Discussion RDNA4 + CDNA3 Architectures Thread

Page 324 - 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:

Dezii90

Junior Member
Jan 9, 2025
19
41
51
Yeah would be interesting, what is MB


AMD Radeon RX 9070 XT & RX 9070 GPU Performance Leaks Out: Comparable To RX 7900 GRE & RX 7800 XT​


another same repeat story about 7900GRE
They're reducing expectations. This doesn't even make sense, Frank said final performance is higher than the leaks we have.
 
Last edited:
  • Like
Reactions: Elfear and marees

Jan Olšan

Senior member
Jan 12, 2017
581
1,141
136
They're reducing expectations. This doesn't even make sense, Frank said final performance is higher than the leaks we have.
What the title states is just leaked opencl/vulkan synthetic scores in geekbench. It probably understates the real difference in gaming performance, RX 9070 XT is faster than RX 7900 GRE.

Geekbench is hugely unreliable for GPU comparisons, huge error margin. Not as useless as GFXbench or how it was called but getting there.
 

Tuna-Fish

Golden Member
Mar 4, 2011
1,678
2,564
136
Furmark is not a very representative benchmark for games, possibly the iC being closer and lower latency gives it more of a boost than it would see in a workload with more scene complexity?
 
  • Like
Reactions: Tlh97 and Elfear

SolidQ

Golden Member
Jul 13, 2023
1,516
2,492
106
Highest 9070xt furmark score i found is 8000
Very different results
f1780bc29c0a4306e1af58dc6691994d.png
 

gaav87

Senior member
Apr 27, 2024
659
1,279
96
Lol this furmark result use the same beta chinese drivers that are flooting around since january that were said too have lower PERF.
What the heck is AMD ploting ?
1740146877765.png
 

MrTeal

Diamond Member
Dec 7, 2003
3,919
2,708
136
What the heck is AMD ploting ?
hidden 4090 power!
They realized that Nvidia was shipping a tiny quantity of burning cards that are sometimes missing specs and are selling for hundreds over MSRP at retail, and if they didn't do something quick they were going to have an absolute winner on their hands.

Don't worry, prices and market segments have been adjusted and they've steered back into their lane of Nvidia raster - $50 where they can comfortably lord over their 8% market share.
 
Last edited: