Question AMD Rembrandt/Zen 3+ APU Speculation and Discussion

Page 57 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

izaic3

Member
Nov 19, 2019
61
96
61
Alright, so we've had some leaks so far. I don't know if any of it's been confirmed yet, as it's pretty early, but here is what I've surmised so far (massive grain of salt of course):

If if turns out to have RDNA 2 and 12 CU, I could see iGPU performance potentially almost doubling over Cezanne.

If I've made any mistakes or gotten anything wrong, please let me know. I'd also love to hear more knowledgeable people weigh in on their expectations.
 
Last edited:

tamz_msc

Diamond Member
Jan 5, 2017
3,726
3,560
136
Although I wish they tested more games: kind of comprehensive test from ComputerBased: AMD Radeon 680M: The Ryzen 6000 iGPU in the test: Benchmarks of the Radeon 680M in games - ComputerBase

Simple TL;DR for results is:
View attachment 57865
Computerbase's ROG Flow x13 is severely underpeforming. Here's Jarrod getting 53 FPS in Death Stranding at 1080p medium compared to 30 FPS that Computerbase got.

They should have double checked these results when even Iris Xe is getting more FPS than the 1650 Max-Q.
Shoddy work from Computerbase.
 

Attachments

  • Screenshot 2022-02-25 095334.png
    Screenshot 2022-02-25 095334.png
    57.6 KB · Views: 36
  • Screenshot 2022-02-25 095257.png
    Screenshot 2022-02-25 095257.png
    477 KB · Views: 35

uzzi38

Platinum Member
Oct 16, 2019
2,565
5,575
146
Computerbase's ROG Flow x13 is severely underpeforming. Here's Jarrod getting 53 FPS in Death Stranding at 1080p medium compared to 30 FPS that Computerbase got.

They should have double checked these results when even Iris Xe is getting more FPS than the 1650 Max-Q.
Shoddy work from Computerbase.
What are you talking about.

You can't just compare results across different reviews like that - you have absolutely no clue if they even tested the same scenes or not.
 
  • Like
Reactions: Kaluan

Shivansps

Diamond Member
Sep 11, 2013
3,835
1,514
136
  • Like
Reactions: Kaluan

ryanjagtap

Member
Sep 25, 2021
108
127
96
Well then I don't think much more improvement can be done in igpu capabilities of rembrandt at least. I though that just like the mobile APUs went from DDR4-2400 to DDR4-3200 in these past generations, we would get better speeds on DDR5 as well (improved bandwidth due to increase in speeds). Maybe future APUs will have that?
 

jpiniero

Lifer
Oct 1, 2010
14,510
5,159
136
Well then I don't think much more improvement can be done in igpu capabilities of rembrandt at least. I though that just like the mobile APUs went from DDR4-2400 to DDR4-3200 in these past generations, we would get better speeds on DDR5 as well (improved bandwidth due to increase in speeds). Maybe future APUs will have that?

Desktop DIY should be able to get higher speeds.
 
  • Like
Reactions: Kaluan

ryanjagtap

Member
Sep 25, 2021
108
127
96
Desktop DIY should be able to get higher speeds.
But will it come to the DIY, and how long will it take to come? With zen4 CPUs having igpu integrated across the stack, and Rembrandt still having zen3 cores with efficiency optimizations, it will lag behind the zen4 products CPU performance wise at least.
 

moinmoin

Diamond Member
Jun 1, 2017
4,934
7,620
136

eek2121

Platinum Member
Aug 2, 2005
2,904
3,906
136
Would be nice if AMD had 2 dies.
4-6 cores with full 12 CU and 8-12 cores with 6CU.
Those higher core counts APUs are meant to be paired with discrete GPUs so it's a waste to give so many CUs to these APUs.

But Intel also does this, right?
It goes against logic, people who want to pay less for weaker CPUs are the ones that most need that extra iGPU.
Will this ever happen one day?

There is no money in large GPU/small GPU based chips. The GPU die real estate in either AMD or Intel systems is enormous. The only way we end up with huge, awesome GPUs is if designers find a way around this. I would personally love a fast, small, power efficient GPU, however, it isn't going to happen.

Although I wish they tested more games: kind of comprehensive test from ComputerBased: AMD Radeon 680M: The Ryzen 6000 iGPU in the test: Benchmarks of the Radeon 680M in games - ComputerBase

Simple TL;DR for results is:
View attachment 57865

Out of curiosity, what games would you like to see? Take a few notes. May act on them later.

Well it seems it easily outperforms a RX560, even if it's not at GTX1650 level. But it's right where I'd expected it to be.

Given the fact it shares both TDP and power consumption with a CPU, it is a miracle. This is the spiritual successor to Polaris, no doubt. Compare perf/watt numbers to the RX 580 and let these chips blow your mind. Looking forward to the "U" variants.

Lol @4GB VRAM in RT games.

6500XT was always going to be a total meme for RT workloads. Nothing could have ever saved it.

So, I'm curious about this. In theory, the 6500 XT should dominate the 680m in all areas. My thoughts are:

  1. PCIE and Memory latency is KILLING RDNA2 based solutions.
  2. The 6500XT is the absolute worst in terms of perf/watt, as I suspected
  3. Chiplet based designs combined with point 1 are really harming gaming performance. Monolithic designs clearly offer much better performance in terms of perf/watt.
What I suspect is that either AMD did not use a vanilla RDNA2 design or one or more of the points above lead to the 6500XT getting crushed in terms of perf/watt.

Regardless, I hope I can score a laptop with a 680m pretty soon along with a 6500xt, it would be interesting to subject both to workloads that fall outside the normal gaming/compute workloads.
 

uzzi38

Platinum Member
Oct 16, 2019
2,565
5,575
146
Out of curiosity, what games would you like to see? Take a few notes. May act on them later.

Oh I've got no complaints with the list of games there, just wish more were tested is all. I think these sorts of games are great tests - recent AAA games push the iGPUs hard. As for what games specifically, I can't think of them off the top of my head but a normal dGPU review from ComputerBase or a HUB review should give you plenty of examples of games.
 

ahimsa42

Senior member
Jul 16, 2016
225
194
116
Short summary, and the question remains when the Rembrandt APU Desktop AM5 version arrives.

desktop RMB-there is still no indication of when the mobile versions will go on sale, not to mention the price & availability. i would assume that most people would be interested in the 6800U yet there is only reviews of the H models.
 

Thibsie

Senior member
Apr 25, 2017
727
752
136
New Thinkpad models announced. The T14s gen 3with Rembrandt has USB 4. The T14 gen 3 does not. Is this more of an opt in feature for OEMs? Kind of disconcerting to see on a nonbudget line of laptops.

Completely ridiculous IMO.
Ans AMD version id only LPDDR if I read correctly. Better chose wisely while shopping....
 

majord

Senior member
Jul 26, 2015
433
523
136
Short summary, and the question remains when the Rembrandt APU Desktop AM5 version arrives.





Approaching and maintaining 1050/560 performance should be doable for many games, but, it's going to be very situational and the exception, not the rule. It will certainly, combined with AlderLake's improvements, completely eliminate any realistic market for any of the existing line of Nvidia MX dGPUs in mobile, as the MX450 won't be able to improve on anything. Low power configured 1650s will also not justify their cost. I also have a feeling that 4GB dGPUs will all feel the pressure as these iGPUs won't have those sorts of limits in modern games and won't suffer from having to swap across the PCIe bus to change textures.

But, I'm not expecting world changing performance. If they can give decent FPS in 1080p with mid to high detail settings, that's going to be enough for most. If FSR/XeSS can make native 900p rendering look great at high and ultra detail with playable frame rates, all the better.

Let's not forget: The desktop 3400g had 11 CUs and could routinely clock north of 1600mhz. 12 CUs of RDNA 2, while being more efficient and likely clocked above 2Ghz in some parts, isn't a massive uplift. Assuming that the DDR5 can keep it fed, I'd still be shocked if it consistently reached RX560/1050 levels of in game performance.

So.. Are you suitably shocked yet? :p

I for one concede I was too pessimistic in predicting 1050ti for desktop TDPs