Benchmarking Performance: CPU Web Tests

One of the issues when running web-based tests is the nature of modern browsers to automatically install updates. This means any sustained period of benchmarking will invariably fall foul of the 'it's updated beyond the state of comparison' rule, especially when browsers will update if you give them half a second to think about it. Despite this, we were able to find a series of commands to create an un-updatable version of Chrome 56 for our 2017 test suite. While this means we might not be on the bleeding edge of the latest browser, it makes the scores between CPUs comparable.

All of our benchmark results can also be found in our benchmark engine, Bench.

SunSpider 1.0.2: link

The oldest web-based benchmark in this portion of our test is SunSpider. This is a very basic javascript algorithm tool, and ends up being more a measure of IPC and latency than anything else, with most high-performance CPUs scoring around about the same. The basic test is looped 10 times and the average taken. We run the basic test 4 times.

Web: SunSpider on Chrome 56

Mozilla Kraken 1.1: link

Kraken is another Javascript based benchmark, using the same test harness as SunSpider, but focusing on more stringent real-world use cases and libraries, such as audio processing and image filters. Again, the basic test is looped ten times, and we run the basic test four times.

Web: Mozilla Kraken 1.1 on Chrome 56

Google Octane 2.0: link

Along with Mozilla, as Google is a major browser developer, having peak JS performance is typically a critical asset when comparing against the other OS developers. In the same way that SunSpider is a very early JS benchmark, and Kraken is a bit newer, Octane aims to be more relevant to real workloads, especially in power constrained devices such as smartphones and tablets.

Web: Google Octane 2.0 on Chrome 56

WebXPRT 2015: link

While the previous three benchmarks do calculations in the background and represent a score, WebXPRT is designed to be a better interpretation of visual workloads that a professional user might have, such as browser based applications, graphing, image editing, sort/analysis, scientific analysis and financial tools.

Web: WebXPRT 15 on Chrome 56

Benchmarking Performance: CPU Rendering Tests Benchmarking Performance: CPU Encoding Tests
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