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

  • peevee - Monday, October 29, 2018 - link

    You don't have real workstation tests except for Chromium compile, and even that is apparently broken (for example, no /Gm on the projects or something like that).
  • Schmich - Monday, October 29, 2018 - link

    Your ads are one of the worst of tech blogs. Distracting ads with moving items. Dynamic resizing of the slow loading header ads, so by the time you want to click on something you've clicked on something else. Autoplaying videos that follow you down as you read the article. No wonder people install adblock but strangely blogs call the readers a problem.
  • peevee - Wednesday, October 31, 2018 - link

    Somebody reading anandtech who does not use adblocking?
    I am genuineley shocked.

    And it's not a blog.
  • firestream - Monday, October 29, 2018 - link

    Can someone test the those in-memory business application like Qlikview? It should be very interesting whether TR2 can replace the developer machine who are crunching large amount of dataset to build dashboard or analytic.
  • crotach - Tuesday, October 30, 2018 - link

    Damn, this i9-9900k is a beast! It even looks like good value for money when compared like this.
  • SanX - Wednesday, October 31, 2018 - link

    What the problem with AMD AVX or test's AVX?
  • GreenReaper - Wednesday, October 31, 2018 - link

    AMD's AVX units are limited due to the Zen architecture. Basically, they cut stuff down into 128-bit chunks but only certain modules can do certain things. AVX2 requires work over two instructions. And it can't do AVX-512 yet. This might well have been the appropriate decision - after all, wider units means more to go wrong, and more power. But it limits performance on AVX workloads.
  • Henk Poley - Saturday, November 10, 2018 - link

    I wonder when they'll include a few high performance cores for single core heavy tasks. Kinda ridiculous that an iPad Pro / iPhone XR can get +33 to +50% better performance on Speedometer 2.0
  • Henk Poley - Saturday, November 10, 2018 - link

    It could be cool to throw in a 4-core Intel Core i7-7740X, which appears to be fairly efficient in multicore performance. I wouldn't be surprised if it held up decently at the bottom spot, but using much less cores.

Log in

Don't have an account? Sign up now