Overclock.net - An Overclocking Community

Overclock.net - An Overclocking Community (https://www.overclock.net/forum/)
-   Intel CPUs (https://www.overclock.net/forum/5-intel-cpus/)
-   -   Intel Core i9-10980XE: 5 GHz on 18 cores (https://www.overclock.net/forum/5-intel-cpus/1737048-intel-core-i9-10980xe-5-ghz-18-cores.html)

elmor 11-25-2019 11:09 AM

Intel Core i9-10980XE: 5 GHz on 18 cores
 
https://www.elmorlabs.com/wp-content...bg-500x332.png


Presenting Cascade Lake-X

With Intel’s 10 nm products not yet being ready for the desktop market, they’ve had to get creative with their product releases. In a third processor update for the X299 platform they present us with Cascade Lake-X. It arrives with promises of increased performance through frequency bumps, courtesy of another advancement in 14 nm process technology.


Higher boost clocks

https://www.elmorlabs.com/wp-content...1/cpu-5002.png

The specification of the Core i9-10980XE is not much changed from its predecessor, the Core i9-9980XE. CPU-Z 1.90.1 even reports it as being the same chip. It keeps the same 3.0 GHz base speed but increases the peak boost clocks by 100 MHz to 4.8 GHz. There are still 18 cores and 36 threads at a 165W TDP. The monolithic die stays soldered to its IHS. With Intel typically being conservative about their advertised frequencies, there is potential for better overclocking results.


Test setup

  • Intel Core i9-10980XE (QS)
  • ASUS ROG Rampage VI Extreme Encore (BIOS 0010)
  • G.SKILL F4-4000C18Q-32GTZKW (4x8GB)
  • EK-MLC Phoenix 360 CLC
  • Windows 10 1903, High Performance power plan


Effective Clock

https://www.elmorlabs.com/wp-content...rf-600x508.png


The primary reason “Effective Clock” was added to HWInfo from v6.14 was an issue with clock reporting on Cascade Lake-X. When initially performing these tests, it looked like the new processor got nowhere near its rated boost clocks. After investigation, the boost specification seemed to be met based on performance. This meant the clock reporting had an issue. An alternative was found by relying on CPU clock counters instead of the reported clock ratio. An added benefit is that this method reflects all frequency changes during the measurement period instead of reporting time-discrete readings. This includes clock gating, clock stretching and throttling. Using this new method returned results much closer to the expected values and is used for frequency reporting in this article.

Further information: https://www.hwinfo.com/forum/threads...te-clock.5958/


Method

Any benchmark results are the average of three runs. In the single threaded tests, the thread affinity for the benchmark was manually set to the highest ranked core. HWInfo 6.14 was used to record the monitoring information during the run. The average frequency was measured using the “Effective Clock” item. The average power was measured directly from the VRM controller and reports the CPU input power.

Results and Analysis


Stock Performance

https://www.elmorlabs.com/wp-content...erformance.png

In the single-threaded test, the clock frequency is very close to its advertised boost during the entire benchmark. When looking at the multi-threaded test the frequency is not as impressive and drops all the way to 3.4 GHz in order to stay within the default power limit. What is impressive is the highest temperature reported during this test, highlighting significant overclocking headroom through the use of soldered TIM (Thermal Interface Material).


Overclocked Performance

https://www.elmorlabs.com/wp-content...formance-1.png

Through the overclocked results we can verify that there is indeed plenty of headroom. Reaching a full 5 GHz on all 18 cores is very impressive, even considering the insane power consumption of 512 W during this benchmark. Comparing to the stock results translates in 45% more performance at 218% higher power consumption.

https://www.elmorlabs.com/wp-content...-12K-FFT-2.png

Continuing with Prime95 tests reveals which frequencies could be expected for long term overclocks. This tells a similar story of impressive frequencies at the cost of much increased power consumption. Up to 4.7 GHz when not utilizing AVX instructions is about 200 MHz higher than what could be achieved on a decent Skylake-X processor. When enabling full AVX 512-bit instructions, the frequency had to be lowered to 4.2 GHz to keep stability and prevent overheating. The high performance liquid cooling used just barely prevented the processor from throttling at just under 500 W of processor power consumption.

Original article: https://www.elmorlabs.com/index.php/...z-on-18-cores/

manolith 11-27-2019 04:29 PM

I know that this is not the cutting edge that we wanted especially when compared to the 3950x or the new TR cpus but the 10980xe is a monster when overclocked. I also think there are certain circumstances where we could make the argument for it as a gaming cpu. Two gaming rigs in one case =D

Falkentyne 11-27-2019 04:43 PM

@elmor

I wonder how this processor would do if you disabled 10 cores and turned it into an 8 core 16 thread processor and then pushed it similar to a 9900k?
Might be interesting how far it would scale on "reasonable" Loadline calibration, and which cores turn out to be 'weak' (since i think voltages can be set for each core on this platform?).

I Just wish the Ring mesh didn't have so many performance issues in games :(

Baasha 11-27-2019 05:09 PM

1.325V?? Yikes that is really high for 18-cores.

CapitanPelusa 11-27-2019 05:43 PM

Thank you for the post.

Results like these is what i am hoping to achieve in my rig as soon as my 10980xe arrives. I am configuring a custom loop right now using 2x 280mm (30mm thick) rads, its the 'most rad' i can have without investing in a new case, to see if i can try to tame the heat that this sucker is gonna output.

In all honesty all core 4.6 and manageable temps would make me happy and will be a nice upgrade from what i have atm.

Kalm_Traveler 11-27-2019 06:16 PM

Quote:

Originally Posted by Falkentyne (Post 28214076)
@elmor

I wonder how this processor would do if you disabled 10 cores and turned it into an 8 core 16 thread processor and then pushed it similar to a 9900k?
Might be interesting how far it would scale on "reasonable" Loadline calibration, and which cores turn out to be 'weak' (since i think voltages can be set for each core on this platform?).

I Just wish the Ring mesh didn't have so many performance issues in games :(

What issues? I haven't had any trouble playing games on my 'old' 7960x

Quote:

Originally Posted by Baasha (Post 28214122)
1.325V?? Yikes that is really high for 18-cores.

Is it? my last winter 9900k rig was doing 5.2ghz all core on that same voltage... and right now while I'm finally trying to dial in the max daily OC on this 7960x it seems to want 1.300 for stable all core 4.8ghz. Going to try pushing for 5 but I'm not sure it'll be daily stable, though it was passing 3dmark runs last winter outdoors at 5.2ghz all core so maybe there's a chance (mind you cores were hitting 70-75 C in 10 F ambient with a giant fan aimed at the radiator intake fans).

wingman99 11-27-2019 09:05 PM

Quote:

Originally Posted by Falkentyne (Post 28214076)
@elmor

I wonder how this processor would do if you disabled 10 cores and turned it into an 8 core 16 thread processor and then pushed it similar to a 9900k?
Might be interesting how far it would scale on "reasonable" Loadline calibration, and which cores turn out to be 'weak' (since i think voltages can be set for each core on this platform?).

I Just wish the Ring mesh didn't have so many performance issues in games :(

The gaming performance is compatible with the i9 9900k, they change some things on the i9-10980XE. See video.


D-EJ915 11-27-2019 11:32 PM

Quote:

Originally Posted by Falkentyne (Post 28214076)
@elmor

I wonder how this processor would do if you disabled 10 cores and turned it into an 8 core 16 thread processor and then pushed it similar to a 9900k?
Might be interesting how far it would scale on "reasonable" Loadline calibration, and which cores turn out to be 'weak' (since i think voltages can be set for each core on this platform?).

I Just wish the Ring mesh didn't have so many performance issues in games :(

It would be pretty sick to have a broadwell chip at these speeds lol. Imagine the 22 core E5-2699 V4 overclocked @[email protected]

Quote:

Originally Posted by Kalm_Traveler (Post 28214172)
What issues? I haven't had any trouble playing games on my 'old' 7960x

Is it? my last winter 9900k rig was doing 5.2ghz all core on that same voltage... and right now while I'm finally trying to dial in the max daily OC on this 7960x it seems to want 1.300 for stable all core 4.8ghz. Going to try pushing for 5 but I'm not sure it'll be daily stable, though it was passing 3dmark runs last winter outdoors at 5.2ghz all core so maybe there's a chance (mind you cores were hitting 70-75 C in 10 F ambient with a giant fan aimed at the radiator intake fans).

Voltage makes temps go pretty crazy on these chips is all really.

Mesh also hinders performance a bit compared to ring cache on 1151 chips. If you downclock cache on an 1151 part (say my 9700k) it nukes performance in some things if you want an easy example (set to 24-30x).

ftln 11-27-2019 11:53 PM

2 Attachment(s)
Quote:

Originally Posted by CapitanPelusa (Post 28214144)
Thank you for the post.

Results like these is what i am hoping to achieve in my rig as soon as my 10980xe arrives. I am configuring a custom loop right now using 2x 280mm (30mm thick) rads, its the 'most rad' i can have without investing in a new case, to see if i can try to tame the heat that this sucker is gonna output.

In all honesty all core 4.6 and manageable temps would make me happy and will be a nice upgrade from what i have atm.

Don't get the 10980xe, try to find a second hand 7980xe then delid and direct die (I just did this)for results like this in p95 no avx & Cinebench:

https://www.overclock.net/forum/atta...308518&thumb=1

https://www.overclock.net/forum/atta...308516&thumb=1

RichKnecht 11-28-2019 06:18 AM

Quote:

Originally Posted by ftln (Post 28214490)
Don't get the 10980xe, try to find a second hand 7980xe then delid and direct die (I just did this)for results like this in p95 no avx & Cinebench:

https://www.overclock.net/forum/atta...308518&thumb=1

https://www.overclock.net/forum/atta...308516&thumb=1

Honestly, I would rather get the 10980. After going through the delidding and direct die mounting process with my 7900X, I will never do it again. Was it worth it? I guess. I have a rock stable all core 4.7OC with temps @ 70C under load and 21C at idle. But the frustration and time spent makes me rethink the whole ordeal.


All times are GMT -7. The time now is 02:08 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.