Xbox Performance
Forum » General / Bug Reports » Xbox Performance
Started by: kolk3kolk3
On: 1256955036|%e %b %Y, %H:%M %Z|agohover
Number of posts: 5
rss icon RSS: New posts
Xbox Performance
kolk3kolk3 1256955036|%e %b %Y, %H:%M %Z|agohover

Hi, i have downloaded the last source of JiglibX. Then when i build it for Xbox360 the performance was very bad. I dont know if the example was to windows(there was only a keyboard and mouse input)… And i found a bug when tried to compile. The bug was found at GetVelocity method or something like this. A " out Vector3 result" parameter is used and is set with result.X = someValue; but on Xbox this is not possible. the correct is "result = new Vector3()" and then set the result values.

Sorry about my english, im brazilian!

Thankz!

unfold Xbox Performance by kolk3kolk3, 1256955036|%e %b %Y, %H:%M %Z|agohover
Re: Xbox Performance
Benjamin Dobell (guest) 1256974111|%e %b %Y, %H:%M %Z|agohover

The bug you mentioned is a known bug, I'm not sure why it hasn't been fixed actually. However in regards to Xbox 360 performance the problem is that the CLR implementation on Xbox 360 doesn't optimise code very much and doesn't make use of the Xbox 360's floating point calculation hardware. As a result floating point calculations are very slow on Xbox 360. As a result you'll never get the same performance on Xbox 360 that you get on PC, at least not without a CLR update from Microsoft.

unfold Re: Xbox Performance by Benjamin Dobell (guest), 1256974111|%e %b %Y, %H:%M %Z|agohover
Re: Xbox Performance
kolk3kolk3 1256994161|%e %b %Y, %H:%M %Z|agohover

Hmm I understand. But the problem is that on Xbox any collision was very slow =/ I tried both Bepu and Ooops 3D! either, and their performance was quite good comparing with JiglibX. I liked very much of JiglibX and i want help it.

unfold Re: Xbox Performance by kolk3kolk3, 1256994161|%e %b %Y, %H:%M %Z|agohover
Re: Xbox Performance
kolk3kolk3 1256997707|%e %b %Y, %H:%M %Z|agohover

Hi again.. i was reading something about XBox Performance and i found this.

"
Floating Point

Now that all said, both the Xbox 360 hardware and gaming scenarios are very different from what NetCF has been traditionally optimized for. The NetCF 2.0 JIT compiler for Windows CE does not support hardware floating point. In fact, hardware floating point isn’t supported in the ARMv4 architecture that current Windows Mobile devices target.

Thankfully, the Xbox 360 version of NetCF now does support hardware floating point. That work resulted in over a 10-fold improvement in our micro-benchmarks. So we think we’re satisfied with floating point perf for now. Nevertheless, it hasn’t been maximized in this release and that‘s an area of focus for the future. For example, the Xbox 360 also supports VMX128 (often referred to as AltiVec), but NetCF doesn’t take advantage of that hardware today.
"

Here's the font: http://blogs.msdn.com/netcfteam/archive/2006/12/22/managed-code-performance-on-xbox-360-for-the-xna-framework-1-0.aspx

unfold Re: Xbox Performance by kolk3kolk3, 1256997707|%e %b %Y, %H:%M %Z|agohover
Re: Xbox Performance
PGlynnPGlynn 1257287856|%e %b %Y, %H:%M %Z|agohover

I believe there have been some fixes to JigLibX on the non public repo. I don't know how much floating point optimization has been put in place, But apparently theres alot of garbage collection fixes.

You might want to sync to the non-public repo, or download it and give it a shot. http://www.codeplex.com/JigLibX/SourceControl/ListDownloadableCommits.aspx

unfold Re: Xbox Performance by PGlynnPGlynn, 1257287856|%e %b %Y, %H:%M %Z|agohover
New post
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License