• 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.

Next Gen Graphics and Process Migration: 20 nm and Beyond

Soldato
Joined
2 Jan 2012
Posts
12,410
Location
UK.
The Really Good Times are Over

We really do not realize how good we had it. Sure, we could apply that to budget surpluses and the time before the rise of global terrorism, but in this case I am talking about the predictable advancement of graphics due to both design expertise and improvements in process technology. Moore’s law has been exceptionally kind to graphics.

http://www.pcper.com/reviews/Editorial/Next-Gen-Graphics-and-Process-Migration-20-nm-and-Beyond
 
This is a hit piece against AMD's Hawaii chip. They're using the arguments: "not a Titan killer so worthless", "wait for Maxwell", "nothing to see here" etc etc

PCPer again... hmm.
 
This is a hit piece against AMD's Hawaii chip.

PCPer again... hmm.

Paid arm of Nvidia marketing thats why. ;)

9Lgsm5e.jpg
 
AMD isn't up to anything. I know it's blasphemy on here but they are just behind the curve on this one. Hawaii (to me, I'm not saying this is an absolute truth) seems to be very stretched for a new architecture what with the thermal targets and the entire concept of Uber mode. This just screams to me that they're ringing Hawaii within a few steps of it's life to gain the all important edge.

With such a struggle and delay to tackle 20nm I pray they overcome the limitations and we don't get leaf blower reference cards next year and beyond :).


I do miss the days where it was so easy to be impressed though. I remember walking into HMV and seeing Quake 2 running on Voodoo 2 SLI (The proper SLi that incorporated memory scaling ;)).
 
Last edited:
I think you're reading too much in to Uber mode. There doesn't appear to be any difference in benchies seen so far, if it was a trick to get around max TDP requirements the numbers would show that.
 
I think Uber mode will just be a much louder fan profile with the TDP limits removed (think power tune at +20%) and full voltage control.
 
Not convinced but call me a sceptic. It may well be it does just that but again, if it's really that loud I wouldn't touch a reference card with a barge pole.
 
Not convinced but call me a sceptic. It may well be it does just that but again, if it's really that loud I wouldn't touch a reference card with a barge pole.

That's why quiet mode is there i suspect. The reference 7970 i had at 40% fan speed was silent.
 
Ok, that may be. But these are reference cards for a NEW line. With a temperature target of 95c and a reasonably high TDP is this card really going to give manufacturers a lot to play with for 7-10 months? I'll happily hold my hands up if I'm way off the mark but I guess we won't have to wait long now. The low supply only furthers my suspicions...
 
Last edited:
Ok, that may be. But these are reference cards for a NEW line. With a temperature target of 95c and a reasonably high TDP is this card really going to give manufactures a lot to play with for 7-10 months? I'll happily hold my hands up if I'm way off the mark but I guess we won't have to wait long now.

Reference coolers are never great for exotic cooling though. AIB's like MSI and HIS will have no problem keeping the card much cooler and quieter. My 7970 reference used to sit in the mid 80's at auto fan speed at 1010/1375. When i slapped an accelero on there the core would barely hit 50c at 1125/1575.
 
eh? how is this a hit piece, he talks about foundries and processes and how after 20nm the next steps that could give us a transistor density boost are years off

in the same paragraph where he criticises AMD's rebrand and minor update in the new range he also criticises the 7** series for essentially being a rebrand of the 6** series plus Titan

in every paragraph where he mentions a problem for AMD he mentions the same issues for Nvidia
 
This is a hit piece against AMD's Hawaii chip. They're using the arguments: "not a Titan killer so worthless", "wait for Maxwell", "nothing to see here" etc etc

PCPer again... hmm.


One reason for Mantle, slow down of nodes means little to no performance boosts due to 2 years cycle of hardware or even more down the line.
The main thing here might be Nvidia has no answer to Mantle which will ensure amd domination for years both with Mantle and open gl.
I said that the cpu business will also get a boost for amd as Mantle comes out due to the ipc advantage Intel have had goes away.
 
A very good read. I missed the slating of AMD parts? Maybe because I wasn't looking for them was the reason but he is pretty spot on for the entire article IMO.
 
Good comment from someone on that article

I just had this same conversation with AMD's Raja Kudari. Raja's response is that it will take new architectures to improve performance, not just process shrinks and die area growth. It's going to take improvements in architecture efficiency and effectiveness. It also means that the GPU designers need to work closer with game engine developers to find efficiency improvements - Mantle is one example.

Or in the case of AMDs cards, find ways to defy thermal physics :p

Kidding, although could water be a viable cooling option at reference level? You'd potentially put the card out of reach for small form factors
 
Last edited:
Back
Top Bottom