Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

extremetech.com

Post reply on HN
Print view View original

51–60 of 88 posts

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#51

Post by burrish »

account42 wrote: post #46
burrish wrote: post #24

I mean... is it really necessary to overclock a AMD Threadripper, for the price of this new Threadripper ($9,999) I wouldn't take the risk of overclocking it..

> I mean... is it really necessary to overclock a AMD Threadripper Yes? The main point of the Threadripper (especially non-PRO) is that you have a many-core CPU that can still run at high frequencies. Othervise EPYC (many-core) or Ryzen (high speeds) would be enough.

Ah I see thanks, but still for this generation of Threadripper, I would avoid overclocking it if it means having no warranty.

Also shit move from AMD because even if you overclock with their software, the warranty still becomes void

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#52

Post by woleium »

PartiallyTyped wrote: post #42
scrlk wrote: post #12

Earlier quoted context omitted.

On a related note, AMD's EPYC CPUs have eFuses that enforce a vendor lock. This means you can't transfer an EPYC CPU from, say, a Dell server to a Lenovo server. https://www.servethehome.com/amd-psb-vendor-locks-epyc-cpus-...

Smh this is ridiculous. You literally bought the hardware...

Come on, these are server chips. No sensible organization is going to be moving chips between vendor boards, at least until they are written off.

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#53

Post by codeflo »

DeathArrow wrote: post #35
codeflo wrote: post #18

Earlier quoted context omitted.

One argument used to be that there's always manufacturing tolerances that you can exploit to your advantage. However, those tolerances were in many cases optimized out of the process by better binning -- if a particular CPU reliably worked at a higher clock speed, it would simply be sold at a higher speed. But also, whether a chip is actually stable at settings X or Y has become a lot harder to determine due to compl…

>But also, whether a chip is actually stable at settings X or Y has become a lot harder to determine due to complexity There are many good software for stress testing CPUs and GPUs. Just run AIda64 or OCCP stress tests for a long time and you are good to go if no problems arise. If there are problems, you redo the settings and run the tests again.

I think that's naive, or let's say oversimplified. There are too many cases where systems pass these tests and then fail in real-world scenarios, sometimes quickly. There's simply no way that a specific set of software routines can guarantee that a processor behaves in spec.

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#54

Post by thfuran »

woleium wrote: post #52
PartiallyTyped wrote: post #42

Earlier quoted context omitted.

Smh this is ridiculous. You literally bought the hardware...

Come on, these are server chips. No sensible organization is going to be moving chips between vendor boards, at least until they are written off.

It mostly just cripples the secondary market for used server hardware.

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#55

Post by bryanlarsen »

Dalewyn wrote: post #30
pjc50 wrote: post #23

Earlier quoted context omitted.

The equivalent of those "warranty void if removed" stickers. Not a problem in and of itself.

The real problem is marketing overclocking as if it's just an everyday common thing to do with little to no thought.

The complaint in the article is the inverse: the BIOS displays a big scary warning about overclocking voiding the warranty when in fact overclocking does not necessarily void the warranty. It's more of an "everyday common thing" than the message in the BIOS implies.

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#56

Post by unregistereddev »

burrish wrote: post #24

I mean... is it really necessary to overclock a AMD Threadripper, for the price of this new Threadripper ($9,999) I wouldn't take the risk of overclocking it..

It depends. If I'm an IT manager at Pixar and this is going in the workstation of my best and most productive animator, the price might not matter. If reducing the time s/he spends waiting on the computer means I can produce movies faster, I'll take risks to give them the best machine possible.

If I'm a home freelancer staking my livelihood on this workstation, I'm not taking the risk.

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#57

Post by woleium »

thfuran wrote: post #54
woleium wrote: post #52

Earlier quoted context omitted.

Come on, these are server chips. No sensible organization is going to be moving chips between vendor boards, at least until they are written off.

It mostly just cripples the secondary market for used server hardware.

I dont see the economics of splitting servers for parts. Aside from pulling drives for shredding, servers are mostly sold as pulled on the aftermarket

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#58

Post by PartiallyTyped »

bell-cot wrote: post #45
PartiallyTyped wrote: post #42

Earlier quoted context omitted.

Smh this is ridiculous. You literally bought the hardware...

First Thought: Are those CPU's available (at Dell-sized quantities) with vendor-specific features? If so, Dell has excellent reason to keep possibly-incompatible CPU's out of their systems.

If they have Dell-specific features, then I agree.

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#59

Post by jpgvm »

DeathArrow wrote: post #39
chmod775 wrote: post #19

Earlier quoted context omitted.

The most basic "overclocking" these days is actually undervolting. The clock speed you can leave to the chip. The undervolting makes the chip run cooler, which in turn means it can stay at higher frequencies longer.

You need higher voltage to have a chip (CPU, GPU, RAM) stable at a higher frequency. Higher voltage means more heat, so you need better cooling.

This actually depends on silicon quality. The mainboard manufacturers generally configure the OOB CPU voltages higher than they need to be in anticipation of handling crappy silicon.

If you have a higher binned CPU then you can reduce that voltage and still be stable at a given clock, the chip will then be able to boost higher because there will be more thermal headroom.

Re: AMD's New Threadripper Chips Have a Hidden Fuse That Blows When Overclocking

#60

Post by WarOnPrivacy »

woleium wrote: post #57
thfuran wrote: post #54

Earlier quoted context omitted.

It mostly just cripples the secondary market for used server hardware.

I dont see the economics of splitting servers for parts. Aside from pulling drives for shredding, servers are mostly sold as pulled on the aftermarket

> I dont see the economics of splitting servers for parts.

You can see that economy on ebay. Those parts extend the life of existing boxes by years.

I'm typing this on a machine powered by parts from 'split' servers.

Post reply on HN