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.
Respinning Fury III on a 7nm process is not the answer. Getting past the 4 geometry wide front end is their next solution.
Respinning Fury III on a 7nm process is not the answer. Getting past the 4 geometry wide front end is their next solution.
unfortunately, Navi just looks to be more of the same. Although there was rumors of a 12nm respin of Polaris and some renaming going on so what was going to be navi might get named something else.
7nm would be a great time to jump to a whole new architecture. The extra transistor budget is really required, and even if the first iteration is not well optimized the node shrink itslef will see a large performance gain. 7nm will be around a long time, but with several evolutions which can be used to refine a new architecture
This is just more BS, because the simple fact is Nvidia is along way ahead so whatever AMD does such as lowering margins or increasubg voltage and clocks, Nvidia can do the same.
There is a size.limkt for a commercialy via me GPU, and a physical limit. Same with power. If you ahve to produce a GPU that is far bigger or power hi Gary then your technology is a long way behind. It is relatively trivial to scale upwards in siS to gain performance, it is much harder to gain performance within the same transistor cpubtbor die size.
And the die size is of critical importance to the viavilvia of the GPU. Nvidia make far more profit per GPU sold because smaller dies have far higher yields and more GPUs per wafer - costs increase at least quadraticly with die size.
If Nvidia ever felt threatened they could start a price war and crush AMD right now.
I was saying this Day one when Ngreedia went with this GPP.
Amd is LUCKY they have not went price drop way. We all know (I hope) That Nvidias cards are CHEAPER to produce. They could Uncercut AMD on all gpu Tiers so much they would just have to sell cards at loss and NV would still make profit !!!
Image thatExactly, if Nvidia really wanted to do massive damage to AMD they could sell the 1080ti cheaper than Vega64 and still make a reasonable profit. They don't because a company needs to make a profit to exist, continue R&D. It also means the AIbs are amking a larger than normal profit, which keeps them happy
Image that
Ti below Vega 64
1080 below Vega 56
1070 at 580
GG
Don't give them ideas!!!!!!!
![]()
![]()
![]()
Exactly, if Nvidia really wanted to do massive damage to AMD they could sell the 1080ti cheaper than Vega64 and still make a reasonable profit. They don't because a company needs to make a profit to exist, continue R&D. It also means the AIbs are amking a larger than normal profit, which keeps them happy
I am intrigued how the X2 are working. We know already Vega 64X2 is on production but have no idea how it works.
It is not for gaming
I was saying this Day one when Ngreedia went with this GPP.
Amd is LUCKY they have not went price drop way. We all know (I hope) That Nvidias cards are CHEAPER to produce. They could Uncercut AMD on all gpu Tiers so much they would just have to sell cards at loss and NV would still make profit !!!
Exactly, if Nvidia really wanted to do massive damage to AMD they could sell the 1080ti cheaper than Vega64 and still make a reasonable profit. They don't because a company needs to make a profit to exist, continue R&D. It also means the AIbs are amking a larger than normal profit, which keeps them happy
I am wondering how they are working not if they are for gaming.
I am intrigued how the X2 are working. We know already Vega 64X2 is on production but have no idea how it works.
Well, in the same way like all previous cards - HD 3870 X2, HD 4870 X2, HD 5970, HD 6990, HD 7990, R9 295X2 and Radeon Pro Duo.
With a PLX chip: https://www.anandtech.com/show/2428
upload pic
They are working well for compute I imagine, the same as any other duel GPU cards using xfire/sli and duplicated memory pool.