TWEAK: Enable HPET (in BIOS and OS) for better performance and FPS


Recommended Posts

HPET off in WIndows: Timers are not in sync:

Windows8RTCBugTestingV2_12.png

 

HPET on in Windows: Timers are in sync:

Windows8RTCBugTestingV2_13.png

 

 

There is a timer big in Win 7 & 8

http://www.ocaholic.ch/modules/smartsection/item.php?itemid=1071

 

 

Because of a bug this deep, it's expected for software such as games and applications perform differently. So for to get the best result with application in question, one just has to benchmark, test and see.

 

The timer bug issue is real.

I thought these "tweaks" were dying out.

 

This does absolutely nothing positive on anything I've tried it with.  At best it does nothing, at worst it makes the system completely unpredictable in terms of performance.

 

What are you going to tell us to do next? Go into msconfig and tell Windows to use multiple cores during boot?

He really misses the forest for the trees there. All of this wasted idle time accounts for only small fractions of energy in comparison to load times. I would hazard a guess that Idle loads make up 1-3% of the power budget of server farms and super computers. The focus in HPC has generally been on saving power during load times and reducing maximum power consumption because that's were you see obvious savings.

 

He also makes the same mistake that is being made in this thread: not testing for overhead in real workloads. You can't establish a relationship for %overhead in real loads by testing a toy benchmark. He's probably right that there is noticeable overhead from higher timers resolution in general, but he certainly isn't proving it .

  • 3 weeks later...

To test the impact of HPET specifically for my system I decided to use the Bioshock Infinite Benchmarking utility.

The reason being simply because I plan on playing this game.
In the tool I chose the options: (2) UltraDX11_DDOF, (2) Custom resolution, (1) 16:9, (4) 1920 x 1080
I ran the 5 tests in succession after first restarting the computer and verified the HPET settings were activated via WinTimerTester I then let the computer idle for 5 minutes.

My Operating system is: Windows 7 Pro x64
CPU: Core i5 3570K OC to 3.8GHz - CPU power saving features disabled so it runs at a constant 3.8GHz always.
Mobo: Asus P8z77-v pro (Note the LPCIO is a Nuvotron)
RAM: Gskill Sniper 2133 2x4GB
GPU: EVGA Nvidia Geforce 560Ti 1GB Crysis 2 edition

I read somewhere that Nuvotron timer on Asus boards perform worse than the regular timers - which is reflected below.

With HPET enabled in bios and useplatformclock yes: (WinTimerTester reports QPF 14.31818 MHz)
test 1 avg fps: 42.06 min: 13.34 max: 82.70
test 2 avg fps: 42.04 min: 17.39 max: 77.26
test 3 avg fps: 42.07 min: 15.40 max: 80.88
test 4 avg fps: 41.92 min: 13.98 max: 87.14
test 5 avg fps: 42.11 min: 16.25 max: 82.07
Total Average FPS: 42.04

With HPET disabled in bios and useplatformclock no: (WinTimerTester reports QPF 3.32038 MHz)
test 1 avg fps: 42.50 min: 15.48 max: 82.53
test 2 avg fps: 42.50 min: 11.54 max: 87.50
test 3 avg fps: 42.59 min: 18.49 max: 87.16
test 4 avg fps: 42.51 min: 15.68 max: 86.36
test 5 avg fps: 42.55 min: 19.99 max: 85.29
Total Average FPS: 42.53 (gain of 0.49 fps or 1%)

Interestingly, If I leave HPET enabled in BIOS and used bcdedit /deletevalue useplatformclock and reboot, WinTimerTester reports QPF to be 3.32037. FPS avg was 42.37.

When I used latencyMon to do latency tests this is what I got with HPET on and off:

HPET ON:

Highest measured interrupt to process latency (?s):   137.307954
Average measured interrupt to process latency (?s):   3.937589

Highest measured interrupt to DPC latency (?s):       72.285723
Average measured interrupt to DPC latency (?s):       1.535534

HPET Off:

Highest measured interrupt to process latency (?s):   78.304503
Average measured interrupt to process latency (?s):   1.111873

Highest measured interrupt to DPC latency (?s):       77.099818
Average measured interrupt to DPC latency (?s):       0.492777

both tests were done after letting the computer idle 10 minutes after rebooting it and checking that wintimertester reported the correct frequencies.
The tests were also let to run for 10 minutes.

Conclusion: (For me at least or people using the same board/Nuvotron LPCIO with Win7) Leave HPET disabled in motherboard and useplatformclock set to no.
If you are using windows 8 you probably want HPET enabled if you are overclocking or using turbo boost as it can actually mess up your clock and possibly do other things.

 

I still have the benchmark results saved so if you need more detail I can provide it.

The FPS results are too "noisy", you have a variance of 10fps in one of the tests, so an average increase of 0.49fps is just "noise", if you repeated those tests you'd get different results again.

Not really surprising. If there was a difference, gaming sites would have been widely reporting the results and we'd have seen professional benchmarks of HPET vs non-HPET for gaming.

Well its not like the Bioshock Infinite benchmark is an accredited benchmarking program or anything. However the latencymon tests are pretty clear to me. Honestly I can't really feel or see any difference between this setting being set to on or off but it is true my latency is lower with hpet completely disabled. An average of nearly 4us compared to 1.1us on interrupt to process latency is pretty big.

 

I did my work. I would like to see others do some benchmarks and compare scores like I did. Especially to confirm whether or not the Nuvotron LPCIO results in worse timings compared to other manufacturers.

Well its not like the Bioshock Infinite benchmark is an accredited benchmarking program or anything. However the latencymon tests are pretty clear to me. Honestly I can't really feel or see any difference between this setting being set to on or off but it is true my latency is lower with hpet completely disabled. An average of nearly 4us compared to 1.1us on interrupt to process latency is pretty big.

 

I did my work. I would like to see others do some benchmarks and compare scores like I did. Especially to confirm whether or not the Nuvotron LPCIO results in worse timings compared to other manufacturers.

Don't discount your Bioshock results. Bioshock is real world benchmark and is exactly what you would want test here to see if HPET results in tangible real-world performance gains/losses. It's the difference between micro-benchmarking and benchmarking actual applications. See: http://en.wikipedia.org/wiki/Benchmark_(computing) and see post #73 in this thread where I discussed the numerous issues with how the original benchmarking was done in this thread.

 

In this particular case with your DPC benchmarks, we are talking about DPC latencies with a few millionths of a second difference on average. These results are so tiny that it would be impossible to perceive a difference for real-time audio/video. Now if there had been large spikes that would be a different story.

 

Also, one last things to note, the LPC Bus is separate from clock generation (It's not the clock source).

 

Hi there, where to get this timers tool from, shown in hardbags screenshots?

He used this: http://en.wikipedia.org/wiki/Windows_System_Assessment_Tool

sure? how to show this timers window then?

I thought you were talking about the scores from post #61 (. For those you need to run winsat in command line:

http://windowsitpro.com/systems-management/how-can-i-run-windows-system-assessment-tool-winsat-update-directly-command-line

 

For the other benchmarks, he list those in the corresponding post.

thanks a lot for your efforts. just for better understanding, im talking about the pictures in post #77. there is a link, but i'm not able to find this software anywhere!

Oh, that particular piece of software is private. Comments on the website of that thread asked for it, and the author declined to give it for some reason. As such, the results should be taken with a grain of salt since they are not verifiable.

 

You may be able to find another piece of software that gives the resolution for the other timers, but you can test HPET using wintesttimer.

Don't discount your Bioshock results. Bioshock is real world benchmark and is exactly what you would want test here to see if HPET results in tangible real-world performance gains/losses. It's the difference between micro-benchmarking and benchmarking actual applications. See: http://en.wikipedia.org/wiki/Benchmark_(computing) and see post #73 in this thread where I discussed the numerous issues with how the original benchmarking was done in this thread.

 

In this particular case with your DPC benchmarks, we are talking about DPC latencies with a few millionths of a second difference on average. These results are so tiny that it would be impossible to perceive a difference for real-time audio/video. Now if there had been large spikes that would be a different story.

 

Also, one last things to note, the LPC Bus is separate from clock generation (It's not the clock source).

...

Yeah, this is one of those things where benchmarking doesn't help much, since any improvements won't be visible. The default timer resolution on Windows is only 16ms (You can lower it, but Microsoft recommends against it for a bunch of reasons), so seeing an improvement of a few microseconds on one benchmark isn't going to translate into a real world difference.

And the benchmark that is useful (The Bioshock one) is noisy enough to not actually show any improvements, and that's just a fact of how computers work (The game isn't the only thing running, each run of the game will actually be different due to multiprocessing, etc.). If we saw a large improvement over multiple runs of the benchmark then we could see that the tweak had some actual effect.

  • Like 1

These are my results:

 

 

cbv9.jpg

wnfz.jpg

 

My Hardware: 3770K std clock on a GA-Z77-DS3H (TimerResolution.exe running in background) (HPET on, OS and EFI)

 

I saw, for example on Cartels pictures (#60), people with way lower latencies. How to reach them? With HPET off I'm still not able to reach these low latencies... :(

In what scenario does it possibly matter?

 

There are no actual use benefits from a lower latency here.

 

 

Hi there,

 

in Germany it's very rude to answer a question with a counter question. But I'd like some help, so I'll try to explain. Before I experimented with the HPET Option activated, I had a lower latency. Many things ran smoother and more fluent. Now with HPET on, some other things work better. So why shouldn't I try to combine these options? Obviously this should be the best possible system setting for me.

 

Kind regards,

WonG.

Hi there,

 

in Germany it's very rude to answer a question with a counter question. But I'd like some help, so I'll try to explain. Before I experimented with the HPET Option activated, I had a lower latency. Many things ran smoother and more fluent. Now with HPET on, some other things work better. So why shouldn't I try to combine these options? Obviously this should be the best possible system setting for me.

 

Kind regards,

WonG.

My former co-worker from Germany use to do this :laugh:. That's a bit of a digression but there are many cases where asking a counter question is perfectly valid. In this case, Wakers has a valid point and question. The reason being that you are seeing latencies in the 500 millionths of a second range. The resolution is so tiny that you should be able to handled deferred real time video and audio without delays (read as: smooth playback).

 

That being said to answer your question, you probably aren't going to be able to achieve lower latencies than you are currently seeing. The only thing else you can do is play with turning off device drivers. For example, turning off wireless will lower my DPC latencies. One other things you can do that I don't personally recommend is disable dynamic scaling of cores (in the power options set the minimum processor state to 100%).

 

Let me be clear about what happens when you have the platformclock setting as false. It's not that it disables HPET, what really happens is that it Windows uses a combination of timers for timing (TSC + HPET). Why? Because using the TSC is cheaper to sample than HPET so it is better suited for scheduling operations. However, at the same time HPET is useful for scheduling one-shot interrupts for sleeping or idling systems (it saves power). The point, I'm making is that different timers have advantages and disadvantages in certain scenarios and this is not, "HPET is the best timer on the system" as the information you'll find around the web would seem to indicate.

 

As for how that relates back to DPC latencies: I noticed a consistent difference of only 50-100us minimum on my laptop between forcing / not forcing HPET. It was far too low make any perceivable difference. To put that in context, in testing the difference is ~1-2% of the maximum latencies I see on my laptop (wifi causes spiking of 1000-3000us at times).

 

To be perfectly honest, I'm not even convinced that the timer they are using to measure DPC has consistent reliable results between when HPET is forced and not forced. Why? The Windows API doesn't give you a consistent clock source. It depends on the system configuration which we are changing in this scenario. See section 2.1.4 here: http://www.windowstimestamp.com/description -- so how can I be sure the differences aren't accounted for by changes in the timer function behavior itself?

But I already saw way lower latencies on other screenshot, for example in post #60. Without HPET activated my latency was about 60-90?s. And believe me, the difference is huge (especially in video games). I saw people with latencies about 20-50 with HPET activated. A stable latency (around 100?s) should work for me. Otherwise I'll have to deactivate HPET again, because the disadvantages outbalance the advantages. That's not what I'm aiming for, I don't want to miss the advantages I already acquired :(

This topic is now closed to further replies.
  • Recently Browsing   0 members

    • No registered users viewing this page.
  • Posts

    • Cuktech 10 Ultra charger review: big display, four ports, 110W total power by Taras Buria Cuktech recently announced a couple of Ultra-branded chargers, including a desktop 300W charger, which I reviewed a few weeks ago. For those who do need that much (or who do not want to spend that much on a charger), Cuktech also offers the 10 Ultra, a traditional wall charger with similar features. Four ports, a big display, and up to 110W of power output. After using it for a few weeks, here are my impressions. Disclaimer: Cuktech provided the review unit without any editorial input or pre-approval. Like the 30 Ultra, the 10 Ultra arrived in a box made of nice cardboard with quality print all over it. Inside, besides the charger, you will find a 240W 6A charger, which, this time, is fully braided. While Cuktech always bundles high-power cables with its chargers and power banks, they are usually regular and unassuming. This time, the cable is much nicer, matching the charger's $59.99 price tag. The charger itself measures 67 x 76 x 33 mm or 2.6 x 3.0 x 1.3 inches and weighs about 250 grams. Considering the charger has four ports and a big display, I would say the compact size is quite impressive, albeit a little hefty. The overall design is similar to other chargers from the manufacturer, minus the chrome Cuktech logo next to the four ports. The Cuktech 10 Ultra has retractable prongs for better portability. Its front side is covered with piano black plastic housing two elements: a capacitive button with backlight and a quite large display for various charging stats. Ports are downward-facing, and I have mixed feelings about such a design. It is not the most convenient when you frequently connect and disconnect cables. It makes you bend over to find the right port to connect, and it is a no-go with outlets mounted closer to the floor. On the bright side, design like this eliminates clutter and sagging, especially when using four cables at once. Plus, you get plenty of space for a big display. Ports include two high-speed USB Type-C ports, one Type-C for less demanding devices, and one classic USB Type-A. The first two ports deliver full 100W, while the third is capped at 45W. As for the Type-A port, its maximum output is 18W. In total, the charger delivers 110W of power, but in my testing, I managed to squeeze 117W when charging two power banks and a tablet. Quite impressive. Type-C1 Type-C2 Type-C3 Type-A Single-port 100W 100W 45W 18W Two ports 80W 20W - - Three ports 65W 20W 20W - Four ports 65W 20W 10W 10W The charger can detect handshake protocols and balance power across all four ports according to each device's needs. As such, power is not limited to the values in the table above. You can have two ports charging at 55W, three ports at 45W + 20W, and more. For some reason, Cuktech is not listing the supported protocols, but a quick test showed that it is compatible with PD3.0, PPS, QC5, DCP, and UFCS. When you connect a compatible device, the charger automatically detects its charging standard and displays it on the screen, for example, Apple 6A or Samsung 3A. Speaking of the screen. The main highlight of the 10 Ultra is its 1.57-inch display with a maximum brightness of 700 nits and 160-degree viewing angles. The display takes up most of the front, and it shows various charging-related information, including total output power, current temperature, power distribution across ports with watts, volts, and amps, a screensaver, and more. You can toggle between the different views by tapping the button, and holding it changes the screen orientation (portrait or horizontal, plus flipped) according to your socket position. The screen is very nice. It is sharp, vivid, and the fonts are easy to read. As for settings, you can change the following: Keep the screen on or off Lock the screen orientation (hold the button to change the screen orientation) Keep the USB Type-A port on Toggle power modes The charger has three power modes: AI: standard mode that automatically allocates power to each connected device. Power Priority: prioritizes power for high-demand devices, such as laptops or power banks. Balanced: splits power evenly across connected devices according to their needs I was skeptical at first, but after testing a few devices in different modes, I can see the benefit of these three modes. The most useful is power priority, which gives the first Type-C port more power. When I was charging a 100W power bank (port 1) alongside a 140W power bank (port 2), Power Priority split the total output about 75-30. Balanced mode, as the name suggests, splits the total output between the two ports more or less equally. As for AI mode, the charger uses its brain to detect which device needs more power. In my testing, it figured out that the 140W power needs a bit more juice. As I said, I expected this to be more of a gimmick, but the three built-in modes turned out quite useful. For example, you can prioritize your laptop while giving other ports a little less power, but still enough to charge at acceptable speeds. Unfortunately, unlike the 30 Ultra, this charger cannot display the battery level of the device being charged. This small feature turned out to be very useful when I was testing the 30 Ultra, as it allowed me to see my phone's battery level without picking it up. Like other Cuktech chargers I tested, the 10 Ultra one proved itself reliable and well-made. It uses Gallium nitride semiconductor technology to reduce the charger's size and improve efficiency. It is also better at dissipating heat, but I have to say that when charging two power banks at 117W total, the charger got hotter than what I would call comfortable (hold it for a few seconds, and you start feeling a burning sensation at your fingertips). However, the built-in thermal indicator remained below the temperature threshold, with the screen reassuring that the device operated at "High performance" (I tested it in a 21 °C / 69 °F room). Overall, the Cuktech 10 Ultra is a solid choice. If you need four ports and you like to nerd out on various stats, it is a very easy recommendation. It will take care of your laptop, phone, tablet, and power bank without breaking a sweat, plus the build, material, and cable quality are top-notch. The mode switcher is handy when charging different devices with different power needs, too. I cannot say a display is a must-have in a charger, especially when it makes you more conscious about where to plug it, but it is a neat addition if you have a socket at your table or bed level, so that you can actually use the display and its features. The more important fact is that despite its size and quality, the display does not make the charger that much more expensive than similarly powerful chargers from competitors. Plus, you can save 10% on the 10 Ultra with a promo code on Amazon. Buy Cuktech 10 Ultra charger - $53.99 on Amazon with a promo code As an Amazon Associate, we earn from qualifying purchases.
    • Last week I was investigating an issue with contacts and tried using the new Outlook. In the real (Classic) Outlook, you can easily go to any Outlook folder and present it in a Table View, then customize the columns to show/sort any field, which was exactly what I needed. But of course, the new Outlook doesn't have this feature at all. I gave up. Oh, and can we possibly stop claiming the new Outlook has PST support? What it really has is the ability to use the real Outlook in the background to pretend to have PST support. There is no PST support without the real Outlook installed.
    • Honestly just before Panos left it started to feel like MS just wasnt interested in them so they were being less innovative with them, and then when he DID leave for Amazon its kind of clear the direction is gone. It felt like Panos had both goals and drive, and a vision, but it felt like no matter what his title/department was the Surface devices never had the full interest of the rest of management and he was just pushing a bolder up a hill that MS was adding dirt to as he went.
    • A roguelike and a 4X strategy game are free to claim on the Epic Games Store by Pulasthi Ariyasinghe The final leg of the Epic Games Store's mystery giveaways promotion just landed, and it brought along two more games to keep. Last week's Lonestar and Calico giveaways have now been replaced with copies of Rogue Waters and Songs of Conquest to claim for PC gamers. As always, the game is yours to add permanently to your Epic Games Store library within the next seven days. Diving into the games, Songs of Conquest is developed by Lavapotion. This is a turn-based 4X strategy experience that has players making tough decisions and participating in tactical combat while also managing their kingdom. "Songs of Conquest is a turn-based strategy game inspired by 90s classics. Lead powerful magicians called Wielders and venture to lands unknown," explains the developer. "Wage battles against armies that dare oppose you, hunt for powerful artifacts and expand your territory. The world is ripe for the taking – seize it." Meanwhile, Rogue Waters comes from developer Ice Code Games. This rogue-lite experience has you taking the role of Captain Cutter as he commands his ship and crew through procedurally generated encounters. You'll be recruiting and training crew, use sea creatures, and battle with other ships and pirates. "Set sail as Captain Cutter, a pirate caught in a deadly struggle for power and vengeance," adds the developer. "Navigate dangerous waters, unleash mythical sea creatures, and outwit enemies as you chase legendary treasure and confront dark secrets." The newly available Rogue Waters and Songs of Conquest giveaways on the Epic Games Store are set to run until June 11, giving PC gamers seven days to claim the latest offer. Once this closes out, a new freebie will take its place on the same day, which is slated to be Warhammer 40K Speed Freeks. Don't forget that mobile gamers can check out the Epic Game Store's weekly giveaways on Android and iOS to grab a freebie there as well.
    • Still using Classic Outlook? Microsoft highlights 15 reasons to switch to New Outlook by Usama Jawad As many of you may know, Microsoft has been trying to get customers to ditch Classic Outlook in favor of New Outlook for quite some time now. To that end, it has added numerous capabilities to the latter, including PST features, and it is working on several more, such as a unified inbox. However, customer response has been a bit lukewarm so far, with many considering the New Outlook to be "hot garbage". Now, Microsoft has highlighted 15 features that users can leverage in New Outlook in yet another attempt to get customers to migrate. Although not all of the 15 capabilities are exclusive to New Outlook, in fact, most of them are available in Classic Outlook as well. But Microsoft hopes that this combination of familiar and fresh features will be able to attract existing users as well as new ones. For ease of readability, we have summarized the 15 features below: Pin an email: This makes it easier to track important emails Snooze an email: You can temporarily snooze an email thread for a specific time frame until it becomes relevant again. This can be very useful in scenarios where you don't feel like actively following a thread or simply want to follow up on a later date Add multiple categories at the same time: You can assign multiple categories to an email through a single, simplified interface Sweep: As the name implies, you can define automated move processes on your inbox to declutter it, rather than cleaning it up manually Schedule send: Does exactly what it says on the tin, and can be useful when accommodating recipients in different timezones Simplified folder sharing: The sharing process has been simplified so permissions are automatically applied on parent folders Follow a meeting: This is an RSVP option that lets people know that you won't be able to join the meeting but would still like to access a recap Save calendar views: You can save different views for the calendar based on different workflows Improved meeting tracking: Organizers have more controls in viewing meeting responses, such as the ability to sort and download them. Typically useful when there is a large audience Meeting recap: The Outlook Calendar surfaces a meeting recap with recordings, transcripts, and shared files Filtered views: Allows you to declutter your Calendar so that it's easier to scan and schedule Change a recurring event: Users can modify future events of a series of meetings while preserving the configuration of previous ones Rename your email account: This labeling makes it easier to identify multiple accounts in Outlook Modern themes: Exactly what the name says, plus Dark Mode Keyboard shortcuts: This facilitates flexible user behavior as customers can choose between Outlook for Windows shortcuts, Outlook for the web, or turn them off completely There you have it. It's a decent list, but it remains to be seen if it will move the needle in a meaningful way for users who are attached to Classic Outlook. Again, a lot of the aforementioned features are already available in Outlook Classic, but for some, native functionality is not present, and people typically resort to workarounds. Microsoft will be hoping that it's primarily those capabilities that get people to finally switch.
  • Recent Achievements

    • Conversation Starter
      mobandz earned a badge
      Conversation Starter
    • Apprentice
      fernan99 went up a rank
      Apprentice
    • One Month Later
      nothanks earned a badge
      One Month Later
    • One Month Later
      B2Proxy earned a badge
      One Month Later
    • One Year In
      MadMung0 earned a badge
      One Year In
  • Popular Contributors

    1. 1
      +primortal
      478
    2. 2
      PsYcHoKiLLa
      247
    3. 3
      Skyfrog
      79
    4. 4
      FloatingFatMan
      76
    5. 5
      Michael Scrip
      60
  • Tell a friend

    Love Neowin? Tell a friend!