Question 'Ampere'/Next-gen gaming uarch speculation thread

[Ottonomous]

How much is the Samsung 7nm EUV process expected to provide in terms of gains?
How will the RTX components be scaled/developed?
Any major architectural enhancements expected?
Will VRAM be bumped to 16/12/12 for the top three?
Will there be further fragmentation in the lineup? (Keeping turing at cheaper prices, while offering 'beefed up RTX' options at the top?)
Will the top card be capable of >4K60, at least 90?
Would Nvidia ever consider an HBM implementation in the gaming lineup?
Will Nvidia introduce new proprietary technologies again?

Sorry if imprudent/uncalled for, just interested in the forum member's thoughts.

 

[Glo.]

Huh??

What does "in terms of everything" even mean? And whatever it means, what are you basing it off?

Where are you getting this bit on AMD having issues on power delivery? Power livery is a trivial thing, why on earth would this be an issue?

Are you saying that Microsoft is lying about their power consumption?

And how is there already a tradition of being power hungry for a chip that has never been released? Just because Fiji was a bit more power hungry than the 1080Ti doesn't mean RDNA2 will be also. There is literally thing compatible between Fiji and Navi. They aren't even the same ISA, much less a similar chip design.

He is FUDing. Or doing damage control for Nvidia.

Ignore him.

 

[Konan]

You expecting the RTX3070 to be more than the RTX2080ti ?? and if so by how much ??

Because RTX2070 Super to RTX2080Ti is roughly at +32% at 1440p (according to latest reviews in Techpowerup)

KatCorgi on Twitter says within 5%

 

[Glo.]

KatCorgi on Twitter says within 5%

Where?

 

[Maverick177]

Well, the fact that you came out of silence 3 years since your last post, right now, and all you do is FUD in Nvidia thread, talking about AMD tech, tells a lot.

Yeah, AMD might have for once kicked Nvidia's ass.

Well Im saying this round Nvidia has the Finewine factor but not because of their drivers.

Huh??

What does "in terms of everything" even mean? And whatever it means, what are you basing it off?

Where are you getting this bit on AMD having issues on power delivery? Power delivery is a trivial thing, why on earth would this be an issue?

Are you saying that Microsoft is lying about their power consumption?

And how is there already a tradition of being power hungry for a chip that has never been released? Just because Fiji was a bit more power hungry than the 1080Ti doesn't mean RDNA2 will be also. There is literally thing compatible between Fiji and Navi. They aren't even the same ISA, much less a similar chip design.

Pretty much a landslide Ampere vs RDNA2. Early RDNA2 samples ran really hot, think Vega OC hot. Microsoft put 1x there for the wow factor, that's it.

 

[Maverick177]

He is FUDing. Or doing damage control for Nvidia.

Ignore him.

Funny because I have never owned an nVidia card nor stock in my life.

 

[Maverick177]

Where?

You won't find it.

 

[Mopetar]

Hasn't this generation taught us nothing? AMD won't play the value brand anymore if they have premium products. So our only hope for lower prices is actually - Nvidia.

Well the 5700XT was AMD's premium product, so it's hard to draw too many conclusions about their pricing from the soon to be last generation.

I do realize that's kind of a trolly statement, but it's also kind of true. AMD hasn't had a top end competitor in a while so it's hard to say what they'd do.

 

[Glo.]

Well the 5700XT was AMD's premium product, so it's hard to draw too many conclusions about their pricing from the soon to be last generation.

I do realize that's kind of a trolly statement, but it's also kind of true. AMD hasn't had a top end competitor in a while so it's hard to say what they'd do.

Forgot about Radeon VII?

 

[Glo.]

You won't find it.

Because such a twitt does not exist .

 

[AtenRa]

Well the 5700XT was AMD's premium product, so it's hard to draw too many conclusions about their pricing from the soon to be last generation.

I do realize that's kind of a trolly statement, but it's also kind of true. AMD hasn't had a top end competitor in a while so it's hard to say what they'd do.

Huge dies, not unlimited 7nm volume, high NVIDIA prices
Well from the above i believe NAVI 2.0 prices will continue the same Turing-NAVI 1 trend.

 

[Maverick177]

Because such a twitt does not exist .

Because twitter leakers aren't actually leakers. Only reason they have that much infos to leak is because of the quarantine.

 

[uzzi38]

Pretty much a landslide Ampere vs RDNA2. Early RDNA2 samples ran really hot, think Vega OC hot.

Oh really now. Enlighten us on the timeframe for these 'early samples'. You don't have to be too specific if you don't want to, even a quarter is enough for me to judge anything you say.

 

[Glo.]

Because twitter leakers aren't actually leakers. Only reason they have that much infos to leak is because of the quarantine.

Like you have, and thats why you talk about RDNA2 and Xbox Series X here? .

 

[Konan]

Because such a twitt does not exist .

there you go....

GA104 (non Tti) ~5%

https://twitter.com/x/status/1237748855426310144

 

[Glo.]

Huge dies, not unlimited 7nm volume, high NVIDIA prices
Well from the above i believe NAVI 2.0 prices will continue the same Turing-NAVI 1 trend.

Yeah, pretty much.

Unfortunately. It appears as if there will not be any more dGPUs for "cheap"...

 

[Glo.]

there you go....

GA104 (non Tti) ~5%

https://twitter.com/x/status/1237748855426310144

Very old. Also if his 106 and 107 dies are correct...

 

[uzzi38]

Because twitter leakers aren't actually leakers. Only reason they have that much infos to leak is because of the quarantine.

Kimi's been around in the Twitter space leaking since mid last year. He leaked the Super line a couple of days after announcement. For the longest time he's been behind a locked account.

In reality, there were discussions on 7LPP related issues regarding Nvidia as of late last year behind private Tweets, DMs and other places.

 

[Maverick177]

Kimi's been around in the Twitter space leaking since mid last year. He leaked the Super line a couple of days after announcement. For the longest time he's been behind a locked account.

In reality, there were discussions on 7LPP related issues regarding Nvidia as of late last year behind private Tweets, DMs and other places.

Believe what you believe. He's not a leaker.

 

[Konan]

Very old. Also if his 106 and 107 dies are correct...

Kimi confirmed it. The GA 104 core count too recently. Oh and at 220W

 

[uzzi38]

Believe what you believe. He's not a leaker.

Well he is and he's not.

He's not the original source if that's what you mean. The original source is someone else. Kimi's just someone who acts as a public face for the other guy.

But there is a legit leaker at the end of the trail.

 

[Glo.]

Well he is and he's not.

He's not the original source if that's what you mean. The original source is someone else. Kimi's just someone who acts as a public face for the other guy.

But there is a legit leaker at the end of the trail.

Are you sure that was good idea to post it HERE?

 

[uzzi38]

Are you sure that was good idea to post it HERE?

No chance anyone will ever find the end of said trail. It's not a common source, nor is it anyone will ever find out easily.

Or so I've been told by a friend.

 

[Glo.]

Kimi confirmed it. The GA 104 core count too recently. Oh and at 220W

If you mean a twitt from 8th July, then he said that 220W TDP is RTX 3070, not 3070 Ti, which is full die, according to him, and has 250W TDP.

Then yes, this GPU(RTX 3070 Ti) might actually be within 5% of RTX 2080 Ti. That is fully believable.

Why? According to him RTX 3070 Ti has GDDR6X, instead of GDDR6. Thats what changes the perspective for this. It might be 95% of RTX 2080 Ti's performance, then.

No chance anyone will ever find the end of said trail. It's not a common source, nor is it anyone will ever find out easily.

Or so I've been told by a friend.

Lets hope so, then...

 

[USER8000]

The 1x Xbox One power consumption figure you saw on Hotchip slide is actually more like 1.3 ~ 1.4. Big Navi die is power hungry as in tradition.

Because they can lie to their investors at a technical conference. I am doubtful.

 

[Stuka87]

Pretty much a landslide Ampere vs RDNA2.

Early RDNA2 samples ran really hot, think Vega OC hot. Microsoft put 1x there for the wow factor, that's it.

Ok, first off "hot" just means inadequate cooling. It literally means nothing else. You can have a 10W chip run 'super hot'. The whole reason the RX 3090 has a gigantic cooler is so that it won't run hot while consuming 350W+.

Claiming Microsoft broke FTC law for a 'wow' factor is rather ludicrous.

And finally, you last posted in 2017 in posts attacking AMD and making claims that we now know were wrong, why come back now?