Benchmarking Performance: CPU 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.

Legacy: 3DPM v1 Single Threaded

Legacy: 3DPM v1 MultiThreaded

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.

Legacy: CineBench 11.5 Single ThreadedLegacy: CineBench 11.5 MultiThreadedLegacy: CineBench 10 Single ThreadedLegacy: CineBench 10 MultiThreaded

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.

Legacy: x264 3.0 Pass 1Legacy: x264 3.0 Pass 2

Benchmarking Performance: CPU Office Tests Gaming Performance: Civilization 6 (1080p, 4K, 8K, 16K)
Comments Locked

140 Comments

View All Comments

  • Ian Cutress - Thursday, July 27, 2017 - link

    So one, overclocking is for a later review. Can't pass judgement on something that's not been tested. Other sites have certainly had more time (I get my chips 3-4 days after the US sites do, as I'm not in the US). This review was being written as the deadline passed, and is still being tested. It's not written it weeks in advance, with time to tooth comb and perfect every sentence. I've pulled an all-nighter to get to where it is now, even with some of the missing tests which are still being run. So when you say 'does not tell the full story', well not everything has been tested. I've made that abundantly clear several times in the review.

    Two, these chips are filling in volume at the lower end, especially in B2B where nothing is overclocked. You want me to sing the praises of a feature that we haven't had time to test for a product that's going to fill a market that won't use that feature, even though some in a different market might? If/when we get around to a pt2, I'll focus more on the enthusiast perspective. If you've read most of our CPU reviews over the past two years, most of the emphasis usually goes on out-of-the-box performance anyway.

    Third, on the very first page, in black and white, it states 'The big upswing for AMD here is going to be overclocking, and potentially push the Ryzen 3 CPUs through to compete with the next one up the stack depending on stock performance.'
  • vanilla_gorilla - Thursday, July 27, 2017 - link

    Ian, first off, great review as always and thank you. Second, you should just write up a large FAQ/disclaimer for your reviews that you can just link in the article and in comment replies. The same questions and complaints come up over and over, you've got to be tired of addressing them.
  • DrKlahn - Thursday, July 27, 2017 - link

    As I said, I understand it is for a later review. I also understand that a lot of these chips will never be overclocked. I don't want you to sing the praises of anything. I want a caveat in the conclusion that this potential exists and it impacts the value proposition. History has shown us (think the initial Radeon 290 reviews) that the first impression sticks with the reader regardless of how a product fares in the future. I have zero issues with your conclusion as an out of the box evaluation and appreciate your efforts. However your conclusion should have a caveat attached to it to call attention to everything the chip offers.
  • mikato - Thursday, July 27, 2017 - link

    I think that's fair. Here's another vote.
  • Gothmoth - Thursday, July 27, 2017 - link

    just saw your reply.... and i count on that. :-)
  • Gothmoth - Thursday, July 27, 2017 - link

    i hope anandtech will test the overcloked ryzen against the locked intels.
    but then... is amd paying enough fot advertising on anandtech..... :)
  • willis936 - Thursday, July 27, 2017 - link

    There is an R7 review and now an R3 review but nothing on the most interesting segment: R5. I've seen multiple other sites say that the R5 segment is where AMD is the clear winner for all workloads. Go up or down $50 and Intel makes more sense for gaming.
  • MrCommunistGen - Thursday, July 27, 2017 - link

    http://www.anandtech.com/show/11244/the-amd-ryzen-...
  • willis936 - Thursday, July 27, 2017 - link

    I wonder why that doesn't show up when using anandtech's search feature.

    http://www.anandtech.com/SearchResults?q=R5
  • MrCommunistGen - Thursday, July 27, 2017 - link

    This article doesn't show up when you search R3, and the 1800X article doesn't show up if you search R7.

    AMD isn't actually using R3, R5, and R7 as part of their branding for Ryzen, though I guess at least some are using that shorthand. The R3/5/7 are being used for GPU branding for some generations of discrete cards and APUs.

    If you look at the top of the article underneath the author's name, you'll see what tags the article has (and thus search terms) that you could use to find it in the future. Looks like "Ryzen" or "Ryzen 3" "Ryzen 5" and "Ryzen 7" are good terms.

    On the other hand, I found the link I posted above by going to Google and typing:
    anandtech 1600x review

Log in

Don't have an account? Sign up now