.

390x performance at 110w for $300? I'm in as soon as they are available, with the condition they don't suffer from coil whining.

Edit :

4GB card.

 

[Udgnim]

before people get overhyped

remember the performance rumors on Fury / Fiji

 

[kraatus77]

before people get overhyped

remember the performance rumors on Fury / Fiji

And Furyx is the fastest 4k/dx12 card atm. i see nothing wrong.

 

[96Firebird]

And Furyx is the fastest 4k/dx12 card atm. i see nothing wrong.

I'm sure the rumors from a year ago were predicting for today.

 

[kraatus77]

I'm sure the rumors from a year ago were predicting for today.

Sorry, i didn't know people buy gpu on launch day, use for that day and then throw it in dustbin afterwards.

 

[96Firebird]

Sorry, i didn't know people buy gpu on launch day, use for that day and then throw it in dustbin afterwards.

This has nothing to do with what rumors point to...

But nice try?

 

[BlitzWulf]

http://arstechnica.co.uk/gadgets/2016/04/amd-focusing-on-vr-mid-range-polaris/

Arstechnica interview with Roy Taylor posted today

"If you look at the total install base of a Radeon 290, or a GTX 970 or above [the minimum specs required for VR], it's around 7.5 million units," explained Taylor. "But the issue is that if a publisher wants to sell a £40/$50 VR game, there's not a big enough market to justify that yet. We've got to prime the pumps, which means somebody has got to start writing cheques to big games publishers. Or we've got to increase the install TAM [total addressable market].

"The reason Polaris is a big deal," continued Taylor, "is because I believe we will be able to grow that TAM significantly. I don't think Nvidia is going to do anything to increase the TAM, because according to everything we've seen around Pascal, it's a high-end part. I don't know what the price is gonna be, but let's say it's as low as £500/$600 and as high as £800/$1000. That price range is not going to expand the TAM for VR. We're going on the record right now to say Polaris will expand the TAM. Full stop."

 

[AtenRa]

Yeap that concludes the R9 390/GTX 970 performance at lower price. Full stop.

This going to be another HD4870 vs GTX 280, unless NV will lower the price of the top cards to $500.

 

[railven]

Yeap that concludes the R9 390/GTX 970 performance at lower price. Full stop.

This going to be another HD4870 vs GTX 280, unless NV will lower the price of the top cards to $500.

If this is HD 4870 all over again, I'd buy two! (one for me, one for her, she does have a FreeSync monitor) and I'd give the 980 Ti to my nephews and ignore em for two years haha.

(I'm also tired of looking at the G-Sync tax as I monitor hunt.)

EDIT: It has to be 90-110% of whatever NV puts out, if both are aiming for some where near 980 Ti, I'd go for the better perf / price option like I did last time.)

 

[AtenRa]

If this is HD 4870 all over again, I'd buy two! (one for me, one for her, she does have a FreeSync monitor) and I'd give the 980 Ti to my nephews and ignore em for two years haha.

(I'm also tired of looking at the G-Sync tax as I monitor hunt.)

EDIT: It has to be 90-110% of whatever NV puts out, if both are aiming for some where near 980 Ti, I'd go for the better perf / price option like I did last time.)

I Believe GP104 (full die) will be more than 10-15% faster than GTX 980Ti. The thing to look at is the performance at DX-12 games, Polaris may be extremely close to GP104 at a significant lower price for the 1080/1440p resolutions.

 

[maddie]

I think performance will be improved by a perceptible amount in the mid range at roughly the same msrp. Power consumption should be down considerably.

I don't think they are going to give you 100% performance increases while lowering prices significantly. What's in it for them? Those 14nm transistors are going to very, very expensive.

Interesting. I see the flaws in your thinking.

Just like the 28nm > 14nm transition, you don't get max reduced power AND max frequency increase at the same time, as some persistently keep claiming.

You don't get 100% performance increase AND significantly lower prices at the same time.

You will get a 970/290 equivalent at a significantly lower price. I betting $225 max.
You will (almost ?) get a Fury X/980Ti equivalent at a significantly lower price.

Same performance, lower price. Not "100% performance increases while lowering prices significantly", as you claim.

Nvidia will probably go to higher than a 980Ti performance. Will they try for a higher price also instead of an equivalent one? We'll see soon.

"What's in it for them? Those 14nm transistors are going to very, very expensive"
The same as it has always been. An upgrade inducement/incentive.
The latest info I've seen has, at worst, a 14nm transistor = a 28nm one. How do you get these beliefs? Can you share your info (real numbers)?


edit: Missed that Taylor interview post. Pure confirmation there.

 

[maddie]

Yeap that concludes the R9 390/GTX 970 performance at lower price. Full stop.

This going to be another HD4870 vs GTX 280, unless NV will lower the price of the top cards to $500.

If this is HD 4870 all over again, I'd buy two! (one for me, one for her, she does have a FreeSync monitor) and I'd give the 980 Ti to my nephews and ignore em for two years haha.

(I'm also tired of looking at the G-Sync tax as I monitor hunt.)

EDIT: It has to be 90-110% of whatever NV puts out, if both are aiming for some where near 980 Ti, I'd go for the better perf / price option like I did last time.)

If true, it's beyond essential that they are on the Samsung/GloFlo fabs.

Can you imagine the problems filling demand if still on TSMC?

 

[Headfoot]

If nVidia is the only one dropping a chip fast enough to replace my 2x290 then I'll be going that way. If only multigpu wasn't so spotty on day 1... if Polaris 10 is truly very close to a 980 Ti though, and overclocks as well, then it could be a worthwhile upgrade. I'm okay losing a little top end performance to get the consistency of single GPU back

 

[kraatus77]

This has nothing to do with what rumors point to...

But nice try?

What rumors point to means jack as long as it's performing better than nvidia.
because that's the thing which matters.

if rumors point that polaris10 will be 3x faster than GP104. and it ends up being faster by just 10%. what do you think is best option ? GP104 ?because it's just 10% behind? LOL

same thing with furyx, doesn't matter what rumors said. it's the fastest 4k/dx12 card atm with better cooler. even on dx11 it's faster in some games.
unless game has gamewrecks.

 

[AtenRa]

If nVidia is the only one dropping a chip fast enough to replace my 2x290 then I'll be going that way. If only multigpu wasn't so spotty on day 1... if Polaris 10 is truly very close to a 980 Ti though, and overclocks as well, then it could be a worthwhile upgrade. I'm okay losing a little top end performance to get the consistency of single GPU back

If you have 2x 290 i would wait for Vega, unless Polaris 10 at $299 is ~GTX980ti . You could sell your 2x 290 and buy a single Polaris 10 for the same price. Or, by 2x $199 Polaris 10 Pro and be faster than GP104 at lower cost when CF is supported

 

[Headfoot]

When I bought my 2x290 I was mostly playing older games, but since then ive had less time to play games, and ironically the only time I get to do that anymore is when I take release day off for a game I'm anticipating to LAN with my buddies. So I've turned from a usually-not-day-1-gamer to pretty-much-only-day-1 gamer. So really trying to move single gpu. Would have gone 980 Ti if it wasnt for the fact that 14/16 is so close. It'll really depend on the benchmarks it seems. I can't imagine Polaris 10 will be slower than a 390x