The AMD Threadripper 2990WX 32-Core and 2950X 16-Core Review
by Dr. Ian Cutress on August 13, 2018 9:00 AM ESTTest Setup and Comparison Points
In our review kit from AMD, we were supplied with almost complete systems for testing. Inside the box of goods, AMD included:
- AMD Threadripper 2990WX (32C, 250W, $1799)
- AMD Threadripper 2950X (16C, 180W, $899)
- ASUS ROG Zenith Extreme motherboard, rev 2
- MSI X399 MEG Creation motherboard
- 4x8 GB of G.Skill FlareX DDR4-3200 14-14-14
- Wraith Ripper Cooler, co-developed with Cooler Master
- Enermax Liqtech 240 TR4 Liquid Cooler, rated to 500W
For our usual testing, we stick to the same power supplies, the same storage, ideally the same motherboard within a range of processors, and always use the latest BIOS. Despite AMD shipping us some reasonably fast memory, our standard policy is to test these systems at the maximum supported frequency as promoted by the processor manufacturer, or in this case DDR4-2933 for the new Threadripper 2000-series processors.
For our testing we compared the first generation Threadripper processors with the second generation parts. We also have the Intel 18-core Core i9-7980XE, some results from the Core i7-7900X (10-core), and also two mainstream processors, one Intel and one AMD. This is due to our new CPU testing suite, which takes effect today.
Due to an industry event occuring in the middle of our testing, we had to split some of the testing up and take 30 kg of kit half-way around the world to test in a hotel room during Flash Memory Summit. On the downside, it means there is some discontinuity in our testing, although not that much - on the plus side, the hardware tested in the hotel room had a good amount of air-conditioning to keep cool.
| AMD Test Setup | |||||
| CPUs | TR 2990WX | ASUS ROG Zenith | 0078 | Liqtech TR4 | 4x8GB DDR4-2933 |
| TR 2950X | ASUS ROG Zenith | 0078 | Liqtech TR4 | 4x8GB DDR4-2933 | |
| TR 1950X | ASUS X399-A Prime | 0806 | TRUE Cu | 4x4GB DDR4-2666 | |
| TR 1920X | ASUS ROG Zenith | 0078 | Liqtech TR4 | 4x8GB DDR4-2666 | |
| TR 1900X | ASUS X399-A Prime | 0806 | TRUE Cu | 4x4GB DDR4-2666 | |
| R7 2700X | ASUS Crosshair VI Hero | 0508 | Wraith Max | 4x8GB DDR4-2933 | |
| EPYC 7601 | GIGABYTE MZ31-AR0 | Fryzen | 8x128GB DDR4-2666 | ||
| GPU | Sapphire RX 460 2GB (CPU Tests) | ||||
| PSU | Corsair AX860i Corsair AX1200i |
||||
| SSD | Crucial MX300 1TB | ||||
| OS | Windows 10 x64 RS3 1709 Spectre and Meltdown Patched |
||||
The memory for our test suites was mostly G.Skill, with some Crucial. For the EPYC system, Micron sent us some LRDIMMs, so we fired up 1TB of memory to get all eight channels working.
On the Intel side, we are still getting up to speed on our testing.
| Intel Test Setup | |||||
| CPUs | i9-7980XE | ASRock X299 OC Formula | P1.40 | TRUE Cu | 4x8GB DDR4-2666 |
| i9-7900X | ASRock X299 OC Formula | P1.40 | TRUE Cu | 4x8GB DDR4-2666 | |
| i7-8700K | ASRock Z370 Gaming i7 | P1.70 | AR10-115XS | 4x4GB DDR4-2666 | |
| GPU | Sapphire RX 460 2GB (CPU Tests) | ||||
| PSU | Corsair AX860i Corsair AX1200i |
||||
| SSD | Crucial MX300 1TB | ||||
| OS | Windows 10 x64 RS3 1709 Spectre and Meltdown Patched |
||||
Over time we will be adding to our Intel CPUs tested.
Many thanks to...
We must thank the following companies for kindly providing hardware for our multiple test beds. Some of this hardware is not in this test bed specifically, but is used in other testing.
Thank you to Crucial for providing us with MX200 SSDs and to Micron for LRDIMMs. Crucial stepped up to the plate as our benchmark list grows larger with newer benchmarks and titles, and the 1TB MX200 units are strong performers. Based on Marvell's 88SS9189 controller and using Micron's 16nm 128Gbit MLC flash, these are 7mm high, 2.5-inch drives rated for 100K random read IOPs and 555/500 MB/s sequential read and write speeds. The 1TB models we are using here support TCG Opal 2.0 and IEEE-1667 (eDrive) encryption and have a 320TB rated endurance with a three-year warranty.
Further Reading: AnandTech's Crucial MX200 (250 GB, 500 GB & 1TB) Review
Thank you to Corsair for providing us with an AX1200i PSU. The AX1200i was the first power supply to offer digital control and management via Corsair's Link system, but under the hood it commands a 1200W rating at 50C with 80 PLUS Platinum certification. This allows for a minimum 89-92% efficiency at 115V and 90-94% at 230V. The AX1200i is completely modular, running the larger 200mm design, with a dual ball bearing 140mm fan to assist high-performance use. The AX1200i is designed to be a workhorse, with up to 8 PCIe connectors for suitable four-way GPU setups. The AX1200i also comes with a Zero RPM mode for the fan, which due to the design allows the fan to be switched off when the power supply is under 30% load.
Further Reading: AnandTech's Corsair AX1500i Power Supply Review
Thank you to G.Skill for providing us with memory. G.Skill has been a long-time supporter of AnandTech over the years, for testing beyond our CPU and motherboard memory reviews. We've reported on their high capacity and high-frequency kits, and every year at Computex G.Skill holds a world overclocking tournament with liquid nitrogen right on the show floor.
Further Reading: AnandTech's Memory Scaling on Haswell Review, with G.Skill DDR3-3000
Facebook
Twitter
RSS
171 Comments
View All Comments
just4U - Monday, August 13, 2018 - link
Ian, were you testing this with the CM Wraith Cooler? If not is it something you plan to review?Ian Cutress - Monday, August 13, 2018 - link
Most of the testing data is with the Liqtech 240 liquid cooler, rated at 500W. I do have data taken with the Wraith Ripper, and I'll be putting some of that data out when this is wrapped up.IGTrading - Monday, August 13, 2018 - link
To be honest, with the top of the line 32core model, it is interesting to identify as many positive effect cases as possible, to see if that entire set of applications that truly benefit of the added cores will persuade power users to purchase it.Like you've said, it is a niche of a niche and seeing it be X% faster of Y% slower is not as interesting as seeing what it can actually do when it is used efficiently and if this this makes a compelling argument for power users.
PixyMisa - Tuesday, August 14, 2018 - link
Phoronix found that a few tests ran much faster on Linux - for 7zip compression in particular, 140% faster (as in, 2.4x). Some of these benchmarks could improve a lot with some tweaking to the Windows scheduler.phoenix_rizzen - Wednesday, August 15, 2018 - link
It'd be interesting to redo these tests on a monthly basis after Windows/BIOS updates are done, to see how performance changes over time as the Windows side of things is tweaked to support the new NUMA setup for TR2.At the very least, a follow-up benchmark run in 6 months would be nice.
Kevin G - Monday, August 13, 2018 - link
Chiplets!The power consumption figures are interesting but TR does have to manage one thing that the high end desktop chips from Intel don't: off-die traffic. The amount of power to move data off die is significantly higher than moving it around on-die. Even in that context, TR's energy consumption for just the fabric seems high. When only threads are loaded, they should only be with dies with the memory controllers leaving two dies idle. It doesn't appear that the fabric is powering down while those remote dies are also powering down. Any means of watching cores enter/exit sleep states in real time?
I'd also be fun to see with Windows Server what happens when all the cores on a die are unplugged from the system. Consdiering the AMD puts the home agent on the memory controller on each die, even without cores or memory attached, chances are that the home agent is still alive consuming power. It'd be interesting to see what happens on Sky Lake-SP as well if the home agents on the grid eventually power themselves down when there is nothing directly connected to them. It'd be worth comparing to the power consumption when a core is disabled in BIOS/EFI.
I also feel that this would be a good introduction for what is coming down the road with server chips and may reach the high end consumer products: chiplets. This would permit the removal of the off-die Infinity Links for something that is effectively on-die throughout the cluster of dies. That alone will save AMD several watts. The other thing about chiplets is that it would greatly simplify Thread Ripper: only two memory controller chiplets would be to be in the package vs. four as we have now. That should save AMD lots of power. (And for those reading this comment, yes, Intel has chiplet plans as well.). The other thing AMD could do is address how their cache coherency protocols work. AMD has hinted at some caching changes for Zen 2 but lacks specificity.
gagegfg - Monday, August 13, 2018 - link
do not seem to exist more than once the 16 additional core of the 2990wx compared to the 2950xIan Cutress - Monday, August 13, 2018 - link
https://www.anandtech.com/bench/product/2133?vs=21...Chaitanya - Monday, August 13, 2018 - link
Built for scientific workload.woozle341 - Monday, August 13, 2018 - link
Do you think the lack of AVX512 is an issue? I might build a workstation soon for data processing with R and Python for some Fortran models and post-processing. Skylake-X looks pretty good wit its quad memory channels despite its high price.