Overclock.net › Forums › Industry News › Rumors and Unconfirmed Articles › [TT] NVIDIA should launch its next-gen Pascal GPUs with HBM2 in 2H 2016
New Posts  All Forums:Forum Nav:

[TT] NVIDIA should launch its next-gen Pascal GPUs with HBM2 in 2H 2016 - Page 63

post #621 of 724
Quote:
Originally Posted by mcg75 View Post

They probably would have still sold 95% of what they did had they advertised it with 3.5 gb.

But that's not the point really.

The amount of bad publicity from it will come back to haunt them for awhile. Deservedly so.

Yes, it is the point really.

Because all that this generated was bad publicity. This was a mistake, and only a mistake. Not a con, not a cheat, not a deception, not a lie. The ONLY thing this did was make Nvidia look bad. As you said, deservedly so, because it was a foolish error they should have caught. But that's why I make the claim that the forum-riot impact of this issue is way, way WAY out of proportion with the actual facts of the issue. And as for a motive, the only thing I can think of is people want Nvidia to be bad, so they latch onto anything that they can find that's bad and don't let go, don't see other perspectives, don't consider any mitigating possibilities or likelihoods, and instead fixate on how evil Nvidia must be because they make us pay for things they design.
post #622 of 724
Quote:
Originally Posted by Mand12 View Post

I'm still not clear why you think there's anything "unscrupulous" about this. There was no deception involved, there was no upside to making people think the spec sheet was correct. This could only ever have blown up in their faces, and it really wouldn't have made much difference had it been correct from the start.

To call them "unscrupulous" means that they pulled a fast one on us, which means intent. Far more likely, it was just a stupid mistake on the part of their marketing team, that you are now demonizing them for because you want them to be demons.

I don't THINK it was a mistake. I think they decided that it would be easier to claim it was a feature if it was ever found out about instead of being upfront about it to begin with. One way ensures you sale tons of cards before anyone finds out and the other way impacts sales from the start.
Super P's rig
(20 items)
 
  
CPUMotherboardGraphicsRAM
5960x ASUS X99-A II Asus GTX 1080 Ti Corsair Vengeance DDR4 3000 
Hard DriveHard DriveHard DriveOptical Drive
MyDigitalSSD BPX NVMe Samsung 850 EVO Seagate Momentus XT 500 GB External DVDRW 
CoolingCoolingOSMonitor
EK-XLC Predator 240 Swiftech 240mm Radiator Windows 10 Samsung 40" 4K - UN40KU6290 
KeyboardPowerCaseMouse
G710+ EVGA SuperNOVA 850G2 Fractal Design Define S G700s 
Mouse PadAudioAudioAudio
Vipamz Extended XXXL Asus U7 M-Audio AV40 Sennheiser HD 439 
  hide details  
Reply
Super P's rig
(20 items)
 
  
CPUMotherboardGraphicsRAM
5960x ASUS X99-A II Asus GTX 1080 Ti Corsair Vengeance DDR4 3000 
Hard DriveHard DriveHard DriveOptical Drive
MyDigitalSSD BPX NVMe Samsung 850 EVO Seagate Momentus XT 500 GB External DVDRW 
CoolingCoolingOSMonitor
EK-XLC Predator 240 Swiftech 240mm Radiator Windows 10 Samsung 40" 4K - UN40KU6290 
KeyboardPowerCaseMouse
G710+ EVGA SuperNOVA 850G2 Fractal Design Define S G700s 
Mouse PadAudioAudioAudio
Vipamz Extended XXXL Asus U7 M-Audio AV40 Sennheiser HD 439 
  hide details  
Reply
post #623 of 724
Quote:
Originally Posted by criminal View Post

No mistake. I think they decided that it would be easier to claim it was a feature if it was ever found out about instead of being upfront about it to begin with. One way ensures you sale tons of cards before anyone finds out and the other way impacts sales from the start.

rolleyes.gif

Why bother with facts, when a conspiracy will do, eh?

There is no upside to them trying this. There is ZERO chance this wouldn't have been found out. And then it blows up in their faces.
post #624 of 724
Quote:
Originally Posted by Mahigan View Post

It's possible to do on GDDR5 but GDDR5 isn't as fast as HBM.
Which is completely irrelevant to the ability of a GPU's VRAM pool to store or swap in/out data from system RAM. HBM-based bandwidth figures refer only to the speed of the GPU in reading from and writing to VRAM. VRAM exists as local storage because system RAM is too far away/slow (because of PCI-e limitations, which are completely unaffected by VRAM bandwidth) to capably store all the data any given GPU needs at any given time.

Whether it's Fiji's 512 GB/s, GM200's 336 GB/s, GM206's 112 GB/s, etc. for example is completely irrelevant to accessing system RAM and therefore capacity remains a comparable limitation (meaning no additional ways to get around it) regardless of VRAM bandwidth. Therefore, your claim of HBM being different doesn't strike me as relevant.

Quote:
And I never said it reduced the data held in system RAM. You created that strawman yourself.


I created that? I never even said that. I was disagreeing with your position that it made capacity in VRAM non-comparable across GPUs with differing VRAM bandwidth however, which is the only possible thing you could have been implying with this statement, particularly the section in bold:

Quote:
HBM is different than GDDR5. Its bandwidth is used like an embeded cache. Anything that requires quick access, sits in the HBM, other lower bandwidth sensitive storage needs go into the System RAM.

Implying that VRAM capacity (and/or associated limitations) between HBM and GDDR5 isn't entirely comparable because, "HBM is different than GDDR5" is the only relevant thing you could have meant by this.

Quote:
Yes it is 4GB capacity but used as a quick access embeded cache like we see on some consoles. Any data requiring quicker access resides on the HBM, data which is not bandwidth bound resides on the system RAM. The end result is 0 performance hit.

Excluding whether or not you're examining enough cases to say that is the case that there is "0 performance hit", please explain what you mean in the context of your above quote about HBM being different? What about HBM being "different" from GDDR5 has any bearing on capacity limitation comparisons?

Quote:
Prior to the Fiji launch AMD had this to say:
And they were right.

Right that certain optimizations could be made, of course. Right that Fiji's VRAM would never be a problem? Haven't seen enough actual testing on the matter to figure it out; VRAM in general isn't very strenuously-tested in benchmarks, but that's irrelevant to my contention of your point of HBM being different.
Edited by Serandur - 3/1/16 at 6:44am
Ice-nine
(17 items)
 
  
CPUMotherboardGraphicsRAM
i7-6700K Asus Z170-DELUXE Gigabyte G1 GTX 980 Ti Corsair Vengeance LPX DDR4 3000 
Hard DriveHard DriveOptical DriveCooling
Samsung 850 Evo 500 GB Seagate Barracuda 7200 RPM 2 TB Asus DVD Drive DRW-24B1ST/BLK/B/AS Phanteks PH-TC14PE 
OSMonitorKeyboardPower
Windows 8.1 Pro AOC Q2770PQU Corsair K95 RGB - Cherry MX Blue EVGA Supernova G2 750W 
CaseMouseMouse PadAudio
NZXT Phantom 410 Gunmetal Edition Logitech G502 Proteus Core Razer Goliathus Speed Edition Small Cyber Acoustics Satellite CA-3602 
Audio
Oppo PM-3 Closed Back Planar Magnetic Headphones 
  hide details  
Reply
Ice-nine
(17 items)
 
  
CPUMotherboardGraphicsRAM
i7-6700K Asus Z170-DELUXE Gigabyte G1 GTX 980 Ti Corsair Vengeance LPX DDR4 3000 
Hard DriveHard DriveOptical DriveCooling
Samsung 850 Evo 500 GB Seagate Barracuda 7200 RPM 2 TB Asus DVD Drive DRW-24B1ST/BLK/B/AS Phanteks PH-TC14PE 
OSMonitorKeyboardPower
Windows 8.1 Pro AOC Q2770PQU Corsair K95 RGB - Cherry MX Blue EVGA Supernova G2 750W 
CaseMouseMouse PadAudio
NZXT Phantom 410 Gunmetal Edition Logitech G502 Proteus Core Razer Goliathus Speed Edition Small Cyber Acoustics Satellite CA-3602 
Audio
Oppo PM-3 Closed Back Planar Magnetic Headphones 
  hide details  
Reply
post #625 of 724
Quote:
Originally Posted by Mand12 View Post

rolleyes.gif

Why bother with facts, when a conspiracy will do, eh?

There is no upside to them trying this. There is ZERO chance this wouldn't have been found out. And then it blows up in their faces.

rolleyes.gif

There are no absolute facts regarding the 970. We will never know what is 100% fact because Nvidia has no reason to be completely truthful about the incident. What is fact is that they tried to spin it as some feature instead of what it actually is... a handicap.
Super P's rig
(20 items)
 
  
CPUMotherboardGraphicsRAM
5960x ASUS X99-A II Asus GTX 1080 Ti Corsair Vengeance DDR4 3000 
Hard DriveHard DriveHard DriveOptical Drive
MyDigitalSSD BPX NVMe Samsung 850 EVO Seagate Momentus XT 500 GB External DVDRW 
CoolingCoolingOSMonitor
EK-XLC Predator 240 Swiftech 240mm Radiator Windows 10 Samsung 40" 4K - UN40KU6290 
KeyboardPowerCaseMouse
G710+ EVGA SuperNOVA 850G2 Fractal Design Define S G700s 
Mouse PadAudioAudioAudio
Vipamz Extended XXXL Asus U7 M-Audio AV40 Sennheiser HD 439 
  hide details  
Reply
Super P's rig
(20 items)
 
  
CPUMotherboardGraphicsRAM
5960x ASUS X99-A II Asus GTX 1080 Ti Corsair Vengeance DDR4 3000 
Hard DriveHard DriveHard DriveOptical Drive
MyDigitalSSD BPX NVMe Samsung 850 EVO Seagate Momentus XT 500 GB External DVDRW 
CoolingCoolingOSMonitor
EK-XLC Predator 240 Swiftech 240mm Radiator Windows 10 Samsung 40" 4K - UN40KU6290 
KeyboardPowerCaseMouse
G710+ EVGA SuperNOVA 850G2 Fractal Design Define S G700s 
Mouse PadAudioAudioAudio
Vipamz Extended XXXL Asus U7 M-Audio AV40 Sennheiser HD 439 
  hide details  
Reply
post #626 of 724
Quote:
Originally Posted by criminal View Post

Nvidia has no reason to be completely truthful about the incident.

If you really believe this, then there's no point discussing this topic with you.
post #627 of 724
Quote:
Originally Posted by Mand12 View Post

If you really believe this, then there's no point discussing this topic with you.

Just like every other topic with you. You know all and no one else knows anything. rolleyes.gif
Super P's rig
(20 items)
 
  
CPUMotherboardGraphicsRAM
5960x ASUS X99-A II Asus GTX 1080 Ti Corsair Vengeance DDR4 3000 
Hard DriveHard DriveHard DriveOptical Drive
MyDigitalSSD BPX NVMe Samsung 850 EVO Seagate Momentus XT 500 GB External DVDRW 
CoolingCoolingOSMonitor
EK-XLC Predator 240 Swiftech 240mm Radiator Windows 10 Samsung 40" 4K - UN40KU6290 
KeyboardPowerCaseMouse
G710+ EVGA SuperNOVA 850G2 Fractal Design Define S G700s 
Mouse PadAudioAudioAudio
Vipamz Extended XXXL Asus U7 M-Audio AV40 Sennheiser HD 439 
  hide details  
Reply
Super P's rig
(20 items)
 
  
CPUMotherboardGraphicsRAM
5960x ASUS X99-A II Asus GTX 1080 Ti Corsair Vengeance DDR4 3000 
Hard DriveHard DriveHard DriveOptical Drive
MyDigitalSSD BPX NVMe Samsung 850 EVO Seagate Momentus XT 500 GB External DVDRW 
CoolingCoolingOSMonitor
EK-XLC Predator 240 Swiftech 240mm Radiator Windows 10 Samsung 40" 4K - UN40KU6290 
KeyboardPowerCaseMouse
G710+ EVGA SuperNOVA 850G2 Fractal Design Define S G700s 
Mouse PadAudioAudioAudio
Vipamz Extended XXXL Asus U7 M-Audio AV40 Sennheiser HD 439 
  hide details  
Reply
post #628 of 724
Quote:
Originally Posted by Serandur View Post

Which is completely irrelevant to the ability of a GPU's VRAM pool to store or swap in/out data from system RAM. HBM-based bandwidth figures refer only to the speed of the GPU in reading from and writing to VRAM. VRAM exists as local storage because system RAM is too far away/slow (because of PCI-e limitations, which are completely unaffected by VRAM bandwidth) to capably store all the data any given GPU needs at any given time.

Whether it's Fiji's 512 GB/s, GM200's 336 GB/s, GM206's 112 GB/s, etc. for example is completely irrelevant to accessing system RAM and therefore capacity remains a comparable limitation (meaning no additional ways to get around it) regardless of VRAM bandwidth. Therefore, your claim of HBM being different doesn't strike me as relevant.
I created that? I never even said that. I was disagreeing with your position that it made capacity in VRAM non-comparable across GPUs with differing VRAM bandwidth however, which is the only possible thing you could have been implying with this statement, particularly the section in bold:
Implying that VRAM capacity (and/or associated limitations) between HBM and GDDR5 isn't entirely comparable because, "HBM is different than GDDR5" is the only relevant thing you could have meant by this.
Excluding whether or not you're examining enough cases to say that is the case that there is "0 performance hit", please explain what you mean in the context of your above quote about HBM being different? What about HBM being "different" from GDDR5 has any bearing on capacity limitation comparisons?
Right that certain optimizations could be made, of course. Right that Fiji's VRAM would never be a problem? Haven't seen enough actual testing on the matter to figure it out; VRAM in general isn't very strenuously-tested in benchmarks, but that's irrelevant to my contention of your point of HBM being different.

Nobody said anything about HBM increasing Fiji's ability to swap in/out of the system memory pool except you.

It's about what your graphics driver stores in the framebuffer vs what it stores in the system memory. If the graphics driver stores bandwidth constrained data into your frame buffer and non constrained into the system memory, you won't notice a difference in-game. And you also won't notice a difference when benchmarking. In other words, aside from using more system memory, there is no performance penalty.

So you get the full benefit of HBMs increased memory bandwidth. So what's different about HBM? Only that it is wider and thus offers more bandwidth than GDDR5. And as I stated above, nothing is stopping AMD from using the same optimizations for Hawaii and its 4GB GDDR5.

The evidence speaks for itself. Please, feel free to return once you have evidence for your claims.

Ps.
In theory, varying on PCIe bus saturation, CrossfireX configurations could suffer however. This would require further testing.
Edited by Mahigan - 3/1/16 at 6:57am
Kn0wledge
(20 items)
 
Pati3nce
(14 items)
 
Wisd0m
(10 items)
 
Reply
Kn0wledge
(20 items)
 
Pati3nce
(14 items)
 
Wisd0m
(10 items)
 
Reply
post #629 of 724
Quote:
Originally Posted by criminal View Post

Just like every other topic with you. You know all and no one else knows anything. rolleyes.gif

My point was that it's not worth discussing this topic with you because you're already convinced that everything Nvidia says is a lie. It doesn't matter what they say, it doesn't matter what I say, it doesn't matter what anyone says at that point - you won't care.

It's not that you don't know anything, it's that you choose to not care what is known.
post #630 of 724
Quote:
Originally Posted by Mahigan View Post

Nobody said anything about HBM increasing Fiji's ability to swap in/out of the system memory pool except you.

It's about what your graphics driver stores in the framebuffer vs what it stores in the system memory.

The evidence speaks for itself. Please, feel free to return once you have evidence for your claims.

What are you talking about? Do you even know what VRAM is and how it relates? Evidently not: You're not answering my questions, you're vaguely spouting nonsense.

The evidence for my "claims" are basic understandings of memory configurations. YOU need to learn about those before making bold assertions about tech you're demonstrating little understanding of. You're talking about VRAM capacity not being a problem for Fiji because "HBM is different from GDDR5" due to some vague claim about HBM being used as an "embedded cache". Literally nothing about the claim differs from GDDR5's use and therefore doesn't in any way explain the supposed different from between HBM and GDDR5 that is relevant in capacity limitation comparisons.

If your claims about HBM's bandwidth don't relate to system RAM access speeds, then there's literally no relevant claim to be made there. VRAM exists as a local memory pool in lieu of ineffective system RAM speeds. The only way that capacity limitations could be inherently different between any two memory technologies is if they cut down on the reliance of local memory storage (which would require improved system RAM access capability). Otherwise it's purely down to memory management techniques like the ones AMD detailed. Those I don't dispute, but it's you (not me) who made the claim of HBM being different from GDDR5 in this context. I expect an explanation, not your condescending refusal to acknowledge when you don't understand a technology.
Ice-nine
(17 items)
 
  
CPUMotherboardGraphicsRAM
i7-6700K Asus Z170-DELUXE Gigabyte G1 GTX 980 Ti Corsair Vengeance LPX DDR4 3000 
Hard DriveHard DriveOptical DriveCooling
Samsung 850 Evo 500 GB Seagate Barracuda 7200 RPM 2 TB Asus DVD Drive DRW-24B1ST/BLK/B/AS Phanteks PH-TC14PE 
OSMonitorKeyboardPower
Windows 8.1 Pro AOC Q2770PQU Corsair K95 RGB - Cherry MX Blue EVGA Supernova G2 750W 
CaseMouseMouse PadAudio
NZXT Phantom 410 Gunmetal Edition Logitech G502 Proteus Core Razer Goliathus Speed Edition Small Cyber Acoustics Satellite CA-3602 
Audio
Oppo PM-3 Closed Back Planar Magnetic Headphones 
  hide details  
Reply
Ice-nine
(17 items)
 
  
CPUMotherboardGraphicsRAM
i7-6700K Asus Z170-DELUXE Gigabyte G1 GTX 980 Ti Corsair Vengeance LPX DDR4 3000 
Hard DriveHard DriveOptical DriveCooling
Samsung 850 Evo 500 GB Seagate Barracuda 7200 RPM 2 TB Asus DVD Drive DRW-24B1ST/BLK/B/AS Phanteks PH-TC14PE 
OSMonitorKeyboardPower
Windows 8.1 Pro AOC Q2770PQU Corsair K95 RGB - Cherry MX Blue EVGA Supernova G2 750W 
CaseMouseMouse PadAudio
NZXT Phantom 410 Gunmetal Edition Logitech G502 Proteus Core Razer Goliathus Speed Edition Small Cyber Acoustics Satellite CA-3602 
Audio
Oppo PM-3 Closed Back Planar Magnetic Headphones 
  hide details  
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Rumors and Unconfirmed Articles
Overclock.net › Forums › Industry News › Rumors and Unconfirmed Articles › [TT] NVIDIA should launch its next-gen Pascal GPUs with HBM2 in 2H 2016