-
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.
Radeon pro Vega 2
- Thread starter Gerard
- Start date
Soldato
It's exotic:
Last edited:
Soldato
Can i play games on it?
Caporegime
Looks fairly chunky.
Soldato
It's exotic:
Can we get it with 3 8-pin connectors and not that weird 475W pcie connector? No need for cooler either, it goes under water.
Soldato
Soldato
Is it the usual memory divided by two so only 16GB per chip? ("Only" lol). Would be nice if they solved the non-shared memory issue, but my assumption is they haven't.
I shudder at the potential cost.
I shudder at the potential cost.
Man of Honour
But will it run Crysis? 
Sorry, someone had to do it!
Sorry, someone had to do it!
Soldato
But will it run Crysis?
Sorry, someone had to do it!
Yes
http://portingkit.com/game/1238
Can grate cheese also as you know
Soldato
Apple provides a 1400W PSU. If this card comes to PC, there are going to be cries that needs such PSU.
Soldato
It will be bottlenecked like no other GPU
Since it's paired with a 2.2Ghz Xeon. Poor thing.
Caporegime
Infinity Fabric on a GPU....
Soldato
- Joined
- 19 Oct 2008
- Posts
- 5,951
Many assumed that would happen at some point.
Got me thinking whether NV would go the dual GPU route again too given that RT has caused a slowdown in raw FPS increase this generation. Would be a good time to revive SLI
.Looks quite impressive albeit as pro cards.
When I saw the info this morning apple the Apple and 28 cores I did wonder why not AMD CPU, although would have to be 32 cores.
Soldato
525w of deliverable power on a single board, you kinda need them.
Soldato
Hopefully it'll be a nice reasonable 500 quid
The Mi50 and Mi60 You a which are the same as this VEGA duo already had infinity fabric.
This is AMD's version of NVLink. This just provides faster data transfer for Compute applications.
Finally IF connecting two GPUs.
Now that we've seen this, I'd be surprised if by mid 2020 we don't see a bunch of multi GPU in the consumer space from AMD.
It just makes sense, for the same reason it does on the CPU side. More smaller dies = better yields = lower costs and better bins = higher performance, competitive advantage, and lower cost to consumers.
As bigger Navi is obviously coming, and 'next gen' next year I highly doubt Vega 20 Duo gets a consumer launch.
Question is, do they wait for Next Gen, or do it with Navi?
As I've said before, IMO the driver side of things making this work and getting software to treat it like a single GPU really shouldn't be a big deal at all, it was about scaling IF to the bandwidth and latency, over longer traces that are needed for graphics. As they now appear to have that solved finally, I think the rest is a fait accompli.
Also wonder if this now means that, per old rumours, PS5 and XBN will be multi GPU.
Now that we've seen this, I'd be surprised if by mid 2020 we don't see a bunch of multi GPU in the consumer space from AMD.
It just makes sense, for the same reason it does on the CPU side. More smaller dies = better yields = lower costs and better bins = higher performance, competitive advantage, and lower cost to consumers.
As bigger Navi is obviously coming, and 'next gen' next year I highly doubt Vega 20 Duo gets a consumer launch.
Question is, do they wait for Next Gen, or do it with Navi?
As I've said before, IMO the driver side of things making this work and getting software to treat it like a single GPU really shouldn't be a big deal at all, it was about scaling IF to the bandwidth and latency, over longer traces that are needed for graphics. As they now appear to have that solved finally, I think the rest is a fait accompli.
Also wonder if this now means that, per old rumours, PS5 and XBN will be multi GPU.