Some Early AMD Ryzen Threadripper 1950X Linux Benchmarks

[bridgman]

I would love to hear some confirmation about this! What's up with the 2 unused dies?

My understanding is that there are two active die and two spacers, although this is based on feedback from other AMD folks to web reviewers (ie I read the articles).

[duby229]

My understanding is that there are two active die and two spacers, although this is based on feedback from other AMD folks to web reviewers (ie I read the articles).

Do you suppose they are non-working dies, or are they literally just blanks?

[pegasus]

Check your stream numbers. I'm able to easily get 192GB/s on dual epyc without even trying hard. So I assume threadripper to be able to do 48GB/s easily. If you use compiler that can do streaming stores (like icc) then the numbers should be 20-30% higher still.

[Zucca]

why the stupid environmentally polluting packaging? For what all the plastic foam crap? Can they not put it in a nice paper box? :-/
a AMD fan since my first am386, but this plastic waste stupidity should be boycotted to save our only planet, …!

Yeah. I've been thingking that too. I wonder how much extra TR costs because of that fancy packaging... Propably not very significantly compared to the total price but still.

[Brisse]

Do you suppose they are non-working dies, or are they literally just blanks?

I've read a handful of Windows focused reviews of Threadripper, and some of them state that they are just blanks to provide structural integrity to the entire package.

[Zan Lynx]

^ This, exactly. Server benchmarks on a desktop chip are pointless. It's a fake use case. Nobody is using desktop peecee chips in a server. It's no different than running gaming benchmarks on a server chip - nobody cares how Crysis 3 runs on Xeon because nobody is playing Crysis 3 on a Xeon.

Well, that isn't true. People do play games on Xeons. Motherboards using the C236 chipset were pretty popular. Lots of PCIe lanes for full speed M.2 NVMe drives and SLI GPUs.

[schmidtbag]

I'm surprised it performed so well against the i9 even in AVX tests. I may be wrong, but it seems Threadripper performs better in Linux than AM4 models. Seems like a pretty obvious choice if you're going to spend $1000 on a CPU.

Do you suppose they are non-working dies, or are they literally just blanks?

If you're hoping to use the dummy dies via core unlocking, the answer will be a resounding "no". Even if they're imperfect dies (which I've heard they're not) it seems Ryzen's architecture is highly dependent upon symmetry, where they wouldn't be usable anyway unless you started disabling cores.

[tildearrow]

No benchmark request

Typo:

Overall though the Ryzen Threasdripper 1950X is very encouraging

[vsteel]

I've read a handful of Windows focused reviews of Threadripper, and some of them state that they are just blanks to provide structural integrity to the entire package.

I doubt they are blanks. In the chip world they would be foolish to be cutting up good silicon to fill the spaces with. I would be they take dead die that failed at probe and pull them and just them as spacers. So while they wouldn't be blank die, they would be about as useful.

You want to get as many useful die on a wafer as possible and when you have blanks in the mix it would mess up etch uniformity and mess some with the CMP.

I know just a small detail but I do really get a kick out of the stories on windows sites and the people who comment that talk about making chips, you can tell most have no idea what they are doing and the ones that semi know most of them are in college or professors that have not been in the real world and don't realize how far off their ideas are. (Yes I work for a company that makes chips at small geometries and high speed) Though not all are that way, there are some you can tell that know their stuff.

[profoundWHALE]

Do you suppose they are non-working dies, or are they literally just blanks?

If my memory serves me well, which it usually doesn't, an EPYC chip would be a threadripper but with all 4 dies working