• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD Polaris architecture – GCN 4.0

Steampunk said:
I think AMD have made a marketing mistake by making everyone think Polaris 11 will be hugely powerful, when it's really only going to be Fury(ish) levels of performance on a smaller, cheaper, cooler chip. We think Polaris 10 is high end and Polaris 11 is low end, but in fact, there's also Vega coming at the end of the year, and that will be the true high end product that takes the place of the current Fury with something much better.

People are going to be disappointed in Polaris because it isn't a jump from Fury. AMD will be showing the price and efficiency and expecting us to be impressed, and we'll all be asking where the next-gen jump in performance is. It won't be coming until the end of the year or early 2017 when Vega arrives.

I'm sure Polaris will be great for what it is and what market segment it's aimed at, but it's not the high end product we are waiting for.
Click to expand...

AMD never claimed anything, they often claimed the opposite, that they are focused on efficiency and price tag, not their fault if ppl build up on rumors, and they cannot go denying every rumor that pops up.
beside AMD isn't really targeting enthusiasts to impress, they are mostly going for OEMs and notebooks for this line up, along with entry mainstream desktop market, AMD learned very well that no matter how good their product is, desktop market will always be mesmerised by Nvidia, even if between AMD and Nvidia, AMD got the better product, Nvidia will outsell them, so there is no point really, right now they want to grab market share elsewhere, and wait for their product to shine with DX12 benchs, or better optimised console ports, untill they ready up a high end, then push for desktop and try to impress then.
 
AlamoX said:
AMD never claimed anything, they often claimed the opposite, that they are focused on efficiency and price tag, not their fault if ppl build up on rumors, and they cannot go denying every rumor that pops up.
beside AMD isn't really targeting enthusiasts to impress, they are mostly going for OEMs and notebooks for this line up, along with entry mainstream desktop market, AMD learned very well that no matter how good their product is, desktop market will always be mesmerised by Nvidia, even if between AMD and Nvidia, AMD got the better product, Nvidia will outsell them, so there is no point really, right now they want to grab market share elsewhere, and wait for their product to shine with DX12 benchs, or better optimised console ports, untill they ready up a high end, then push for desktop and try to impress then.
Click to expand...


Not managing their customers' expectations and letting the rumour-mill be the only message out there is why AMD always get out-marketed by Nvidia. Which is a pity, because the hardware is every bit as good, and I expect Polaris and Vega to be something a bit special. When Polaris arrives and isn't a titan killer, it will be labelled a big fail, even though it's not supposed to be one. AMD needs to start managing that now, not after the product is tarnished. Look at what happened to R9 290 because of the awful stock cooler.
 
Last edited:
Steampunk said:
I think AMD have made a marketing mistake by making everyone think Polaris 11 will be hugely powerful, when it's really only going to be Fury(ish) levels of performance on a smaller, cheaper, cooler chip.
Click to expand...

Polaris 11 can't be Fury(ish) performance, as Polaris 10 is the top one thats only coming this year, and thats not even Fury(ish), its 390, Polaris 11 is the next one down in the stack, so will be 380.
 
Last edited:
Steampunk said:
Not managing their customers' expectations and letting the rumour-mill be the only message out there is why AMD always get out-marketed by Nvidia. Which is a pity, because the hardware is every bit as good, and I expect Polaris and Vega to be something a bit special. When Polaris arrives and isn't a titan killer, it will be labelled a big fail, even though it's not supposed to be one. AMD needs to start managing that now, not after the product is tarnished. Look at what happened to R9 290 because of the awful stock cooler.
Click to expand...

This just shows you didn'tread articles about polaris.
AMD stated numerous times in the last months that Polaris is the mainstream GPU.
 
Steampunk said:
That's so vague, it's meaningless.
Click to expand...

No its not they clearly said that VR ready is 970/390 performance and they aim to bring this performance at lower price.

I agree for the enthusiats its is a disappointment that they start the new generation from the lower tier and then building up, but its a logical choice. They need market share, and those are the tiers where they can sell volumes, plus they received criticism because they used the same low tier cards over and over with different names.

I myself was hyped to change my 390 for Polaris when it was first announced, butas it seems i need to wait for Vega or a bigger polaris -whichever will be the 490x - to change to.
 
humbug said:
For a start GP104 is 16nm while Polaris is 14nm, but they probably arent on the same performance level anyway.

Its the whole premise that Polaris 10 is equivalent in performance to a 390X that is ridiculous. not just because we don't know enough about it but also because your equations don't add up to the little we do know.
Click to expand...
Why I said 'mostly' the same new process. They're variations on a theme, both largely still based on the 20nm process. Maybe there's a huge difference between them, but it seems unlikely.

And I wasn't saying that P10 was 'equivalent' to a 390X with any certainty. I merely estimate that's the ballpark where it will be. If you read all of what I've said, I have specifically mentioned my guess is that it will actually be a tad ahead of that. I would hope it would be, at least.

And my reasoning is simply that I dont think a 2xperformance/watt improvement in efficiency is going to translate into a 232mm^ die new card outperforming a previous 28nm 438mm^ card by some hugely significant margin. Performance/watt is almost assuredly used as the most 'appealing' figure they could come up with. There are better metrics to use to show how much more powerful the new cards are, after all.

We'll see man. I dont think I'm being ridiculous at all. If I'm totally wrong, I'll be glad to admit it. I've got no problem with that whatsoever. I'm rooting for Polaris to be great.
 
That's,the thing the GP104 is meant to be around 320MM2 and will outperform a 600MM2 GM200 and that is on a less denser 16NM process. So unless there is some big issue with Polaris 10,it should be by extension beating an R9 390X quite easily too.

LoadsaMoney said:
Well hopefully we get a reversal of the FuryX this time :p
Click to expand...

Reverse hype?! :p
 
Mtom said:
This just shows you didn'tread articles about polaris.
AMD stated numerous times in the last months that Polaris is the mainstream GPU.
Click to expand...

Again, they use vague phrases like "enthusiast". Lots of hype is building, and no tamping down of that fire from AMD. When Polaris turns up and isn't Vega levels of performance, there will be a backlash.
 
Steampunk said:
Again, they use vague phrases like "enthusiast". Lots of hype is building, and no tamping down of that fire from AMD. When Polaris turns up and isn't Vega levels of performance, there will be a backlash.
Click to expand...
In fairness, this narrative seems to be entirely in your head. Certainly I haven't seen any evidence of it in real life. People's expectations for Polaris seem to be firmly in line with what it's likely to offer. In fact, people seem rather grounded for both Polaris and Pascal, with the general feeling being that huge performance gains over the current high end not likely to be seen until next year when Vega and Big Pascal arrive.

Of course you're always going to have the odd hopeful individual/raging fanboy expecting miracles, but they're the minority and will only have themselves to blame for letting their imagination run wild.
 
390 performance at half the power, it should sell very well. It will be interesting how long NVidia waits to launch the GP106 to combat it.
 
You must log in or register to reply here.
Back
Top Bottom