Will PS/XBX follow Nintendo's footsteps?

[derpysquirtle64]

Trumpstyle said:

derpysquirtle64 said:

Now, let's assume that the potential next-gen would be the time that both companies will think about moving away from X86.

I'll first start with Sony, because it's more easier in my opinion. Sony is not a big tech company nowadays, far from it. They simply don't have the resources to keep a state of engineers to build SoCs for them, like Apple does. So, the only way for them would be to buy an existing solution for partners and maybe ask them to make some tweaks (similar to what Nintendo did with Tegra and nVidia). The problem is - BC. We already see that all backwards compatibility on Playstation consoles is built around the idea of having the same or double core GPU config. Like PS4 -> PS4 Pro. PS4 Pro just had two PS4 GPUs stuck together and running at higher clock. PS5 GPU has the exact same core config as PS4 Pro does, but once again running at higher clocks.
So, the conclusion is - PS6 going ARM way is possible if x86 will end up at a really huge disadvantage over ARM by the time PS6 is gonna enter the planning phase (which I don't think is quite likely), but it will most likely end up in PS6 having no backwards compatibility with PS4 and PS5 games.

Now, for Microsoft. Recently there has been a Bloomberg report that Microsoft is looking into building their own ARM chips in house, just like Apple does. But as it is usual for Microsoft nowadays, the main goal is to use them for Azure cloud. Unlike Sony, Microsoft has the capability and resources to hire engineer to build their own ARM SoCs if they really see some advantage there. And given that all existing Xbox One games and Xbox Series X|S games are running in Hyper-V containers from what we know, I don't think it will be an impossible task for MS engineers to prepare some low-level command translation software like Rosetta to make this virtualized containers running on a completely different architecture. The problem with Microsoft is - will they really see a reason to put quite a lot of resources into such transition for Xbox hardware which is not selling really well? I don't think so. It's still a big question mark about will we even see the next Xbox console iteration or not and we are talking about Microsoft investing a ton of resources into making x86 - ARM transition for the very small and almost irrelevant for them part of their business.
So, the conclusion for Microsoft is - they can pull it off without any issues if they will see the need for that (which they probably won't)

P.S. Also, the ARM chips main advantages over x86 are scalability and power-efficiency. It does not seem like these things are the priority for both Sony and Microsoft consoles.

Just wanna point out several things, first if the next-gen consoles launches around 2025-2026 I can easily see they having 16-core ARM cpu with more than 2x ipc than current consoles, probably clocked at 4ghz.

I don't know anything about emulation but this should make it easy for both Sony and MS to emulate previous gen games. They don't really need 100% perfect emulation anyway.

It will be AMD who builds the SOC, not Sony/MS. Most likely ARM(Cpu) + RDNA(gpu).

Second point, the main advantage ARM has over X86 is its ipc advantage, I don't know much about this but just what I read from very highly knowledgable people, X86 will lose against ARM because it's basically stuck at 4 decoders, it's very hard for a x86 cpu to go beyond this while ARM can go unlimited. Skylake from intel supposedly have 5 decoders in some press news but this is inaccurate, it has 4 decoders same as zen3. M1 has 8 decoders. It's because of the decoders ARM can have much higher ipc (Perf/ghz).

M1 has around 1.53x higher ipc than Zen3, the new snapdragon that will launch soon around 15%.

The Perf/w and smaller cores ARM gives is just a bonus.

"It will be AMD who builds the SOC, not Sony/MS. Most likely ARM(Cpu) + RDNA(gpu)."

But what if AMD would not want to build ARM-based SoCs? Yes, as I've mentioned in my post, I don't see Sony being able to create their own ARM SoC. So they would have to rely either on Nvidia with Tegra or AMD (if they'll jump on board with ARM). Another options can be Qualcomm or Samsung I suppose. By the way if I'm not mistaken Samsung is partnering with AMD for some of their newer Exynos SoCs to improve graphics. I think I've heard it somewhere.

"Second point, the main advantage ARM has over X86 is its ipc advantage, I don't know much about this but just what I read from very highly knowledgable people, X86 will lose against ARM because it's basically stuck at 4 decoders, it's very hard for a x86 cpu to go beyond this while ARM can go unlimited. Skylake from intel supposedly have 5 decoders in some press news but this is inaccurate, it has 4 decoders same as zen3. M1 has 8 decoders. It's because of the decoders ARM can have much higher ipc (Perf/ghz).

M1 has around 1.53x higher ipc than Zen3, the new snapdragon that will launch soon around 15%."

I'm not really sure what is meant here by decoders, I guess it is probably refering to GPRs (General Purpose Registers), but not sure. The issue is with IPC comparison. It's not indicative of performance at all. Because x86 is a CISC processor and ARM is a RISC processor. They have completely different instruction sets. Just an example from the internet, in x86 assembly a=b/c operation looks like this:

mov eax, b

xor edx, edx

div dword ptr c

mov a, eax

4 instructions only. Result will be put in memory where a is stored, plus the remainder will be left in edx GPR.

In ARM it would be like this:

mov r5, addr b

mov r5, [r5]

mov r6, addr c

mov r6, [r6]

div r7, r5, r6

mov r5, addr a

mov [r5], r7

7 instructions. The result will be stored to "a" as in x86 but you also will never receive a remainder anywhere.

That's the perfect example of why you can't compare IPC between ARM and x86, as with ARM's reduced instruction set, it is usually required to run more instructions compared to x86 to perform the same operation.