CPU Performance: Synthetic Tests

As with most benchmark suites, there are tests that don’t necessarily fit into most categories because their role is just to find the peak throughput in very particular coding scenarios. For this we rely on some of the industry standard tests, like Geekbench and Cinebench.

GeekBench4: Synthetics

A common tool for cross-platform testing between mobile, PC, and Mac, GeekBench 4 is an ultimate exercise in synthetic testing across a range of algorithms looking for peak throughput. Tests include encryption, compression, fast Fourier transform, memory operations, n-body physics, matrix operations, histogram manipulation, and HTML parsing.

I’m including this test due to popular demand, although the results do come across as overly synthetic, and a lot of users often put a lot of weight behind the test due to the fact that it is compiled across different platforms (although with different compilers).

We record the main subtest scores (Crypto, Integer, Floating Point, Memory) in our benchmark database, but for the review we post the overall single and multi-threaded results.

Geekbench 4 - ST OverallGeekbench 4 - MT Overall

LinX: LINPACK

The main tool for ordering the TOP500 computer list involves running a variant of an accelerated matrix multiply algorithm typically found from the LINPACK suite. Here we use a tool called LinX to do the same thing on our CPUs. We scale our test based on the number of cores present in order to not run out of scaling but still keeping the test time consistent.

This is another of our new tests for 2020. Data will be added as we start regression testing older CPUs.

LinX 0.9.5 LINPACK

 

Cinebench R20

The Cinebench line of tests is very well known among technology enthusiasts, with the software implementing a variant of the popular Cinema4D engine to render through the CPU a complex scene. The latest version of Cinebench comes with a number of upgrades, including support for >64 threads, as well as offering a much longer test in order to stop the big server systems completing it in seconds. Not soon after R20 was launched, we ended up with 256 thread servers that completed the test in about two seconds. While we wait for the next version of Cinebench, we run the test on our systems in single thread and multithread modes, running for a minimum of 10 minutes each.

Cinebench R20 Single ThreadedCinebench R20 Multi-Threaded

CPU Performance: Web and Legacy Tests CPU Performance: SPEC 1T
POST A COMMENT

220 Comments

View All Comments

  • DrKlahn - Wednesday, May 20, 2020 - link

    My biggest issue with gaming is that these reviews rarely show anything other than low resolution scenarios. I realize a sizable slice of the gaming community uses 1080p and that some of them are trying to hit very high frame rates. But there also a lot of us with 1440p+ or Ultrawides and I think it gets overlooked that Intels gaming "lead" largely evaporates for anyone not trying to hit very high frames at 1080p. Reply
  • ElvenLemming - Wednesday, May 20, 2020 - link

    Honestly, I think it's ignored because it's well understood that at 1440p+ the CPU just doesn't matter very much. There's not much value in anything above 1080p for a CPU review the vast majority of games are going to be GPU limited. That said, plenty of other outlets include them in their reviews if you want to see a bunch of charts where the top is all within 1% of each other. Reply
  • DrKlahn - Wednesday, May 20, 2020 - link

    I do agree with you that a lot of us do understand that as resolution and detail increases, CPUs become almost irrelevant to gaming performance. However you do see a fair few posters parroting "Intel is better for gaming" when in reality for their use case it really isn't any better. That's why I feel like these reviews (here and elsewhere) should spotlight where this difference matters. If you are a competitive CS:GO player that wants 1080p or lower with the most frames you can get, then Intel is undoubtedly better. But a person who isn't as tech savvy that games and does some productivity tasks with a 1440p+ monitor is only spending more money for a less efficient architecture that won't benefit them if they simply see "Intel better for gaming" and believe it applies to them. Reply
  • shing3232 - Thursday, May 21, 2020 - link

    3900X or 3800X can beat Intel 9900Kf on csgo with pbo on if I remember correctly. Reply
  • silencer12 - Saturday, May 23, 2020 - link

    Csgo is not a demanding game Reply
  • vanilla_gorilla - Monday, June 15, 2020 - link

    >If you are a competitive CS:GO player that wants 1080p or lower with the most frames you can get, then Intel is undoubtedly better.

    It's actually more complicated than that. Even midrange Zen 2 CPU can hit well over 200 fps in CS:GO. So unless you have a 240hz monitor, it won't make any difference buying Intel or AMD in that case.
    Reply
  • Irata - Wednesday, May 20, 2020 - link

    Techspot shows a seven game average and there the avg fps / min 1% difference to the Ryzen 3 3300x is less than 10% using a 2080ti. Reply
  • CrimsonKnight - Thursday, May 21, 2020 - link

    This review's benchmarks goes up to 4K/8K resolution. You have to click the thumbnails under the graphs. Reply
  • Meteor2 - Wednesday, July 15, 2020 - link

    To be clear: Anandtech tests at low resolutions so the bottleneck is the CPU, not the GPU. A Ryzen 5 won’t bottleneck a 2080 Ti at 4K. Reply
  • kmmatney - Wednesday, May 20, 2020 - link

    Those of us who live near a Microcenter can get the 3900X for $389, along with a $20 discount on a motherboard (and a serviceable heatsink). The Ryzen 5 (what I bought) is $159, also with a $20 motherboard discount and a decent cooler. So my effective motherboard cost was $79, and total cost of $240 + tax, with a motherboard that can (most likely) be upgraded to Zen 3 Reply

Log in

Don't have an account? Sign up now