The ThrottleStop Guide

I think we might need a Cstate version that reports all available core (and preferably package) C states to get a full picture.

The following screenshot was taken with the "Balanced" power-profile active. According to Performance Monitor the cores spent 99%+ time in Windows C3 state, half of them were parked.

Interestingly my profile that parks all but one core during idle (to reach x34) reports *no* C2/3/6/7 states at all, neither package nor core, while Performance Monitor keeps reporting 99%+ Windows C3 for all parked cores. My interpretation is that parked cores are in no C state at all, and the one active core is likely using C7 core states during idle.

The profile that allows *no* parking is the one where Cstate reports C3 core, Performance Monitor reports 50/50 C1/C2 and TS reports 0-1% C2 and C3 package.

 

I agree. It will take a few days to get around to this but I'll put it on the things to do list. I'll expand the CStates program to show everything that can be shown.

It's hard to make any sort of comparison between CPU C States and what Performance Monitor reports since they use the same C1/C2/C3 name but the two sources are recording two different things.

 

Thanks for the hard work!

 

I wonder about the "erratic" behavior of the "Do not reset FIS/ VID on exit" option when it is *disabled*. Or better to say the impact of the "Set Multiplier" feature when it is enabled.

This is what happens:

"Balanced" profile

When "Set Multiplier" is enabled and set to anything higher than 8x then clocks are constantly changing while the CPU is idle, this also happens with C1E disabled. The average multiplier moves between 11x and 13x, unless load happens.

Once "Set Multiplier" is disabled or TS turned off (with "Do not reset" disabled) clocks of all cores fall down to 8x at once and stay there unless load happens.

"High Performance" profile

Here it doesn't matter whether "Set Multiplier" is enabled or not, in both cases the average multiplier moves between 11x and 14x during idle.

Customized profile that allows all cores to be parked

With "Set Multiplier" enabled TS reports maximum clocks for all cores (close to 34x for the active core, 31x for the parked cores). With "Set Multiplier" disabled all cores fall down to 8x. This happens even C1E is disabled.

Customized profile that allows *no* cores to be parked and is set to stay away from Idle states as much as possible

Here it doesn't matter whether "Set Multiplier" is enabled or not, in both cases the average multiplier moves between 13x and 15x during idle when C1E is *enabled*. Once C1E is *disabled* all cores increase to x31 (+1 Turbo bin). This is the only combination that allows keeps the CPU more or less at maximum frequency even while idle. This also is the only profile that makes Performance Monitor report 50%/50% C1/C2 instead of 99%+ C3, obviously the C1E switch has a big impact on wattage in this situation (as reported before).

I think I build the core parking profile on basis of the "Balanced" one while my non core parking is build on "High Performance" and behaves accordingly (all cores active at x31 at idle regardless of the option set or not).

Question is: Why does TS increase the idle multiplier of the "Balanced" and the core parking customized profile just by enabling "Set Multiplier"? I might have to go through all the profile options to find out which is the one affecting this, but maybe you can explain what TS does when "Set Multiplier" is enabled?

I thought it is a "one time" switch, that only sends a single instruction to the CPU once activated or changed. But seemingly it sends an ongoing/repeated instruction?! Whatever it does seems to be similar to what is hidden in the "High Performance" profile, because it behaves exactly the same as turning on "Set Multiplier".

 

I fear there is something more going on with the Reset/Turn Off thing. I have it that once turned off the multiplier would stay at 8x even with high CPU load up to 95%+ C0 according to TS .

The only way to fix this is to turn on TS with "Set Multiplier" again. Once it works I can turn off "Set Multiplier" as long as I leave TS turned on in general. So the Reset seems to do something not quite right.

All tested with the "Balanced" profile.

 

If you look in the ThrottleStop docs, the first important thing it says is:

When you are using the Balanced profile, Windows and ThrottleStop will both be writing information to the same register that controls the multiplier so the result is anyone's guess. ThrottleStop will check this register, see that Windows has changed it and think that it is trying to do some throttling so it will reset this register back to the highest value. Windows will see that, wonder what's going on and it will drop the multiplier trying to save power. This fight over this register goes on infinitely so you will likely see the average multiplier going up and down.

The "Reset FID/VID on Exit" option determines if this multiplier control register is reset to the highest value upon exit. If it resets it to the highest value, Windows should be able to take over full control of your multiplier. If ThrottleStop doesn't reset this register when it exits, the multiplier might get locked at the lowest possible value and remain there even when fully loaded.

 

That's the information I could only assume, that TS keeps checking and changing the register repeatedly instead of just once. *But* even with the "High Performance" profile the multiplier does *not* get fixed at highest value, even with C1E disabled. I needed to create my own power-profile in combination with "Set Performance" to achieve that.

Issue here is that it behaves exactly the other way around than you describe. The option is called "DO NOT reset...", but it behaves like "DO reset", and if the "DO NOT" option is disabled the multi is locked at the lowest value.

Sorry, give me some piece of technology and I stumble over what may be broken.

PS: This is what my profile "Run program" looks like to automatically switch power-profiles with TS profiles. Works like a charm. "C:\Windows\System32\powercfg.exe -s f1e8acb4-62fc-4b54-9a0c-a8249bdf5b90"

 

If the average multiplier that ThrottleStop is reporting is not fixed when C1E is disabled then I think that would only happen if one of the other C States is active such as C2/C3/C6/C7. I haven't done any C2 testing yet. Once the CStates program is expanded, maybe we can learn some more. Most of the desktop boards with various bios options to disable C1E/C3/C6 tend to have a high multiplier at idle that varies maybe +/- 0.05. I don't recall seeing any C2 options in their bios so I assume that C2 is usually off or maybe it gets turned on in conjunction with C3.

The original TS behavior was to always reset the multiplier register when it exited to prevent a user from accidentally getting their multiplier stuck at the lowest value after exiting. This caused a problem with overclockers that used a lower than maximum default multiplier. On an E8400, if they liked to use 8.0 x 500 MHz = 4000 MHz and they ran TS once and immediately exited because they didn't like it, ThrottleStop would set this CPU to its default 9.0 multiplier and suddenly the CPU would try to run at 9.0 x 500 MHz = 4500 MHz and the blue screen was sure to follow. I decided to add the option, Do Not Reset FID / VID to control this. Checking this should prevent the CPU from going up to 9.0. I haven't checked this feature for a while and when you have a check mark to select a "Do Not" option, I agree that's confusing. If I redesign this, I'll do some testing and I'll read your logical argument before I do so.

I'm happy to hear you found the Run Program feature useful. ThrottleStop is a handy program once you spend some time with it and figure out what it can do.

 

I'm currently reading through a pile of white papers and blogs to better understand the whole P-state, C-state, ACPI C-state and whatnot (and turn my half-wisdom into full-wisdom).

The Cstate you send me seems to work, but still leaves some questions open, or rather educated interpretation to be made. I'll get back to you once I'm over this.

One thing you could have a look at is page 823 + 824 of the Intel volume 3b. Not only does it tell us "Note: This field cannot be used to limit
package C-state to C3", but it seems to present a way to demote C6/7 to C3 and C3/6/7 to C1.

If the latter even worked on a core basis it would be an interesting feature. Especially since the "Package C-State limit" does not seem to have any conceivable impact (same power consumption setting TS to C1 as on C7/MAX).

Concerning "Do not Reset" you may have understood me wrong. I am not confused by the "Do not", but the option simply seems to behave the other way around as described. For me the "Do not" option seems to behave like a "Do" option, and removing the "Do not" option behaves as if I had removed a "Do" option.

On the other hand I just get a hold on how to control all this P-State stuff via power-profiles, so I may not need TS for this anymore. Does TS use P-States for "Set Multiplier" anyway? It seems like it does, because VID changes accordingly. Or does the CPU/ACPI do this on their own when a multiplier change happens?! VID also changes when CMod throttling is used, both via TS or via Windows power-profile. Do you happen to know why 800 mHz via CMod is considerably slower (and displays higher C0%) than 800 mHz via P-State?

BTW, Performance Monitor's C-States seem to correspond to ACPI C-States, and according to Intel's white paper C3 and C6 may be mapped to ACPI C2 or C3 depending on BIOS implementation. Still strange that Cstate reports less C3 core % than Performance Monitor reports C2 then.

 

CState 1.2
http://www.mediafire.com/?axqc0138wxxwv9h

Here's the latest version if anyone else wants to know a little more about what C State their Core i CPU is in when idle.

Performance Monitor's C-States and ACPI C-States should be the same thing but these are different than the CPU C States.

I have read that part of the docs you mentioned but the promote and demote options are only for the CPU package and you can't control individual cores like I would like to be able to do.

After a brief test, on my CPU, the Do not Reset option seems to be working correctly. When you were testing were you using the Windows high performance profile? I'm not sure what this option will do if you were using a Windows Balanced profile. You can try monitoring MSR 0x199 with the MSR Tool to see what ThrottleStop is doing on your computer.

TS simply monitors and writes to MSR 0x199 to try and control the multiplier so I assume that Sandy Bridge CPUs adjust VID automatically based on multiplier requests to this register.

I know the way CMod works has changed with Sandy Bridge compared to previous CPU generations but I haven't done any hands on testing or performance comparisons.

 

See screenshot.

My guess is that Windows keeps the "package" from entering C7 most of the time even when all cores are in C7. Maybe Microsoft decided that C7 is too "expensive" compared to C6, because C7 flushes the L3 cache, too.

Yes, but if Core C3 (CC3) is considered ACPI C2 or C3 is handled by the BIOS. And since my Mac's EFI BIOS seems to map CC3 to ACPI C2 I wonder why CState reports much lower C3 percentage for all but one core compared to Performance Monitor? The only answer I can come up with is that CC2 may also be mapped to ACPI C2 and since CState is not able to report Core C2 we don't see these adding up. Anyway, under normal profile circumstances my package seems to spent most time in C2 and I assume this is made C2E when TS' C1E option is enabled.

As far as I understand it is specifically for cores! But by default demotion is disabled and needs to be enabled. See this excerpt:

This sounds like a very interesting feature: Keeping cores from entering C3/6/7 when they have been "too busy" lately.

I specifically retested with the "High Performance" profile and it does just that. If "Do not Reset" is *not* set then the multiplier is reset to x8 as soon as I push the Turn Off button.

One more issue: Changing TS profiles via tray-icon leads to TS spamming the "Run Program after profile change", but not always. This didn't happen before Beta 4 and does not happen when changing profiles via keyboard shortcut or TS GUI.

 

MSR 0xE2
MSR_PKG_CST_CONFIG_CONTROL

This register is the Package C State Configuration Control register. Bits 28, 27, 26 and 25 can be set to control the C State demote options. I was originally testing with a Core i5 desktop CPU and these options did not give me any control over individual cores, only the package.



Edit: I just remembered that ThrottleStop already has a feature that lets you play around with the 4 demotion options.

http://forum.notebookreview.com/har...531329-throttlestop-guide-37.html#post7231834

No one posted much testing of this so I kind of forgot about this feature even though a couple of users got increases of over 100% in their 4K SSD write speeds when using this INI option.

CStateDemotion=

This value can be set to any value from 0 to 15 which lets you toggle on different CState options.
Here is Intel's explanation about what these changes do.

1 - C3 state auto demotion enable. (R/W)
When set, the processor will conditionally demote C6/C7 requests to C3 based on uncore auto-demote information.

2 - C1 state auto demotion enable. (R/W)
When set, the processor will conditionally demote C3/C6/C7 requests to C1 based on uncore auto-demote information.

4 - Enable C3 undemotion (R/W)
When set, enables undemotion from demoted C3.

8 - Enable C1 undemotion (R/W)
When set, enables undemotion from demoted C1.

If you wanted to use all of these options, you would just add up 1 + 2 + 4 + 8 and set this INI option to 15.
error-id10t is using the first two options so is using CStateDemotion=3

I originally wasn't sure if this feature would work when using a Sandy Bridge CPU because of the various lock bits that Dell is using but I don't think your Apple is locking these options. You can use the MSR Tool and monitor MSR 0xE2 to see how these options change that register.

Edit: I haven't made any recent changes to the Run Program feature. I tested this 10+ times but each time I switched profiles via the system tray, the .exe program was only run once. If this is happening randomly then I'll try to add some code to 100% prevent this from happening. Is it possible that this could be an Apple specific bug because of the difference in mouses between PCs and Apples?

 

ThrottleStop 3.10 b6
http://www.mediafire.com/?d628ipulfekuklm

-changed how the Package C-State limit control works in Sandy Bridge CPUs.
-added the above CStateDemotion= information to the documentation.

 

It does not give control over "individual" cores, but it affects cores, not packages. So when setting demotion to C3 then all *cores* are demoted from C6/7 to C3, not the package.

One oddity is that according to your MSR tool you can write different values to cores 0/1 vs. 2/3, but only the last written value is active (even when the registers still show different ones). Writing to one of the core registers sets the same value for a pair of 0/1 or 2/3.

And it works!

Yes, but I begin to seriously doubt that any of those benchmarks really measures disc performance, rather than driver or maybe even just the benchmark application's ability to deal with the data.

To stay with the 4K write example, I can get values between 35 mb/s to 110 mb/s depending on the CPU setting. Normally C1E has an impact, as has the choice of my customized power-profiles that also keep C3/6/7 from happening. Even more strange, demotion seems to have an additional impact even when Cstate already reports 0% C3/6/7 without demotion.

This is a bit of an awkward way to set it though, because it cannot be changed without restarting TS and it stays at the customized setting when TS is stopped/exited.

It all works and has an impact. So it's really nice to have.

I'm using a Logitech mouse. I just tried again and it did not happen, but I also changed all Run entries to run "before" and now changed them back to "after". Maybe that cleared something up. No idea. Will report back when it happens again.

 

The MSR Tool is only capable of accessing 4 threads of your CPU. Threads 0/1 belong to the same core and threads 2/3 belong to the next core so when you write a value to one thread, it gets automatically written to both threads of the same core. The MSR Tool needs an update so it can monitor and adjust all 8 threads of a Core i7 with hyper threading.

I thought the reported improvements in 4K Write times might have something to do with the CPU taking extra time to get out of one of the deep sleep states during a benchmark. The Crystal Disk Mark test doesn't put a heavy load on the CPU so maybe the CPU doesn't have a chance to get into high gear unless some of the C States are disabled.

Now that I know that the CStateDemotion option is useful, I'll add a separate panel to adjust this so it is a lot more user friendly and you will be able to adjust it without having to restart ThrottleStop. Thanks for all of your feedback and helping to make ThrottleStop a better program.

 

I seriously have no idea what the heck is going on with SATA connections with SSD. They behave like PIO mode in the 1980s in that they seem completely CPU bound.

It's even worse than just with C-states and deep sleep. Even when I disable all of these the performance depends on CPU clock-rate (aka P-states). Only at full >3.3 gHz clock-rate I get full 4 kb throughput (both read/write, sequential and random). The lower the CPU clock, the lower the performance.

This is where TS' "Power Saver" could come into play again. One can disable all P-states and only let TS clock up/down depending on load. One drawback is that it more or less needs realtime priority to do that, but TS in realtime priority can cause audio dropouts with audio applications (still testing).

 

I'll add an INI option for you so you can adjust ThrottleStop priority and test this further. The throttling problems in the Dell XPS 1645 laptop were best solved when ThrottleStop was using a Realtime priority. For many users, this is probably not necessary. I tried to reduce this once but the complaints came in so I went back to Realtime priority.

Some of the audio dropouts might be driver related. Windows mostly works in spite of itself and its archaic roots. With the hardware available today, you could create a super computer if Microsoft was able to ditch all backwards compatibility. I think there are still a few Windows 3.1 or Windows 95 skeletons hiding in the closet.

 

Thanks, that will be useful once I decided which priority TS should use best. I simply changed its priority via Task-Manager for testing (and could have enforced it externally), but the INI option is welcome.

Even when settings TS' prio to "Normal" it still uses 15 for its main EXE. This may be a problem, because it seems the GUI is also handled by this thread. So every time the GUI is used to monitor some things it runs at high priority and since it measures and draws stuff it can interfere with other processes. The cycles delta increases whenever the GUI is visible (not so much when restored but hidden beneath another windows) and shots up to 200k when "More data" is used, all at high priorities.

The reason why TS can interfere with audio software is that most audio applications still use the highest non-realtime priority 15 for their audio and midi threads. So the driver itself is not at fault, but the application that links the ASIO/driver dll at priority 15 only. Aero/DWM is also working at 15 since Vista, so audio app developers should get their act together and either support MMCSS or realtime priority (some do, but it's far from perfect yet).

 

unclewebb>>> how to set <0.925V on my T8300, because cpu world shows this info, that in SLFM mode Core works between 0.75 - 0.925V:
Intel Core 2 Duo T8300 processor - FF80577GG0563M (BX80577T8300)

tnx

 

ojojoj: When a Core 2 Duo CPU enters one of the deeper sleep states like C3/C4 it will automatically use a lower VID than ThrottleStop will let you set. The minimum SLFM VID my T8100 uses is 0.9500. The minimum value is unique for each CPU so if the ThrottleStop adjuster only goes down to 0.925 then that's as low as your CPU can go in SLFM. If the C States are working correctly, it will drop down to a lower value than this.

 

On a dual cpu mobo, is it possible to tell ThrottleStop on which cpu to apply the modifications (eg multiplier change) ?
Thanks for your support.

 

ThrottleStop is designed for single CPU motherboards only. I don't have any dual CPU motherboards to develop on so I probably won't be adding this feature.

 

Having just moved up from an E6400 with its throttling problems that throttlestop solved nicely, to a new E6420 with a i7 processor, I have a couple questions.

On the old machine, undervolting helped considerably in the temps. Is this still a viable option on a i7 2720qm?

Can you point me to any TS settings that could help out this new system or is it pretty much leave it alone and monitor?

 

Intel eliminated simple under volting when they first switched from Core 2 to Core i processors.

With many of the newer Sandy Bridge laptops, there are still throttling problems. I think Dell learned their lessons that it's not a good idea to do this anymore unless absolutely necessary. I'm not hearing about throttling problems on the Dells like the Acer x830 series and some Asus G53/G73 owners are reporting. Try using ThrottleStop in monitoring mode and run a log file. If your CPU is not throttling when loaded then there probably isn't much need for ThrottleStop on your computer. Keep it handy and do some more testing every few months just to make sure that the heatsink is still working properly and your CPU is running at its designed speed.

 

Does ThrottleStop support i5-2410m?

 

ThrottleStop supports the newer Sandy Bridge processors like the Core i5-2410M but laptop manufacturers have decided to lock most features that can be adjusted. If your laptop has a throttling problem then ThrottleStop should be able to completely fix or greatly reduce this problem. Let me know what laptop model you have and I will tell you if there are any known issues.

ThrottleStop is a very useful tool to accurately monitor these new CPUs so you can make sure that it is running at its Intel rated speed and not being throttled. Turn on the Log File feature and then go use your laptop for a while and you can send me a ThrottleStopLog.txt file when you are done if you want me to have a look. Too much data is always best. You can upload it to www.mediafire.com and then send me the link.

 

glad to see development is still going on

I'm still happily using version 3.00

 

ThrottleStop 3.20 beta 2
http://www.mediafire.com/?4ug155h06073w5v

Beta testing of the latest version is looking good so far. Version 3.10 has a new HotKey manager feature so you can quickly change ThrottleStop profiles with a user defined hotkey. The most recent version above includes a new C State monitoring and control window for Core i processors as well as per profile Turbo Ratio Limits for the Core i Extreme CPUs like the 920XM and 940XM.

I thought when Sandy Bridge came out that ThrottleStop wouldn't be needed anymore but there are a lot of throttling issues with these new CPUs because manufacturers are designing cooling solutions that are barely adequate and packing a lot of hardware muscle into smaller and smaller laptops.

The new C1 and C3 Auto Demote options for Core i CPUs can significantly increase SSD 4K Write times so it looks like ThrottleStop will be around for a while yet. When StamatisX was testing his 940XM on Tech Inferno, he saw an increase of almost 200% with ThrottleStop set up like this.



I'm not sure if the newer chipsets will respond like this but you can do your own before and after testing if you have a Core i CPU and are curious.

AS SSD Benchmark 1.6.4194.30325
http://www.alex-is.de/PHP/fusion/downloads.php?cat_id=4&download_id=9

 

I have tried this (as you know...), but when tested with my Z68 chipset and 2600K the Package C State Limit option(s) are grayed out.

Is this the part you weren't 'sure if the newer chipsets will respond' similarly to?

Either way, it still made a 4% difference in the reads of an Intel 510 when under load (SuperPI to 32M).

See:
http://forum.notebookreview.com/7763449-post6.html

 

tilleroftheearth, maybe your BIOS sets the lock bit (15) in MSR 0xE2 thus preventing any changes to package C-states. If your curious and want to test for a difference though you could try changing the power scheme in Windows to not use any C-states except C0, but be aware your idle power and temps will be quite high.

 

tilleroftheearth: Unfortunately a lot of Sandy Bridge motherboard manufacturers have decided to set the lock bit that Dufus mentioned. ThrottleStop checks that bit and if it is set, it disables the Package C State Limit button so you can't adjust it. This feature can only be unlocked by the bios. Once you boot up into Windows, if this lock bit is set, there is no way to unlock the CPU and get this feature working.

I noticed that the Apply button is not working correctly in the new C State window but other than that, everything seems OK. I'll get that fixed up tomorrow I hope for beta 2.

 

I have C0% throttle issue. This is on HP 8730w with core2quad QX9200 QAVR cpu on the proper quad core mobo.

Basically the problem is that upon overclocking, the C0% begins to decrease, but CMod and Chip %'s remain at 100%. And load in task manager etc remains at 100%, but benchmark results drop to match the C0% reporting.

I think it might be power related. Its as if the ACPI is monitoring CPU power consumption, and then running something in the background to limit it. I'm using a 180W PSU, and have even connected 2 PSUs in parallel for 300W total, but to no avail.

Examples:
1. If I use "TS Bench", I can run pretty much any realistic multiplier I want, as long as the voltage remains at 1.3V max. In TS Bench this limits me to a 12x multi before errors/BSOD occurs. If I bump the voltage above 1.3V, even the first step 1.3125, you can see C0% starts dropping towards the end of the 32M run, and the result is a lower score. The % drop in C0% relates to how high the voltage is set, and at 1.4000V it clips pretty much straight away. the lowest C0% drops to seems to be around 85%

The speed at which it begins clipping, and the on/off instant nature of the C0% clipping leads me to believe it is power related rather than temperature related. But I think it might be temperature now, since I blocked off the vent and got it to happen at 1.3V too. Hmmm.

Example 2: Using Prime95, I can only run 1.2625V before C0% drops, which means a 11.5x multi stable.

Example 3. Using Intel burn in test (linpak) I can only run 1.2500V before C0% drops, 11x multi stable.

Is there any way I can stop this from happening?

EDIT: I guess this is the difference between the 8730w and 8530w quads. It would seem the 8530w simply cuts all power (instant machine power off) in this situation, whereas the 8730w seems to do this C0% modulation thing instead. The exact same CPU in my quad 8530w can only run/boot if I pinmod it to 1.2V max, which means a realistic max of 10.5x multi on that chassis.

 

unclewebb,

Thanks for the feedback.

What should I be looking for in the BIOS to try to enable this setting?

Would it be called C State package state or something else?

Looking forward to Beta2.

 

ThrottleStop 3.20 beta 2
http://www.mediafire.com/?4ug155h06073w5v

-minor update so the Apply button in the new C State window should work immediately now.

tilleroftheearth: I don't know of any bios from any manufacturer that will give you an option to unlock this feature. I have no idea why the bios guys have decided to lock a fairly harmless feature like the C State Limits but this is very common for many Sandy Bridge motherboards. This was rarely if ever locked in previous motherboard generations.

stumo: It's always good to hear that the ThrottleStop C0% is telling you that your CPU is slowing down internally even when the useless Task Manager load meter is telling you everything is running at 100%.

Your problem seems power related. On Core 2 CPUs, Prime95 draws more power than TS Bench and Linpack testing usually draws more power than Prime95 so as power consumption goes up, throttling starts sooner or you have to reduce the core voltage to keep the power consumption under the limit that triggers throttling. A Kill-a-Watt meter would probably show this very clearly where your laptop hits the power wall.

ThrottleStop has a hidden feature that might be able to help with this problem. I'll send you a PM shortly to explain further.

 

Thanks for the update and for the additional info. (downloaded and running).

Hey! I want to know about the 'hidden' features too!

Just want to note that running my Q9450 (O/C'd to 3.4GHz) system with ThrottleStop running makes it feel (effectively) like a new SNB platform with an SSD (SATA3) for 'light' tasks like web browsing (up to 80 tabs open across 4 or 5 instances of IE9) or light multi-tasking (IE, Word, Excel, Accounting software, 'selecting images' in LR3, etc.).

And this 'snappiness' is on a system with no SSD too (XT Hybrid though)...

 

After I get some feedback from stumo, maybe I'll share a ThrottleStop secret.

The secret won't make any difference on a properly running CPU. It's only if there is a throttling problem like stumo is experiencing.

My main programming computer has a similar QX9650 running at 3.67 GHz and it's more than fast enough for the things I do with it. It takes 2 seconds to do a new compile of ThrottleStop. Some new SNB hardware would be great for development purposes but I really can't justify an upgrade at the moment to shave a quarter or half a second off my compile times. This computer spends the majority of time barely above an idle.

 

Thanks uncleweb, I will try out your suggestion when I get back into the office in about 8hrs time, and will let you know.

In the meantime I have been running a kill a watt on it, and I would say the throttling happens at just under 130W.

 

On the Dell laptops when you try to draw too much power from their adapters, they usually turn themselves off. After that you have to power cycle them off and on by unplugging them and plugging them back in to get them working again. With your 180W adapter you shouldn't have that problem but the bios might be set up so it assumes you are using the default adapter for this laptop. It will be interesting if ThrottleStop can help power through this limitation.

 

These elitebooks use what hp call a smart adapter. The laptop is supposed to be able to detect when you are using a too low rating one, and downclocks (specifically they only mention gpu downclock) and it's supposed to show a notification in that case. EDIT: Actually I've just tried it with a 120W adapter and yes, it gives a notification in the tray saying to "connect a different adapter for full speed".

I believe 180W is the biggest one it came with, so a hard upper internal limit around 130W would make sense, to allow for conversion overheads etc. especially if using 120VAC. I also have a 220W one that came with a NAS docking station, and I can also run in parallel, so hopefully we can defeat the internal limit. Fingers crossed.

 

Unclewebb...

Ran Crystal Disk Mark 64 Bit 3.01 with and without the 3.20 b2 running. Here are snapshots of the results...I hope this is helpful...The 4K write times increased by 50%. What do you attribute that to???

 

920xm oem @22x133
TDP/TC 85/70

3dmark06 test.

logs from trottlestop

Code:

DATE     TIME    MULTI   C0%   CKMOD  CHIPM  PWR_mW  TEMP
08/02/11 00:41:28  20.88   96.9  100.0  100.0       0   67
08/02/11 00:41:30  20.68   99.8  100.0  100.0       0   69
08/02/11 00:41:30  20.62   99.8  100.0  100.0       0   69
08/02/11 00:41:32  20.51   99.8  100.0  100.0       0   70
08/02/11 00:41:33  20.46   99.8  100.0  100.0       0   70
08/02/11 00:41:34  20.38   99.8  100.0  100.0       0   72
08/02/11 00:41:35  20.33   99.8  100.0  100.0       0   72
08/02/11 00:41:36  20.32   99.8  100.0  100.0       0   73
08/02/11 00:41:37  20.33   99.8  100.0  100.0       0   74
08/02/11 00:41:38  20.14   99.8  100.0  100.0       0   74
08/02/11 00:41:39  20.20   99.8  100.0  100.0       0   75
08/02/11 00:41:40  20.16   99.8  100.0  100.0       0   75
08/02/11 00:41:41  20.06   99.8  100.0  100.0       0   75
08/02/11 00:41:42  20.07   99.8  100.0  100.0       0   76
08/02/11 00:41:43  20.03   99.8  100.0  100.0       0   77
08/02/11 00:41:44  20.02   99.8  100.0  100.0       0   78
08/02/11 00:41:45  19.99   99.8  100.0  100.0       0   77
08/02/11 00:41:46  19.96   99.8  100.0  100.0       0   78
08/02/11 00:41:47  19.96   99.8  100.0  100.0       0   79
08/02/11 00:41:48  19.92   99.8  100.0  100.0       0   78
08/02/11 00:41:49  19.90   99.8  100.0  100.0       0   79
08/02/11 00:41:50  19.90   99.8  100.0  100.0       0   81
08/02/11 00:41:51  19.84   99.8  100.0  100.0       0   80
08/02/11 00:41:52  19.85   99.8  100.0  100.0       0   81
08/02/11 00:41:53  19.81   99.8  100.0  100.0       0   82
08/02/11 00:41:54  19.78   99.8  100.0  100.0       0   82
08/02/11 00:41:55  19.80   99.8  100.0  100.0       0   82
08/02/11 00:41:56  19.75   99.8  100.0  100.0       0   82
08/02/11 00:41:57  19.73   99.8  100.0  100.0       0   83
08/02/11 00:41:58  19.74   99.8  100.0  100.0       0   83
08/02/11 00:41:59  19.70   99.8  100.0  100.0       0   83
08/02/11 00:42:00  19.71   99.8  100.0  100.0       0   83
08/02/11 00:42:01  19.68   99.8  100.0  100.0       0   83
08/02/11 00:42:02  19.66   99.7  100.0  100.0       0   84
08/02/11 00:42:03  19.69   99.8  100.0  100.0       0   84
08/02/11 00:42:04  19.65   99.8  100.0  100.0       0   85
08/02/11 00:42:05  19.65   99.8  100.0  100.0       0   84
08/02/11 00:42:06  19.65   99.8  100.0  100.0       0   85
08/02/11 00:42:07  19.63   99.7  100.0  100.0       0   85
08/02/11 00:42:08  19.62   99.8  100.0  100.0       0   85
08/02/11 00:42:09  19.61   99.8  100.0  100.0       0   85
08/02/11 00:42:10  19.59   99.8  100.0  100.0       0   86
08/02/11 00:42:11  19.60   99.8  100.0  100.0       0   86
08/02/11 00:42:12  19.56   99.8  100.0  100.0       0   86
08/02/11 00:42:13  19.56   99.8  100.0  100.0       0   86
08/02/11 00:42:14  19.57   99.6  100.0  100.0       0   86
08/02/11 00:42:15  19.53   99.8  100.0  100.0       0   86
08/02/11 00:42:16  19.57   99.7  100.0  100.0       0   86
08/02/11 00:42:17  19.52   99.8  100.0  100.0       0   87
08/02/11 00:42:18  19.51   99.8  100.0  100.0       0   86
08/02/11 00:42:19  19.56   99.8  100.0  100.0       0   86
08/02/11 00:42:20  19.51   99.8  100.0  100.0       0   87
08/02/11 00:42:21  19.50   99.8  100.0  100.0       0   87
08/02/11 00:42:22  19.52   99.8  100.0  100.0       0   87
08/02/11 00:42:23  19.48   99.8  100.0  100.0       0   87
08/02/11 00:42:24  19.51   99.8  100.0  100.0       0   86
08/02/11 00:42:25  19.47   99.8  100.0  100.0       0   87
08/02/11 00:42:26  19.46   99.8  100.0  100.0       0   88
08/02/11 00:42:27  19.47   99.8  100.0  100.0       0   88
08/02/11 00:42:28  19.44   99.8  100.0  100.0       0   88
08/02/11 00:42:29  19.45   99.8  100.0  100.0       0   87
08/02/11 00:42:30  19.46   99.8  100.0  100.0       0   87
08/02/11 00:42:31  19.43   99.8  100.0  100.0       0   87
08/02/11 00:42:32  19.41   99.8  100.0  100.0       0   87
08/02/11 00:42:33  19.44   99.8  100.0  100.0       0   88
08/02/11 00:42:34  19.41   99.8  100.0  100.0       0   87
08/02/11 00:42:35  19.43   99.8  100.0  100.0       0   88
08/02/11 00:42:36  19.40   99.8  100.0  100.0       0   89
08/02/11 00:42:37  19.39   99.8  100.0  100.0       0   89
08/02/11 00:42:38  19.42   99.8  100.0  100.0       0   89
08/02/11 00:42:39  19.62   94.8  100.0  100.0       0   89

Do you have any idea why the cpu didn't maintain 22x ratio?

 

Maybe the BIOS throttles the CPU because of the temps.
Do you have the latest BIOS?

 

ok I'll try the latest bios.

I've just found about this hidden option
http://cdiefer.proboards.com/index.cgi?board=i8kfan&action=display&thread=707

 

Bobmitch: Blocking the CPU from using some of the low power package C states can improve some SSD benchmarks. I've heard that this new benchmark is more consistent than Crystal Disk Mark so you might want to do a comparison with that.

AS SSD Benchmark 1.6.4194.30325
Alex Intelligent Software - Downloads

error-id10t is the person that introduced me to the C State Demotion stuff so if it works for you, thank him!

aldam: As a CPU heats up, power consumption also goes up. Your log file that shows the average multiplier slowly throttling down is usually a sign that you are hitting the CPU's TDP / TDC limits. You might be able to raise those limits a little and maintain full turbo boost longer but then you are going to be running into the thermal limits of your CPU. You need better CPU cooling to get the most out of the XM CPUs. The best performance I've seen is with the Alienware M17x-R2. With a few tricks I have seen users running the 26 multiplier across all 4 cores when fully loaded. With your cooling, that's not ever going to be close to possible. Power consumption can also vary from one CPU to the next depending on how much leakage that CPU has.

Edit: Here's a good example of 5150Joker's 940XM running 8 threads of the demanding wPrime benchmark with the 26.00 multiplier on each thread and not a hint of throttling or over heating.

 

unclewebb,

On my i3 350M U30Jc on the High performance profile, I can't seem to make the cpu stay at 2.26GHz without dropping down to 1.1GHz (for example...).

Is this a limitation of the chipset, or am I not setting up ThrottleStop 3.2 Beta2 correctly as indicated in post 728 on page 73?

See:
http://forum.notebookreview.com/7755405-post728.html


What else must I do to make sure the cpu clock doesn't vary?

(On my Q9450 it behaves properly...).

 

Try disabling C1E, that should stop the clocks from dropping down when idle.

 

Core i mobile CPUs have a wandering multiplier at idle regardless of how ThrottleStop is set up. I have heard of a Windows registry mod possible to lock these CPUs but it results in more power consumption and more heat as it blocks the CPU from using any of the power saving C States. Most users that have tried this have not found it to be a desirable long term mod for a laptop.

The previous 45nm Core 2 processors could be locked to the highest multiplier at idle without causing any problems or excessive power consumption. I asked a friend about the above mod so if I hear more, I'll post some more info so you can test it yourself. This mod is not practical for most Core i mobile CPUs because blocking the C3/C6 C states will limit the amount of turbo boost to a multiplier increase of only +1. Your i3 does not use turbo boost so maybe the mod might be just what you're looking for.

Edit: Here's the trick. Open up the registry and navigate to here:

HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Services\intelppm

Inside this folder is a REG_DWORD value called Start. Change this from 3 to 4 and reboot and see what happens. Play around with ThrottleStop and make sure C1E is disabled. Let me know if this works for you and if there are any 24/7 downsides like too much heat. I believe this blocks C3 and C6 being used so the multi doesn't wander around when lightly loaded. It can also give a boost to SSD benchmark scores since the CPU is ready for action. I'm not sure if you will need to disable EIST in ThrottleStop for this to work correctly.

 

I noticed that the new highest multiplier is permanently available after setting it in TS, since I can access it in CPU Genie and RMClock, as well, without starting Throttlestop.

That's awesome since I'm using RMClock to control voltage/p-states (I set it to switch at 85% load, so it stays at lower states most of the times, unlike in TS or CPUGenie, where it jumps to the highest for every light/moderate load), and I was afraid I would lose the ability to use multipliers higher than the default 9x.

Also, sometimes the FSB frequency is reported wrong - it increases randomly to 277-350 MHz. I noticed it when updating the BIOS and also when running Prime95 at frequencies above 2.8 GHz - what could be causing that? All of the other utilities report it fine at 266 MHz, and the temperature doesn't go over 81 degrees for the CPU... Could it be the north bridge overheating?

 

As soon as ThrottleStop unlocks a new maximum multiplier, that multiplier will be available for any other software to use. The bios usually resets this when you reboot. If you like RM Clock then you can use the ThrottleStop ExitTime=5 INI option so TS will run, unlock your processor and then automatically exit 5 seconds later. It's best to only have 1 program trying to control your multiplier at a time.

The problem I had with RM Clock is that it didn't seem to work correctly with Core 2 Quad processors. Even when my CPU was fully loaded, it still left 2 of the 4 cores locked at the lowest 6 multiplier. I thought that was more of a bug than a feature. ThrottleStop has an INI option called SplitQuad. You can read about it in the included docs. When you are using this option you should be able to double click on ThrottleStop and have it run either side of your Core 2 Quad CPU at the highest multiplier while the other 2 cores are running with the minimum 6 multiplier. You can continue to double click on ThrottleStop and cycle through this.

In the Options window there is a value called PowerSaver C0%. This lets you adjust the sensitivity of the PowerSaver feature. When you increase this value, it will take a bigger load before your CPU goes up to its maximum speed.

ThrottleStop was designed to be a little different than RM Clock because I found for the newer 45nm Core 2 CPUs, there isn't always a big difference in idle power consumption even when there is a huge difference in FID and VID. Here's an example of my T8100.

http://forum.notebookreview.com/6369641-post5060.html

The reason for this is that these CPUs will enter the lower power C sleep states automatically and the VID drops down to a lower value automatically. The value that RM Clock or ThrottleStop or any software lets you set is ignored 95% of the time at idle. For this reason, coming up with the perfect FID / VID combos for every multiplier doesn't always translate into less power consumption. There have been some studies where the opposite is true and running a CPU at a slow speed only makes it inefficient. Running a CPU in short fast bursts lets it get its work done and then quickly get back into one of the deeper C3/C6 sleep states for longer periods of time where the real power savings are found. I'll try to post a link to a paper about this later on.

Every time you click on the FSB button in ThrottleStop, the bus speed is recalculated. Are you using SetFSB or a similar program to adjust your bus speed? There is a Windows 7 feature / bug that when you adjust your bus speed this way, it can screw up the high performance timer that ThrottleStop uses. If you are a regular SetFSB user, there is a simple fix for this. My code to try and correct for this issue might need some improvement. How often does this happen and does clicking on FSB correct it or does it stay screwed up?

Thanks for the feedback.

 

Thanks for the reply, Unclewebb! I knew there were more settings to Throttlestop, but I can't open the Throttlestopdocs file for some reason (it's just blank). Is there an online copy of the documentation?

I'm not using setFSB or anything like it, so the wrong FSB reading is weird...

I did use PowerSaver for a while, and it works fine, but even at C0% 90% it's still too trigger happy, going to the maximum voltage and multiplier for much longer times than with RMClock, and the temperature on average is higher. RMClock seems to work well - it just doesn't exit sometimes (which leads to the settings not being saved), I haven't noticed any other weird behavior.