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

A small bump in the result here because of the added core frequency.

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)

For the compile test, the 9980XE brings the 18-core up to being more competitive, however this test does seem to prefer fewer cores, lower crosstalk, and higher frequencies. AMD's 16-core TR2 wins here, adding 20% perf over the 9980XE for under half the cost.

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

The newer engines can take advantage of the higher core count parts, and Intel's unified memory design also helps here.

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

HEDT Performance: System Tests HEDT Performance: Web and Legacy Tests
Comments Locked

143 Comments

View All Comments

  • Cellar Door - Tuesday, November 13, 2018 - link

    The best part is that an i7 part(9800X) is more expensive then a i9 part(9900k). Intel smoking some good stuff.
  • DigitalFreak - Tuesday, November 13, 2018 - link

    You're paying more for those extra 28 PCI-E lanes
  • Hixbot - Tuesday, November 13, 2018 - link

    And much more L3. It's also interesting that HEDT is no longer behind in process node.
  • Hixbot - Tuesday, November 13, 2018 - link

    And AVX512
  • eastcoast_pete - Tuesday, November 13, 2018 - link

    @Ian: Thanks, good overview and review!
    Agree on the "iteration when an evolutionary upgrade was needed"; it seems that Intel's development was a lot more affected by its blocked/constipated transition to 10 nm (now scrapped), and the company's attention was also diverted by its forays into mobile (didn't work out so great) and looking for progress elsewhere (Altera acquisition). This current "upgrade" is mainly good for extra PCI-e lanes (nice to have more), but it's performance is no better than the previous generation. If the new generation chips from AMD are halfway as good as they promise, Intel will loose a lot more profitable ground in the server and HEDT space to AMD.
    @Ian, and all: While Intel goes on about their improved FinFet 14 nm being the reason for better performance/Wh, I wonder how big the influence of better heat removal through the (finally again) soldered heat spreader is? Yes, most of us like to improve cooling to be able to overclock more aggressively, but shouldn't better cooling also improve the overall efficiency of the processor? After all, semiconductors conduct more current as they get hotter, leading to ever more heat and eventual "gate crashing". Have you or anybody else looked at performance/Wh between, for example, an i7 8700 with stock cooler and pasty glued heat spreader vs. the same processor with proper delidding, liquid metal replacement and a great aftermarket cooler, both at stock frequencies? I'd expect the better cooled setup to have more performance/Wh, but is that the case?
  • Arbie - Tuesday, November 13, 2018 - link

    The "Competition" chart is already ghastly for Intel. Imagine how much worse it will be when AMD moves to 7 nm with Zen 2.
  • zepi - Tuesday, November 13, 2018 - link

    How about including some kind of DB test?

    I think quite a few people are looking at these workstation class CPU's to develop BI things and it might quite helpful to actually measure results with some SQL / NoSQL / BI-suites. Assuming bit more complex parallel SQL executions with locking could show some interesting differences between NUMA-Threadrippers and Intels.
  • GreenReaper - Wednesday, November 14, 2018 - link

    It's a good idea, Phoronix does them so in the short term you could probably look there.
  • jospoortvliet - Friday, November 16, 2018 - link

    But then make sure it is realistic, not running in cache or such... A real db suitable for these chips is terabytes, merely keeping the index in ram... rule of thumb: if your index fits in cache your database doesn't need this CPU ;-)
  • FunBunny2 - Tuesday, November 13, 2018 - link

    I guess I can run my weather simulation in Excel on my personal machine now. neato.

Log in

Don't have an account? Sign up now