The AMD Ryzen Threadripper 1950X and 1920X Review: CPUs on Steroids
by Ian Cutress on August 10, 2017 9:00 AM ESTCPU Office Tests
The office programs we use for benchmarking aren't specific programs per-se, but industry standard tests that hold weight with professionals. The goal of these tests is to use an array of software and techniques that a typical office user might encounter, such as video conferencing, document editing, architectural modeling, and so on and so forth.
All of our benchmark results can also be found in our benchmark engine, Bench.
Chromium Compile (v56)
Our new compilation test uses Windows 10 Pro, VS Community 2015.3 with the Win10 SDK to compile a nightly build of Chromium. We've fixed the test for a build in late March 2017, and we run a fresh full compile in our test. Compilation is the typical example given of a variable threaded workload - some of the compile and linking is linear, whereas other parts are multithreaded.
One of the interesting data points in our test is the Compile, and it is surprising to see the 1920X only just beat the Ryzen 7 chips. Because this test requires a lot of cross-core communication, the fewer cores per CCX there are, the worse the result. This is why the 1950X in SMT-off mode beats the 3 cores-per-CCX 1920X, along with lower latency memory support. We know that this test is not too keen on victim caches either, but it does seem that the 2MB per core ratio does well for the 1950X, and could explain the performance difference moving from 8 to 12 to 16 cores under the Zen microarchitecture.
PCMark8: link
Despite originally coming out in 2008/2009, Futuremark has maintained PCMark8 to remain relevant in 2017. On the scale of complicated tasks, PCMark focuses more on the low-to-mid range of professional workloads, making it a good indicator for what people consider 'office' work. We run the benchmark from the commandline in 'conventional' mode, meaning C++ over OpenCL, to remove the graphics card from the equation and focus purely on the CPU. PCMark8 offers Home, Work and Creative workloads, with some software tests shared and others unique to each benchmark set.
Strangely, PCMark 8's Creative test seems to be failing across the board. We're trying to narrow down the issue.
SYSmark 2014 SE: link
SYSmark is developed by Bapco, a consortium of industry CPU companies. The goal of SYSmark is to take stripped down versions of popular software, such as Photoshop and Onenote, and measure how long it takes to process certain tasks within that software. The end result is a score for each of the three segments (Office, Media, Data) as well as an overall score. Here a reference system (Core i3-6100, 4GB DDR3, 256GB SSD, Integrated HD 530 graphics) is used to provide a baseline score of 1000 in each test.
A note on context for these numbers. AMD left Bapco in the last two years, due to differences of opinion on how the benchmarking suites were chosen and AMD believed the tests are angled towards Intel processors and had optimizations to show bigger differences than what AMD felt was present. The following benchmarks are provided as data, but the conflict of opinion between the two companies on the validity of the benchmark is provided as context for the following numbers.
Facebook
Twitter
RSS
347 Comments
View All Comments
imaheadcase - Thursday, August 10, 2017 - link
So you lost respect for a website based on how they word titles of articles? I think you don't understand advertising at all. lolIf you want to know a website that lost respect, look at HardOCP and you know why people don't like them for obvious reasons.
Alexey291 - Thursday, August 10, 2017 - link
No offence but HardOCP is far more respectable than what we have in ATech these days.But that's not hard. AT website is pretty much a shell for the forum which is where most of the traffic is. I'm sure they only so the reviews because 'it was something we have always done'
Johan Steyn - Thursday, August 10, 2017 - link
You may not understand how wording is used to convey sentiments in a different way. That is what politicians thrive on. You could for instance say "I am sorry that you misunderstood me." It gives the impression that you are sorry, but you are not. People also ask for forgiveness like this: "If I have hurt you, please forgive me." It sounds sincer, but it is a hidden lie, not acknowledging that you have actually hurt anybody, actually saying that you do not think that you did.Well, this is a science and I cannot explain it all here. If you miss it, then it does not mean it is not there.
mikato - Monday, August 14, 2017 - link
I thought I'd just comment to say I understand what you're saying and agree. Even if a sentence gives facts, it can sound more positive one way or another way based on how it is stated. The author has to do some reflection sometimes to catch this. I believe him whenever he says he doesn't have much time, and maybe that plays into it. But articles at different sites may not have this bias effect and it can be an important component of a review article."Intel recently announced that its new 18-core chip scores 3200 on Cinebench R15. That would be an extra 6.7% performance over the Threadripper 1950X for 2x the cost."
These 2 sentences give facts, but sound favorable to Intel until just the very end. It's a subtle perception thing but it's real. The facts in the sentences, however, are massively favorable to AMD. Threadripper does only 6.7% less performance than an announced (not yet released) Intel CPU for half the cost!
Here is another version-
"Intel recently announced that its new 18-core chip scores 3200 on Cinebench R15. So Threadripper, for half the cost of Intel's as-yet unreleased chip, performs only 6.7% slower in Cinebench."
There, that one leads with Threadripper and "half the cost" in the second sentence, and sounds much different.
Johan Steyn - Thursday, August 10, 2017 - link
HardOCP and PCPer is more respected in my opinion. Wccftech is unpredictable, sometimes they shine and sometimes they are really odd.mapesdhs - Thursday, August 10, 2017 - link
I've kinda taken to GamersNexus recently, but I still always read AT and toms to compare.Ian.
fanofanand - Tuesday, August 15, 2017 - link
WCCFtech is a joke, it's nothing but rumors and trolling. If you are seriously going to put WCCFtech above Anandtech then everyone here can immediately disregard all of your comments.Drumsticks - Thursday, August 10, 2017 - link
Fantastic review In. I was curious exactly how AMD would handle the NUMA problem with Threadripper. It seems that anybody buying Threadripper for real work is going to have to continue being very aware of exactly what configuration gets them the best performance.One minor correction, at the bottom of the CPU Rendering tests page:
"Intel recently announced that its new 18-core chip scores 3200 on Cinebench R15. That would be an extra 6.7% performance over the Threadripper 1950X for 2x the cost." - this score is for the 16 core i9-7960X, not the 7980XE.
Drumsticks - Thursday, August 10, 2017 - link
Ian*. Can't wait for the edit button one day!launchcodemexico - Thursday, August 10, 2017 - link
Why did you end all the gaming review sections with something like "Switching it to Game mode would have made better numbers..."? Why didn't you run the benchmarks in Gaming mode in the first place?