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.

Mozilla Kraken 1.1: link

Kraken is a  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

With the newer high-performance cores, AMD gets a fair crack at benchmarks like Mozilla, where it historically lagged behind with its Bulldozer-family architecture.

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

In recent years, Intel has made strides on its Octane performance. So even with cores and threads, and the sizable jump up from Kaveri, AMD is still behind on this test.

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

177 Comments

View All Comments

  • speely - Monday, February 12, 2018 - link

    "Where is the i5-8400 that has the same price as the 2400G?
    Oh, yeah, they totally left it out from the benchmarks since it would have proved an absolute supremacy of the Intel offering.
    Ops."

    In which benchmarks do you expect to see the i5-8400 prove its "absolute supremacy" where the i5-7400 didn't? Seriously, I'd like to know.

    Because what I see is either the i5-7400 beating the 2400G or going punch to punch with it, or being thoroughly decimated by it.

    If the i5-7400 beats or competes with the 2400G, the i5-8400 refresh chip will do the same. If the i5-7400 gets trounced by the 2400G, the i5-8400 refresh chip isn't suddenly and magically going to beat it.

    I fail to see anything in the article to indicate a pro-AMD bias on AT's part, either intentional or unintentional.

    What I do see is a fanboy who's upset to see his team losing some benchmarks.
  • Kamgusta - Monday, February 12, 2018 - link

    Ehm sir, 7400 is 4 core and 8400 is 6 core.
    Other reviews shows a 30% performance dominance of i5-8400 over the 2400G.
  • speely - Monday, February 12, 2018 - link

    Fair point, and my apologies. I keep forgetting that they upped the i5's to 6 cores after a decade of 4c4t i5's (including the 4690K I currently use).

    That being said, the i5-8400 itself is the same price as the 2400G, but getting the i5-8400 running is not the same price as getting the 2400G running. The 2400G was tested on an MSI B350I Pro AC (https://www.anandtech.com/show/12227/msi-releases-... which is new and doesn't yet have a publicly-known MSRP, but is built and featured like other $70-80 B350 motherboards. What motherboards are on the market today for $70-80 that support the i5-8400?

    So we've taken into account the additional 2 cores and the subsequent boost to the CPU-focused benchmarks, which the 7400 sometimes lost and sometimes won against the 2400G, and put a couple small notches into the 8400's belt. For another 50 bucks or so on the motherboard just to use the 8400, that's not too bad I suppose. It's what I would expect pitting a 6c6t CPU against a 4c8t CPU in CPU benchmarks. It's certainly not "absolute supremacy" but it's something, right?

    Were you expecting that "absolute supremacy" to show up in iGPU gaming? I'll just laugh about that and move on.

    Sure, the 8400 could probably step past the 2400G in gaming and graphics if you paired it with a $120-or-so graphics card (assuming you can find one at $120 or so), but then you're comparing a dGPU to an iGPU and you're still only barely stepping past.

    So the only real way to make the 8400 show "absolute supremacy" over the 2400G is to cherry-pick just the benchmarks you like, and bolster the 8400 with another $200 of additional hardware.

    "Absolute supremacy".
  • Manch - Monday, February 12, 2018 - link

    No it's not.In regards to vs the 8400, its a mixed bag. For programs that favor Intel CPU's there is a clear advantage. For programs that favor AMD the advantage swings the other way. For everything else that's generally proc agnostic they tie, pull ahead slightly or gets beat relatively evenly in regards to CPU performance.

    Now GPU wise, it gets crushed. That's obvious that is gonna happen.

    If you plan on getting a DGPU with some beef, either is good, If you looking to game on the cheap, which is the target of the AMD proc in this review, its the hands down winner. Comparable perf, but with a beefier iGPU that can hang with a 1030. Also it gives you the option of adding a DGPU later when you need more grunt. It's clearly the better buy this go around. No other site that Ive seen has argued against this.
  • dromoxen - Tuesday, February 13, 2018 - link

    Are these going to get a 12nm refresh , as all the other ryzen cpus? I am thinking of upgrade either i58400 or r5 1600/1700 or possibly 2400g.. decision decisions ...
  • Manch - Wednesday, February 14, 2018 - link

    Originally it was labeled as 12nm, now referred to 14nm+.Probably will be updated.
  • cheshirster - Monday, February 12, 2018 - link

    You need Z370 for the "supremacy" to work.
    Ops.
  • bug77 - Monday, February 12, 2018 - link

    That will be fixed when lower tier 300-series chipsets launch. However, it's a significant problem for those wanting to build a cheap setup until then.
  • Ian Cutress - Monday, February 12, 2018 - link

    I used the chips I have on hand for the tests, forgot to add already tested chips - we haven't tested the i5-8400 IGP, but the CPU results are on hand in Bench. I can add those results to the graphs when I get a chance.
  • Manch - Monday, February 12, 2018 - link

    Ian, I dont know if fhis is just when browing from a phone but the bench when listing CPUs while alphabetic, bc of the chips names ~lake, etc. The listing jumps all over the place. 8 series before 4 seriez then 7 series. Can yall fix this? Thanks

Log in

Don't have an account? Sign up now