The AMD Ryzen Threadripper 1950X and 1920X Review: CPUs on Steroids
by Ian Cutress on August 10, 2017 9:00 AM ESTCPU Legacy Tests
Our legacy tests represent benchmarks that were once at the height of their time. Some of these are industry standard synthetics, and we have data going back over 10 years. All of the data here has been rerun on Windows 10, and we plan to go back several generations of components to see how performance has evolved.
All of our benchmark results can also be found in our benchmark engine, Bench.
3D Particle Movement v1
3DPM is a self-penned benchmark, taking basic 3D movement algorithms used in Brownian Motion simulations and testing them for speed. High floating point performance, MHz and IPC wins in the single thread version, whereas the multithread version has to handle the threads and loves more cores. This is the original version, written in the style of a typical non-computer science student coding up an algorithm for their theoretical problem, and comes without any non-obvious optimizations not already performed by the compiler, such as false sharing.
CineBench 11.5 and 10
Cinebench is a widely known benchmarking tool for measuring performance relative to MAXON's animation software Cinema 4D. Cinebench has been optimized over a decade and focuses on purely CPU horsepower, meaning if there is a discrepancy in pure throughput characteristics, Cinebench is likely to show that discrepancy. Arguably other software doesn't make use of all the tools available, so the real world relevance might purely be academic, but given our large database of data for Cinebench it seems difficult to ignore a small five minute test. We run the modern version 15 in this test, as well as the older 11.5 and 10 due to our back data.
x264 HD 3.0
Similarly, the x264 HD 3.0 package we use here is also kept for historic regressional data. The latest version is 5.0.1, and encodes a 1080p video clip into a high-quality x264 file. Version 3.0 only performs the same test on a 720p file, and in most circumstances the software performance hits its limit on high-end processors, but still works well for mainstream and low-end. Also, this version only takes a few minutes, whereas the latest can take over 90 minutes to run.
The 1950X: the first CPU to score higher on the 2nd pass of this test than it does on the first pass.
Facebook
Twitter
RSS
347 Comments
View All Comments
lefty2 - Thursday, August 10, 2017 - link
except that they haven'tDr. Swag - Thursday, August 10, 2017 - link
How so? You have the performance numbers, and they gave you power draw numbers...bongey - Thursday, August 10, 2017 - link
Just do a avx512 benchmark and Intel will jump over 300watts , 400watts(overclocked) only from the cpu. (prime95 avx512 benchmark).See der8auer's video "The X299 VRM Disaster (en)"DanNeely - Thursday, August 10, 2017 - link
The Chromium build time results are interesting. Anandtech's results have the 1950X only getting 3/4ths of the 7900X's performance. Arstechnica's getting almost equal results on both CPUs, but at 16 compiles per day vs 24 or 32 is seeing significantly worse numbers all around.I'm wondering what's different between the two compile benchmarks to see such a large spread.
cknobman - Thursday, August 10, 2017 - link
I think it has a lot to do with the RAM used by Anandtech vs Arstechnica .For all the regular benchmarking Anand used DDR4 2400, only the DDR 3200 was used in some overcloking.
Arstechnica used DDR4 3200 for all benchmarking.
Everyone already knows how faster DDR4 memory helps the Zen architecture.
DanNeely - Thursday, August 10, 2017 - link
If ram was the determining factor, Ars should be seeing faster build times though not slower ones.carewolf - Thursday, August 10, 2017 - link
Anandtech must have misconfigured something. Building chromium is scales practically linearly. You can move jobs all the way across a slow network and compile on another machine and you still get linear speed-ups with more added cores.Ian Cutress - Thursday, August 10, 2017 - link
We're using a late March v56 code base with MSVC.Ars is using a newer v62 code base with clang-cl and VC++ linking
We locked in our versions when we started testing Windows 10 a few months ago.
supdawgwtfd - Friday, August 11, 2017 - link
Maybe drop it then as it is not at all usefull info.Johan Steyn - Thursday, August 10, 2017 - link
I refrained from posting on the previous article, but now I'm quite sure Anand is being paid by Intel. It is not that I argue against the benchmarks, but how it is presented. I was even under the impression that this was an Intel review.The previous article was stated as "Introducing Intel's Desktop Processor" Huge marketing research is done on how to market products. By just stating one thing first or in a different way, quite different messages can be conveyed without lying outright.
By making the "Most Powerful, Most Scalable" Bold, that is what the readers read first, then they read "Desktop Processor" without even reading that is is Intel's. This is how marketing works, so Anand used slanted journalism to favour Intel, yet most people will just not realise it eat it up.
In this review there are so many slanted journalism problems, it is just sad. If you want, just compare it to other sites reviews. They just omit certain tests and list others at which Intel excel.
I have lost my respect for Anandtech with these last two articles of them, and I have followed Anandtech since its inception. Sad to see that you are also now bought by Intel, even though I suspected this before. Congratulations for making this so clear!!!