• Competitor rules

    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.

Dark days, AMD share price at lowest ever.

Amen to that. Can you imagine the whole market rely on Intel & Nvidia only? We would be still on Quad core and 4th generation of Maxwell.
Oops forgot, we are on the 3rd iteration of Maxwell already and if rumours are correct the 11xx series will be the 4th generation.....

Oh cutting!

Though until developers actually make advanced DX12/Vulkan games/applications I would argue its a decent architecture I'm more critical of how they've iteratively trickled it out to milk consumers than the merits at a hardware level.
 
Oh cutting!

Though until developers actually make advanced DX12/Vulkan games/applications I would argue its a decent architecture I'm more critical of how they've iteratively trickled it out to milk consumers than the merits at a hardware level.

The problem is nVidia don't run DX12 or Vulkan well, those architectures just ain't built for it, AMD's GPU's have been designed and built with those API's in mind since Hawaii, but AMD are no-where in market share, nVidia whose best interest is suppress the use of DX12 and especially Vulkan are utterly dominant.
 
Oh cutting!

Though until developers actually make advanced DX12/Vulkan games/applications I would argue its a decent architecture I'm more critical of how they've iteratively trickled it out to milk consumers than the merits at a hardware level.

Developers have done advances on DX12 and async compute, but these left to consoles only.
The optimizations like async compute, are stripped when games are ported to PC because Nvidia doesn't support it on hardware level.

Games who decided to do so, had to strip hardware async compute because of complains over performance on Nvidia cards, because it very taxing to do it through the drivers.
 
Jumping back to the GPUs for a second, let me throw this out there for comment:

We know Vega 20 is 7nm and is Instinct for data centers. We know 7nm is coming to gaming cards, but everything points at that being Navi end of next year.

BUT, there is no way in hell Vega 20 production will see 100% perfect, fully functioning dies. Surely those non-perfect dies would get chopped down for RX cards? 7nm refreshed RX Vega isn't an official thing on the roadmap, but a year's worth of not-quite Instinct 7nm Vega dies simply can't go in the bin, can they?
 
AMD are at risk of falling off the GPU map completely, right now the RX 580 is a good £250 card, i would argue its better than the GTX 1060 6GB but those performance level cards are about to be made one up from entry level GTX 1050 / RX 560 cards so unless AMD have a £250 GTX 1070 level card up their selves they have serious problems, Vega 56 is GTX 1070 level and its a very expensive monstrosity in comparison, are AMD about to make small efficient GPU's that have performance like Pascal?
No, AMD need an architectural shift, recycling existing stuff to lower end has reached that unsustainable end for AMD.

What I found really weird,is AMD already has a higher shader Polaris/Vega hybrid GPU.....in the XBox One X. Its a 2816 shader part with a 384 bit memory controller. It has many Vega features outside FP16:

https://www.gamespot.com/forums/sys...rence-xbox-one-x-reveal-with-vega-n-33402577/

Thats 22% more shaders and a huge bump in memory bandwidth too.

Vega56 is around 33% faster than an RX580 at 1080p:

https://tpucdn.com/reviews/AMD/Radeon_RX_Vega_56/images/perfrel_1920_1080.png

So in theory a 2816 shader part would be close to a Vega56 at 1080p.
 
Jumping back to the GPUs for a second, let me throw this out there for comment:

We know Vega 20 is 7nm and is Instinct for data centers. We know 7nm is coming to gaming cards, but everything points at that being Navi end of next year.

BUT, there is no way in hell Vega 20 production will see 100% perfect, fully functioning dies. Surely those non-perfect dies would get chopped down for RX cards? 7nm refreshed RX Vega isn't an official thing on the roadmap, but a year's worth of not-quite Instinct 7nm Vega dies simply can't go in the bin, can they?

It also uses 4 stacks of HBM2,so unless the salvage part can be a performance bump over a Vega64 with only two stacks of HBM2 it might not be finanically viable.
 
Jumping back to the GPUs for a second, let me throw this out there for comment:

We know Vega 20 is 7nm and is Instinct for data centers. We know 7nm is coming to gaming cards, but everything points at that being Navi end of next year.

BUT, there is no way in hell Vega 20 production will see 100% perfect, fully functioning dies. Surely those non-perfect dies would get chopped down for RX cards? 7nm refreshed RX Vega isn't an official thing on the roadmap, but a year's worth of not-quite Instinct 7nm Vega dies simply can't go in the bin, can they?

They will be chopped down for smaller Intrinsic cards
 
Amen to that. Can you imagine the whole market rely on Intel & Nvidia only? We would be still on Quad core and 4th generation of Maxwell.
Oops forgot, we are on the 3rd iteration of Maxwell already and if rumours are correct the 11xx series will be the 4th generation.....

It'd definitely suck, Fingers crossed Ryzen was the turning point & AMD's making enough money for the penny-pinchers to show RTG some loving.
 
Back
Top Bottom