CPU System Tests

Our first set of tests is our general system tests. These set of tests are meant to emulate more about what people usually do on a system, like opening large files or processing small stacks of data. This is a bit different to our office testing, which uses more industry standard benchmarks, and a few of the benchmarks here are relatively new and different.

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

PDF Opening

First up is a self-penned test using a monstrous PDF we once received in advance of attending an event. While the PDF was only a single page, it had so many high-quality layers embedded it was taking north of 15 seconds to open and to gain control on the mid-range notebook I was using at the time. This put it as a great candidate for our 'let's open an obnoxious PDF' test. Here we use Adobe Reader DC, and disable all the update functionality within. The benchmark sets the screen to 1080p, opens the PDF to in fit-to-screen mode, and measures the time from sending the command to open the PDF until it is fully displayed and the user can take control of the software again. The test is repeated ten times, and the average time taken. Results are in milliseconds.

System: PDF Opening with Adobe Reader DC

This opening test is single threaded, so the high-frequency Intel parts get a clear win. There's not much between the Threadripper CPUs here.

FCAT Processing: link

One of the more interesting workloads that has crossed our desks in recent quarters is FCAT - the tool we use to measure and visually analyze stuttering in gaming due to dropped or runt frames. The FCAT process requires enabling a color-based overlay onto a game, recording the gameplay, and then parsing the video file through the analysis software. The software is mostly single-threaded, however because the video is basically in a raw format, the file size is large and requires moving a lot of data around. For our test, we take a 90-second clip of the Rise of the Tomb Raider benchmark running on a GTX 980 Ti at 1440p, which comes in around 21 GB, and measure the time it takes to process through the visual analysis tool.

System: FCAT Processing ROTR 1440p GTX980Ti Data

Similar to PDF opening, single threaded performance wins out.

Dolphin Benchmark: link

Many emulators are often bound by single thread CPU performance, and general reports tended to suggest that Haswell provided a significant boost to emulator performance. This benchmark runs a Wii program that ray traces a complex 3D scene inside the Dolphin Wii emulator. Performance on this benchmark is a good proxy of the speed of Dolphin CPU emulation, which is an intensive single core task using most aspects of a CPU. Results are given in minutes, where the Wii itself scores 17.53 minutes.

System: Dolphin 5.0 Render Test

Dolphin likes single thread performance as well, although having some cores to back it up seems to be required. 

3D Movement Algorithm Test v2.1: link

This is the latest version of the self-penned 3DPM benchmark. The goal of 3DPM is to simulate semi-optimized scientific algorithms taken directly from my doctorate thesis. Version 2.1 improves over 2.0 by passing the main particle structs by reference rather than by value, and decreasing the amount of double->float->double recasts the compiler was adding in. It affords a ~25% speed-up over v2.0, which means new data.

System: 3D Particle Movement v2.1

Our first pure multithreaded test, and the 1950X wins with 32 threads. The 1920X beats the 1950X in SMT-off mode, due to 24 threads beating 16 threads.

DigiCortex v1.20: link

Despite being a couple of years old, the DigiCortex software is a pet project for the visualization of neuron and synapse activity 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. The results on the output are given as a fraction of whether the system can simulate in real-time, so anything above a value of one is suitable for real-time work. The benchmark offers a 'no firing synapse' mode, which in essence detects DRAM and bus speed, however we take the firing mode which adds CPU work with every firing.

System: DigiCortex 1.20 (32k Neuron, 1.8B Synapse)

DigiCortex requires a mash of CPU frequency and DRAM performance to get a good result, and anything with quad-channel memory is usually preferred. The 1950X in SMT-off mode wins here due to its low main memory latency combined with having 16 threads to access it. The Broadwell-E is the nearest competitor, over Skylake-X, most likely due to the mesh vs ring topology. The 1950X in Creator mode scores way down the field however, lower than the standard Ryzen chips, showing that under a unified memory architecture there can be significant performance drops. The 1920X failed in this test for an unknown reason.

Agisoft Photoscan 1.0: link

Photoscan stays in our benchmark suite from the previous version, however now we are running on Windows 10 so features such as Speed Shift on the latest processors come into play. The concept of Photoscan is translating many 2D images into a 3D model - so the more detailed the images, and the more you have, the better the model. The algorithm has four stages, some single threaded and some multi-threaded, along with some cache/memory dependency in there as well. For some of the more variable threaded workload, features such as Speed Shift and XFR will be able to take advantage of CPU stalls or downtime, giving sizeable speedups on newer microarchitectures.

System: Agisoft Photoscan 1.0 Total Time

The variable threaded nature of Agisoft shows that in our workflow, it's a mix of cores, IPC and frequency required to win. AMD takes a back seat here, likely due to its AVX implementation.

The 2017 Benchmark Suite Benchmarking Performance: CPU Rendering Tests
Comments Locked

347 Comments

View All Comments

  • Zoeff - Thursday, August 10, 2017 - link

    Yeeeees! Thanks for the review! I was hoping there'd be an embargo lift at this hour. :D
  • Zingam - Sunday, August 13, 2017 - link

    The best CPUs for MineSweeper in 2017 in a single article!!!!
  • NikosD - Monday, August 14, 2017 - link

    Anandtech is simply wrong regarding Game mode or "Legacy Compatibility Mode" as you prefer to call it and make jokes about it.

    It seems that you don't know what ALL other reviewers say that Game mode doesn't set SMT off, but it disables one die.

    So, Threadripper doesn't become a 16C/16T CPU after enabling Game mode as you say, but a 8C/16T CPU like ALL other reviewers say.

    Go read Tom's Hardware which says that Game mode executes "bcdedit /set numproc XX" in order to cut 8 cores and shrink the CPU to one die (8C/16T) but because that's a software restriction the memory and PCIe controller of the second die is still alive, giving Quad Channel memory support and full 60+4 PCIe lanes even in Game mode.

    And you thought you are smart and funny regarding your Game mode comments...
  • monglerbongler - Tuesday, July 10, 2018 - link

    real renderers buy epyc or xeon. Either they have the money because its corporate money, they have the money because it comes from plebs paying someone comission/subscription money, or they have the money because they are plebs buying pre-built workstations.
  • craptasticlemon - Wednesday, September 13, 2017 - link

    Here's the real Threadripper review:
    AMD thrashes Intel i9 in every possible way, smushes it's puny ass into the dirt, and dances on the grave for the coup de gras. It is very entertaining to watch the paid Intel lackeys here try to paper over what is clearly a superior product. Keep up with the gaming scores guys, like anyone is buying this for gaming. I for one am looking forward to those delicious 40% faster render times, for the same price as the Intel space heater.
  • alysdexia - Thursday, April 18, 2019 - link

    its, shit-head
    swifter
  • Dr. Swag - Thursday, August 10, 2017 - link

    In paragraph two you say Ryzen 3 has double the threads of i3, I think you mean to say double the cores :)
  • IanHagen - Thursday, August 10, 2017 - link

    Not trying to nitpick or imply anything but... There is a logical reason for Threadripper getting five pages of gaming performance review and Skylake-X not even appearing on the charts more than a month after it was reviewed?
  • Ian Cutress - Thursday, August 10, 2017 - link

    Bottom of page one.
  • IanHagen - Thursday, August 10, 2017 - link

    With all due respect Mr. Cutress, "circumstances beyond our control" and "odd BIOS/firmware gaming results" didn't prevent anyone from bashing Ryzen for its gaming performance on its debut.

Log in

Don't have an account? Sign up now