unified shader model 4.0

[dh19440113]

What do you guys think about the new unified shader hardware of shader model 4.0?

Do you think it will be better than the separated pixel/vertex shader nvidia 32/32 and ati 16/48 have right now?

Personally I think a unified cross vector and dot scalar units will be a balance of speed and stability. For example, a unified 64 pipeline can allocate pipeline resource according to the need of the 3d software so frame rate will remain steady and playable.

However, a unified pipeline is slower than a dedicated pipeline design to handle specific pixel/vertex.
The result is slower maximum fill rate in exchange for steady fill rate that never drop below threshhold.

 

[NoStateofMind]

I learned enough from reading your post that I think my head is going to expload!

 

[tuteja1986]

which is better ;? Dedicated pig or a pig that can mutlitask :?

 

[dh19440113]

Originally posted by: PC Surgeon
I learned enough from reading your post that I think my head is going to expload!

CMPE Talk 🙂, anyways I couldn't make my post any simpler and get my point across.

Since window vista uses window graphics foundation, we will be seeing unified shader hardware whether we like it or not.

 

[tuteja1986]

well i like it already :! i see XBOX 360 graphic and i like them 🙂

 

[RobertR1]

Originally posted by: dh19440113
What do you guys think about the new unified shader hardware of shader model 4.0?

Do you think it will be better than the separated pixel/vertex shader nvidia 32/32 and ati 16/48 have right now?

Personally I think a unified cross vector and dot scalar units will be a balance of speed and stability. For example, a unified 64 pipeline can allocate pipeline resource according to the need of the 3d software so frame rate will remain steady and playable.

However, a unified pipeline is slower than a dedicated pipeline design to handle specific pixel/vertex.
The result is slower maximum fill rate in exchange for steady fill rate that never drop below threshhold.

If you want to dicuss such in-depth technical merits, check out www.beyond3d.com

 

[DeathReborn]

All it would need is software developers to actually take advantage of the unified architecture properly and not half ass it with poor coding.

It should also mean the pipelines in differing SM4.0 GPU's are similar and offer similar if not identical features. It should help highlight driver problems more than current cards do.