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
Comments Locked

220 Comments

View All Comments

  • arashi - Sunday, May 24, 2020 - link

    Replacing Stewart with xx does not a clone account make.

    Try again.
  • Spunjji - Tuesday, May 26, 2020 - link

    Good catch XD
  • Spunjji - Tuesday, May 26, 2020 - link

    You're talking past yourself.

    Sure, it's impressive what Intel's disaster management engineers managed to pull out the wreckage of their failure at 10nm. Their failure at 10nm was an engineering failure too, though, and they still haven't managed to backport their 10nm-planned architecture to 14nm.

    In other words, those engineering failures are the only reason they had to build this crazy nonsense - of which you express such admiration - in the first place.
  • extide - Wednesday, May 20, 2020 - link

    This is not HEDT
  • Spunjji - Tuesday, May 26, 2020 - link

    He's still reading from the 2016 Intel playbook :D
  • Icehawk - Saturday, May 23, 2020 - link

    I care because I like silent machines and use fanless PSUs. I can’t afford to blow 250-300W of the power budget on the CPU when I am limited to 450W, the small difference in real world gaming isn’t worth popping for a higher power PSU that brings with it fan noise. I should be able to run my 3900X with a nV 3070 with what I have, I don’t think I could with this i9.

    If power budget isn’t a concern then it’s down to brand preference, usage mix, etc to me. I have an intel 8700 as well, at the time I felt that was the best CPU choice, when I needed another new machine a few months ago the 3900 was - I still feel it would be today for me.

    YMMV
  • Spunjji - Tuesday, May 26, 2020 - link

    Cool, another person who thinks their personal views on a topic outweigh all others and is psychologically projecting that onto the reviewer. This is how 90% of disinformation works now...
  • prophet001 - Wednesday, May 20, 2020 - link

    I'm curious as to why this only has 16 pcie lanes into the CPU. How much does running your high performance SSD through the PCH or running your GPU in x8 mode affect performance?
  • GreenReaper - Wednesday, May 20, 2020 - link

    Conveniently, there is an article (almost) about that: https://www.anandtech.com/show/15720/intel-ghost-c...
  • azfacea - Wednesday, May 20, 2020 - link

    with intel DIY PC marketshare being well below 50% and 10th gen itself having to compete with 9th, 8th, 7th, with supply shortage and everything I doubt these new LGA1200 motherboards can reach 10% of DIY PC which means the

    " ... 44+ entrants ranging from $150 all the way up to $1200 ..."

    are all massive cash burning operations that would never make sense in a million years w/- intel "development funding". they are literally squandering billions of dollars that they took from ripping of the customers. intel is so stupid, gouging its customers like this and then squandering the money for what ?? LGA 1200 has the option to have pcie 4 by the time its irrelevant ? my god WTF is going on there.

Log in

Don't have an account? Sign up now