Discussion RDNA4 + CDNA3 Architectures Thread

Page 379 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

DisEnchantment

Golden Member
Mar 3, 2017
1,777
6,791
136
1655034287489.png
1655034259690.png

1655034485504.png

With the GFX940 patches in full swing since first week of March, it is looking like MI300 is not far in the distant future!
Usually AMD takes around 3Qs to get the support in LLVM and amdgpu. Lately, since RDNA2 the window they push to add support for new devices is much reduced to prevent leaks.
But looking at the flurry of code in LLVM, it is a lot of commits. Maybe because US Govt is starting to prepare the SW environment for El Capitan (Maybe to avoid slow bring up situation like Frontier for example)

See here for the GFX940 specific commits
Or Phoronix

There is a lot more if you know whom to follow in LLVM review chains (before getting merged to github), but I am not going to link AMD employees.

I am starting to think MI300 will launch around the same time like Hopper probably only a couple of months later!
Although I believe Hopper had problems not having a host CPU capable of doing PCIe 5 in the very near future therefore it might have gotten pushed back a bit until SPR and Genoa arrives later in 2022.
If PVC slips again I believe MI300 could launch before it :grimacing:

This is nuts, MI100/200/300 cadence is impressive.

1655034362046.png

Previous thread on CDNA2 and RDNA3 here

 
Last edited:

PJVol

Senior member
May 25, 2020
854
838
136
F1 2024 1% is good in RT mode
From another great review website from Germany,
RX 9070XTX (yes, why not?) almost at 5080 and 5070 ti level performance (non-RT/RT). I think good-old EK water block would just nail it.
 
Last edited:

SolidQ

Golden Member
Jul 13, 2023
1,501
2,463
106
Overall between cnn and transformer mode
49034de59841bb6abd01e516099eed5a.jpg




Perfomance hit
Screenshot-20250305-144922-Edge.jpg
 

adroc_thurston

Diamond Member
Jul 2, 2023
7,074
9,824
106
  • Like
Reactions: Tlh97 and marees

Mahboi

Golden Member
Apr 4, 2024
1,058
1,969
96
Random thought: I think the power efficiency on the cards tells a lot as to why AMD gave up on the high end. If one 9070 XT is barely able to get close to a 4080, I doubt that chiplets stacked together into 120 CUs would have done great.
 

branch_suggestion

Senior member
Aug 4, 2023
824
1,788
106
I meant the non-XT should stay where it is, while the XT version should have a much higher CU count but be downclocked instead. They are obviously clocking the XT to the moon which tanks the efficiency completely.
That requires a bigger die than what exists.
 
  • Like
Reactions: Mopetar

exquisitechar

Senior member
Apr 18, 2017
722
1,019
136
Random thought: I think the power efficiency on the cards tells a lot as to why AMD gave up on the high end. If one 9070 XT is barely able to get close to a 4080, I doubt that chiplets stacked together into 120 CUs would have done great.
They could just dial down the clocks and it would have been fine.
 
  • Like
Reactions: lightmanek

GTracing

Senior member
Aug 6, 2021
478
1,114
106
It seems that the 9070 is being overlooked. It should've been the real star of the RDNA4 lineup. I assume AMD’s original plan was to position the 9070 to match the performance of the RX 7900 XT, but they somehow managed to push the clocks higher, bringing it closer to the RX 7900 XTX. As a result, they decided to introduce an additional SKU (9070XT). Based on TPU’s review, the 9070's efficiency is roughly on par with the RTX 5070 Ti, which suggests that the 9070 XT is clocked excessively high, leading to a significant drop in efficiency. A better approach would have been to increase the number of CUs while reducing clock speeds to maintain a more balanced power-to-performance ratio.
Keep in mind that a lot of the cards given to reviewers are factory overclocked. Most of the models sold will have a more sane power limit. For example, TechPowerUp has a Sapphire Nitro which draws 350W. Whereas PCGamesHardware has a Sapphire Pulse which draws 310W.
 

coercitiv

Diamond Member
Jan 24, 2014
7,355
17,423
136
Why are there quite a number of instances where the 9070 XT performs relatively better against other GPUs at 4K than it does at 1440p?
 

Heartbreaker

Diamond Member
Apr 3, 2006
5,159
6,776
136
Actually manage the supply so that they don't have to cut prices. They want you to buy the XT.

Again, that's doesn't make 9070 a good product. Having a product exist only to act as a poor value, to make another product in your lineup look better in comparison is just dumb.

This is the third time in a Row AMD has done this, and they ended up with terrible reviews for those products, only to cave and lower the price after the damage was done.

9070 pricing is mainly a gift for NVidia.
 

adroc_thurston

Diamond Member
Jul 2, 2023
7,074
9,824
106
Having a product exist only to act as a poor value, to make another product in your lineup look better in comparison is just dumb.
No it's good.
This is the third time in a Row AMD has done, this and they ended up with terrible reviews for that product, only to cave and lower the price after the damage was done.

9070 pricing is mainly a gift for NVidia.
It's not something they wanna sell.