New rumor about ATI Southern Islands

[Manicdan]

If the gtx 295 was clock like a fermi card, it would almost certainly be faster. Also the gtx 480 loses pretty soundly to SLI gtx 285. Per transister, fermi is worse than the gtx 280, which is pretty bad considering it is a new architecture.

this
nvidia is way behind in perf per mm2, and amd is about to get even better. if they continue to lead in perf per $, then gaming market share will continue to head toward them.

the 28nm race could change everything though

[Carfax]

this
nvidia is way behind in perf per mm2, and amd is about to get even better. if they continue to lead in perf per $, then gaming market share will continue to head toward them.

the 28nm race could change everything though

This is only relevant if you take Fermi as a gaming GPU.....which it isn't.

Fermi was designed for both HPC and gaming.. The HPC market is much more profitable than the high end gamer market (and from the benchmarks I've seen, Fermi decimates ATI in that area), so ATI leading in perf per mm2 isn't as important as you'd believe.

[Iconyu]

This is only relevant if you take Fermi as a gaming GPU.....which it isn't.

Fermi was designed for both HPC and gaming.. The HPC market is much more profitable than the high end gamer market (and from the benchmarks I've seen, Fermi decimates ATI in that area), so ATI leading in perf per mm2 isn't as important as you'd believe.

Does that same defence stand for the 460? It's bigger than the 5870... and designed with lobotomised HPC capabilities.

[Carfax]

Does that same defence stand for the 460? It's bigger than the 5870... and designed with lobotomised HPC capabilities.

Yes and no. The 460 is much more geared towards gaming than the 465/470/480, but it still has many HPC qualities that increase the size of the die.

Basically, none of the Fermi derived GPUs are purely gaming or HPC GPUs. Instead, they are hybrid processors.

[Manicdan]

This is only relevant if you take Fermi as a gaming GPU.....which it isn't.

Fermi was designed for both HPC and gaming.. The HPC market is much more profitable than the high end gamer market (and from the benchmarks I've seen, Fermi decimates ATI in that area), so ATI leading in perf per mm2 isn't as important as you'd believe.

perf per mm2 translates to price and profit.
if amd felt threatened, they would have lowered the price.

funny you bought 2 gpus that arnt even for gaming, lol

[Carfax]

perf per mm2 translates to price and profit.
if amd felt threatened, they would have lowered the price.

But as I said, the HPC market is far more profitable than the gamer market, so increasing the HPC capability of your GPU leads to more profit than just focusing on gaming only.

Just think, how much does a high end Quadro GPU cost? Thousands of dollars....for ONE!

Increasing the HPC and Scientific capability of their GPUs while retaining their ability to be used as primary gaming GPUs, is one of the best moves Nvidia has ever come up with.

Because of Fermi, Nvidia has strengthened it's hold on the HPC market, which like I said, is inherently much more profitable than the gaming market.....even though less GPUs are sold.

funny you bought 2 gpus that arnt even for gaming, lol

They are for gaming. I should have been more specific, but I thought I clarified in my following sentence:

Fermi was designed for both HPC and gaming

Fermi was designed for BOTH gaming and HPC, and as such, it's pretty amazing since they are the top performers in both areas.....at this time.

[flopper]

There is a increasing need for HPC which amd also will adress most likely in the upcoming 6000 series, but also down the line with new generations as the market expand.

the oem with fusion makes sense a lot, no extra videocard or such features on the motherboard allows the cheaper things to be build all the things a oem like.

I see amd in a better position than Nvidia after they got things togeheter.

AMD still lacks a good PR and communicating department but they havent hired me yet.

[Carfax]

There is a increasing need for HPC which amd also will adress most likely in the upcoming 6000 series, but also down the line with new generations as the market expand.

If AMD genuinely desires to address the HPC market, they will have to invest more transistors into their designs for dedicated HPC function....which will mirror what Nvidia has done with Fermi.

Of course, the AMD fan boys will herald this as the greatest thing ever even if the power envelope is increased dramatically, much as what happened with Fermi

[flopper]

If AMD genuinely desires to address the HPC market, they will have to invest more transistors into their designs for dedicated HPC function....which will mirror what Nvidia has done with Fermi.

Of course, the AMD fan boys will herald this as the greatest thing ever even if the power envelope is increased dramatically, much as what happened with Fermi

Fusion as a concept and the aim for power/price/performance strategy will allow them to come up with stuff that suits that concept of a HPC tech card down the line.
I cant think they be skipping a growing new market as we move towards a union between different structural elements, combining for example a videocamera with a normal camera is now on the way, you buy both in the same toy as the technology now have moved far with that.
Like the phone that is now, music, video, chat, and well a phone.

social networking is increasing, at a rate that is astounding, and software and hardware needs to met up there as that continues.
If I be hired by amd I advice them to get going there with their commercials even more.

So, our hardware, video and cpu, and other things is getting soon to a point where we can have a combined element, and fermi is just powerhungry due to bad design, first generation tends to be that.
I expect that Nvidia will improve the power issue a lot in the upcoming revisions they do.