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
Notmyusualid - Sunday, August 13, 2017 - link
Yep, I'll get the door for him.Jeff007245 - Friday, August 11, 2017 - link
I don't comment much (if ever), but I have to say one thing... I miss Anand's reviews. What happened to AnandTech?What ever happened to IPC testing when IPC used to be compared on a clock for clock basis? I remember the days when IPC used to be Instructions Per Clock, and this website and others would even use a downclock/overclock processors at a nominal clock rate to compare the performance of each processor's IPC. Hell, even Bulldozer with a high clock architecture was downclocked to compare is "relative IPC" in regards using a nominal clockrate.
And to add to what other's are saying about the bias in the review... Honestly, I have been feeling the same way for some time now. Must be because AnandTech is at the "MERCY" of their mother company Purch Media... When you are at the mercy of your advertisers, you have no choice but to bend the knee, or even worse, bend over and do as they say "or else"...
Thanks for taking the time in creating this review, but AnandTech to me is no longer AnandTech... What other's say is true, this place is only good for the Forums and the very technical community that is still sticking around.
fanofanand - Tuesday, August 15, 2017 - link
Downclocking and overclocking processors to replicate a different processor within the same family can lead to inaccurate results, as IPC can and does rely (at least to a degree) on cache size and structure. I get what you are saying, but I think Ian's work is pretty damn good.SloppyFloppy - Friday, August 11, 2017 - link
Why did you leave out the i9s from the gaming tests?Why didn't you include the 7700k when you include 1800x for gaming tests?
People want to know that if they buy a $1k 7900X or 1950X if it's not only great for media creation/compiling but also gaming.
silverblue - Friday, August 11, 2017 - link
Stated why at the bottom of page 1. Also, he used the 7740X, so there is little to no point in putting the 7700K.Lolimaster - Friday, August 11, 2017 - link
The 1950X is as good at gaming as the 1800X, OCed 1700, with many more cpu resource to toy with.Swp1996 - Friday, August 11, 2017 - link
Thats The Best Title I have ever seen ...😂😂😂😂🤣🤣🤣🤣🤣 Steroids 😂😂😂🤣🤣🤣🤣🤣🤣🤣corinthos - Friday, August 11, 2017 - link
in other words.. AMD Ryzen is still the best bet for most people, and the best value. 1700 OC'd all day!BillBear - Friday, August 11, 2017 - link
>Move on 10-15 years and we are now at the heart of the Core Wars: how many CPU cores with high IPC can you fit into a consumer processor? Up to today, the answer was 10, but now AMD is pushing the barrier to 16I don't personally think of Threadripper or parts like Broadwell-E as being consumer level parts.
For me, the parts most consumers use have been using for the last decade have been Intel parts with two cores or four cores at the high end.
It's been a long period of stagnation, with cutting power use on mobile parts being the area that saw the most attention and improvement.
James S - Friday, August 11, 2017 - link
Agree the HEDT platforms are not for the average consumer they are for enthusiasts, professional workstation usage, and some other niche uses.When the frequency war stopped and the IPC war started. We should have had the core competition 5-8 years back since IPC stagnated to a couple percent gains year on year.