CPU Performance: System Tests

Our System Test section focuses significantly on real-world testing, user experience, with a slight nod to throughput. In this section we cover application loading time, image processing, simple scientific physics, emulation, neural simulation, optimized compute, and 3D model development, with a combination of readily available and custom software. For some of these tests, the bigger suites such as PCMark do cover them (we publish those values in our office section), although multiple perspectives is always beneficial. In all our tests we will explain in-depth what is being tested, and how we are testing.

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

Application Load: GIMP 2.10.4

One of the most important aspects about user experience and workflow is how fast does a system respond. A good test of this is to see how long it takes for an application to load. Most applications these days, when on an SSD, load fairly instantly, however some office tools require asset pre-loading before being available. Most operating systems employ caching as well, so when certain software is loaded repeatedly (web browser, office tools), then can be initialized much quicker.

In our last suite, we tested how long it took to load a large PDF in Adobe Acrobat. Unfortunately this test was a nightmare to program for, and didn’t transfer over to Win10 RS3 easily. In the meantime we discovered an application that can automate this test, and we put it up against GIMP, a popular free open-source online photo editing tool, and the major alternative to Adobe Photoshop. We set it to load a large 50MB design template, and perform the load 10 times with 10 seconds in-between each. Due to caching, the first 3-5 results are often slower than the rest, and time to cache can be inconsistent, we take the average of the last five results to show CPU processing on cached loading.

AppTimer: GIMP 2.10.4

As a raw single threaded test, we see Intel's high 5.0 GHz CPUs near the top. The Ryzen 3700X and Ryzen 3900X beats the 3950X here by small margins, perhaps due to memory traffic or the complexity of dealing with more cores in the system. However the Ryzen 9 3950X sails past Intel's HEDT chips.

3D Particle Movement v2.1: Brownian Motion

Our 3DPM test is a custom built benchmark designed to simulate six different particle movement algorithms of points in a 3D space. The algorithms were developed as part of my PhD., and while ultimately perform best on a GPU, provide a good idea on how instruction streams are interpreted by different microarchitectures.

A key part of the algorithms is the random number generation – we use relatively fast generation which ends up implementing dependency chains in the code. The upgrade over the naïve first version of this code solved for false sharing in the caches, a major bottleneck. We are also looking at AVX2 and AVX512 versions of this benchmark for future reviews.

For this test, we run a stock particle set over the six algorithms for 20 seconds apiece, with 10 second pauses, and report the total rate of particle movement, in millions of operations (movements) per second. We have a non-AVX version and an AVX version, with the latter implementing AVX512 and AVX2 where possible.

3DPM v2.1 can be downloaded from our server: 3DPMv2.1.rar (13.0 MB)

3D Particle Movement v2.1

For some simple math without AVX acceleration, the 3950X piles on the core performance and IPC to give our best results, above and beyond what the Core i9-9980XE can provide for less power at under half the cost.

3D Particle Movement v2.1 (with AVX)

However, this is one benchmark where ratcheting in AVX2 and AVX512 really helps. There's no escaping the Intel HEDT family here, but on AVX2 mode AMD wins the best of the rest.

Dolphin 5.0: Console Emulation

One of the popular requested tests in our suite is to do with console emulation. Being able to pick up a game from an older system and run it as expected depends on the overhead of the emulator: it takes a significantly more powerful x86 system to be able to accurately emulate an older non-x86 console, especially if code for that console was made to abuse certain physical bugs in the hardware.

For our test, we use the popular Dolphin emulation software, and run a compute project through it to determine how close to a standard console system our processors can emulate. In this test, a Nintendo Wii would take around 1050 seconds.

The latest version of Dolphin can be downloaded from https://dolphin-emu.org/

Dolphin 5.0 Render Test

Dolphin is another ST test, and Intel's 4.7+ GHz family are ahead of AMD here. The 3700X is a smidgen ahead of the 3950X, perhaps due to having only one chiplet rather than two.

DigiCortex 1.20: Sea Slug Brain Simulation

This benchmark was originally designed for simulation and visualization of neuron and synapse activity, as is commonly found in the brain. The software comes with a variety of benchmark modes, and we take the small benchmark which runs a 32k neuron / 1.8B synapse simulation, equivalent to a Sea Slug.

Example of a 2.1B neuron simulation

We report the results as the ability to simulate the data as a fraction of real-time, so anything above a ‘one’ is suitable for real-time work. Out of the two modes, a ‘non-firing’ mode which is DRAM heavy and a ‘firing’ mode which has CPU work, we choose the latter. Despite this, the benchmark is still affected by DRAM speed a fair amount.

DigiCortex can be downloaded from http://www.digicortex.net/

DigiCortex 1.20 (32k Neuron, 1.8B Synapse)

DigiCortex likes memory channels, and so Intel's HEDT chips win here. Again we see the 3700X beating the 3950X, likely due to the available bandwidth per core being higher and more cores not making much of a difference in performance.

y-Cruncher v0.7.6: Microarchitecture Optimized Compute

I’ve known about y-Cruncher for a while, as a tool to help compute various mathematical constants, but it wasn’t until I began talking with its developer, Alex Yee, a researcher from NWU and now software optimization developer, that I realized that he has optimized the software like crazy to get the best performance. Naturally, any simulation that can take 20+ days can benefit from a 1% performance increase! Alex started y-cruncher as a high-school project, but it is now at a state where Alex is keeping it up to date to take advantage of the latest instruction sets before they are even made available in hardware.

For our test we run y-cruncher v0.7.6 through all the different optimized variants of the binary, single threaded and multi-threaded, including the AVX-512 optimized binaries. The test is to calculate 250m digits of Pi, and we use the single threaded and multi-threaded versions of this test.

Users can download y-cruncher from Alex’s website: http://www.numberworld.org/y-cruncher/

y-Cruncher 0.7.6 Single Thread, 250m Digitsy-Cruncher 0.7.6 Multi-Thread, 250m Digits

y-Cruncher is another piece of software that can use AVX-512, but AMD still comes very close. For single threadeded AVX2, the 5.0 GHz CPUs from Intel have a small lead, but in multi-threaded AVX2 the 16-cores with Zen 2 allow AMD to power through Intel's maintream offerings by 25%.

Agisoft Photoscan 1.3.3: 2D Image to 3D Model Conversion

One of the ISVs that we have worked with for a number of years is Agisoft, who develop software called PhotoScan that transforms a number of 2D images into a 3D model. This is an important tool in model development and archiving, and relies on a number of single threaded and multi-threaded algorithms to go from one side of the computation to the other.

In our test, we take v1.3.3 of the software with a good sized data set of 84 x 18 megapixel photos and push it through a reasonably fast variant of the algorithms, but is still more stringent than our 2017 test. We report the total time to complete the process.

Agisoft’s Photoscan website can be found here: http://www.agisoft.com/

Agisoft Photoscan 1.3.3, Complex Test

This variable threaded workload shows the power of AMD's 16 Zen 2 cores at a high frequency. Despite 5.0 GHz all-core turbo being on the 9900K, only having 8 cores lets it down here. Intel's HEDT line of processors just don't have the per-core performance to keep up.

Test Bed and Setup CPU Performance: Rendering Tests
Comments Locked


View All Comments

  • Netmsm - Saturday, November 16, 2019 - link

    Also, in section "x264 HD 3.0: Older Transcode Test" the result of "3DPM v1 Multi-Threaded" is mistakenly placed instead of "x264 HD 3.0 Pass 2".
  • The_Assimilator - Thursday, November 14, 2019 - link

    "I’m sure some people will disagree about those 50 MHz"

    We call those people "whiny bitches who should STFU".
  • nathanddrews - Thursday, November 14, 2019 - link

    In a world of such precision and technical pedants, you have to admit that it is false advertising to say 4.7GHz, when it is 50MHz shy. Rounded up, it's OK, but it's only 1% shady.

    For my use case, this sentence nails it perfectly: "the Core i9-9900KS is still running at 5.0 GHz for sustained single threaded work, which is still 7-15% higher than the Ryzen 3950X, and as a result it does pull out ahead in a number of ST tests as well as in low resolution (CPU-bound) gaming". Most of the games I play are not current-gen visual spectacles, but rather twitch and competitive games that are a few years old. My priority is the highest possible frame rates for high refresh gaming. I'm not sure that I do enough video editing to justify Ryzen, as tempting as the rest of the package is.
  • Cooe - Thursday, November 14, 2019 - link

    Most every other review I've seen has it hitting the full 4.7GHz, with many even going beyond into the 4.75GHz range when adequate cooling is used. The silicon binning quality of the 3950X seems to be absolutely freaking insane. Meethinks this -50MHz deficit is unique to something specific to Ian's setup here.
  • RSAUser - Thursday, November 14, 2019 - link

    Gamersnexus also seems to have gotten a bit of a dud. LTT seems to have gotten a good one.
  • Cooe - Thursday, November 14, 2019 - link

    Not just Linus, most people have gotten "good ones". I can count the number reviews with chips that didn't reach the advertised 4.7GHz on one hand & have fingers left over to spare (and if I include all those within 50ishMHz or so, like Ian's here, it drops to just one).
  • zmatt - Thursday, November 14, 2019 - link

    Every cpu I have ever owned has always been a percent or so off the advertised frequency either above or below. The number on the box is really just an average and always has been.
  • uefi - Thursday, November 14, 2019 - link

    Don't forget, Intel has their share of the occasional performance shaving microcode patches every year or so.
  • eek2121 - Thursday, November 14, 2019 - link

    I walked away with a very different picture. Right now Anandtech is clearly GPU bound in the benchmarks. They are benchmarking on a GTX 1080, and the results clearly reflect that. Having run some of these games on a 1080ti on my stock 1950X, I get a better result. They really need a 2080ti or 2080 super at this point.
  • plonk420 - Thursday, November 14, 2019 - link

    they can't really use a 1080Ti or better with GTA5... check out GN's coverage: if you hit over ~180fps, you hit a cap that results in insane stuttering (same with RDR2 and 144hz or so)

Log in

Don't have an account? Sign up now