Benchmarking Performance: CPU Office Tests

The office programs we use for benchmarking aren't specific programs per-se, but industry standard tests that hold weight with professionals. The goal of these tests is to use an array of software and techniques that a typical office user might encounter, such as video conferencing, document editing, architectural modelling, and so on and so forth.

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

Chromium Compile (v56)

Our new compilation test uses Windows 10 Pro, VS Community 2015.3 with the Win10 SDK to combile a nightly build of Chromium. We've fixed the test for a build in late March 2017, and we run a fresh full compile in our test. Compilation is the typical example given of a variable threaded workload - some of the compile and linking is linear, whereas other parts are multithreaded.

Office: Chromium Compile (v56)

Our compile test has an eclectic mix of requirements, with different segments having different bottlenecks. The Ryzen 5 2400G matches the higher frequency of the Core i3-8350K, even though it already has a core and memory advantage. An interesting thing here is that the Ryzen 3 2200G and the Ryzen 5 1400 are almost evenly matched, even though the 1400 has double the threads. This is because of the frequency of the 2200G, and the memory speed.

PCMark 10

PCMark 10 is the latest all-in-one office-related performance tool that combines a number of tests for low-to-mid office workloads, including some gaming, but focusing on aspects like document manipulation, response, and video conferencing.

Office: PCMark10 Extended Score (Overall)

Office: PCMark10-1 Essential Set Score

Office: PCMark10-2 Productivity Set Score

Office: PCMark10-3 Creation Set Score

Office: PCMark10-4 Physics Score

PCMark8: link

Despite originally coming out in 2008/2009, Futuremark has maintained PCMark8 to remain relevant in 2017. On the scale of complicated tasks, PCMark focuses more on the low-to-mid range of professional workloads, making it a good indicator for what people consider 'office' work. We run the benchmark from the commandline in 'conventional' mode, meaning C++ over OpenCL, to remove the graphics card from the equation and focus purely on the CPU. PCMark8 offers Home, Work and Creative workloads, with some software tests shared and others unique to each benchmark set.

Office: PCMark8 Creative (non-OpenCL)

Office: PCMark8 Home (non-OpenCL)

Office: PCMark8 Work (non-OpenCL)

 

Benchmarking Performance: CPU Encoding Tests Benchmarking Performance: CPU Legacy Tests
Comments Locked

177 Comments

View All Comments

  • HStewart - Monday, February 12, 2018 - link

    I don't get the idea of desktops except if you want ultimate gaming PC - go with High End CPU a long with High End GPU. Otherwise go mobile. You can pretty much go that route unless you desired extreme top end performance

    If you primary into game get a Xbox One X or S and HDTV are cheap or PS 4,

    But lower end desktop PC - I see no need them for now. Times have changed
  • Lolimaster - Monday, February 12, 2018 - link

    If you wanna upgrade a laptop, be prepared for a bunch of cabling.

    Have 3-4 drives on mobile?
    Dedicated capture/sound card?
    Keep your thermals in check?
    Upgrade your cpu/apu whenever you like?
  • mikato - Saturday, February 17, 2018 - link

    To me laptops are annoying, and only convenient for basic tasks with their mobility. Otherwise they are slow, have a small screen, often don’t a have mouse, and no number pad on keyboard. As a result, typing is slower, pointing is slower, app speed is slower, and gaming performance is worse. With the smaller screen, juggling things, dragging files, etc is more difficult. I just can’t get stuff done as well on a laptop as a desktop.
  • oldschool_75 - Monday, February 12, 2018 - link

    Why do the Intel systems have 32 gigs of ram while the AMD systems only have 16?

    Also bulldozer was not 2 cores 4 threads, it was two modules with two cores sharing the modules so 4 cores.
  • Lolimaster - Monday, February 12, 2018 - link

    Why use 2933 memory?

    As far as i know AMD send 3200 CL14 Flare X to pretty much everyone for the sake of testing the gpu at 3200 CL14 !!!!
  • jjj - Monday, February 12, 2018 - link

    They use the frequencies officially supported , anything above that is OC and would fall into the OC section. It's debatable how right or wrong that is but that's what AT does.
  • Lolimaster - Monday, February 12, 2018 - link

    Guru3d got the reviewer's kit with 3200 cl14 flare-x as 100% of the techtoubers too.
  • ScottSoapbox - Monday, February 12, 2018 - link

    The number of typos in the first two sentences was enough for me to stop reading.
  • Lolimaster - Monday, February 12, 2018 - link

    The avrg l3 latency for non-APU multiple CCX Ryzen's was around 11-12ns, on the single CCX APU is aroun 9.5ns.

    Memory latency Ryzen
    91ns DDR4 2400
    77ns DDR4 3200

    2400G
    66ns DDR4 3200
  • Macpoedel - Monday, February 12, 2018 - link

    Good to see you started testing CPU's with maximum supported RAM speed instead of JEDEC frequency. These APU's would have really suffered if tested with 2133MHz DDR4 RAM.

Log in

Don't have an account? Sign up now