AMD Ryzen Threadripper 3970X Review 32 Cores of Madness


AMD Ryzen Threadripper 3970X Power Consumption

Power consumption can vary a significant amount depending on processors used and the number of HDDs/SSDs/Expansion cards used. Here we test just a primary system. We test with the same graphics card and NVMe SSD in all our tests. Power is measured at the wall and the graphics card and SSD were not stress tested.

For our tests, we use the AIDA64 Stress test which allows us to stress all aspects of the system.

AMD Threadripper 3970X Power Consumption
AMD Threadripper 3970X Power Consumption

In the MSI Creator TRX40 the AMD Ryzen Threadripper 3970X fared better than we were perhaps expecting. The maximum power consumption is somewhere between the Threadripper W2990WX on our test bench and the Threadripper 1950X. It is also in-line with the Intel numbers for higher-end platforms.

Idle is showing what we fear quite a bit with this platform. 130W is in-line with other CPUs in this category like the Intel Xeon W-3275 and Threadripper 3960X, but it is still much higher than we see down the stack. Perhaps the best course of action is to ensure you have sufficient air conditioning for the summer in a room full of these systems.

AMD Ryzen Threadripper 3970X Market Positioning

Thes chips are not released in a vacuum instead, they have competition on both the Intel and AMD sides. When you purchase a server and select a CPU, it is important to see the value of a platform versus its competitors.

AMD Ryzen Threadripper 3970X v. AMD Alternatives

Buyers of the AMD Ryzen Threadripper 3970X have a few options from AMD. We wanted to run through a few of those here.

First, one can look to the Ryzen 9 3950X and point to a lower cost/ core figure. Since there is an advantage to scaling up to more cores in a single system, we see these as completely different products.

Compared to the 2nd gen AMD Ryzen Threadripper 2990WX, this is simply a better platform. It is slightly more costly, but the 3970X is the part you will want going forward for 32 cores in a workstation.

Looking at the AMD Ryzen Threadripper 3960X in comparison is really interesting. If you need the speed and want to pay for it, the 3970X is clearly the way to go. On the other hand, the Threadripper 3960X has the same expansion capabilities and with 24 cores it still offers much of the same performance at a lower cost. At a $600 delta, AMD did a solid job with differentiation. If that delta was $1000, it would be much harder to recommend the 3970X. If the delta was $300, it would be difficult to recommend the 3960X.

Professional applications are often licensed by core, which is a good reason one may opt for a different CPU, but the per-core performance is still very good. If you have applications licensed by system, then scaling to 32 cores makes perfect sense. Indeed, the licensing costs will outweigh the marginal $600 one pays for eight extra cores with the Threadripper 3970X over the 3960X.

AMD Threadripper 3960X & 3970X
AMD Threadripper 3960X & 3970X

This licensing is also why the AMD EPYC chips do not make as much sense on the desktop. While AMD has low-cost EPYC 7002 series chips with high core counts for single-socket applications, anything below the AMD EPYC 7702P 64 core or AMD EPYC 7642 parts would be hard to justify unless one needs massive RAM capacity and ECC (L)RDIMM support.

The good news is that AMD has choices.

AMD Ryzen Threadripper 3970X v. Intel Alternatives

The AMD Ryzen Threadripper 3970X’s biggest competition may come on the Intel side. Intel has two product lines that the Threadripper 3970X competes against. These are the LGA3647 Xeon W-3275 and the LGA2066 Xeon W/ Core i9 lines.

On the Intel Xeon W-3275, we see the AMD Ryzen Threadripper as a direct competitor for much of that chip’s installed base. AMD has a better platform and more cores. Intel still has six-channel memory and ECC RDIMM support which means that there are features AMD is not matching in this generation. AMD could do it, but they are not supporting RDIMMs on the Threadripper platform despite the fact that it would be relatively easy for AMD to support it on the platform with the EPYC I/O die. That is the missing feature that would have made this a clean kill versus the Xeon W-3275.

Unfortunately, Intel is launching a HEDT part today. The Intel Core i9-10980XE is priced exactly where it needs to be. While the AMD Ryzen Threadripper 3970X is a generally better-performing part with more expansion capabilities, the Intel Core i9-10980XE is no longer in the same price bracket. Instead, it costs half as much but delivers more than 50% of the more expensive part’s performance. Platform cost and capabilities dilute this delta, but it is a $1000 delta. It is slightly strange to write since it is a HEDT marketed part, but the Intel Core i9-10980XE is not really a direct competitor to the Threadripper 3970X given its pricing.

A wildcard is, of course, the Intel Xeon W-2200 series. Pricing is more in-line with the 24-core AMD Ryzen Threadripper 3960X, but the Intel Xeon W-2295 supports ECC DDR4 RDIMMs which makes getting to higher capacity memory configurations both possible and less expensive. Still, it will have closer to Core i9-10980XE performance, so unless one is memory capacity constrained, it is competing with a different chip.

Final Words

Putting this into context, this is a $2000 CPU. Motherboards for larger platforms like this are neither small nor inexpensive. It is challenging to compare the AMD Ryzen Threadripper 3970X to a mainstream system just given pricing and expansion capabilities. When we look at the Intel Core i9-10980XE launched today, one can outfit an entire Core i9-10980XE system for less than the cost of the Threadripper 3970X so it is difficult to even make that comparison. Performance is better, but it should be at this pricing level.

Looking up the stack to the Intel Xeon W-3275, if you are using ~128GB of memory and do not need ECC RDIMMs, then the AMD Ryzen Threadripper 3970X is a much better buy. Power consumption is relatively similar even with a 75W TDP delta.

Whereas the AMD EPYC 7002 series is essentially a top-to-bottom better platform than the Intel Xeon Scalable platform, the AMD Ryzen Threadripper 3970X is close to being perfect. If AMD supported higher-capacity ECC RDIMMs making lower-cost high-memory configurations, then the Intel Xeon W-3275 would be left with little to no differentiation. That single choice is what is keeping the Threadripper 3970X from joining the small group of STH Editors Choice Award Winners. Even though it is not getting our elite honor like its server counterpart, this is still a great platform.


  1. Really a shame about those RDIMMs. For this reason I’m going to have to get an EPYC at lower clocks for a workstation I’ll be getting next year instead of a TR. It’s a shame, really.

    Totally agree about the platform thing. I’m not switching out CPUs in $6000+ computers.

  2. How were the CPU temps with the noctua-nh-u14s-tr4-sp3? I am surprised that an air cooler could handle this monster!

  3. Any tests that showcase performance for single threaded math heavy operations? I had to dump a previous threadripper built because it hugely lagged behind Intel CPUs mostly due to the absence of AVX2. Since then I have never touched AMD ever again. Am happy to revisit but I would like to see how it performs in single threads that require matrix computations and many millions of mathematical operations per second, ideally vectorized. Any such tests?

  4. @John Lee Could you please make the textual output from lscpu available? I don’t want to be typing all these abbreviations by hand yet I want to see how many different features does it have compared to my trusty TR1920X. Thanks!

  5. By the way, does anyone know what is the situation with encrypted memory main and encrypted memory for virtual machine with this generation of threadripper? The first generation showed support in the cpu flags but was missing something else from BIOS so it didn’t (wasn’t supposed to) work. It’s dick move by AMD to not support them on ThreadRipper, IMO, and I wonder if they kept it.

  6. Thank you for a great review as always. I appreciate the inclusion of SPECworkstation, lots of programs there I use in the HPC world. I need to do some digging on my own to figure out how they build their tests though. Some of those programs are a mess of potential different libraries, MPI,BLAS,LAPACK,FFTW, etc.

    Also I’d love to see some RandomX benchmarks like you did for Epyc. The 3970X should be perfect for it, I expect 25-30kh/s. While I’m asking, a deep dive on the cache would be interesting too, I’ve been seeing some results around online indicating there may be architectural differences in Zen2 Threadripper’s cache access vs Zen2 Ryzen.

  7. Threadripper comes with an ECC caveat that’s if the Motherboard maker chooses to support it and then that ECC support is somewhat lacking compared to AMD’s Epyc branded SKUs. And the single socket Epyc P series of 7002 SKUs are still affordable with the MBs offering up more memory channels(8) and more PCIe lanes with the full vetting/certification for ECC memory types compared to any consumer Zen-2/MB based variants currently.

    There are a few Benchmarks where the 3960X is performing on par or a little better than the 3970X and could that be the result of the 3 out of 4 enabled CPU cores on the 3960X’s CCX units still getting access to the same amount of L3 cache as the 4 enabled cores on the 3970’s CCX units where the 4 enabled cores have effectively less total L3 per CCX core to share among the enabled CPU cores than on the 3960X. I hope there will be more testing of the Cache subsystems on Zen-2 going forward for any SKUs that may have the full complement of L3 cache made available even though there is one, or more, core/cores pre CCX unit disabled and what workloads may benefit from having more total L3 Cache per enabled core on the CCX.

    I’m really interested on seeing any testing done to confirm that for Zen-2 but Zen-3 will see AMD getting rid of the CCX construct altogether and making the CCD die/chiplet have its full Complement of L3 available to the full 8 cores instead of partitioning the CCD into 2 CCX Units. The big question for 8 cores per CCD and no CCX units besides less Infinity Fabric traffic needed to get at that larger shared pool of L3 cache on Zen-3’s CCD die/chiplet is will AMD switch to a Ring Bus configuration on the 8 core CCD or some more complicated topology for 8 cores versus the 4 cores/CCX construct that’s used currently.

    Both AMD and Intel appear to be going wider order superscalar with their respective core designs in order to get more IPC in the face of getting less in performance advantages with the newer smaller process nodes not able to yield as much generational clock frequency increases as in the past. So Zen-3 will have to go wider order superscalar and maybe have some AVX512 options as well. I’d love to see AMD Bring some L4 cache to the I/O die at some point in time for any workloads that really can benefit but that’s maybe something that will have to wait for Zen-4 with hopefully Zen-3 getting some larger shared per CCD Die/Chiplet L3 cache over what Zen-2 offers.

    Really the Epyc/SP3 motherboard warranty/support periods are much longer than any Consumer/Threadripper offerings and that has to factor in to TCO for any professional end users that can really also deduct Epyc’s higher up front costs as a business expense. And really as far as ECC CPU/MB partner support goes Epyc CPU/MBs are vetted/certified on all the professional software packages whereas Threadripper CPUs/MBs will have less testing/certification guarantees and less product support should that be needed from AMD and the SP3 Motherboard makers .

    Threadripper may be sufficient for some if they absolutely need the higher clocks and are not dependent on ECC for certain workloads and maybe that’s good enough for some but folks need to do some more in depth cost/benefit analysis that also factors in the CPU’s cost/per memory channel and cost/per PCIe lane as well as the MB’s cost/memory channel and cost/PCIe lane. And that can make Epyc/SP3 the better deal on a cost/feature basis.

  8. @Fabian,what has this to do with dirty tricks? Fact is that my math/linear algebra heavy programs on Intel CPUs ran circles around both the previous gen Threadripper and Epyc CPUs at otherwise identical frequencies and memory speeds. I could not care less what “games” anyone is playing when my back tests and other heavy math procedures finish in half the time on one CPU vs the other. I have been a very heavy amd critic for math heavy applications and voice such on this website multiple times. Am always happy to revisit to test new amd products but so far neither Epyc nor Threadripper came even close in performance to Intel’s cpu for math heavy applications.

  9. @matt what fabian pointed to is that if you simply force matlab to properly recognize the math abilities of the AMD CPU it will run many more circles around the intel chips… the amd cups are faster on anything except a few avx512 special cases, so if you dont see that good chance it’s your math library that is heavily under utilizing the AMD chip. Nothing to criticize amd for, they cant fix your code for you.


Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.