This site may earn chapter commissions from the links on this folio. Terms of apply.

Terminal week, we covered the successful delidding of AMD'due south Threadripper CPU. It's not for the faint of heart, given that information technology requires multiple hot air soldering stations and a variety of razor blades, and the expert overclocker who managed to remove the heat spreader still killed the chip.

Even so, der8auer's findings left us a touch confused. What the delid showed was that AMD had put four dies on the bundle, but merely ii of them were obviously active, every bit opposed to using four cores across each dice for a total of 16. We've since spoken to AMD about this, as has Overclock3D, and nosotros can explain what's actually going on.

The caption is straightforward: The reason Threadripper has four dies under the hood with only ii in utilise is because leaving them off would create mechanical instability when the heatsink is mounted. AMD apparently needs 4 dies in that arrangement to stabilize the packaging. This does make sense, given some of the esoteric cooling solutions with loftier pressure attachments that overclockers use.

Why Not Use All Four Die?

There are several reasons AMD isn't using four ii+ii configurations. First, 2+2 would increase latency and striking gaming performance, as data has to exist passed across the Infinity Material. So far, tests accept shown that configuring Ryzen seven 1800X in a 2+ii or 4+0 configuration has a fairly express impact on performance, only that could change when core counts rise to the level Threadripper offers.

The other important matter to know about Threadripper is that the other two die apparently aren't really chips at all. They're manifestly structural inserts required for back up, but do not represent "bad" Epyc cores or any kind of core recycling. OC3D also states that the two active die in Threadripper are on the diagonal from each other.

Der8auer-Indium

Paradigm by der8auer

The die arrangement makes sense — using the two die with the most space between them ensures that hot spot formation will exist minimized. And at that place's nonetheless likely some truth to our speculation as to why Threadripper and Epyc share so much infrastructure (though it's non clear if Epyc CPUs can be used in X399 motherboards, or if Threadripper would function in an Epyc board).

Either style, nosotros tin can run across a mutual blueprint to what AMD is doing. Ryzen, Epyc, Threadripper — these chips aren't just built on a common CPU cadre, they're congenital according to a fairly rigid set of design specifications. Intel tends to offer a more varied range of products, with various features fused off depending on which marketplace segment each belongs to. This can make information technology difficult to purchase a chip that supports all of the features you want.

AMD went a different, simpler route. The same CCX configurations that power Epyc also power Ryzen 3, though these fries are tested to different specifications and intended for vastly different markets. Every bit such, ramping Threadripper and Epyc at the same time, on a common platform, is probably a major cost-saver for the company. When y'all're trying to pause into major markets you lot haven't had a share in for half-dozen-vii years, information technology's extremely important to leverage economies of calibration, fifty-fifty if the ideal solution would be a separate CPU socket or set up of products.

Feature image past der8auer