Question Speculation: RDNA3 + CDNA2 Architectures Thread

Page 167 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

uzzi38

Platinum Member
Oct 16, 2019
2,705
6,427
146

Glo.

Diamond Member
Apr 25, 2015
5,803
4,777
136
AMD want: lowest possible cost APU that is competitive with Intel.

That is the brutal truth.

If any OEM, or group of OEMs want a giant GPU APU, they can commission it.

AMD will build a custom APU for anyone that wants it. They do it for Sony/MS consoles. They do it for Steamdeck. They did it for Subor Z+ console.

Thus far, it appears no OEM is asking for this in the PC market.
Lowest possible cost means not the ultimate lowest possible cost, but a lowest possible cost that gives AMD advantage over their competitors.

10 mm2 more for die size may be enough high cost for AMD to improve something if it will translate into huge performance gains, increase the TAM, and increase volume of sales.

And yes, their customers indeed ask for not only something like Strix Point: 8P/4E/24 CU design, they are asking for even more powerful hardware that is able to compete with M2 Pro and M2 Max.
 
Last edited:

Glo.

Diamond Member
Apr 25, 2015
5,803
4,777
136
You're missing the point here, AMD in particular could have made a spiritual successor to Kaby Lake-G that WAS an APU (or more APU-like) any time within the last couple years (i.e big iGPU with special sauce to meet increased bandwidth requirements), they didn't, and one must assume they have a good reason.



Also missing the point, the choice isn't between powerful iGPU and CPU + dGPU, its between powerful iGPU and skimpy iGPU. A powerful iGPU on die is functionally useless for a lot of laptops so OEMs will not pay more for a chip that essentially costs more to manufacture.

Widening memory controller buses and/or adding dedicated on-chip caches (neither of which scale well with die shrinks by the way) for performance which may not be valued by buyers is stupid. Law Firms and Consultants are not. going. to. pay. more. for the next Thinkpad Carbon just because the chip has a big iGPU + 64MB SLC to feed said GPU.
You are moving the goalpost to fit your narrative, how it is impossible for AMD to make powerful APU in todays world, because you do not believe in it.

And the facts are. It was not AMD who created Kaby Lake-G, it was Intel. And spiritual successor to KB-G are MTL and Arrow Lake-P. Fact.

Secondly. Powerful iGPU on die is functionally useful for every use case, especially for higher res experiences. You have to just be able to control its power draw in idle.

I will not go into the discussion of changing software and experience paradigms very soon, which will require powerful integrated solutions. A lot will change(in customers mind, only...) when AR/VR headset from Apple will be released.


Something like this is what you will need powerful APUs for. But hey, ITS ONLY A PC WORLD!!!111oneone
 
  • Like
  • Haha
Reactions: Tlh97 and Kaluan

Heartbreaker

Diamond Member
Apr 3, 2006
4,340
5,464
136
Lowest possible cost means not the ultimate lowest possible cost, but a lowest possible cost that gives AMD advantage over their competitors.

On the GPU side,they already have an advantage over Intel, so no need to spend more.


And yes, their customers indeed ask for not only something like Strix Point: 8P/4E/24 CU design, they are asking for even more powerful hardware that is able to compete with M2 Pro and M2 Max.

What you wish for, and what OEMs will pay for are two different things.

If OEMs really wanted that, they would have it buy now. Subor Z+ had 24 CU APU from AMD in 2019, simply because they wanted it enough to pay for it.
 

biostud

Lifer
Feb 27, 2003
18,700
5,434
136
Isn't what your asking for basically the xbox/ps5 SoC? So I don't think there is a problem making them, I just don't think the market is there.

Microsoft could make a Xbox/PC laptop if they wanted. But I guess they don't....
 

beginner99

Diamond Member
Jun 2, 2009
5,233
1,610
136
A powerful iGPU on die is functionally useless for a lot of laptops so OEMs will not pay more for a chip that essentially costs more to manufacture.

exactly. And hence economy of scale is missing. if you make multiple chips/apu one with small, medium and large iGPU it is simply not worth it. better to have a cpu with a small iGPU and add a dGPU in case of need.
especially the APU with large iGPU would be niche as it can't be reused on desktop while said dGPU is a repurposed desktop chip.
 

leoneazzurro

Golden Member
Jul 26, 2016
1,052
1,716
136
There is a market for SFF PCs, handheld consoles and thin & light laptops with high battery life. In all these cases a reasonably powerful IGPU APU is the better solution as it allows to play even recent games at low settings/low resolution, having good video playback support while keeping a smaller footprint and a way less complex PCBs/cooling (this is also a cost). With an dGPU you need to reserve additional space for the chip, cooling, memory...
One can say the market is small, but the recent success of the Steam deck and the fact that most of the high end corporate laptops rely on IGPUs say otherwise. Of course, the "reasonably" powerful is in relation with the cost and that means, the amount of area dedicated to IGPU. At the moment, PS5/XBox-like APUs would have small market outside consoles, yes. But, in a couple of years, who knows...
 
Last edited:

Heartbreaker

Diamond Member
Apr 3, 2006
4,340
5,464
136
There is a market for SFF PCs, handheld consoles and thin & light laptops with high battery life. In all these cases a reasonably powerful IGPU APU is the better solution as it allows to play even recent games at low settings/low resolution, having good video playback support while keeping a smaller footprint and a way less complex PCBs/cooling (this is also a cost). With an dGPU you need to reserve additional space for the chip, cooling, memory...

No one is saying get rid of APU. AMDs current APUs are powerful enough for that role, and their continued evolution will keep them serving it.

The pushback is merely against the wishful thinking that seems to have an expectation of a sudden giant GPU in the APU. This is simply unrealistic.


One can say the market is small, but the recent success of the Steam deck and the fact that most of the high end corporate laptops rely on IGPUs say otherwise.

Again, no one is against APUs, just the realism of the Big GPU, APU wishful thinking.

Steamdeck is actually a great counter example against the Big GPU APU meme. Steam deck has a custom part, so Valve could have ordered any size GPU in their APU that they wanted, but the Steamdeck has only half the GPU size vs AMDs standard 6800U gpu.

That's a dedicated handheld game machine, and they chose only half the GPU of AMDs standard APU.

Given that it seems unlikely that there is much OEM demand for standard APU to have a much bigger GPU section.
 

Heartbreaker

Diamond Member
Apr 3, 2006
4,340
5,464
136
Isn't what your asking for basically the xbox/ps5 SoC? So I don't think there is a problem making them, I just don't think the market is there.

Microsoft could make a Xbox/PC laptop if they wanted. But I guess they don't....

Sadly, because I'd love it if Microsoft put a 50% markup on the XBSX HW, included windows and sold it as a PC. I'd be clicking on the "add to cart" the moment they went on sale. I've never tried to compete for first day purchase of any HW. What makes the XBSX a great console would also make it a great SFF gaming PC, and still a great value as PC with a 50% markup.

So I definitely get the desire for something like this. But I don't let my desire for something, translate into a belief that it will happen. We need to wary of wishful thinking.

The realistic take, is that AMD will just keep making a generic APU for wide usage, ignoring the console like APU niche, unless some OEM asks (pays) for it.
 
  • Like
Reactions: insertcarehere

Glo.

Diamond Member
Apr 25, 2015
5,803
4,777
136
No one is saying get rid of APU. AMDs current APUs are powerful enough for that role, and their continued evolution will keep them serving it.

The pushback is merely against the wishful thinking that seems to have an expectation of a sudden giant GPU in the APU. This is simply unrealistic.




Again, no one is against APUs, just the realism of the Big GPU, APU wishful thinking.

Steamdeck is actually a great counter example against the Big GPU APU meme. Steam deck has a custom part, so Valve could have ordered any size GPU in their APU that they wanted, but the Steamdeck has only half the GPU size vs AMDs standard 6800U gpu.

That's a dedicated handheld game machine, and they chose only half the GPU of AMDs standard APU.

Given that it seems unlikely that there is much OEM demand for standard APU to have a much bigger GPU section.
Strix point with 24 CU is NOT a big APU.

Its completely, and utterly standard die. Just like Rembrand, Phoenix Point are.
 

Heartbreaker

Diamond Member
Apr 3, 2006
4,340
5,464
136
Strix point with 24 CU is NOT a big APU.

Its completely, and utterly standard die. Just like Rembrand, Phoenix Point are.

That's a sudden doubling of GPU size, so it is a Much bigger GPU.

Where is any evidence that it will actually be 24 CUs, or is this just more wishful thinking?

Given AMD current GPU BW, 24 CUs (between Navi 24 and Navi 23) would need over 200 GB/S of BW, where would that come from? Note that is AFTER already having an infinity cache, so you can't pretend a cache would eliminate that need.
 
Last edited:

Dribble

Platinum Member
Aug 9, 2005
2,076
611
136
Widening memory controller buses and/or adding dedicated on-chip caches (neither of which scale well with die shrinks by the way) for performance which may not be valued by buyers is stupid. Law Firms and Consultants are not. going. to. pay. more. for the next Thinkpad Carbon just because the chip has a big iGPU + 64MB SLC to feed said GPU.
That applies as long as the gpu is only there for games and professional visualisation. If we start using gpu compute more then it starts to make more sense to have big gpu's. If Nvidia had an x86 license you know that's what they would be doing - adding it to normal cpu's and then helping and incentivizing key software to use the gpu compute. They aren't because they lack the x86 license, but that doesn't mean AMD shouldn't do that, in fact there's a chance that Intel go down that route now they are back making serious gpu's. If AMD had any sense they'd be pro-actively going for this market, not waiting to get beaten to the punch then reacting late.
 
  • Like
Reactions: Tlh97

insertcarehere

Senior member
Jan 17, 2013
639
607
136
Sure people swear the same about MLID. It's all BS clickbait to me.

Did mister "never off" explain where the BW was coming from? It's on the same socket, so same DDR5 memory, which has about ~100GB/s of BW.

Edit: I looked up the Rumor. He's talking about 9 TFlops GPU, that is the same as a RX 6600.

RX 6600 has 32 MB of "Infinity Cache" to compensate for lower memory BW, AND 224 GB/s of Memory BW. Best case it seems the fictional part will have less than half the required Memory BW.

Hopes and dreams, that's where the bandwidth would come from.

Still waiting for Mr "never off's" N33 & N31 btw:
1674661947491.png
1674662076251.png
 

leoneazzurro

Golden Member
Jul 26, 2016
1,052
1,716
136
No one is saying get rid of APU. AMDs current APUs are powerful enough for that role, and their continued evolution will keep them serving it.

The pushback is merely against the wishful thinking that seems to have an expectation of a sudden giant GPU in the APU. This is simply unrealistic.

It depends on what you think a "big APU" is. The iGPU in Rembrandt is the equivalent of a midrange dGPU of some years ago, and more powerful than all the PS4 generation consoles but in terms of actual area it is not huge for sure. Of course you will not see 400+ mm^2 APU dies in a market that covers from low end to high end laptops (which are the primary target). But with 200 to 300mm^2 at disposal and new processes being available (and with MCM as the future), who knows if cannot really see what you could consider today a "big" APU in a matter of a couple of years.


Steamdeck is actually a great counter example against the Big GPU APU meme. Steam deck has a custom part, so Valve could have ordered any size GPU in their APU that they wanted, but the Steamdeck has only half the GPU size vs AMDs standard 6800U gpu.

That's a dedicated handheld game machine, and they chose only half the GPU of AMDs standard APU.

Given that it seems unlikely that there is much OEM demand for standard APU to have a much bigger GPU section.

That was because Valve gave more importance to battery life and cost than pure performance, also because they control the software layer. But there are other handhelds (even smaller than the Deck) in commerce already using a 6800U and soon with a 7040U class APU, for example. As there are several XSFF PCs (X here stays for Extra) used as multimedia and gaming stations, which can benefit in having a beefier iGPU compartment. This does not mean that we will immediately see huge dies with IGPU measuring 200+ mm^2 alone (well, will have in the HPC market, see MI300). But, with the proper balance between CPU and IGPU side, there are clear advantages for such solutions. I.e. in the highend corporate market, we saw often solutions based on only APU or with a CPU and a quite small dGPU (MX450/550 class). A Rembrandt/Phoenix already would kill all dGPU solutions of that class by offering similar performance at a lower cost (or higher margin for the OEM) and even in the mainstream notebook segment smaller dGPUs could be substituted by slightly beefier APUs than we see today. Main problem here is more availability than technical/cost issues.
 
Last edited:
  • Like
Reactions: Tlh97

Heartbreaker

Diamond Member
Apr 3, 2006
4,340
5,464
136
It depends on what you think a "big APU" is.

I've been pretty clear on that. Reasonable expectation is a continuation of current evolution. GPU section continues to evolve performance along with the evolution of memory BW on the standard socket.

It's unreasonable to expect that the GPU section will suddenly double while memory BW is stagnant. That would just be a waste of silicon bottlenecked by too weak memory BW.
 

leoneazzurro

Golden Member
Jul 26, 2016
1,052
1,716
136
I've been pretty clear on that. Reasonable expectation is a continuation of current evolution. GPU section continues to evolve performance along with the evolution of memory BW on the standard socket.

It's unreasonable to expect that the GPU section will suddenly double while memory BW is stagnant. That would just be a waste of silicon bottlenecked by too weak memory BW.

There are technical solutions for improving effective bandwidth (cache stacking, new memory standards). Today a new LPDDR5 speed (LPDDR5-T where T stays for Turbo) was launched by Hynix, with effective transfer rate up to 9,600 Gbps. Yes there are costs related, it must be seen how and on what these costs can be justified, but there could be eve more segmentation in the future, based on the iGPU performance.
 

Heartbreaker

Diamond Member
Apr 3, 2006
4,340
5,464
136
There are technical solutions for improving effective bandwidth (cache stacking, new memory standards). Today a new LPDDR5 speed (LPDDR5-T where T stays for Turbo) was launched by Hynix, with effective transfer rate up to 9,600 Gbps. Yes there are costs related, it must be seen how and on what these costs can be justified, but there could be eve more segmentation in the future, based on the iGPU performance.

See above with the Strix Point/RX 6000 example. You need more than Double high speed DDR5 BW, and that's already after you have a large infinity cache mitigating lower memory speed.
 

leoneazzurro

Golden Member
Jul 26, 2016
1,052
1,716
136
See above with the Strix Point/RX 6000 example. You need more than Double high speed DDR5 BW, and that's already after you have a large infinity cache mitigating lower memory speed.

You need double the BW if you need to double the performance in all departments, and that only if the BW is the only limiting factor. Maybe the target is different. And the new LPDDR5-T standard is already giving +50% BW in comparison to today's LPDDR5-6400. Also, if Strix Point is on N3, the area used on a 24CU/12WGP iGPU on RDNA3+ may be not be much different than the area used on Rembrandt, or Phoenix, iGPUs. Not saying that we will really see a 12 WGP (after the usual hype debacle, I will believe only in what it will be effectively delivered), but the possibility exists.
 
  • Like
Reactions: Tlh97

Heartbreaker

Diamond Member
Apr 3, 2006
4,340
5,464
136
You need double the BW if you need to double the performance in all departments, and that only if the BW is the only limiting factor. Maybe the target is different. And the new LPDDR5-T standard is already giving +50% BW in comparison to today's LPDDR5-6400. Also, if Strix Point is on N3, the area used on a 24CU/12WGP iGPU on RDNA3+ may be not be much different than the area used on Rembrandt, or Phoenix, iGPUs. Not saying that we will really see a 12 WGP (after the usual hype debacle, I will believe only in what it will be effectively delivered), but the possibility exists.

Why would you think area will stay constant, when wafers are getting more expensive at each process shrink?
 

insertcarehere

Senior member
Jan 17, 2013
639
607
136
You need double the BW if you need to double the performance in all departments, and that only if the BW is the only limiting factor. Maybe the target is different. And the new LPDDR5 standard is already giving +50% BW in comparison to today's LPDDR5-6400. Also, if Strix Point is on N3, the area used on a 24CU/12WGP iGPU on RDNA3+ may be not be much different than the area used on Rembrandt, or Phoenix, iGPUs.

Except even 128bit LDDDR5-9600 is only gonna be ~150GB/s in bandwidth. For reference, 28CU RDNA3 on 6nm (7600m) is listed as 128bit GDDR6 with 256 GB/s, and that also needs a 32mb IC on top. To actually use 24CU RDNA3 at the sort of clock speeds that N3 should permit would require a 32mb IC at the very, very least. Caches don't shrink well with node process so a decent IC to mitigate low memory bandwidth will take a substantial proportion of the precious die space within such an APU by themselves.
 

Dribble

Platinum Member
Aug 9, 2005
2,076
611
136
You mean so long as we are talking about reality. So yeah it applies.
The reality is any modern pc is capable of some level of gpu compute, and the fact that it's not being used by a lot of software is due to lack of standardisation, and someone big willing to champion it. It's a great potential market for AMD as they have the x86 cpu's and the knowledge to make integrated gpu's that could do compute well. Like most things the market moves fast, if you don't take advantage someone else will.
 
  • Like
Reactions: Tlh97