CPU Performance: Encoding Tests

With the rise of streaming, vlogs, and video content as a whole, encoding and transcoding tests are becoming ever more important. Not only are more home users and gamers needing to convert video files into something more manageable, for streaming or archival purposes, but the servers that manage the output also manage around data and log files with compression and decompression. Our encoding tasks are focused around these important scenarios, with input from the community for the best implementation of real-world testing.

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

For our graphs, some of them have two values: a regular value in orange, and one in red called 'Intel Spec'. ASUS offers the option to 'open up' the power and current limits of the chip, so the CPU is still running at the same frequency but is not throttled. Despite Intel saying that they recommend 'Intel Spec', the system they sent to us to test was actually set up with the power limits opened up, and the results they provided for us to compare to internally also correlated with that setting. As a result, we're providing both sets results for our CPU tests.

Handbrake 1.1.0: Streaming and Archival Video Transcoding

A popular open source tool, Handbrake is the anything-to-anything video conversion software that a number of people use as a reference point. The danger is always on version numbers and optimization, for example the latest versions of the software can take advantage of AVX-512 and OpenCL to accelerate certain types of transcoding and algorithms. The version we use here is a pure CPU play, with common transcoding variations.

We have split Handbrake up into several tests, using a Logitech C920 1080p60 native webcam recording (essentially a streamer recording), and convert them into two types of streaming formats and one for archival. The output settings used are:

  • 720p60 at 6000 kbps constant bit rate, fast setting, high profile
  • 1080p60 at 3500 kbps constant bit rate, faster setting, main profile
  • 1080p60 HEVC at 3500 kbps variable bit rate, fast setting, main profile

Handbrake 1.1.0 - 720p60 x264 6000 kbps FastHandbrake 1.1.0 - 1080p60 x264 3500 kbps FasterHandbrake 1.1.0 - 1080p60 HEVC 3500 kbps Fast

.

7-zip v1805: Popular Open-Source Encoding Engine

Out of our compression/decompression tool tests, 7-zip is the most requested and comes with a built-in benchmark. For our test suite, we’ve pulled the latest version of the software and we run the benchmark from the command line, reporting the compression, decompression, and a combined score.

It is noted in this benchmark that the latest multi-die processors have very bi-modal performance between compression and decompression, performing well in one and badly in the other. There are also discussions around how the Windows Scheduler is implementing every thread. As we get more results, it will be interesting to see how this plays out.

Please note, if you plan to share out the Compression graph, please include the Decompression one. Otherwise you’re only presenting half a picture.

7-Zip 1805 Compression7-Zip 1805 Decompression7-Zip 1805 Combined

.

WinRAR 5.60b3: Archiving Tool

My compression tool of choice is often WinRAR, having been one of the first tools a number of my generation used over two decades ago. The interface has not changed much, although the integration with Windows right click commands is always a plus. It has no in-built test, so we run a compression over a set directory containing over thirty 60-second video files and 2000 small web-based files at a normal compression rate.

WinRAR is variable threaded but also susceptible to caching, so in our test we run it 10 times and take the average of the last five, leaving the test purely for raw CPU compute performance.

WinRAR 5.60b3

.

AES Encryption: File Security

A number of platforms, particularly mobile devices, are now offering encryption by default with file systems in order to protect the contents. Windows based devices have these options as well, often applied by BitLocker or third-party software. In our AES encryption test, we used the discontinued TrueCrypt for its built-in benchmark, which tests several encryption algorithms directly in memory.

The data we take for this test is the combined AES encrypt/decrypt performance, measured in gigabytes per second. The software does use AES commands for processors that offer hardware selection, however not AVX-512.

AES Encoding

.

CPU Performance: Office Tests CPU Performance: Web and Legacy Tests
Comments Locked

136 Comments

View All Comments

  • Icehawk - Thursday, January 31, 2019 - link

    Yup. At the desktop level we have things like Adobe for $1k/seat/yr.

    Our big iron costs an order of magnitude more than these machines (recent orders were $150k ea and were mid-spec HP boxes). In the end most of the costs of a big server are memory and storage (SSDs). The high heat/energy consumption of this setup would be a concern, especially if in a colo.
  • jardows2 - Wednesday, January 30, 2019 - link

    What are you rambling on about? It's a solid performing product, at a much reduced price than Intel's normal markup. I don't get where you come off thinking this is a fanboy post, and you totally missed my point - why is it limited to so few pieces? In Intel's lineup, it's a winner, and there are plenty of people in workstation markets who will only buy systems with Intel CPUs. So for Intel to make a good performing product, at a much lower than normal for Intel price, but only make a couple thousand of them? What's going on over there?
  • edzieba - Thursday, January 31, 2019 - link

    Because this is a cherry-picked part from a low-run die production. Intel don't make many XCC dies, and only a handful will be able to tolerate the high voltages and frequencies of this part across all 28 cores. It's also not going to be a big earner at $3000, that may break even on production but probably a loss overall when you take R&D into account.
  • mapesdhs - Saturday, February 2, 2019 - link

    A movie company I know buys systems in such bulk, a CPU/system like this wouldn't even show up on their radar. They prefer systems they can buy lots of, for multiple sites with a common setup.

    People are arguing here about A vs. B, about the CPU cost, but as many have pointed out it's often the sw cost and availability which determine what a company will purchase. As for workstation use, especially the prosumer market, that has its own set of issues, especially whether a particular app is written well enough to exploit so many cores. Blender is, but Premiere isn't.
  • FMinus - Friday, February 1, 2019 - link

    Or you can get two TR 2970W system and make them work in tandem for what I would think would be almost half the price at this point, considering you can buy this Intel gem only pre-built for probably well bloated prices.
  • SanX - Friday, February 1, 2019 - link

    Intel are killing good at particle movement -- 4x faster then TR2. Till AMD makes AVX512 they are still dead for science
  • ET - Wednesday, January 30, 2019 - link

    I find it amazing how application dependent performance is. Whether a product is a good buy depends so much on precisely what you're going to do with it, down to the application level.

    Still, on the whole, it looks like Intel has little to offer over AMD's much cheaper Threadripper platform.
  • BigMamaInHouse - Wednesday, January 30, 2019 - link

    I think soon we gonna see "Leaks" about new TR64 cores, this "5GHZ 28C" stunt made AMD to release 2990WX instead just 24C 2970WX, now after the Fail attempt by Intel - We gonna see new leaks :-).
  • FMinus - Friday, February 1, 2019 - link

    Considering AMD was attending the same trade show, where Intel announced this 28 core chip and AMD a day later announced the new TR lineup, I'd say AMD planned to release the 2990WX regardless of what Intel had.
  • mapesdhs - Saturday, February 2, 2019 - link

    Yes, but the tinfoil hat industry is strong. :D

Log in

Don't have an account? Sign up now