System Performance

Moving on from SPEC to some of our more traditional laptop tests, I’ve taken the opportunity to add some new tests to the suite, which we’ll include on all laptops going forward. While SPEC is a fantastic set of tests to probe the limits of a platform, not everyone is going to run a workload that runs at nearly 100% CPU utilization for such a long time on a laptop. The 8-Thread tests took 4.5 hours to complete on Ice Lake, and 6.5 hours to complete on Picasso, which is likely not something most people would turn to a thin and light laptop for, so it’s important to see how both platforms perform on shorter tests where they can leverage their peak boost frequencies for a higher percentage of the duration.

PCMark 10

PCMark 10 - Essentials

PCMark 10 - Productivity

PCMark 10 - Digital Content Creation

PCMark 10 - Overall

PCMark 10 consists of several real-world tests, including web, video conferencing, spreadsheets, writing, and more. There are several GPU tests as well, including rendering, and some gaming. The suite also measures application start-up, and all aspects of the system’s performance factor into the score.

Intel’s CPU performance lead shows clearly here again, with significant leads in both the Essentials and Productivity tests, although AMD’s strong GPU pulls the Ryzen system very close on the Digital Content Creation tasks. But that is not enough to turn the tide, and the Ice Lake platform carries this win.

Cinebench R20

Cinebench R20 - Single-Threaded Benchmark

Cinebench R20 - Multi-Threaded Benchmark

Looking at the latest version of Cinebench tells a similar story as to what we’ve seen so far. Ice Lake’s significant IPC lead pulls it way ahead. On the multi-threaded test, the AMD platform does close the gap somewhat, which is similar to the SPEC rate 8 results.

7-Zip

7-Zip Compression

7-Zip Decompression

Checking out the popular 7-Zip file compression tool, the results are in-line with what we see in the desktop space. Intel generally has a lead on the compression side, but AMD claws back at decompression. It is a rare win on the CPU side for AMD here.

Handbrake

Handbrake Transcoding (Software)

Transcoding is a popular task, and Handbrake is one of the most popular tools. For this test, a 1080p movie is converted to 720p using the x264 encoder. Once again, Ice Lake offers significantly more performance when transcoding in software.

Handbrake Transcoding (Hardware)

Handbrake also supports various hardware encoders, such as Intel’s QuickSync, which provides significantly quicker transcodes at the same settings – albeit at larger file sizes and slightly lower quality compared to the software transcode, according to the Handbrake documentation. QuickSync has been very popular, and has been around quite a while. AMD also offers hardware encoding and decoding with their Video Core Next platform. Handbrake does support AMD’s Video Coding Engine (VCE) but the Surface Laptop 3 does not offer this as an option in Handbrake, so it was not able to be tested. As this is the only current Ryzen mobile APU we’ve tested, it may be a driver issue specific to the Surface branded processor.

x264

x264 HD 5.x

x264 HD 5.x

Our previous transcoding test, x264, was also run. Here we see that once again Ice Lake has a significant performance advantage, as it did with Handbrake software encoding.

Web Tests

All of our web tests were run with the current version of Microsoft Edge in Windows 10 1909. Web results are highly impacted by the underlying scripting engine, and Microsoft is going to be moving Edge from the EdgeHTML rendering engine to the Chromium open-source project that powers Google Chrome. When they make this change, expected early in 2020, we’ll revamp our suite with new tests.

Mozilla Kraken 1.1

Google Octane 2.0

WebXPRT 3

Intel has aggressively pushed their frequency ramping with Speed Shift, and one of the biggest beneficiaries of Speed Shift is web scripting, since the tasks tend to be very short. AMD is addressing this in Zen 2 with Collaborative Power Performance Control 2, or CPPC2, which is not as elegant of a name as Speed Shift, but promises to drop Zen’s frequency ramping from ~30 ms to ~1 to 2 ms, and will be a welcome addition on our web tests.

SPEC2017 - ST & MT Performance GPU Performance - Vega vs Iris
POST A COMMENT

174 Comments

View All Comments

  • Zoolook - Saturday, December 21, 2019 - link

    @RSAUser I think you nailed it, it's better for their bottom line to dedicate 7nm chips to products with higher margins. Reply
  • shabby - Friday, December 13, 2019 - link

    What is amd waiting for with zen 2 for mobile? Are they prioritizing desktop and server chips first or is there a lack of capacity at tsmc with everyone hogging the 7nm process? Reply
  • RBD117 - Friday, December 13, 2019 - link

    I think it's a mix of everything. Renoir is being worked on actively but AMD doesnt have enough resources to do all of Ryzen AM4, EPYC, and Ryzen Mobile at the same time. The desktop and server chips were prioritized first as those have clear wins over Intel solutions. Mobile however requires a lot more work with battery life and performance optimization. And yeah, we already see chip production issues with Ryzen 16 and 12-core as it is with most of the chips going to EPYC so Zen2 mobile would just add more capacity issues. Reply
  • Targon - Friday, December 13, 2019 - link

    AMD should be releasing the Zen2 laptop chips at or around CES 2020(in another three weeks). Microsoft was probably preparing the Surface Laptop a good five months ago so AMD just didn't have samples ready for Microsoft at that time. Reply
  • sing_electric - Friday, December 13, 2019 - link

    Realistically, TSMC's 7nm process (used in Zen 2's compute chiplets) is expensive and capacity-constrained. AMD gets around this on desktop by creating a separate IO die on an older, cheaper process, but that doesn't scale well to mobile.

    To get Zen 2 on mobile, they'd likely need everything - compute, IO and GPU - to be on 7nm, and the chip would be considerably larger than (desktop) Zen 2's compute chiplet.

    AMD basically had a choice - for a given number of 7nm wafers, they could get a few mobile APUs or a lot more desktop CPUs (and GPUs for their 7nm options). The margins are much better doing the latter, so that's what they did.

    There's also the fact that we don't know what their agreement is with Global Foundries on 14/12nm wafers - we do know that AMD's agreement with them didn't require GloFo to finish its 7nm process. AMD has a commitment to buy some number of wafers from GloFo per year for a certain length of time, and it's likely that is a factor as well.
    Reply
  • lmcd - Friday, December 13, 2019 - link

    Disagreed -- cheaper IO dies have worked on mobile for years. The "cheaper" process is literally the process Zen+ shipped with.

    Problem is entirely integration -- now that Navi (a major release) has shipped, AMD can integrate the current version into chiplet form, then port those integrations to the incremented version of Navi ready to ship next year. Since the chiplets provide a substantial level of decoupling, incremental upgrades should be reasonably easy to integrate.
    Reply
  • RSAUser - Friday, December 13, 2019 - link

    Doubt the I/O die size matters in this case, doesn't scale down well so not an issue.
    Most likely a supply issue and getting Navi to integrate.
    Reply
  • scineram - Monday, December 16, 2019 - link

    What Navi? Reply
  • AnGe85 - Friday, December 13, 2019 - link

    AMD is a smaller company with fewer resources, as you can see with various things. The step by step Navi Launch (currently only Navi 14 is additionally available), delayed 3950X launch, the fragmented Threadripper launch, not until early 2020 Renoir with Zen2, but only combined with Vega (not Navi) and there's still the question when desktop APUs will hit the market.
    The new suface models presumably have been in development for about a year or even longer. There was no mobile Zen2 in sight ... and this also applies to Apple's Mac Pro and stupid demands like "it should have been Threadripper, not Xeon W". There was no appealing Threadripper available (the old 2000 series still has various flaws and limits and the Mac Pro is an even more complex platform).
    Additionally at this point, I would assume, that Microsofts strategy (with the two AMD and ARM models) is more about keeping Intel in check according to pricing and cooperation.
    The ARM Pro X has obvious limits and Microsoft also knew about AMDs comparability in advance. Additionally you can assume, that there is a good reason for Microsoft to offer channel consumers to the AMD 15" model (and to limit the Ice Lake model to business users), most likely, because they have to sell x K SKUs to make this experiment (or this Intel pressurizing model?) worthwhile. Maybe with next surface updates in 2021 AMD will be more competitive.
    Reply
  • 5080 - Friday, December 13, 2019 - link

    Margins. EPYC, Threadripper have a much higher margin than mobile APU's. Reply

Log in

Don't have an account? Sign up now