Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)

Page 621 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Toggle sidebar Toggle sidebar
Sort by date Sort by votes
Hail The Brain Slug

Hail The Brain Slug

Diamond Member
Oct 10, 2005
3,507
2,459
136
tsamolotoff said:
I wonder whether he reset the stats or if these surprisingly low temps are legit. If so, then it can do much more with more watts or static OC
Click to expand...
1.163vcore is pretty low, there's no telling how different his stats are from a retail sample since he has some unknown PBO+CO config (and custom water cooling).

My 7950X at 230W PPT was over 1.2vcore and that was after hitting thermal limit and stepping down a bit due to air cooler. At stock when it was on custom water it would not exceed high 80C, and that would have been even higher vcore than on my air cooler since it was not stepping down at all, just going full tilt.
 
  • Like
Reactions: Tlh97, lightmanek and igor_kavinski
Upvote 0 Downvote
D

deasd

Senior member
Dec 31, 2013
567
922
136
igor_kavinski said:
View attachment 102874

60W: https://forums.anandtech.com/thread...ranite-ridge-ryzen-9000.2607350/post-41246800
90W: https://forums.anandtech.com/thread...ranite-ridge-ryzen-9000.2607350/post-41248191
120W: https://forums.anandtech.com/thread...ranite-ridge-ryzen-9000.2607350/post-41248591
160W: https://forums.anandtech.com/thread...ranite-ridge-ryzen-9000.2607350/post-41249476

View attachment 102875
Click to expand...

9950x ES vs 7950x

Classroom: 21.1%
Junkshop: 26.7%
Monster : 18.4%

Average: 22.1%

blender_classroom_7950x.pngblender_junkshop_7950x.pngblender_monser_7950x.png


I think it's safely bet that Zen5 has larger realworld IPC uplift than Zen2-Zen3 iteration at least in FP performance. 5950x is only 13% faster than 3950x in blender database, and only 9% faster in computerbase test:

opendata.blender.org

Blender - Open Data

Blender Open Data is a platform to collect, display and query the results of hardware and software performance tests - provided by the public.
opendata.blender.org opendata.blender.org
www.computerbase.de

AMD Ryzen 5950X, 5900X, 5800X & 5600X im Test: Benchmarks in Anwendungen

AMD Ryzen 5000 im Test: Benchmarks in Anwendungen / Multi-Core-Szenarien / Single-Core-Szenarien
www.computerbase.de www.computerbase.de
 
Last edited:
  • Like
  • Love
Reactions: Tlh97, Elfear, Tarkin77 and 9 others
Upvote 0 Downvote
A

Abwx

Lifer
Apr 2, 2011
11,544
4,327
136
deasd said:
9950x ES vs 7950x

Classroom: 21.1%
Junkshop: 26.7%
Classroom: 18.4%

Average: 22.1%

View attachment 102891View attachment 102892View attachment 102893


I think it's safely bet that Zen5 has larger realworld IPC uplift than Zen2-Zen3 iteration at least in FP performance. 5950x is only 13% faster than 3950x in blender database, and only 9% faster in computerbase test:

opendata.blender.org

Blender - Open Data

Blender Open Data is a platform to collect, display and query the results of hardware and software performance tests - provided by the public.
opendata.blender.org opendata.blender.org
www.computerbase.de

AMD Ryzen 5950X, 5900X, 5800X & 5600X im Test: Benchmarks in Anwendungen

AMD Ryzen 5000 im Test: Benchmarks in Anwendungen / Multi-Core-Szenarien / Single-Core-Szenarien
www.computerbase.de www.computerbase.de
Click to expand...

The score of the 13900K here is at 350W or so, no way it can be that close of the 7950X if set at 253W.

Computerbase has the 7950X 11% faster in Blender than the power unlimited 14900KS (330W in CB) and 17% faster than a stock 13900K.

www.computerbase.de

Intel Core i9-14900KS im Test: Anwendungs-Benchmarks, Leistungsaufnahme & Temperatur

Intel Core i9-14900KS im Test: Anwendungs-Benchmarks, Leistungsaufnahme & Temperatur / Testsystem und Testmethodik für Anwendungen
www.computerbase.de www.computerbase.de
 
  • Like
Reactions: Tlh97, Mopetar, Racan and 1 other person
Upvote 0 Downvote
A

Abwx

Lifer
Apr 2, 2011
11,544
4,327
136
CouncilorIrissa said:

Gigabyte Technology Co., Ltd. B650E AORUS PRO X USB4 - Geekbench

Benchmark results for a Gigabyte Technology Co., Ltd. B650E AORUS PRO X USB4 with an AMD Ryzen 9 9900X processor.
browser.geekbench.com
A 8000 MT/s run.
Click to expand...

Slightly better run on the same hardware :

Gigabyte Technology Co., Ltd. B650E AORUS PRO X USB4 - Geekbench

Benchmark results for a Gigabyte Technology Co., Ltd. B650E AORUS PRO X USB4 with an AMD Ryzen 9 9900X processor.
browser.geekbench.com
 
  • Like
  • Wow
Reactions: Tlh97, lightmanek, Josh128 and 1 other person
Upvote 0 Downvote
H

Hitman928

Diamond Member
Apr 15, 2012
6,147
10,603
136
PJVol said:
4208 is ether PPT frequency and in that case this should be the Global Frequency, or if global frequency is still 4850 the only limits remain are L3.
But it seems, either SMU or HWinfo reporting Global limit incorrectly.
Click to expand...

Hmm. Still don't really know what you mean.

Global limit is 5.85 GHz, same as the 7950x. The L3 cache runs at the same frequency as the cores for Ryzen CPUs, so there's no separate limit.
 
Upvote 0 Downvote
I

igor_kavinski

Lifer
Jul 27, 2020
19,948
13,669
146
CakeMonster said:
Will the chipset actually make a difference for memory speeds? I've heard both, but I thought the CPU memory controller was the limitation.
Click to expand...
Possibly the X870 chipset/UEFI might be configured out of the box to juice the Zen 5 IMC with more volts, enabling it to sustain higher speeds with compatible EXPO kits. And if that's true, the typical 7950X IMC may not be able to tolerate that high a voltage.
 
  • Like
Reactions: BTRY B 529th FA BN
Upvote 0 Downvote
You must log in or register to reply here.

TRENDING THREADS

COMPANY
RESOURCES
FOLLOW
Top Bottom