A difference that makes no difference is no difference.
-
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.
Radeon RX 480 "Polaris" Launched at $199
- Thread starter Kaapstad
- Start date
A difference that makes no difference is no difference.
Loads of FE stock now. Nothing "paper" at all about the thousands of people that are happily gaming on their 1080's.
You can go pick one up easily right now and have been able to for weeks now. The price is stupid yes and i wouldn't buy a FE, but that isn't the argument here as many people have bought one and are happy with them.
Just because certain models are still hard to get is irrelevant. Often stock of custom cards can take a few weeks or months to come out or be available after an initial GPU launch.
Is supply amazing and enough to keep up with demand for custom models? Not at the moment no. Is it a "paper" launch? No, not at all.
Last edited:
Sorry but you are talking rubbish as above while not the most desirable models especially at the price there are reasonable quantities of some of the FE cards to buy right now - I can't link else where but:
https://www.overclockers.co.uk/gain...ddr5-pci-express-graphics-card-gx-206-gw.html
https://www.overclockers.co.uk/msi-...ddr5-pci-express-graphics-card-gx-327-ms.html
https://www.overclockers.co.uk/zota...s-graphics-card-zt-p10800a-10p-gx-098-zt.html
This is NOT a paper launch and neither are TSMC having any particular yield issues.
Davedree and SiDeards73 you have no idea what you are talking about regarding Kaap and it shows poorly to your argument that you have to take the discussion to a personal level and direct your bile at him directly rather than justify your point about the hardware.
Caporegime
- Joined
- 18 Oct 2002
- Posts
- 33,188
As we all know HBM1 performance can be updated to work entirely differently by drivers... so somehow it is still the HBM1 that is the problem.
From what I recall doesn't Fury X beat a 980ti at 1080p, and at every resolution and every setting except Hyper(de-optimised memory storage Nvidia are paying devs to use to hurt 4GB cards, both Nvidia and AMD ones) and lowest settings... funnily enough.
But still you know, HBM1 sucks, that it's beating the 980ti is irrelevant.
Fury is a not optimised overly large core built on an architecture not particularly designed for that number of shaders. It was more than anything a test bed for HBM so they could implement it, get the production chain for HBM1 established, start ramping that up, learn about HBM and how to optimise their next architecture that will use it and make improvements. Vega will bring chips with architecture tweaks designed for both HBM and a higher number of shaders.
Fury X is the reason AMD is able to bring HBM2 to higher volume and cheaper products than Nvidia will manage this generation.
512GB/s via GDDR5 is a split of 35W chips and 50W PHY layer, via HBM1 it's roughly 17W chip and 12W PHY. GDDR5x doesn't reduce the PHY layer power much at all, regardless of bus size or chip power moving X amount of data off a chip takes Y power without a huge amount of difference, 512bit with 6Gbps chips or 256bit bus with 12Gbps chips will use about the same PHY power. You'll save about maybe 10W at 512GB/s using less GDDR5x chips over GDDR5 as you use half the chips but the chips themselves run faster and use more power overall.
HBM2 makes this comparison even worse as it reduces chip power to achieve 512GB/s.
HBM will always use significantly less power, that 50W difference can't go away. That means a 250W high end chip which will probably use around 512GB/s or more, meaning 75W or so will be purely memory leaving 175W for the chip. AMD within the same power budget will use maybe 25W for the memory leaving 225W for the gpu.
The bandwidth achievable with gddr5/x is not a problem, it never was. The problem is the power it will take to achieve it. HBM will always use significantly less power than GDDR5.
The sole reason an older GCN architecture could remotely rival Maxwell a much updated one in performance/w was purely HBM using much less power. It saved 50W. With gddr5 Fury X would need to use over 300W or more likely, have 500-1000 less shaders, either way reducing performance/watt massively and making a Nano completely unachievable, not size but the compelling performance in that sized package or it would have been so loud and hot it wouldn't have worked.
HBM2 will do the same and be an even bigger difference vs even higher bandwidth high end chips this generation.
From what I recall doesn't Fury X beat a 980ti at 1080p, and at every resolution and every setting except Hyper(de-optimised memory storage Nvidia are paying devs to use to hurt 4GB cards, both Nvidia and AMD ones) and lowest settings... funnily enough.
But still you know, HBM1 sucks, that it's beating the 980ti is irrelevant.
Fury is a not optimised overly large core built on an architecture not particularly designed for that number of shaders. It was more than anything a test bed for HBM so they could implement it, get the production chain for HBM1 established, start ramping that up, learn about HBM and how to optimise their next architecture that will use it and make improvements. Vega will bring chips with architecture tweaks designed for both HBM and a higher number of shaders.
Fury X is the reason AMD is able to bring HBM2 to higher volume and cheaper products than Nvidia will manage this generation.
512GB/s via GDDR5 is a split of 35W chips and 50W PHY layer, via HBM1 it's roughly 17W chip and 12W PHY. GDDR5x doesn't reduce the PHY layer power much at all, regardless of bus size or chip power moving X amount of data off a chip takes Y power without a huge amount of difference, 512bit with 6Gbps chips or 256bit bus with 12Gbps chips will use about the same PHY power. You'll save about maybe 10W at 512GB/s using less GDDR5x chips over GDDR5 as you use half the chips but the chips themselves run faster and use more power overall.
HBM2 makes this comparison even worse as it reduces chip power to achieve 512GB/s.
HBM will always use significantly less power, that 50W difference can't go away. That means a 250W high end chip which will probably use around 512GB/s or more, meaning 75W or so will be purely memory leaving 175W for the chip. AMD within the same power budget will use maybe 25W for the memory leaving 225W for the gpu.
The bandwidth achievable with gddr5/x is not a problem, it never was. The problem is the power it will take to achieve it. HBM will always use significantly less power than GDDR5.
The sole reason an older GCN architecture could remotely rival Maxwell a much updated one in performance/w was purely HBM using much less power. It saved 50W. With gddr5 Fury X would need to use over 300W or more likely, have 500-1000 less shaders, either way reducing performance/watt massively and making a Nano completely unachievable, not size but the compelling performance in that sized package or it would have been so loud and hot it wouldn't have worked.
HBM2 will do the same and be an even bigger difference vs even higher bandwidth high end chips this generation.
Sure no one in their right mind would buy them - but people are buying them and there is stock - it isn't the description of a paper launch.
It is when the stuff people WANT to buy isn't there and the prices are way in excess of MSRP.
Actually it's you are incorrect on this.
Firstly you know of nothing about previous discissions where we have told kaap that hbm isn'y the reason for 1080p. I will provide links if you wish.
Secondly it's not personal i'm agreeing with another forum members viewpoint that kaap is incorrect on the hbm = poor 1080p.
Stay out of it when you are actually incorrectly accusing me with false accusations.
They are fulfilling pre-orders - sure supply isn't abundant but a paper launch is where really only reviewers get their hands on the product.
1070/1080 is not big die. GP100/102 is big die. Remember last new node process - 28nm? AMD launched on a 365mm2 die product. This time nVidia launch on a 314mm2 product with bigger and smaller dice to come.
Last edited:
That's a big die on a shrink from 28 to 16 in anyone's language. What argument next?
He is wrong on just about every aspect - nVidia's supply and ability to reduce prices will only increase with time - AMD need to pre-empt that and show their hand one way or another - holding their cards close to their chest at this point does nothing to help them.
Die size is relative to wafer really. But if you call 318mm2 big, what do you call GP100/102?
That isn't how it works.
A difference that makes no difference is no difference. Pre orders are not sales. Stop obfuscating. Or splitting hairs, whichever.
Soldato
- Joined
- 19 Feb 2011
- Posts
- 5,849
+1 to this actually, there has been many discussions with evidence to back it up.
And likewise its not personal, it's just the way it is on this matter
Yes it is. It obviously isn't working out that well either.