AMD's James Prior Weighs in on the Threadripper "Dummy Dies" Controversy

Megalith

24-bit/48kHz
Staff member
Joined
Aug 20, 2006
Messages
13,000
AMD's Senior Product Manager, James Prior, has clarified that Threadripper’s two extra dies have "no path to operation," dashing all those rumors that extra cores could be unlockable. Prior also says that AMD decided to use the term "dummy" instead of "inactive" to describe Threadripper's additional dies, as there is no way of utilizing/activating these additional CPU dies.

...higher core counts for Threadripper would offer some huge engineering challenges and downsides for the platform, especially when it came to power consumption and clock speeds on X399. Beyond that, there are factors to consider like memory latency for cores on any additional dies, as dies 3+4 (if the even could be used) would need to access memory through another CPU die, adding a lot of memory latencies to additional CPU cores. This may not be a huge deal for some workloads, but it is not exactly a negligible factor. At least all of the dies on EPYC have direct access to some of the system's memory channels.
 
A dummy core you say...

QBJ8cD1.jpg
 
It's probably the 10-20% failed yield used as spacers on a Threadripper because it's cheaper to use one substrate for Threadripper and Epyc than to make one for each. :p
 
It's probably the 10-20% failed yield used as spacers on a Threadripper because it's cheaper to use one substrate for Threadripper and Epyc than to make one for each. :p

Heh I was thinking the same. Brute force approach to low yields... :)
 
It's probably the 10-20% failed yield used as spacers on a Threadripper because it's cheaper to use one substrate for Threadripper and Epyc than to make one for each. :p

Different substrate apparently.
 
What I'm curious about is if there is any consistency as to which two dies are functional and which two are dummies. Their placement could have varying effects on heat displacement and cooling system designs. This could be important for water block design that could optimize flow to one side of the heatspreader or the other.
 
What I'm curious about is if there is any consistency as to which two dies are functional and which two are dummies. Their placement could have varying effects on heat displacement and cooling system designs. This could be important for water block design that could optimize flow to one side of the heatspreader or the other.

That product sounds like the best thing since the Left-Handed Whopper..
 
What I'm curious about is if there is any consistency as to which two dies are functional and which two are dummies. Their placement could have varying effects on heat displacement and cooling system designs. This could be important for water block design that could optimize flow to one side of the heatspreader or the other.
They've said the active dies are diagonal, with cooling in mind.
 
This is Flux Capacitor material.

Tho I am rooting for the success of the Zen architecture. Was contemplating putting one into my home server but decided against it when I saw that Plex wants a very fast single core at times.
 
This is Flux Capacitor material.

Explain?

Tho I am rooting for the success of the Zen architecture. Was contemplating putting one into my home server but decided against it when I saw that Plex wants a very fast single core at times.

When does it want one fast core? I've never noticed such a thing, but I never researched it either...actually curious.
 
Back
Top