Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.


Messages - ADVenturePO

Pages: [1]
1
Hardware / Re: Threadripper 3990x vs 3970x
« on: 2021-05-07, 23:10:20 »
Dear All,

I cannot provide the exact answer why Threadrippers behave differently on different cooling as they do.
I'm just a guy that is sitting all the time with them and making Workstations.
I'm an overclocker who after only 4,5 years in 2020 was no 1 in ambient cooling - Enthusiast Group on HWBOT.

Here You have another 3990x Workstation. Effective Clocks are again much higher than on air cooling.

 

From my observations - the faster the TR is heating up the lower the Effective Clock. It's a cheeky mechanism that lets user to go with almost any bad cooling.
The real answer if cooling is good is the outcome of a long benchmark.

That is all I can really say.

2
Hardware / Re: Threadripper 3990x vs 3970x
« on: 2021-05-05, 13:25:11 »
Quote
These are not my results but my clients, who had forced me to make his WS on Dark Rock 4 Pro

A true client from hell :- )

Using "Dark Rock 4 Pro" as example of reference Air-Cooling skews thing negatively for air-cooling Threadripper, (DR4P) it's the only sTRX socket air-cooler which has horizontally running heatpipes across heatspreader, i.e they only cover the four middle dies. It makes sense, it was designed at 1st generation of chips, still, Noctua made correct design decision at same time..

Dark Rock 4 Pro was never a suitable cooler for 3990X, it does somewhat work for 3960X & 3970X because those have dies in middle of the chip. Which is also why those can be very well cooled by any generic Asetek AIO.

The difference proper TR4 air-cooler like Noctua UH-14s TR4 and Dark Rock 4 Pro on 3990X is simply massive.
Just a reminder, these two coolers had delta of 20 C already with past-generation 2990WX, the first chip with dies that were spread across the full chip.

I've put 3990X under OptimusPC water-block, state-of-art block that is even 2-3C better than the previous winner, Heatkiller IV. After that, it doesn't matter how many radiators it is connected to (in my case 2x420mm) since the issue is heat-transfer from chip, not dissipation from the loop. At room ambient of 25C, the effective boost clocks on long renders are effectively identical between this build and the one with Noctua UH-14s.

That obviously very quickly changes with PBO/Curve Optimizer/Static Voltages/etc.. (any other OC technique), where loop or even the funky tower from Ice-Giant pull quickly ahead, by a large delta. Past 280W (and it's not hard to take 3990X into 700+ W territory), Air is no longer viable.

99perc. of users on this forum are running their PCs stock. That's matter of life for most workstations (discounting XMP/DOCP profile).

Ultimately, my personal suggestion comes down to budget. If you can afford 3990X, get it, even if it scales very little in certain workloads, or particular working conditions.

3970X might indeed be more prudent, more universal option, it does maintain better boost clocks with simple math of diving its 280W power budget only between 4 Dies + 1 MC, a benefit which is partly negatively offset by worse cooling (4 centered dies are harder to cool than 8 spread-out dies).

TL:DR :

Buy the one you won't regret spending budget for.
If you have sizeable render-farm, your choice is more partial towards 3970X. If you have only single-workstation that acts as your main rendering machine as well, absolutely go for 3990X.
Air cooling is absolutely viable, zero-issue choice for 3990X. But you have to choose either Noctua NH-U14s TR4, or Ice-Giant. You can ignore the existence of everything else.

Few graphs to show how much Dark Rock Pro 4 sucks, and why it should never be used as argument against air-cooling Threadripper.
Also article from KitGuru that explains the failed design of this cooler.

https://www.kitguru.net/components/cooling/luke-hill/threadripper-3990x-cpu-cooling-comparison-how-to-tame-the-beast/11/






Please check it out.
Thank You.

I do not care that you have seen pictures on the Internet so you will make a dispute with a guy that built 60+ TR3 Workstations.

Is there any other proof that you need?

3
Hardware / Re: Threadripper 3990x vs 3970x
« on: 2021-04-17, 11:12:51 »
I think the best person to ask this would be Juraj since from what I remember from the forum threads he has the 3990x on both air and loop but I might be wrong :)

@ADVenturePO

I am pretty sure that Blender, Cinebench, and Corona benchmarks don't scale the same way. Maybe I am wrong but from what I've seen on youtube reviews Corona was the only benchmark that was giving 2xperformance versus 3970x.
I never ever ran a Blender benchmark in my life so I can't really talk about that. What I can talk about is real-world performance, and in my case, the results are not always in line with the Corona benchmark.

I won't even mention animation frame rendering (especially frames that are under 20mins) where at least in "my case" the 5950x works the best as it's always the first machine that loads the scene due to the best max turbo on one core. By the time, the 3990x has loaded the scene the 5950x is already a few passes in :).

I would like to hear the opinion of the people who ran their 3990x's on-air and then upgraded to a custom loop. If it's actually that much worth it and their use case scenario since mine is purely from a rendering node perspective :).

Dear VUK,

I am a company that already made 70+ Threadripper Workstations. Few on air, most on LC. I have been comparing times for air and LC. And I'll try to present you my findings.
The problem with 3990x is that for some operations it has to have 8 sticks of RAM - example is video recoding - HWBOT x265 benchmark with 4 sticks 270 FPS and 8 sticks 370 FPS. In rendering that is not the case but with intensive RAM operations the memory configuration is much more influencing.
Also if there's no proper cooling to 3990x its speed will be reduced - also SC Clocks. That is why 5950x which is ultrafast in SC will prepare scene in 3D Max much more faster. 3990x  is without OC at best able to speed up single core to 4.3GHz and 5950x is able to run on good cooling up to 5025Mhz and it's memory controller is not demanding at all. 2 sticks? OK because it is Dual Channel architecture.

As for now, I will show you how rendering times of frames drops on TR3 3960 on air compared to i9-7960x on LC.
alpha is i9 and beta is TR3. These are not my results but my clients, who had forced me to make his WS on Dark Rock 4 Pro.  The MB was MSI TRX40 PRO Wifi. 8 sticks of RAM - 128GB. When cooler is heated up and AMD CPU find itself heating up faster it will drop Effective Clocks.
Please see attached pictures.

Now, I'm sorry I haven't made this video in English it's in Poilish. But here you have Effective Clocks on air:
2.63 on average.

Here You have effective clocks on LC without OC: 2.875 on average


And here are OC Tests at 3.3GHz with 1300W PSU (which screams and dies a little)
You can see that average Effective Clocks are 3.24+GHz.

From my perspective and from enormous amounts of tests OC is boosting TR3 3970x and 3990x rendering speed. For 3990x the amount of boost  is really big.
I'll try to find on which testing M.2 those test are in pictures and send them here.

Cheers


4
Hardware / Re: Threadripper 3990x vs 3970x
« on: 2021-04-14, 20:33:23 »
@ twoheads

I run the 3990x at stock with xmp  turned on in bios on 4x sticks of 32gb memory at 3200mhz. We run it as a render node while the 3970x's and the 3960x's are the main cpu's we use in our workstations. I stopped overclocking all my machines in the last 2-3 years. I can see someone who has 1-2 computers getting out a benefit from this but from my point of view (13+ machines) it is just a hassle.


I build and maintain all the computers in the studio and the overclocked machines are usually consuming 200% of the electricity at the cost of a 5-10% performance increase. Not to mention the stability issues which tend to develop over time. I am not saying I am an expert overclocker but I just don't have time to play with the settings and risk stability issues during project deadlines so lately I just go with the stock+xmp solution which works great for me to be honest.


Also a side note regarding water loops you mention. Just for reference, I paid my water loop and all of its components (EK) + the water block for TRX around 500-550 euros and my 3970x runs at the same temperature as the other identical workstation which runs the Deep Cool Castle V2 360 Aio (135-150 euros) which is an AIO that doesn't even cover the entire CPU like my block does. The performance between ours cpu's is identical so it's pretty much all about the silicon lottery at the end of the day.

Dear VUK,
Please install HWINFO64 on both machines. Find rows Effective Clock on both machines and return after tests.  You can also run PBO. You'll see the difference.

5
Hardware / Re: Threadripper 3990x vs 3970x
« on: 2021-04-14, 08:56:29 »
Also being implied is that maybe overclocking a core or 2 is much much easier on the 70x vs the 90x. How high can single-core overclocks clocks go on either realistically?
Answer: Overclocking only 2 cores is not a good idea for any threadrippers. You cannot have big differences between cores. It's better to use PBO with LC - so single core loads will make CPU run faster.

Regarding scaling on final renders - is the 13s benchmark not a real-world scenario?
Answer: This Corona 1.3 Benchmark is not even using AVX. You will not be able to uphold even 4.3GHz for long. This CPU draws avg 700W at this speed.
Theoretically: 1.you need very good sample with low Vcore hunger. 2. manual regulation 3. Cooling capacity gotta be huge as avg 700W of heat will easily go with water temps above 50 deg. C and than the cooling power is l insufficient to maintain it under 90 deg. So there comes instability.


As for chips - shouldn't 4th gens be coming out sometime soon?
Answer: Should be. But bare in mind the Ryzen 5000 series are flawed and a lot of them have problem with memory and BIOSes.
16,5% of 5950x is supposed to be bad.


Apologies if this is all over the place. It's an expensive system.
Answer: It is. But 3990x only makes sense on LC or it will have efficiency 20% more than 3970x.
For 3990x you have to have min 4 sticks of RAM in other case you'll have 1/3 of it's computing power.

Looks like I might be leaning 3970x.
Comment - IMHO: The thing is tricky. Investing in good cooling and good motherboard now will let you go for 3990x in the future.
But buying 3990x and leaving it on stock with air cooling is just throwing money thru a window. Especially when in near future new chips will arrive and prices of 3990x will drop.

Cheers.

6
Hardware / Re: Threadripper 3990x vs 3970x
« on: 2021-04-13, 18:18:10 »
Hi,
I'm an oveclocker but also a company which builds workstations (99.99% of work)
I have been beating records with CPUs all over the place. Corona, Vray, Kray etc.
The thing is: AMD Threadripper have some sensor which checks how fast CPU is getting hot changing states from C6 to C0 and P0 - core sleep and work modes.
If CPU is heating up fast the Perfect Clock (visible in CPU-Z will not be changed) but Effective Clock will be lower - HWINFO64

Do to only this fact the most benefit from good cooling are for 3970x and 3990x.
With bad cooling and high memory latency those chips are just expensive piece of silicon.
Considering long tests in Blender - as I do not have Corona.

3990x 64GB RAM 4 sticks 1600W PSU
Barbershop scene -  Ultra settings and 4k Resolution.
AIR Dark Rock Pro 4 TR: 1h45m
LC 480+360 HWLABS GTX: 1h 24m
LC     --//--   & OC @3.8GHz: 1h09m

The thing is that 3970x will do that test on LC in 1h33m

Just look at Corona benchmarks :
https://corona-renderer.com/benchmark/results/cpu/3990x
With a LC this CPU will run some about 3.2GHz by itself.
On air (open benchtable) Effective Clock can drop to some about 2.65GHz.
With OC @ 3.8 GHz and 33dB you can go all the time average 3.75GHz.
When silence is not the case: 38db, 4.15GHz and 4.1 Effective clock is maintained.

All TR3 39xxx series have TDP 280W. If you are to work on it efficiently accordingly to its price, than you have to have LC.
You can use AIR like Silver Arrow TT with 3 fans for 3960x and 3970x and you will be able to OC it a bit.
But 3990x is just a power and cooling hungry monster. And even with best air cooling you will not be able to maintain high effective clocks,
do to some internal heating up checking mechanism.

Cheers

 

Pages: [1]