Discussion RDNA4 + CDNA3 Architectures Thread

[DisEnchantment]

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

History for llvm/lib/Target/AMDGPU - llvm/llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. - History for llvm/lib/Target/AMDGPU - llvm/llvm-project

github.com

Or Phoronix

More AMD "GFX940" Enablement Work Landing In LLVM - Phoronix

www.phoronix.com

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

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



Previous thread on CDNA2 and RDNA3 here

Question - Speculation: RDNA3 + CDNA2 Architectures Thread

Man I have been dying to make this one for a while now. First rumours for RDNA3 are here so new thread time! Just going to start off with this one for now: kopite7kimi on Twitter: "@VideoCardz Ah, I mean a simple mcm design with 10240 cores is not enough. Because the lift from RDNA2 to RDNA3...

forums.anandtech.com

 

[marees]

Right, supply and demand. I agreed. However costs also have been going up too, so if you were to establish supply, msrps would be going up because costs are going up too. That's part of the supply bit.

Costs are going up because TSMC is the only game in town

Plus I believe Nvidia has miscalculated/misjudged or something like that

So, What's Next...? The rate of advancement in gaming performance... (Part 2) Is PC gaming dying?!

A couple of years ago, I looked at the rate of advancement of GPUs over time . It's the only way of tracking how the user experiences techno...

hole-in-my-head.blogspot.com

Intel never fabbed a GPU in their fabs
Samsung's contract for AMD chromebook APU sonoma valley seems to have been scrapped

Hopefully things change
Intel in discussion with Microsoft
Samsung in discussion with Sony for PlayStation handheld (could be typical Korean FUD though)

 

[inquiss]

Costs are going up because TSMC is the only game in town

Plus I believe Nvidia has miscalculated/misjudged or something like that

So, What's Next...? The rate of advancement in gaming performance... (Part 2) Is PC gaming dying?!

A couple of years ago, I looked at the rate of advancement of GPUs over time . It's the only way of tracking how the user experiences techno...

hole-in-my-head.blogspot.com

Intel never fabbed a GPU in their fabs
Samsung's contract for AMD chromebook APU sonoma valley seems to have been scrapped

Hopefully things change
Intel in discussion with Microsoft
Samsung in discussion with Sony for PlayStation handheld (could be typical Korean FUD though)

Yes, competition in foundry is another layer of supply and demand. Take that out and you're still left with the fundamental that cost per transistor is going up because it's harder to make them smaller. Chiplets in CPUs have caused a one time drop in cost structure. Need more tricks like that to reset costs for making things.

Chiplets can do that for GPUs if you can solve the workload. But it's much more fun to use them to make things you couldn't make monolithic.

 

[Kepler_L2]

Samsung in discussion with Sony for PlayStation handheld (could be typical Korean FUD though)

It's TSMC N3P

 

[jpiniero]

It's TSMC N3P

That would be more realistic. The price of it is going to be interesting.

 

[reb0rn]

del