Playstation 5 [PS5] [Release November 12 2020]

Someone was going to figur this out soon or late. There will be more of those kinda of 'tests' appearing from time to time.

 

The bottleneck is maybe somewhere else but we will have soon a game benchmark by Digitalfoundry where I expect the PS5 to perform much slower than a 2080 Ti and it will be interesting to compare to a 5700XT.

EDIT:

https://sluglibrary.com/SlugDemo.zip

There is a demo available on windows it is possible to compare GPU result.

https://sluglibrary.com/

The demo use arial but it is possible to change to any font.

 

This an engineer's version of an infinite number of monkeys banging away on typewriters to recreate Shakespeare.

 

Japan and US models had full PS2 hardware for bc. EU launch modell had partial hardware. I do not remember if it was the ps2 cpu or gpu that got removed at EU launch.

 

It was the CPU, but in the end, every PS3 even the ones without any PS2 hardware received full software BC, with hacks you could use it for every title, DF did a video on this

 

Yeah, CPU was removed on CECH-C/E as well as the Rambus memory.

ps2_netemu (the .self that was used for PSN classics) was far far away from full BC even with community configuration patches. For the stuff that is fully playable there might be various audio/visual glitches.

 

In total numbers with what is playable (without glitches) it still dwarfs official Xbox emulation, which is often praised for its numbers. But you are correct, only the games released on PSN were fully tested and playable.

Here is a list:
https://www.psdevwiki.com/ps3/PS2_Classics_Emulator_Compatibility_List

 

What I think you're seeing here is the result of two distinct GPU resources being tested are interleaved as [fill rate] then [computational] then [fill rate] then [computational] then [fill rate] then [computational] repeated but with both GPU tasks initiated by the CPU. Ergo, what this benchmark demonstrates is less overall theoretical computation or fill rate performance but more crucially CPU setup times of the individual operations required to achieve the result.

 

Some compiler stuff from SN System

 

#TOOLS !

 

Sony have been a long-time contributor to LLVM. It's a shame Microsoft don't also use LLVM because that would lead to better performance for all code produced by the compiler.

 

LLVM traditionally compiles faster, it does not necessarily make the code run faster.

 

Compile times definitely do not translate to runtime performance, but I've not seen any comparison of code performance between the two compilers used by Sony and Microsoft. What I'm saying is, the more people using and - contributing using to the improvement of - compiler tech, the better for everybody.

 

So everyone should be using the GNU toolsets like GCC?

 

Well, I disagree. Competition is good also for compilers.

 

No, I'm very happy for anybody not concerned with code performance to use something else and not contaminate the code base of something that is.

 

When you have Free software like GCC and LLVM you can have competition of ideas withing the projects. It becomes a completely different situation than competition between companies' products.

 

Hm... weird, he is getting better temps than Gamer's Nexus. Topping at 97ºC on the memory when covering the console with a blanket. My guess is his results wont get much attraction as they are good.

 

Not surprised. The methodology of Gamer's Nexus have being questioned by some, and not only because of thermal pads. We could see on his setup the cables were preventing the shield to be correctly positioned.