Power Consumption

The nature of reporting processor power consumption has become, in part, a dystopian nightmare. Historically the peak power consumption of a processor, as purchased, is given by its Thermal Design Power (TDP, or PL1). For many markets, such as embedded processors, that value of TDP still signifies the peak power consumption. For the processors we test at AnandTech, either desktop, notebook, or enterprise, this is not always the case.

Modern high performance processors implement a feature called Turbo. This allows, usually for a limited time, a processor to go beyond its rated frequency. Exactly how far the processor goes depends on a few factors, such as the Turbo Power Limit (PL2), whether the peak frequency is hard coded, the thermals, and the power delivery. Turbo can sometimes be very aggressive, allowing power values 2.5x above the rated TDP.

AMD and Intel have different definitions for TDP, but are broadly speaking applied the same. The difference comes to turbo modes, turbo limits, turbo budgets, and how the processors manage that power balance. These topics are 10000-12000 word articles in their own right, and we’ve got a few articles worth reading on the topic.

In simple terms, processor manufacturers only ever guarantee two values which are tied together - when all cores are running at base frequency, the processor should be running at or below the TDP rating. All turbo modes and power modes above that are not covered by warranty. Intel kind of screwed this up with the Tiger Lake launch in September 2020, by refusing to define a TDP rating for its new processors, instead going for a range. Obfuscation like this is a frustrating endeavor for press and end-users alike.

However, for our tests in this review, we measure the power consumption of the processor in a variety of different scenarios. These include full peak AVX workflows, a loaded rendered test, and others as appropriate. These tests are done as comparative models. We also note the peak power recorded in any of our tests.

First up is our loaded rendered test, designed to peak out at max power.

In this test the 3995WX with only 64 threads actually uses slightly less power, given that one thread per core doesn’t keep everything active. Despite this, the 64C/64T benchmark result is ~16000 points, compared to ~12600 points when all 128 threads are enabled. Also in this chart we see that the 3955WX with only sixteen cores hovers around the 212W mark.

The second test is from y-Cruncher, which is our AVX2/AVX512 workload. This also has some memory requirements, which can lead to periodic cycling with systems that have lower memory bandwidth per core options.

Both of the 3995WX configurations perform similarly, while the 3975WX has more variability as it requests data from memory causing the cores to idle slightly. The 3955WX peaks around 250W this time.

For peak power, we report the highest value observed from any of our benchmark tests.

(0-0) Peak Power

As with most AMD processors, there is a total package power tracking value, and for Threadripper Pro that is the same as the TDP at 280 W. I have included the AVX2 values here for the Intel processors, however at AVX512 these will turbo to 296 W (i9-11900K) and 291 W (W-3175X).

AMD TR Pro Review: 3995WX, 3975WX, 3955WX CPU Tests: Rendering
POST A COMMENT

98 Comments

View All Comments

  • mode_13h - Saturday, July 17, 2021 - link

    Sometimes they do show it. I wonder why not, this time?

    One thing to note is how some of the same applications they benchmark in standalone tests are *also* included in SPEC17. So, those tests can get over-represented.
    Reply
  • Blastdoor - Wednesday, July 14, 2021 - link

    Re:

    "We are patiently waiting for AMD to launch Threadripper versions with Zen 3 – we hoped it would have been at Computex in June, but now we’re not sure exactly when."

    Maybe it will happen when Intel offers something remotely competitive in this market? Or maybe when supply constraints ease and AMD can fully meet demand?
    Reply
  • mode_13h - Wednesday, July 14, 2021 - link

    Chagall (Threadripper 5000-series) is rumored to launch in August. Reply
  • Threska - Wednesday, July 14, 2021 - link

    Long as AMD sticks to the same socket the platform should have longevity just like AM4. Reply
  • Bernecky - Wednesday, July 14, 2021 - link

    Your "AMD Comparison" shows Threadripper DRAM as: 4×DDR4-3200.
    This is incorrect: I have a 3970X running on an ASUS ROG Zenith Extreme II Alpha, with
    256GB: 8×DDR4-3600(OC slightly).

    The Alpha no longer appears on the ASUS web site. Not sure what happened to it.
    Reply
  • JMC2000 - Wednesday, July 14, 2021 - link

    The "4xDDR-3200" is referencing 4 channels @ a non-overclocked speed of 3200; what you have is 8 DDR4 DIMMs in 4 channels. Reply
  • Railgun - Sunday, July 18, 2021 - link

    Still here on the UK site.

    https://www.asus.com/uk/Motherboards-Components/Mo...
    Reply
  • Oxford Guy - Wednesday, July 14, 2021 - link

    ‘The only downside to EPYC is that it can only be used in single socket systems, and the peak memory support is halved (from 4 TB to 2 TB).’

    Eh?

    I assume you meant TR Pro. A big downside is that it’s Zen 2.
    Reply
  • Thanny - Wednesday, July 14, 2021 - link

    Ryzen and Threadripper support ECC memory just fine. It's only registered memory that isn't supported, which is why you can only get 128GB into a Ryzen platform and 256GB into a Threadripper platform (32GB is the largest unbuffered DIMM you can get).

    The motherboard must also support it, which not all Ryzen motherboards do. But all Threadripper boards support ECC. I'm using 128GB of unbuffered ECC right now with a 3960X.
    Reply
  • willis936 - Thursday, July 15, 2021 - link

    >Ryzen and Threadripper support ECC memory just fine

    A common misconception. Error reporting does not work with any AM4 chipset on non-pro AMD processors. Sure you have ECC, maybe. How do you know the soft error rate isn't massive?
    Reply

Log in

Don't have an account? Sign up now