By using this site, you agree to our Privacy Policy and our Terms of Use. Close

Forums - Microsoft - Xbox 360 untapped potential? How about a hardware tesselator!

It hasn't really even been used yet.

http://ati.amd.com/developer/Eurographics/2007/Tatarchuk-Tessellation(EG2007).pdf

Read all about it.

Essentially it speeds up triangle rendering by a massive amount and saves a crapload of memory in the process (Laymans terms) So you see they can make the models and landscape look more realistic. Just look at the PDF and you'll see.

 

 



Tease.

Around the Network

^ lulz



 nintendo fanboy, but the good kind

proud soldier of nintopia

 

PDF said:
Squilliam said:

Just look at PDF and you'll see.

 

 No plz Dont look at me.  I find it to be creepy when people stare.

LMAO. g1 dude g1



Great find,keep them coming. And i don`t think the cpu is used to the max either.



Stan85 said:

Great find,keep them coming. And i don`t think the cpu is used to the max either.

Actually the Xbox 360 is currently CPU limited but not in "Cell pwnz uz" way. Its more limited by how inefficiently the Xenon is being used currently. Things like the main hardware thread overloading Core 1 whilst Core 2/Core 3 are being left idle.

As Microsoft makes strides in multi-core research that information is shared with game developers but unfortunately these changes take time.

 



Tease.

Around the Network

Interesting stuff and all. But how does this fit in to 360 untapped potential? Or indeed microsoft news? (edit - just saw the thing about the future of directX, my mistake)



Yes

Using geometry shader to tessellate and render Bezier/B-Spline/Nurbs curves and surfaces has three
benifits:
1. The volume of transferring data to GPU is much less than using triangles. Also it is independent to the
LOD (Level of Detail). Therefore without suffering from limited bandwidth, high quality curves and
surfaces can be displayed.
2. Tessellation and rendering can be processed in parallel way.
3. LOD can be achieved easily and doesn’t cause any overload to CPU. Also adaptive tessellation can be
also achieved along with LOD.
The limitation of geometry shader:
1. The number of emit primitives are limited.
-> We can overcome this by subdividing input curves or surfaces.
2. The size of geometry shader and loop iteration are limited.
-> Sensitive coding and tuning are necessary.

http://www.seas.upenn.edu/~cis665/projects/CIS%20665%20GPU%20Project%20Final%20Report%20-%20Dongsoo%20Han.pdf

And then another one

http://www.tronte.com/content/SST_tromsoe_jmh_trh.pdf

Looking into them is only recomended if you have enough of a techie brain to not get beat over the head with the jargon and formulae.



Tease.

If you want an overview on some of the directions Microsoft is taking Xbox 360 development and where they are improving performance check out this link and pay attention to the ones with the cute Xbox 360 logo under them.

http://www.xnagamefest.com/conference_details08.htm



Tease.

Developers, developers, developers.



In university, one of my graphics professors was really into subdivision surfaces ...

Where I see this as being very valueable is for downloadable content ... You produce a model that is only somewhat more detailed than a model that would be produce for a N64 game and you include some additional information in order to subdivide the model correctly and you should be able to increase the quality of the assets produced for the game without increasing the size of the download.