Hadn’t seen that, and mine is still in the sealed envelope. I suspect soaking it in hot water does a good job of heating the stuff and keeping it reasonably saturated during the application period.
I just put the syringe in the hotest water I could get out of the tap and left it in for 3 minutes. Worked good out of the gate, but covering Threadripper’s large surface, or even the 64s with the HBM2 added surface, the paste cooled before completion. Which was ok, but not optimal.
The stuff just doen’t reflect light very well and on a high contrast, low key exposure like this it looks black as if there was nothing. Trust me, it is there. 
For thermal paste I’m probably going to use the one from Intel.
I’ve heard so much great things about it lately.
…
Or not.
I use the IC-Diamond stuff for all my CPUs and since it is non conductive I don’t see a reason not to use it for Vega as well. Not sure about method, was thinking about the Jayz2Cents version. …
Yup, looking good. 
1 Like
i assume its mostly due to FP16 support.
There are 2 other games coming out with support for it: Aymmdstein 2, and NvidiotCry 5
both titles should give amd lead.
1 Like
I will take your word for it…
Interesting thermal paste technique. Let me know how it turns out…
Thermal Grizzly Kryonaut is working great on mine.
DONE!
It is basically impossible to use the standard baseplate without heavy mods. I went with those included heatsinks. It is not ideal and certainly not the prettiest heatsink array but it is all I can do. Unfortunately I don’t have more separate heatsinks, so that is all the cooling I can provide right now. I guess it’s ok … I hope.
Thanks AMD for that gap on the PCB where the original fan was, my cable-mess fits right in.
And there she is, that hungry, heavy, fat bitch of a Vega64.
I haven’t stress tested the card yet but it posts.
So far for now. Now back to building other stuff.
8 Likes
Noticed this yesterday on Newegg. no more forced bundle. /CHEER
Hurry! Sale ends in six days!!
/s
I really hope to see at least a concept drawing from Sapphire soon™
Do you have a way to check whether the HBM stacks are parallel with the die or not? That would be the only important feature in this case IMO.
As far as I know there is no way to check if you have the molded or unmolded version without taking the cooler of.
What performance inprovements could we expect from the 12nm chips coming next year btw? Or will it only be slightly less power consumption?
It is a thing of beauty 
And only 4 slots wide, just about adequate for a Vega card.
Your Vega is epic!
Global Foundries have been very careful with comparing it to their existing stuff, rather with some unspecified competing process. Their 12nm is a refined 14nm, the name would indicate a shrink. It is not a shrink as existing 14nm chips need no new tape-out. 14+ would be a less missleading name (not that TSMC is any better with their names).
It is mainly a higher density 14nm (high density libs probably). Might see about 5% Fmax increase.
Unfortunately, no. The card is back together and operational; although from what the naked eye could observe, the package was pretty level
I tried to google the different substrate again.
I got needs a 0.5mm shim to 40 μm which is 0.04mm.
The internet is so full of bullshit it can be hard to filter. If a straight edge over the GPU to HBM does not rock then I would say TIM would be fine and you would never know.
I am even unsure how hot HBM2 memory even gets. One google leads to
https://www.skhynix.com/eng/product/dramHBM.jsp
So if the HBM2 does not get hot (uses less power) then even less to worry about other than the cooler sitting level on the GPU for max thermal contact.
2 Cents for another Internet bozzo 
This is why I was curious if he could measure it. I have the tools to do so but got a flush potted package that’s all flat, so no difference here to check.
If software temps are to be believed the HBM2 gets plenty warm, and the real effects can be seen in performance as the timings increase under throttling. Since the memory is on the package with the GPU I suspect it absorbs at least some of that heat as well which may help explain issues in this regard.
Now that my 56 is under water I can find out for myself how it helps, or if it does at all.