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

Page 67 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Ottonomous

Senior member
May 15, 2014
559
292
136
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.
 

GodisanAtheist

Diamond Member
Nov 16, 2006
7,166
7,666
136
So lot of conversation about the high end in this thread, what about the successor to the 16xx family or cards?

Any thoughts on if NV is going to go RTX from high end to entry level or if we're going to see a 17xx GTX series.

For all the leaks I don't think I've heard anything on that front, which would be pretty big...
 

Stuka87

Diamond Member
Dec 10, 2010
6,240
2,559
136
So lot of conversation about the high end in this thread, what about the successor to the 16xx family or cards?

Any thoughts on if NV is going to go RTX from high end to entry level or if we're going to see a 17xx GTX series.

For all the leaks I don't think I've heard anything on that front, which would be pretty big...

nVidia could slide the current TU106 cards down to fill the slot that the TU116 now sits in. Its not uncommon for the low end to be occupied by a previous gen card. Could be sold an RTX 3050 or something. But that won't jive for the mobile side of things. They will definitely wan't a chip on the newer node for the power savings. Under the hood it may be something as simple TU106 on the new node with a handful of tweaks. This is also not unheard of from nVidia's side of things.
 

GodisanAtheist

Diamond Member
Nov 16, 2006
7,166
7,666
136
nVidia could slide the current TU106 cards down to fill the slot that the TU116 now sits in. Its not uncommon for the low end to be occupied by a previous gen card. Could be sold an RTX 3050 or something. But that won't jive for the mobile side of things. They will definitely wan't a chip on the newer node for the power savings. Under the hood it may be something as simple TU106 on the new node with a handful of tweaks. This is also not unheard of from nVidia's side of things.

-If NV can sell the og 2060 for $300 bucks I fully expect them to be able bring down the cost for that level of performance to the $200 and below space after a die shrink and optimizations.

If DLSS 3.0 is truly game agnostic without any need for dev implementation, then I can see NV going RT for the whole stack for sure, no reason not to.

The 16xx series might end up as an one off weird anomaly of a series.
 

arandomguy

Senior member
Sep 3, 2013
556
183
116
So lot of conversation about the high end in this thread, what about the successor to the 16xx family or cards?

Any thoughts on if NV is going to go RTX from high end to entry level or if we're going to see a 17xx GTX series.

For all the leaks I don't think I've heard anything on that front, which would be pretty big...

The main source of Ampere leaks also reported that GA106 and GA107 had taped out presumably sometime in June 2020 judging by the wording. This means GA102, GA104, GA106, and GA107 have seen mentions so far. Judging by that and general timelines I wouldn't expect anything in those segments this year and possibly not even until more so mid next year (at least Q2)

TU102, TU104, TU106 served as the RTX cards. While TU116 and TU117 served as the GTX cards. So we can infer that there is possibility the entire RTX line will extend down to where the GTX 1660 is at the very least. If we look at the past typically XX7 served the bottom end of the GTX cards (eg. down to the GTX 1650) with sometimes a XX8 serving the most entry level GT cards that aren't really gaming targeted.

GA106 also won't be as "big" (at least cutting down 1/4 the memory buss) relative to the rest of the stack as TU106 going by current rumors so it will scale down further and serve what TU116 had to as well. Meaning GA107 services the bottom end for gaming.

I'd guess the product stack returns more to past normalcy without the split possiblity except for a very bottom end that's more so for video than gaming.
 
Last edited:

Mopetar

Diamond Member
Jan 31, 2011
8,113
6,768
136
It probably depends on how much they improved the RT over Turing, but even if it's as good as rumored I don't see a lot of point in including it in the low end cards that might still struggle to hit acceptable performance even with RT turned off.

I suppose that it would make for good marketing though and at some point they need to have a bigger install base to get developers to invest more time into adding ray tracing elements into their games.
 

GodisanAtheist

Diamond Member
Nov 16, 2006
7,166
7,666
136
It probably depends on how much they improved the RT over Turing, but even if it's as good as rumored I don't see a lot of point in including it in the low end cards that might still struggle to hit acceptable performance even with RT turned off.

I suppose that it would make for good marketing though and at some point they need to have a bigger install base to get developers to invest more time into adding ray tracing elements into their games.

- I figure DLSS will do a bunch of the heavy lifting on the lowest end cards.

Even if the cards cannot get acceptable RTRT performance (by our standards), they can move them with the promise of letting folks buy into the feature set and getting IQ improvements where they can afford the FPS hit.
 

Dribble

Platinum Member
Aug 9, 2005
2,076
611
136
It probably depends on how much they improved the RT over Turing, but even if it's as good as rumored I don't see a lot of point in including it in the low end cards that might still struggle to hit acceptable performance even with RT turned off.

I suppose that it would make for good marketing though and at some point they need to have a bigger install base to get developers to invest more time into adding ray tracing elements into their games.
With DLSS they only need 540p for a 1080p resolution. With the massively upgraded ray tracing chances are the new cards will have no trouble running it at 540p at max settings that are actually necessary (you don't need 8k textures at 540p) which means 1080p with ray tracing on probably working fine on a 3050.
 

itsmydamnation

Platinum Member
Feb 6, 2011
2,931
3,556
136
With DLSS they only need 540p for a 1080p resolution. With the massively upgraded ray tracing chances are the new cards will have no trouble running it at 540p at max settings that are actually necessary (you don't need 8k textures at 540p) which means 1080p with ray tracing on probably working fine on a 3050.
Thats a mightly big assumption, can i transact with you using Fermi estimation?
 

BenSkywalker

Diamond Member
Oct 9, 1999
9,140
67
91
Does anyone think it's unreasonable for the 3050 to at least match the 2060 in rasterization? Is it safe to assume the Ampere parts will be better at ray tracing than the Turing parts?

If the 3050 doesn't beat the 2060 in ray tracing I would consider it a disappointment. Also, I wouldn't expect nVidia to have any parts without ray tracing, it was one thing when they could compare the 16xx parts to Radeon VII for feature set, another thing entirely to be below a console chip.
 
  • Like
Reactions: psolord

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
Does anyone think it's unreasonable for the 3050 to at least match the 2060 in rasterization? Is it safe to assume the Ampere parts will be better at ray tracing than the Turing parts?

If the 3050 doesn't beat the 2060 in ray tracing I would consider it a disappointment. Also, I wouldn't expect nVidia to have any parts without ray tracing, it was one thing when they could compare the 16xx parts to Radeon VII for feature set, another thing entirely to be below a console chip.

I dont believe 3050 will reach RTX2060/RX5700 raster performance. They will have to make a 10k Billion transistor chip that even at 8/7nm will be at 250-300mm2 territory. That is too big for a 3050 category Graphics Card.

And you are expecting a faster RT performance on top of that ?? that will increase even farther the die size.
 
Last edited:
  • Like
Reactions: Konan

BenSkywalker

Diamond Member
Oct 9, 1999
9,140
67
91
A die shrunk 2060 with a moderate clock speed bump would check all the boxes necessary. As far as die size, the 1650 is 200mm squared, the 950 was just under 230 mm squared.

Just because we saw obscenely expensive small die parts this generation from one vendor, it doesn't mean that trend will continue.
 
  • Like
Reactions: GodisanAtheist

Thala

Golden Member
Nov 12, 2014
1,355
653
136
I dont believe 3050 will reach RTX2060/RX5700 raster performance. They will have to make a 10k Billion transistor chip that even at 8/7nm will be at 250-300mm2 territory. That is too big for a 3050 category Graphics Card.

And you are expecting a faster RT performance on top of that ?? that will increase even farther the die size.

You can double the number of RT units and we would still be looking at a single digit percentage die size increase. But yes, you would need to invest a gate count similar to 2060 of course.
 

Glo.

Diamond Member
Apr 25, 2015
5,803
4,777
136
Does anyone think it's unreasonable for the 3050 to at least match the 2060 in rasterization? Is it safe to assume the Ampere parts will be better at ray tracing than the Turing parts?

If the 3050 doesn't beat the 2060 in ray tracing I would consider it a disappointment. Also, I wouldn't expect nVidia to have any parts without ray tracing, it was one thing when they could compare the 16xx parts to Radeon VII for feature set, another thing entirely to be below a console chip.
Depends on SM count. 20 CU 107 die will have zero chance of reaching performance of RTX 2060, but will 100% reach GTX 1660 Ti performance.

24 SM 107 Die should have 100% chance to reach 90-95% of performance of RTX 2060.

20 SM die can be 3050, and 24 SM die can be 3050 Ti SKU.
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
A die shrunk 2060 with a moderate clock speed bump would check all the boxes necessary. As far as die size, the 1650 is 200mm squared, the 950 was just under 230 mm squared.

Just because we saw obscenely expensive small die parts this generation from one vendor, it doesn't mean that trend will continue.

GTX950 is not in the same category as GTX1650, the GTX950(GM206) is what the RTX2060 (TU106) is today.

GT750 (GM107) is the same category as GTX1050Ti (GP107) and GTX1650 (TU117)

3050 should use the recently tape-out GA107
 
  • Like
Reactions: Glo. and Konan

BenSkywalker

Diamond Member
Oct 9, 1999
9,140
67
91
The TU106 in 2060 form is the TU106 chip with parts disabled and lowered power targets, your estimation for die size is one based on matching the x70 tier, not the x60 tier.

If we take into consideration the disabled die space combined with a full node drop we end up with a die size roughly equal to the current 1650(4.7B to roughly 8B). This is a full node drop, just matching the prior gen x60 is actually not very good at all, I'm just expecting nVidia to add more tiers this generation in the mainline series.
 

Stuka87

Diamond Member
Dec 10, 2010
6,240
2,559
136
The TU106 in 2060 form is the TU106 chip with parts disabled and lowered power targets, your estimation for die size is one based on matching the x70 tier, not the x60 tier.

If we take into consideration the disabled die space combined with a full node drop we end up with a die size roughly equal to the current 1650(4.7B to roughly 8B). This is a full node drop, just matching the prior gen x60 is actually not very good at all, I'm just expecting nVidia to add more tiers this generation in the mainline series.

Its not actually a full node drop. It is a smaller node to be sure. But 12nm shrunk to 8nm is not a full node drop.

But, to your point, I would also expect an actual 3050 this series. I expect there to not be a GTX replacement for the GTX 1660. There will be an RTX card in that position, which should be the 3050.
 

BenSkywalker

Diamond Member
Oct 9, 1999
9,140
67
91
A full node is 0.7, half node 0.9- the transition in areal density actually exceeded a full node drop by a reasonable margin going from Vega to RDNA. I think that's what's throwing you off.

10.3B- 251mm 41M per mm
12.5B- 495mm 25M per mm

That's 0.64
A node and then another half node is 0.63 as point of reference.

Given we are all currently expecting the lower tier nVidia cards to be on Samsung 8nm a full node drop, 0.7, may even be a bit conservative.
 

Glo.

Diamond Member
Apr 25, 2015
5,803
4,777
136
A full node is 0.7, half node 0.9- the transition in areal density actually exceeded a full node drop by a reasonable margin going from Vega to RDNA. I think that's what's throwing you off.

10.3B- 251mm 41M per mm
12.5B- 495mm 25M per mm

That's 0.64
A node and then another half node is 0.63 as point of reference.

Given we are all currently expecting the lower tier nVidia cards to be on Samsung 8nm a full node drop, 0.7, may even be a bit conservative.
If RDNA2 is more than 40 mln xTors/mm2 then you can throw your calculations into toilet.

Transistor density is not defined by what is possible on this node, but how good effort physical design team has done.

Apple achieves on this node 80 mln xTors/mm2, and Renoir achieves 60 mln xTors/mm2.

Let RDNA2 have 60 mln xTors/mm2 and you calculations are plainly wrong.

Secondly, your calculations would be correct, but not for N7 process, but N10 process from TSMC.
 

Glo.

Diamond Member
Apr 25, 2015
5,803
4,777
136
The TU106 in 2060 form is the TU106 chip with parts disabled and lowered power targets, your estimation for die size is one based on matching the x70 tier, not the x60 tier.

If we take into consideration the disabled die space combined with a full node drop we end up with a die size roughly equal to the current 1650(4.7B to roughly 8B). This is a full node drop, just matching the prior gen x60 is actually not very good at all, I'm just expecting nVidia to add more tiers this generation in the mainline series.
Expect 30-35 mln xTors/mm2 on 8 NM LPP from Samsung, for next gen gaming cards from Nvidia.

107 die will also be sub 200 mm2 die, most likely around 160 mm2. In terms of die sizes - we may be back to sanity again.
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
The TU106 in 2060 form is the TU106 chip with parts disabled and lowered power targets, your estimation for die size is one based on matching the x70 tier, not the x60 tier.

If we take into consideration the disabled die space combined with a full node drop we end up with a die size roughly equal to the current 1650(4.7B to roughly 8B). This is a full node drop, just matching the prior gen x60 is actually not very good at all, I'm just expecting nVidia to add more tiers this generation in the mainline series.

Nope, GTX950 is exactly what RTX2060 is today. GTX960 which is using a full GM206 is what the RTX2070 is today.
 
  • Like
Reactions: Glo.

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
Do not take the Ampere GA100 as standard 7nm density, most probably the GA100 is using the 7nm High Density (HD) library with reduced FMax . Consumer Ampere chips will use the less dense 7nm High Performance (HP) for higher performance.