Last week, we published our AMD 2nd Gen Ryzen Deep Dive, covering our testing and analysis of the latest generation of processors to come out from AMD. Highlights of the new products included better cache latencies, faster memory support, an increase in IPC, an overall performance gain over the first generation products, new power management methods for turbo frequencies, and very competitive pricing.

In our review, we had a change in some of the testing. The big differences in our testing for this review was two-fold: the jump from Windows 10 Pro RS2 to Windows 10 Pro RS3, and the inclusion of the Spectre and Meltdown patches to mitigate the potential security issues. These patches are still being rolled out by motherboard manufacturers, with the latest platforms being first in that queue. For our review, we tested the new processors with the latest OS updates and microcode updates, as well as re-testing the Intel Coffee Lake processors as well. Due to time restrictions, the older Ryzen 1000-series results were used.

Due to the tight deadline of our testing and results, we pushed both our CPU and gaming tests live without as much formal analysis as we typically like to do. All the parts were competitive, however it quickly became clear that some of our results were not aligned with those from other media. Initially we were under the impression that this was as a result of the Spectre and Meltdown (or Smeltdown) updates, as we were one of the few media outlets to go back and perform retesting under the new standard.

Nonetheless, we decided to take an extensive internal audit of our testing to ensure that our results were accurate and completely reproducible. Or, failing that, understanding why our results differed. No stone was left un-turned: hardware, software, firmware, tweaks, and code. As a result of that process we believe we have found the reason for our testing being so different from the results of others, and interestingly it opened a sizable can of worms we were not expecting.

An extract from our Power testing script

What our testing identified is that the source of the issue is actually down to timers. Windows uses timers for many things, such as synchronization or ensuring linearity, and there are sets of software relating to monitoring and overclocking that require the timer with the most granularity - specifically they often require the High Precision Event Timer (HPET). HPET is very important, especially when it comes to determining if 'one second' of PC time is the equivalent to 'one second' of real-world time - the way that Windows 8 and Windows 10 implements their timing strategy, compared to Windows 7, means that in rare circumstances the system time can be liable to clock shift over time. This is often highly dependent on how the motherboard manufacturer implements certain settings. HPET is a motherboard-level timer that, as the name implies, offers a very high level of timer precision beyond what other PC timers can provide, and can mitigate this issue. This timer has been shipping in PCs for over a decade, and under normal circumstances it should not be anything but a boon to Windows.

However, it sadly appears that reality diverges from theory – sometimes extensively so – and that our CPU benchmarks for the Ryzen 2000-series review were caught in the middle. Instead of being a benefit to testing, what our investigation found is that when HPET is forced as the sole system timer, it can  sometimes a hindrance to system performance, particularly gaming performance. Worse, because HPET is implemented differently on different platforms, the actual impact of enabling it isn't even consistent across vendors. Meaning that the effects of using HPET can vary from system to system, as well as the implementation.

And that brings us to the state HPET, our Ryzen 2000-series review, and CPU benchmarking in general. As we'll cover in the next few pages, HPET plays a very necessary and often very beneficial role in system timer accuracy; a role important enough that it's not desirable to completely disable HPET – and indeed in many systems this isn't even possible – all the while certain classes of software such as overclocking & monitoring software may even require it. However for a few different reasons it can also be a drain on system performance, and as a result HPET shouldn't always be used. So let's dive into the subject of hardware timers, precision, Smeltdown, and how it all came together to make a perfect storm of volatility for our Ryzen 2000-series review.

A Timely Re-Discovery
Comments Locked


View All Comments

  • Ryan Smith - Thursday, April 26, 2018 - link

    "Thank you for the analysis. Can you somehow verify that very large variations (RoTR 1-2-3, Civ6) of performance on i7-8700K with HPET not forced are real?"

    Can and done. Using the Timers application we can compare the outputs of all of the timers, and ignoring the ancient 1KHz RTC timer, all of the important timers show no drift versus HPET. So there isn't a loss of accuracy affecting the calclation of frame rates.
  • peevee - Thursday, April 26, 2018 - link

    "and ignoring the ancient 1KHz RTC timer"

    And yet it is _RT_C and should not be ignored. Moreover, it is more than precise enough for every test running at least a second.
  • peevee - Thursday, April 26, 2018 - link

    Just use an external clock (take a 60+ fps video camera, record the sequence, see what is going on outside of the clocks on the same computer).
  • Holliday75 - Thursday, April 26, 2018 - link

    What if the clock on the camera is using HPET? Osnap.

    Suddenly the only clock I trust is in Boulder Colorado.
  • kpb321 - Wednesday, April 25, 2018 - link

    IMO if it has that dramatic an effect on things I'd like to see continued testing and coverage of the issue. As pointed out it's not exactly hard to end up with HPET turned on. I'm pretty sure I've launched the Ryzen master at least once on my system so it should be forced on. I also use my MB mfgs fan controller software which may or may not do the same thing.

    Testing every game on every system with HPET off and then on may not be practical but I'd still like to see tests for CiV6 and/or RoTR as those seem to be the biggest outliers until the impact becomes minimal or statistically meaningless.
  • Silma - Wednesday, April 25, 2018 - link

    Kudos to the Anandtech team, its integrity, its in-depth knowledge, its hard work!

    This is why Anandtech is my number one trusted source for benchmarks.
  • johnsmith222 - Wednesday, April 25, 2018 - link

    I've searched youtube and was suprised with number of videos addressing Intel HPET problem:
    Bassicaly it is known problem.
  • Hifihedgehog - Wednesday, April 25, 2018 - link

    First, Smeltdown and now an HPET bug. This Intel HPET bug deserves an article entirely of its own. Haha...
  • Crazyeyeskillah - Wednesday, April 25, 2018 - link

    It's not a bug. You literally have no concept of what you are talking about, yet you are commenting on an article that explains it in greater detail than ever put to page. HPET has to be used in extreme overclocking scenarios as windows 8/10 create variances in those situations. Ryan misinterpreted that it needed to be on always, and thus this situation was born.

    HPET isn't a but, it's a setting in bios that forces clock synchronization on the faulty Windows 10/8 system that can give incorrect data (ie: benchmark times ect.)
  • RafaelHerschel - Wednesday, April 25, 2018 - link

    Do you realize that they got it wrong? They deviated from the default situation and got results that were misleading...

Log in

Don't have an account? Sign up now