• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD TressFX

I dislike the linking of this to GCN as if GCN has now made it possible and/or its a function thats hidden away in GCN. The technique works on pretty much any GPU with compute shaders and supporting directcompute 11* its just a feature that can put the GCN architecture to use.


*It could even be implemented on Open CL or CUDA, etc.
 
Maybe a visit to specsavers is in order ;)

You need to fix your quote scotty. I went to the trouble of repairing the botch job nightglow did lol.

I dislike the linking of this to GCN as if GCN has now made it possible and/or its a function thats hidden away in GCN. The technique works on pretty much any GPU with compute shaders and supporting directcompute 11* its just a feature that can put the GCN architecture to use.


*It could even be implemented on Open CL or CUDA, etc.

:rolleyes:
 
I dislike the linking of this to GCN as if GCN has now made it possible and/or its a function thats hidden away in GCN. The technique works on pretty much any GPU with compute shaders and supporting directcompute 11* its just a feature that can put the GCN architecture to use.


*It could even be implemented on Open CL or CUDA, etc.

Its Marketing... yes it could have been implemented on CUDA.. But guess what!? It wasn't cus cuda is for pandas :p
 
My comments have nothing to do with CUDA tho people who don't understand what I'm saying might perceive it as such. My objection is that people are seeing it as if TressFX, etc. are features within GCN when infact one of the key elements of GCN is moving away from fixed or limited function pipelines and towards more complex, versatile, general purpose compute units.
 
Back
Top Bottom