[soganess]

Asking this as an open ended (if leading) question: I assume enough people are doing it otherwise PS5 Pro makes no sense... Right?

They (AMD/Sony) shoehorned the RDNA 3/3.5 GPU architecture onto an older Zen 2 core, with a different process node, because... they felt like making a frankenAPU? Especially since the APUs are usually monolithic (vs chiplet) in design and share a memory controller. Surely it would have been easier/cheaper to put in 8 zen 4c/5c cores and call it a day.

I'm pretty sure I'm just missing something obvious...

[wmf]

For PlayStation APUs, it's likely that AMD presents a menu of options and Sony chooses which components they want. For PS5 Pro, the CPU is unchanged from PS5 because Sony doesn't feel the need for anything faster. A newer CPU would take more area. But Sony really wanted better raytracing and AI so they chose RDNA 3.9 or whatever for the GPU. I suspect the cores are all mostly synthesized so they can support any process and Infinity Fabric is compatible enough that you can mix and match new and old cores.

[pjmlp]

PS5 Pro makes no sense, yes.

Most studios aren't even able to push current PS 5 to its limit, given current development schedules and budgets.

PS 5 Pro is for the same target audience as PS 4 Pro, hardcode console fans that will buy whatever the console vendor puts out, and Sony needs to improve their margins.

[deaddodo]

> They (AMD/Sony) shoehorned the RDNA 3/3.5 GPU architecture onto an older Zen 2 core

The original core was already a custom configuration. I don't see why it seems odd that the new version would be a custom configuration based on the previous one.

> with a different process node

This doesn't apply to the PS5 SoC, but is general to AMD's methodology.

AMD has been using an off-chip interposer setup for multiple generations now. They did this specifically to allow for different process nodes for different chips.

It's cheaper (and there are more fab options) to produce chips at a lower process node. If there's no reason to update the CPU, it would make sense to keep it on the cheaper option.

In regards to the PS5 and Xbox SoCs, specifically.

The entirety of the SoC is fabbed at the same process node. A core designed for a 14nm process node and then fabbed at 7nm (assuming drastic changes weren't needed to make it function at the lower node) is going to be much smaller and run cooler on that node size. This is cheaper and leaves more space in the total footprint for the GPU-specific and auxiliary logic cores. Same rule applies above, why use more if it's not needed.

> they felt like making a frankenAPU

All of the game console chips are "frankenAPUs".

> Especially since the APUs are usually monolithic (vs chiplet) in design and share a memory controller.

"Monolithic" vs "chiplet" is an arbitrary distinction, in this case. The individual logic cores are still independent and joined together with interposers and glue logic. This is clear from the die shots:

https://videocardz.com/newz/sony-playstation-5-soc-die-pictu...

To return to the previous point, look at the space dedicated to the CCXs. The Zen2 has ~1.9bln transistors, the Zen3 ~4.1bln, the Zen4 ~6.6bln, etc. To use a newer core would double or triple that space. Increasing the total die size, making it more expensive per chip and increasing the defect rate.

> Surely it would have been easier/cheaper to put in 8 zen 4c/5c cores and call it a day.

Definitely not.

> I'm pretty sure I'm just missing something obvious...

Nothing about chip design is obvious.