HEDT Performance: Office Tests

The Office test suite is designed to focus around more industry standard tests that focus on office workflows, system meetings, some synthetics, but we also bundle compiler performance in with this section. For users that have to evaluate hardware in general, these are usually the benchmarks that most consider.

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

PCMark 10: Industry Standard System Profiler

Futuremark, now known as UL, has developed benchmarks that have become industry standards for around two decades. The latest complete system test suite is PCMark 10, upgrading over PCMark 8 with updated tests and more OpenCL invested into use cases such as video streaming.

PCMark splits its scores into about 14 different areas, including application startup, web, spreadsheets, photo editing, rendering, video conferencing, and physics. We post all of these numbers in our benchmark database, Bench, however the key metric for the review is the overall score.

PCMark10 Extended Score

PCMark seems to be around standard for almost every processor, except the 9900K where the 5.0 GHz really pushes the performance.

Chromium Compile: Windows VC++ Compile of Chrome 56

A large number of AnandTech readers are software engineers, looking at how the hardware they use performs. While compiling a Linux kernel is ‘standard’ for the reviewers who often compile, our test is a little more varied – we are using the windows instructions to compile Chrome, specifically a Chrome 56 build from March 2017, as that was when we built the test. Google quite handily gives instructions on how to compile with Windows, along with a 400k file download for the repo.

In our test, using Google’s instructions, we use the MSVC compiler and ninja developer tools to manage the compile. As you may expect, the benchmark is variably threaded, with a mix of DRAM requirements that benefit from faster caches. Data procured in our test is the time taken for the compile, which we convert into compiles per day.

Compile Chromium (Rate)

Our compile test is a healthy mix of a variable threaded workload, and we can see that the 2950X and the 9900K are the best performers here. However the 2920X, at $649, or the 2700X, are the best bang-for-buck performers here.

3DMark Physics: In-Game Physics Compute

Alongside PCMark is 3DMark, Futuremark’s (UL’s) gaming test suite. Each gaming tests consists of one or two GPU heavy scenes, along with a physics test that is indicative of when the test was written and the platform it is aimed at. The main overriding tests, in order of complexity, are Ice Storm, Cloud Gate, Sky Diver, Fire Strike, and Time Spy.

Some of the subtests offer variants, such as Ice Storm Unlimited, which is aimed at mobile platforms with an off-screen rendering, or Fire Strike Ultra which is aimed at high-end 4K systems with lots of the added features turned on. Time Spy also currently has an AVX-512 mode (which we may be using in the future).

For our tests, we report in Bench the results from every physics test, but for the sake of the review we keep it to the most demanding of each scene: Cloud Gate, Sky Diver, Fire Strike Ultra, and Time Spy.

3DMark Physics - Cloud Gate3DMark Physics - Sky Diver3DMark Physics - Fire Strike Ultra3DMark Physics - Time Spy

Graphics engines still have trouble scaling up the cores, even with the latest models, due to a lack of proper memory bandwidth. The large TR2 chips don't have the right balance of cores to memory to be able to compete.

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 Overall
Geekbench 4 - MT Overall

HEDT Performance: Rendering Tests HEDT Performance: Encoding Tests
Comments Locked

69 Comments

View All Comments

  • lilmoe - Monday, October 29, 2018 - link

    Instead of all the 10+ pages of gaming benchmarks and client side javascript for a platform that most probably won't be used solely for gaming or casual content works, wouldn't it be better to have a suit of server side based benchmarks that are more server oriented? These platforms are becoming very attractive for development and testing of server side applications:

    - gzip
    - pdf conversion
    - database transactions
    - modern web services
    - node.js
    etc, etc...

    I really see no real value in gaming benchmarks. Not for this platform.
  • mapesdhs - Monday, October 29, 2018 - link

    You might not see the value, but your desire does not reflect that of others, and there's no harm in the data points. You're right though that server side testing would be good, but is this site really the right place for that kind of testing? And from what I've read in the past it can be rather more complicated to run those kinds of tests. AT has a wide audience; they have to think more broadly about to whom they can or should appeal.

    Howeverm you're wrong in one regard, the cost of the 12-core inparticular to me looks like a rather nice alternative for those wanting decent gaming performance at 1440p or higher, but also good productivity potential. Given its cost, seems like an ideal streaming/gaming/productivity all-rounder to me.
  • DominionSeraph - Monday, October 29, 2018 - link

    i9 9900k would be a better choice. It splits the heavily multithreaded benchmarks with the 12 core, is $160 cheaper for the CPU, and doesn't require a $400 motherboard.
  • eva02langley - Tuesday, October 30, 2018 - link

    Techspot takes.

    ''We didn’t have time to retest the Core i9-7900X, but I can assure you with the data we have on hand the 2920X also dominates that part as well, mostly because the 10-core Intel CPU costs over 40% more. That just leaves the 9900K, and honestly, if productivity tasks are the focus then we believe the 2920X is the smarter buy. It will end up costing a little more overall but for applications that utilize the 12-core Threadripper CPU well, a heavily overclocked 9900K will melt trying to keep up.''
  • TheinsanegamerN - Tuesday, October 30, 2018 - link

    The i9 9900k would spend its time melting down under water cooling attempting to keep up, while costing more after the cooling solution then threadripper costs.
  • Icehawk - Monday, October 29, 2018 - link

    Please provide your full Handbrake settings (IMO it should be linked in the article), you get about 3x faster encoding than I do at “Fast, Main, 3500kbs”. I’d love to triple my throughput.
  • mapesdhs - Monday, October 29, 2018 - link

    It's amazing how some options in Handbrake can cut performane in half. I've been meddling with it a lot today, certain filters can really slow things down.
  • rony_ph - Monday, October 29, 2018 - link

    Hello,

    With all these threadripper tests, how come we never see any reference or use case scenarios for Virtualization. Those CPUs with with this amount of cores, can easily be used to host multiple VMs, etc... yet all the testing is mainly on Office Apps, Gaming and 3D but never on virtualization and the advantage of having such a CPU would do for these scenarios... I'm certain that there are tons of people using those chips to run VMware & Hyper-V, etc...
  • schujj07 - Monday, October 29, 2018 - link

    You wouldn't use these for VMware or Hyper-V to run mission critical VMs. You might use VMware Workstation with them to run Sandbox systems.
  • rony_ph - Monday, October 29, 2018 - link

    Never mentioned mission critical systems. As hone or power user. A cpu like 2990w or 2970w will easily let you have 60+ vms running in parallel to do your own testing and lab environment. While buying an equivalent from intel for same price range (not talking about Xeon) wont let u make half as much VMs. You can even probably run an azure stack on it for testing purposes. So the use of such a CPU is huge for an IT Pro for instance.

Log in

Don't have an account? Sign up now