• Hey Guest. Check out your NeoGAF Wrapped 2025 results here!

Former Remedy Programmer on Xbox360 vs PS3 coding (via TXB forum)

http://forum.teamxbox.com/showthread.php?t=344508&page=2&pp=20

Gigaflop/s numbers mean nothing, those numbers give us no info about real world performance.
The sad thing is that a lot of devs I know don't have a clue how to exploit NG CPUs power and they are not that much informed about CPUs architecture.
As example: first time I ported our old CPU skinning code from PC/XBOX to PS2 I profiled it and observed main character skinning (7000 polys) on PS2 took 20 ms!! A full PAL frame!
The same code on XBOX run 10 time faster, It was just running on EE and it didn't make any use of some fancy vector unit, no DMA, no data customization/reordering.
Now, after making some use of VU0 and DMA engine it takes about 2 ms, it's an order of magnitude faster than before and probably it could be, if further optmized, 2x faster than that.
'Exotic' new architectures need a lot of custom work but I believe this time things will not be THAT different between X360 and PS3 like it was on XBOX/PS2.

I'm not saying I agree - but then again, I know nothing of programming anyway. the discussion on TXB is also interesting.


edit: Oh, the actual source is nAo on Beyond3D
http://www.beyond3d.com/forum/viewtopic.php?p=515830&highlight=7000+polys#515830
.
.
 
by not being that different, i think he is implying that the programming end of things will be easier for the ps3... meaning the power advantage will show up much faster.. :)

we'll c :)
 
What's interesting is the guy who sounds like he's getting less performance out of the new chips (cell and xenon) than the x86 family of chips.
 
Just to clarify something: I never worked at Remedy!

What's interesting is the guy who sounds like he's getting less performance out of the new chips (cell and xenon) than the x86 family of chips.
In single threaded general purpose code, on a clock per clock basis, it's understandable a modern x86 will beat Xenon CPU and CELL.
Modern x86 CPUs have out of order execution and very big caches, they're pretty good at hiding registers dependency and memory accesses latency.
X360 CPU and CELL don't have out of order execution, they rely on programmers/compilers to schedule memory prefetches and to hide dependencies.
Nothing new under the sun, PS2 EE has no OOOE and it has a ridiculous amount of cache, that's why you badly need to customize/rewrite o even redesign your code to efficiently run it.
 
Nostromo said:
Just to clarify something: I never worked at Remedy!


In single threaded general purpose code, on a clock per clock basis, it's understandable a modern x86 will beat Xenon CPU and CELL.
Modern x86 CPUs have out of order execution and very big caches, they're pretty good at hiding registers dependency and memory accesses latency.
X360 CPU and CELL don't have out of order execution, they rely on programmers/compilers to schedule memory prefetches and to hide dependencies.
Nothing new under the sun, PS2 EE has no OOOE and it has a ridiculous amount of cache, that's why you badly need to customize/rewrite o even redesign your code to efficiently run it.
Thanks for the info. I just hope this redesigning and recoding doesn't affect too much the results we see and how long it takes to see them in next generation games. I certainly haven't been that impressed by the results people still are getting from the ps2 but that could have more to do with the quality of its graphics engine.
 
Top Bottom