Go Back   OC3D Forums > [OC3D] General Forums > OC3D News
Reply
 
Thread Tools Display Modes
 
  #1  
Old 19-05-17, 12:43 PM
WYP's Avatar
WYP WYP is offline
News Guru
 
Join Date: Dec 2010
Location: Northern Ireland, United Kingdom
Posts: 9,458
AMD has confirmed that Vega utilises their new Infinity Fabric tech

AMD confirms that Vega utilises Infinity Fabric, opening up a lot of possibilities for multi-die GPUs.



Read more on AMD's Vega GPUs and the potential of Infinity Fabric.

__________________
I'm not saying that 1984 is a bad book, but the dystopia we are currently living in has much better worldbuilding.
Reply With Quote
  #2  
Old 19-05-17, 02:02 PM
dwatterworth dwatterworth is offline
Member
 
Join Date: Jun 2013
Location: Rhode Island, United States.
Posts: 180
This article hits on something I've always wondered.
Why present a dual GPU card as dual GPU's to the system vs having the card manage it's own information tasking.

Maybe we will see a future GPU review with a chip looking like TTL's 100 fan AIO review.

'Enthusiasts will need to plan ahead with this GPU measuring in at 1500mm'.

In all seriousness though, fantastic idea! If the interconnects worked super well, maybe we could see a 'budget' monster GPU with larger process node sizes with a bunch of less expensive cores?

That multi-module approach sure would be more interesting for load distribution / power savings with GPU 'core parking/gating'?.
__________________
4790K - Z97 Gryphon - 16GB Dom. Plat. - 256GB 840 Pro - 512GB 850 Evo - EVGA 980ti SC - Seasonic X850 - Evolv mATX - H105 - Asus PA279Q / PB278Q --- Evolv mATX TG / VP755 / Eisblock XPX / dual 280mm rad system nearly complete.
Reply With Quote
  #3  
Old 19-05-17, 03:26 PM
NeverBackDown NeverBackDown is offline
AMD Enthusiast
 
Join Date: Dec 2012
Location: Asgard
Posts: 12,339
This was not surprising whatsoever
__________________
“There is only one Lord of the Ring, only one who can bend it to his will. And he does not share power.”
-Gandalf
Reply With Quote
  #4  
Old 19-05-17, 03:28 PM
Avet Avet is online now
Advanced Member
 
Join Date: Dec 2016
Posts: 303
They had good idea with developing infinity fabric. With creating large dies becoming a problem multi die single units are probably the direction in which will future tech go.
Reply With Quote
  #5  
Old 19-05-17, 04:01 PM
Tolemac's Avatar
Tolemac Tolemac is offline
OC3D Elite
 
Join Date: Aug 2014
Location: Bonkersville.UK
Posts: 2,126
Why has Buzz Lightyear suddenly entered my thoughts
__________________

Build Log: http://forum.overclock3d.net/showthread.php?t=72241

STEAM ID: http://steamcommunity.com/id/Tolemac/

“If you knew the magnificence of the three, six and nine, you would have a key to the universe.” – Nikola Tesla
Reply With Quote
  #6  
Old 19-05-17, 04:16 PM
AngryGoldfish's Avatar
AngryGoldfish AngryGoldfish is online now
OC3D Elite
 
Join Date: Jan 2015
Location: Ireland
Posts: 1,261
Navi = scaleable.
__________________
MSI Z97 Gaming 7 ⁞⁞ 4670K 4.5Ghz ⁞⁞ Nepton 240M ⁞⁞ ASUS Fury Strix ⁞⁞ Fury 16GB ⁞⁞ Define R4 ⁞⁞ AX760 ⁞⁞ Pexon PC ⁞⁞ Samsung EVO 120 & 500GB ⁞⁞ WD 1TB & 3TB
BenQ XL2730Z ⁞⁞ Mixonix Naos 7000 ⁞⁞ K70 Cherry MX Brown ⁞⁞ Audio-GD NFB-15 ⁞⁞ EVE SC205 ⁞⁞ AKG K7XX ⁞⁞ Fidelio X2
Reply With Quote
  #7  
Old 19-05-17, 04:29 PM
Tripp's Avatar
Tripp Tripp is offline
too many shrooms
 
Join Date: Dec 2012
Location: mersyside
Posts: 3,811
Quote:
Originally Posted by AngryGoldfish View Post
Navi = scaleable.
Makes a lot if sense now that, exciting things in the future for gpus at amd anyway
Reply With Quote
  #8  
Old 21-05-17, 10:05 AM
FluxTape FluxTape is offline
Newbie
 
Join Date: Jul 2016
Posts: 8
Quote:
Originally Posted by dwatterworth View Post
This article hits on something I've always wondered.
Why present a dual GPU card as dual GPU's to the system vs having the card manage it's own information tasking.
Because it is not easy. The inherent latency of the pcie bus can lead to inefficiencys if you aren't careful. That said vulkan and dx12 make exactly this possible, showing only one unified gpu to the developer.
Reply With Quote
  #9  
Old 21-05-17, 04:33 PM
NeverBackDown NeverBackDown is offline
AMD Enthusiast
 
Join Date: Dec 2012
Location: Asgard
Posts: 12,339
Quote:
Originally Posted by FluxTape View Post
Because it is not easy. The inherent latency of the pcie bus can lead to inefficiencys if you aren't careful. That said vulkan and dx12 make exactly this possible, showing only one unified gpu to the developer.
It's less to due with the PC bus whereas it's more along the lines of latency that's added due to a PLX chip in addition to software latency in trying to get both GPUs to work. It would also hurt that old APIs and engines were using one core to feed two GPUs. There wasn't a standard in place which makes it harder. Even with modern software it's still difficult and now it's the issue of just trying to get it to work well than anything. A hardware solution like this should really help.
__________________
“There is only one Lord of the Ring, only one who can bend it to his will. And he does not share power.”
-Gandalf
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump








All times are GMT. The time now is 01:03 PM.
Powered by vBulletin® Version 3.8.7
Copyright ©2000 - 2017, vBulletin Solutions, Inc.