Overclock.net - An Overclocking Community

Overclock.net - An Overclocking Community (https://www.overclock.net/forum/)
-   Rumors and Unconfirmed Articles (https://www.overclock.net/forum/379-rumors-unconfirmed-articles/)
-   -   [Tom's Hardware] AMD EPYC Rome Benched: 64 Cores, 128 Threads Boosting to 2.2 GHz (for now) (https://www.overclock.net/forum/379-rumors-unconfirmed-articles/1723494-toms-hardware-amd-epyc-rome-benched-64-cores-128-threads-boosting-2-2-ghz-now.html)

WannaBeOCer 03-29-2019 03:20 PM

[Tom's Hardware] AMD EPYC Rome Benched: 64 Cores, 128 Threads Boosting to 2.2 GHz (for now)
 
Source: https://www.tomshardware.com/news/am...ter,38939.html

Quote:

Several benchmarks of AMD's 64-core, 128-thread EPYC Rome processors have popped up in an online database, indicating that the early chips run at a 1.4 GHz base clock and boost to 2.2 GHz.

Earlier this year, AMD CEO Lisa Su announced that the 64 core 128 thread EPYC Rome processors would come to market in mid-2019, perhaps setting the stage for a massive upset victory against Intel as AMD marches forward to the 7nm manufacturing process while its competitor remains mired on 14nm.

J7SC 03-29-2019 03:28 PM

Quote:

Originally Posted by WannaBeOCer (Post 27914028)


yummy..especially if there's a consumer (Threadripper) version at max (yeah, right :arrowhead ) 4 GHz; 16+3 phase mobo ready, willing and waiting, especially while the wallet is out for a Friday lunch...

Hydroplane 03-29-2019 03:29 PM

256MB cache :O

mothergoose729 03-29-2019 03:57 PM

This is the same benchmark with 2 of intels Xeon 8180s.

https://ranker.sisoftware.co.uk/show...781f2cff7&l=en

And this is two EPYC 32 cores

https://wccftech.com/amd-epyc-7601-benchmarks-analysis/

Assuming the score would double with a dual socket configuration (and it usually does) that would yield a result of 1553 GOPS, which is up to a 16.1% higher score than the dual Xeon 8180s, and a 21.1% higher score than dual EPYC 32 cores.

The performance per core though is pretty terrible. The average clock speed for the run was 2.2ghz and it had twice the cores, compared to the 2.7ghz average clock speed of EPYC 32 cores with half the threads, yet only achieving a modest 21% score increase, instead of what you would expect to be a 81% performance increase with similar IPC. There is a lot of performance left on the table. Whether that is due to poor scaling in the sisoft sandra benchmark, errors in the silicon, or some other issue, who can say. These numbers might not even be accurate.

Put another way, two EPYC 32 core CPUs are 30% faster than a single one of these 64 cores CPU, assuming linear scaling with clock speed.

JackCY 03-30-2019 03:07 PM

But can it path trace Quake2 in real time?

guttheslayer 03-31-2019 07:55 PM

Quote:

Originally Posted by mothergoose729 (Post 27914116)
This is the same benchmark with 2 of intels Xeon 8180s.

https://ranker.sisoftware.co.uk/show...781f2cff7&l=en

And this is two EPYC 32 cores

https://wccftech.com/amd-epyc-7601-benchmarks-analysis/

Assuming the score would double with a dual socket configuration (and it usually does) that would yield a result of 1553 GOPS, which is up to a 16.1% higher score than the dual Xeon 8180s, and a 21.1% higher score than dual EPYC 32 cores.

The performance per core though is pretty terrible. The average clock speed for the run was 2.2ghz and it had twice the cores, compared to the 2.7ghz average clock speed of EPYC 32 cores with half the threads, yet only achieving a modest 21% score increase, instead of what you would expect to be a 81% performance increase with similar IPC. There is a lot of performance left on the table. Whether that is due to poor scaling in the sisoft sandra benchmark, errors in the silicon, or some other issue, who can say. These numbers might not even be accurate.

Put another way, two EPYC 32 core CPUs are 30% faster than a single one of these 64 cores CPU, assuming linear scaling with clock speed.


I don't know where you get the 30% figure for single 64C vs 2x 32C. What I saw was:

Dual 7601 vs 64C new cores.

Arithmetic: 1242 vs 766 (Registered. clock GHz: 2.7 vs 2.2)
Multimedia: 1348 vs 2089 (Registered. clock GHz: 1.81 vs 2.2)


What I conclude is that the new Eypc is bad at Arthmetic but impressive at multimedia against the 2x 7601. I am not too sure if the registered clock is reliable, if not you can do a direct IPC comparison.

CynicalUnicorn 03-31-2019 08:03 PM

Quote:

Originally Posted by Hydroplane (Post 27914042)
256MB cache :O

4MB per core, double what's on current Ryzen.

Given how expensive SRAM is, there's probably a good reason for it, and I'm betting that the I/O hub has some shortcomings that will explain why.

Redwoodz 04-01-2019 02:45 AM

The TDP will really tell the whole story along with clock speeds.

rdr09 04-01-2019 08:04 AM

In this type of use case, security (less vulnerabilities) should be top most concern. I guess that falls under performance as well.

mothergoose729 04-01-2019 08:32 AM

Quote:

Originally Posted by guttheslayer (Post 27916508)
I don't know where you get the 30% figure for single 64C vs 2x 32C. What I saw was:

Dual 7601 vs 64C new cores.

Arithmetic: 1242 vs 766 (Registered. clock GHz: 2.7 vs 2.2)
Multimedia: 1348 vs 2089 (Registered. clock GHz: 1.81 vs 2.2)


What I conclude is that the new Eypc is bad at Arthmetic but impressive at multimedia against the 2x 7601. I am not too sure if the registered clock is reliable, if not you can do a direct IPC comparison.

I was only looking at arithmetic. Good catch on multimedia. Odd that there would be such a huge difference in relative performance depending on the workload, considering Ryzen 3 architecture is only supposed to be a minor iteration on Ryzen 2.


All times are GMT -7. The time now is 08:37 AM.

Powered by vBulletin® Copyright ©2000 - 2020, Jelsoft Enterprises Ltd.

User Alert System provided by Advanced User Tagging (Pro) - vBulletin Mods & Addons Copyright © 2020 DragonByte Technologies Ltd.
vBulletin Security provided by vBSecurity (Pro) - vBulletin Mods & Addons Copyright © 2020 DragonByte Technologies Ltd.

vBulletin Optimisation provided by vB Optimise (Pro) - vBulletin Mods & Addons Copyright © 2020 DragonByte Technologies Ltd.