yup listening to it right now.Originally Posted by Manicdan
yup listening to it right now.
[SIGPIC][/SIGPIC]
if there is one message that is clear.....
he could kill Steve Jobs in a fight
Maybe kungfu
Interesting CUDA x86 (Maybe gimped) and Matlab enabling support for CUDA enabled GPU's.
[SIGPIC][/SIGPIC]
FixedMaybe CudaFoo
Nvidia is gonna fail once again. Whatever BS card they release, you can bet it's either gonna be:
a) a sandwich (two slapped together GF104/6's with a sweet new name)
b) a mobile heater.
Last edited by Baron_Davis; 09-21-2010 at 08:59 AM.
Hmmm Sorry Baron but I would just like to address the two points you have highlighted here.Nvidia is gonna fail once again. Whatever BS card they release, you can bet it's either gonna be:
a) a sandwich (two slapped together GF104/6's with a sweet new name
b) a mobile heater.
Point a)
A sandwich?
No, I have a dual GPU Single PCB nVidia solution in my PC at the moment and I can confirm to you it is not a sandwich, in fact it is two GPU's on one PCB elegantly linked together by a 10GB/s NV chip. It is a dual slot card, with a nice back plate and a single fan in the centre of the cooler. The days of the nVidia Sandwich dual GPU dual PCB hackjobs are over and went out with the GTX 295.
b) A mobile heater?
I am afraid you might be correct on this one, the GTX 480 does run awfully hot, in fact it runs hotter than my dual GPU single PCB nVidia solution. (Mine maxes out in the mid 80's after 15minutes of Furmark 1.8.2 @ 1920*1200 with 16X FSAA) I have seen the GTX 480 reach around 100C at this setting.
However it is from my limited understanding that nVidia have somewhat counteracted this with the GF104 series chip by stripping down on a lot of the "Tesla" Computing components and also creating a more efficient architecture for gaming.
I am going to assume that nVidia will do the following (and yes this is an assumption).
1) Gamer based GPU's will have limited DP capability and will boast moderate computational features and performance, but would do well at Physx.
2) Tesla based GPU's will rock the socks off for DP performance and computational features and put all other GPU's (including ATi) to shame.
3) Quadro based GPU's will have a mixture of both worlds. They will boast increased computational horse power over the "Gamer GPU's", but may have, I have this opinion as I feel nVidia would want to drive the Ray-Tracing Bandwagon in Quadro Land.
What this boils down to is that nVidia will and can charge the earth for Tesla and Quadro based GPU's (because of the niche market they serve), but will also hopefully reduce costs to the gamer.
ATi do have a very impressive GPU lineup, just I feel that they lack the diverse feature set nVidia have with their cards. AND ATi have a habit for notoriously cutting corners.
(In the past we had no real SM 3.0 feature set, limited instruction length on R300 (fixed in refresh) and more recently the tessellation bottleneck).
Don't get me wrong, I am a big fan of the leaps and strides ATi have made over the years (Ex Radeon R300 based GPU owner here) and I truly believe that competition is great for the consumer..... just I do not like the way ATi have been assimilated by the AMD collective
John
Stop looking at the walls, look out the window
that's obvious because everyone makes mistakes. nvidia is no exception.
Posting Permissions
Reply With Quote
Bookmarks