@glimpse

Problem is that always two circuits generate more heat, consume more power, use is prohibited by cooling and power restrictions form both PSU and mainboard etc. It is always more expensive (as you pay for double the size cut from wafer). It is also interesting that - what earlier never ...

This is the source: http://videocardz.com/32898/nvidia-prep ... -of-memory

Seems that NVidia has real problem - Tesla 3000 will be based on two Keplers. This is clear that this architecture is not "locked" in consumer products (like GTX680) but is purely lacking computing power. Period.

@t_3 The real raw performance (like hardware sheduler) is missing in "new" design! Also FP64 is poor (some use this for other than graphics compute tasks). It is more than good for gamers, though. I'm almost sure that GTX685 (780?) will be on same compute power level as GTX 590 (but more efficient ...

That is one big FAIL of NVidia!

If we consider that Radeon 7990 will have 7.6 TFLOPS Single Precision compute power and 1.8 TFLOPS Double Precision compute power - then NV is seriously in deep sh%%t.

Octane should be as soon as it is possible, ported to OpenCL.

http://images.anandtech.com ...

@Radiance

I disagree that Cycles will change demand for Octane, higher possibility is that NVidia could ruin it by not delivering (next CUDA toolkit or proper compute power in consumer cards or by forcing differentiation market on: Quadro,GFX, Tesla). Other aspects is AMD delivering (like 3,49 ...

Sill it will be less than GTX 590? Plus 590 is more capable with FP64. Right?

Seem's that NVidia will try to earn some money on us, differentiating products:
- gaming
- compute (eg. Tesla)
It could have opposite effect for them, if AMD OpenCL implementation will be as fast as it is with 7970 and there will be more shift to OpenCL (as Ivy Bridge and Intel will no doubt go in ...

I also have fingers crossed for You all guys and future development of Blender plugin!

Did only I spotted that GTX680 behaves poorly in SmallLux raytracing test? Could it be "That" bad?