The ThrottleStop Guide

Understand though, when using programs like wPrime it throttles at ~88*C. Also, notice the graph, even before my temperature peaks, i have constant fluctuations (look at the the dark blue line). SC2 temps max at ~90*C with a x31 eventually to x28 multiplier. That's why my initial assumption was that TDP was the factor. I could test it always with my cooler to double check if it's temps, but I really don't think they are.

 

its ok xonar i cant maintain my cpus advertised 4 core speeds unless the cpu is not at 100% usage on each core. i get 2.7ghz when using 8 threads 100%. my cpu is also at 76c on the highest core -_-.

 

TPL is an *average*. When the CPU is put on constant load it is throttled to match that average, when the load is going up and down the peaks can exceed that average for a limited time.

By increasing the TPL of my mobile i7 Quad by 3 watts I can increase the throttled multiplier by 1x on constant Prime95 load.

So both temperature and *average* wattage affect the effective multiplier.

Furthermore *all* of the factory Windows 7 power-profiles keep *half* the CPU cores unparked (=hyperthreaded cores are usually parked only). This keeps Turboboost from reaching its maximum multiplier (=single core operation).

 

From what I've seen hyper-threaded cores are parked to enable threads to run on individual physical cores for maximum performance. This helps alleviate core contention when two logical cores run on one physical core. AFAIK parking should not effect your ability to turbo as the parked cores are a result of OS scheduling ie the OS ignores assigning a thread a parked core, however un-parked cores can still transition to the higher c-states to enable traditional turbo to work.

 

Yes, but because threads are constantly being moved between cores you hardly see enough cores in C3/6/7 unless they are actively parked by the OS (which means nothing else than the OS/scheduler not making use of the cores and then putting them to go to C3/6/7). And Windows' power profiles only park 50% of your logical cores while moving threads around for temperature balancing (which is not a bad thing), so you hardly ever get the full single-core Turboboost.

Example: My i7 Quad does x31 with all 8 logical cores (4 physical + 4 HT), x32 with 4 cores and x34 with 2 cores. Windows usually only never allows more than 4 cores to go to C3/6/7 when several threads are running medium to high load, so you never get to x34.

By setting up a custom power-profile you can make Windows to put all (but 1) core to parking and thus more easily reach x34 on a single physical core (=2 logical cores).

I'm not saying that this is an advantage, but the whole core parking vs. thread moving thing does have an effect on your current multiplier.

 

A thread isn't moved around for temperature balancing, it's just a product of the OS scheduling. A thread gets a time-slice from the OS, typically 15.6ms unless clock resolution has been increased. Depending on priority that thread after it's slice (quantum) gets to the back of the queue and once it's rescheduled ends up on any of the 4 cores. It's more beneficial for it to end up on the same core as the L1/2 cache may still be populated with some of the data used by that thread (less cache misses). You might find W7 OS will actually prefer the same core if it's free.

Having the thread move around still leaves plenty of time for the other cores to transition to higher c-states if they become free so not such a big impact on turbo IMO.

It's 4 cores 8 threads. Both threads of a physical core are equal. ie it's not a core thread and a HT thread.
Processor C-states come in 2 flavours, core and package. 2 threads of the same physical core have to have the same shared core state. If you request C3 for one of those threads while the other thread is in C0 the core will remain at C0 and there will be no C3 state obtained.

Your right, most likely sacrificing performance just to reach a higher multi by only using half your processing power unless that is you only have one or two main threads running. You could probably set the affinity mask to achieve much the same.

Anyway, enough from me as it's getting too OT. Sorry about that Uncle.

 

I have disabled HT just to check and regardless on any application that uses 4 cores, BF3, SC2, Prime95, etc, same thing happens.

 

Running a single thread of Prime95 on an another-vise mostly idle system sees Windows shifting around the Prime thread between cores all the time, with Windows unparking/parking cores accordingly.

While I might miss some point, I don't see why Windows would do that for any other reason than load/temperature balancing. As you explain yourself it would be more beneficial to keep the single thread running on a single core for cache reasons.

My statement was that the maximum possible Turboboost multiplier is affected by Windows' behavior of only parking half the logical cores and moving threads around non-parked cores. Sure non-parked cores will transition to C3/6/7 and thus allow Turboboost to increase the multiplier. But parked cores are *always* in C3/6/7, because parking means nothing else than the OS Scheduler not making use of a core.

That's why I wrote "logical" cores. If every second "core" is parked (unparked: CPU 0/2/4/6, parked: CPU 1/3/5/7) then you can say that only "HT" cores are parked.

Thanks for the explanation, but since I helped Unclewebb improving this part of Throttlestop I guess I already knew that.

You misunderstood me here. Setting up Windows to allow more cores to be parked is not the same as setting up affinity. At least not unless you enforce these cores to *stay* parked, which I do not. I just allow a higher maximum of cores to be parked, while Windows can still unpark all cores if necessary. If this has any beneficial effect in a real-world scenario is another story.

More important: I have to correct what I wrote about "average TDP", I meant "average TPL". Sorry for the confusion.

 

Uncle Webb,

Just wanted to say thank you for such a great, useful piece of software:
CPU-Z Validator 3.1

Default is 1.263v, and I'm at 0.963v (a 0.3v drop!) while being totally stable (12hrs. Prime95 blend/50 runs IBT).

Thanks again!

 

Okay, lets try to put this in an order to help explain.

Firstly there is a distinction between cores and threads using HT. With a system that has 2 threads per core it's 4 cores and 8 hyperthreads. So saying only HT cores are parked is incorrect. Better to say one thread of each core is parked.

For you to have a parked core both threads of that core need to be parked, not just one. Do you really mean thread here instead of core? If you have one thread of a core parked and the other unparked the core will be at the lowest c-state of the 2 threads. ie if logical CPU0 and CPU1 share the same physical core and CPU1 is parked while CPU0 is in c-state C0 the core will be in c-state C0.

There may be something already running on the preferred thread. The OS doesn't know how long a software thread is going to run, nano seconds or hours, other than trying to use the previous history of the software thread. If the hardware thread is occupied by another application then wouldn't it be more efficient to assign a different hardware thread rather than wait? How are you monitoring these switches between threads? Probably by software that needs direct access to specific threads/cores in which case this often influences the scheduling behavior.

Here's an example assigning Linpack to one software thread and default affinty of using any cores. By using 20 second sampling time there is less influence the result.







Notice how much of the 20 seconds is spent on core 3.

 

Ok, then lets settle on the threads terminology. I was rather using Windows terminology, which identifies all threads as single CPUs (CPU0/1/2...) and which is more easy to understand for end-users.

Yes, I mean threads, or CPUx. AFAIK there is no such thing as parking from the CPUs perspective anyway. Parking effectively only means that the OS scheduler does not make use of a CPU thread, consequently the thread can be put into C3/6/7.

Indeed, and that is why I am saying that Windows' default behavior of never parking both threads of a core can have an influence on the effective CPU multiplier. The chance for a whole core to go to C3/6/7 decreases because the core is still marked as "use as you please" for the scheduler. That being said the influence doesn't seem to be very big when higher load is present. So take it as a footnote, not as an issue needing discussion.

According to TS my effective multiplier with Windows' profiles is around 32.8 when running a single Prime95 thread. So at least x33 does seem to happen often enough. My own profile that allows all threads to be parked reaches a *lower* effective multiplier in this specific situation, so I may have to tweak it some more.

Yes and no. If a single core is not fully utilized it can be more efficient (both performance and power-vise) to keep threads on that single core and thus allows a higher effective multiplier, not only because of the cache, but also because waking threads from C3/6/7 costs energy and *time*. This is what core-parking is all about.

When I allow all threads to be parked and watch core utilization with mainly Firefox running then all cores but one are only at 0.x% C0 (=99.x% C7). Running the "High Performance" or "Balanced" power-profiles (=only half the threads being parked at max) with the very *same* load makes the load being spread/moving among cores (=higher C0 on all cores = lower C7 on all cores).

This obviously is an idle case and load cases behave somewhat differently. But even when running a single Prime95 thread at Realtime priority (16 for the math doing thread) it keeps switching between cores. I did another test with a single thread of 80% (and less) load using Ableton Live. Curiously my own power-profiles lead to switching happening even with this lower load (and temp) while the default profiles keep close to 80% on a single core/thread.

So there must be some power-settings that affect this behavior. Once I find time I will try to find out which one that is. This whole stuff isn't sufficiently documented and already took quite some time to get into/analyze in real-world scenarios. But since I'm working on professional audio it's something I have to look into anyway.

I'm using Throttlestop and Windows' Performance Monitor. Where can I download your analysis tool that allows to set different polling times?

 

That's a bit of software written long ago that is pretty rough and certainly not user friendly.

Unclewebb has a program called i7Turbo that will let you see C0 usage for each core. If you ask him nicely it should be fairly simple for him to change the timer from 1 second to higher. He might be interested in the results too.

 

Throttlestop already does show C0, C3, C6 and C7 per core (C0 even per thread). Maybe some parameter could be added to the INI that allows to define the polling rate (20s might be a bit much though).

 

does throttlestop work with the i7 2630?

i've tried ver 3.5 and 3.3 and both don't work for me at all. It throttles as soon as the short interval time is up from 2.6ghz...down to 2.4ghz. I've upped my bclk so i've added about 100mhz (without the small OC, 2.4ghz is actually 2.3ghz)

I've done everything right i believe...EIST is enabled, speedstep is enabled.

 

ThrottleStop supports the i7-2630 but if your laptop bios has decided to lock the power register, there is nothing that ThrottleStop can do about that. I think the R3 might have a modified bios out for it now that unlocks this register.

The ThrottleStop C State window is separate from the rest of ThrottleStop so I will look into adding a variable polling interval for some more interesting data. Unfortunately not much time to play or do any programming recently.

 

Unclewebb, you would have to make sure there is no other core polling during the c-state sample time ie no MSR reads.

Something you might be interested to know T1mur, is that W8, at least the pre-beta, default behavior appears much more aggressive with core parking by parking whole cores.

Quad CPU with no HT.

 

thanks Unclewebb...i'll look into it

 

@Dufus: Likely they only changed the option called "Processor performance core parking core override" from its default of enabled to disabled.

According to MS help this option does "Ensure that at least one processor remains unparked per core".

As you can see Microsoft calls these "processors" instead of threads, while Resource Monitor and Performance Monitor call them CPUx. It's all a big confusion and no real standard nomenclature.

 

Each thread is being seen by the OS as a logical CPU and this is how it should be. Makes things easier for the OS.

I did some testing a while back with W7 core parking, turns out it can be a bit buggy in some situations when using affinity mask.

 

Didn't you disagree when I called those threads "logical cores" earlier? Logical CPUs doesn't sound that much different.

Your testing was done with the "Balanced" profile, which - as the name and description suggests - does not necessarily aim for better performance (aka high GFlops). So I wouldn't call it a "bug" at this point, but more a matter of settings. Did you repeat the tests with the "High Performance" profile?

 

hey man can you help me out?

Im not sure if this is normal or not but everytime I did a fresh windows install on all 3 core i7 I owned (2630QM, 2920XM ES, 2860QM) it will stay at 800Mhz (100x8) in idle in balanced mode and will raise to x16 or x32 or in th 2860QM case x36 max to satisfy the demand then throttle down without load.

This is what I prefer so the system will be cool when im not using it and load up required Mhz automatically when needed.

But after a game load (run witcher 2) or doing a 3dmark vantage bechmark that the CPU will stay at x33+ in balanced mode. But I'm not certain if either of those things I did are the cause.

I could change the maximum processor state in power settings to the clock I want but then it will just stay at that exact clock unless i change to another profile.

Is there anything I can do to revert it back to normal as in the first paragraph?

I opened both CPU-Z and the Core temp gadget to detect FSB and they both show the same.

Now I tried the Power saver mode and it behaves like normal but balanced is still the same. And I think it actually run at x33 or higher as I can hear the fan raising its speed to accommodate.

I still struggle using ThrottleStop as my CPU will run full on x33+ by just opening it and I dont know how to set it back rather than reboot.

 

The first thing the ThrottleStop docs say is that ThrottleStop only works correctly when used with the Windows high performance profile with the minimum and maximum processor state set to 100%.

If you want to use the Windows Balanced Profile, don't use ThrottleStop. If you are finished gaming, go into the ThrottleStop Options window and make sure "Do Not Reset FID/VID on Exit" is not checked, click on OK and then exit ThrottleStop and then switch to the Windows Balanced profile.

If you want to see what the average multiplier is doing, try running RealTemp. Many monitoring applications have decided to ignore the Intel recommended monitoring method and can be very misleading when a CPU is idle or lightly loaded.

RealTemp 3.69.1
|MG| Real Temp 3.69.1 Beta Download

I was recently testing a Dual Core Sandy Bridge CPU and the difference in CPU power consumption at idle between Balanced and High Performance was only 0.5W.

 

ThrottleStop 4.00

- added more turbo multiplier options for the Sandy Bridge CPUs.
- added support for Extended Clock Modulation which means it can be adjusted in steps of 6.25% on Sandy Bridge CPUs.
- fixed the Disable Turbo option so it should work on Core 2 as well as first and 2nd generation Core i processors.

It is available from the mediafire link in my sig and it will be available from Tech|Inferno shortly.

 

Nice, now I'm able to test out the individual multipliers and it looks like x29 is the most stable and x30 fluctuates between 29.25x and 29.75x. Thanks for the update Unclewebb!

 

On the first generation Core i CPUs, there was no way to control the turbo boost multiplier. It was either no Turbo Boost or full Turbo Boost. I finally had a 2620M to play with for a couple of days and discovered that Sandy Bridge CPUs give you access to a wide range of Turbo Boost multipliers so I have added that feature to ThrottleStop. Intel's public documentation leaves out a lot of the details so trial and error testing is the only way to figure things out.

When ThrottleStop is showing an average multiplier of say 29.50, that means the CPU is rapidly cycling back and forth between the 29 and the 30 multiplier, usually do to it bouncing off the TDP limit for the CPU. It makes sense that using a maximum 29 multiplier can help you avoid this cycling and make your CPU more stable.

Let me know if you see anything odd since I didn't have enough testing time with the 2620M I was using. Feedback during testing has been positive so I think everything should be OK.

You are most welcome!

 

While it is great to eek out some more CPU performance with ThrottleStop, is it possible to force the GPU to maintain the higher 1100mhz speeds for mobile chips? Those of us stuck on integrated may have it better then on the old Intel graphics, but integrated just isn't quite fast enough for some games (namely World of Tanks), and moving from stock 650mhz up to the turbo sped 1,100mhz would be a significant improvement.

Any ways, I'll be trying this out tonight when I get home and see if just kicking up the turbo a bit on my i5 2410M and see if any more performance is to be had, or if it is 100% iGPU limited.

 

TS reports the TDP roughly at 65-70W during the whole P95 testing. The lowering of the multipliers becomes more obvious as Temp increases, but yet in BIOS, I have CPU throttle disabled, so it shouldn't even be an issue. With my cooling pad I get about an average of x1 higher than I did before. It looks like 95*C is that magical throttle mark. Keep up the good work.

 

Excellent update. I was hitting 98C on full turbo (29x), but now I can run 28x and stay below 95C. Great.

Did you change anything about the thermal sensors? I have an ES i5-2520M, and in using 3.30 it would read temps 15C too low, but now it seems accurate.

 

I forgot to mention in the docs that I added an INI file option to ThrottleStop 4.00 called,

CStateInterval=

This can be set to any value between 1 and 20. This value represents the number of seconds between each data sample when the Core i C State window is open. I think I set this to 5 when testing and it seemed to work OK.

There shouldn't be any significant difference in reported temperatures for any Core i processor. ThrottleStop and all software for that matter, reads the Intel specified TJMax value from one register and reads the sensor data from another register. If there's a problem, it might be a problem with the sensors in your ES CPU.

trueg50: I don't know how to control the integrated Intel GPU. If the power settings were unlocked by your bios, it would be possible to raise the TDP power limits and maybe that would make your GPU run faster but most laptops lock this register so ThrottleStop will show a gray screen and you won't be able to make any adjustments.

Thanks for the feedback.

 

Hi,

I'm reading this subject since a long time and I tried to use throttleStop since the version 3.00 and I have some questions. My laptop is a Dell M6600 with a i5-2520 and the last bios A06. I put 100% cpu for min and max in the high perf windows profil.

Here my questions :
-when you select Set Multiplier in TS and put a value (for instance 27x) it should force the CPU to 27*100 all the time ? or it force the MAXIMUM to 27x only when i want to use 100% of the cpu

-also on the version 4.00, i can chose a new multiplier : 31x but it doesn't seems to work, i'm stuck to 30x. Is that normal ?
-I always wonder if it is possible to force all the cores to run at full multiplier (32x), there is a way to do that ?

Thank you

 

croco69: The ThrottleStop Set Multiplier feature allows you to adjust the maximum multiplier that the CPU will use.

The default multiplier for a Core i5-2520M is 25. Any multiplier higher than that requires Turbo Boost. Intel designed this CPU so when a single core is active, the maximum turbo multiplier is 32 and when both cores go active, the maximum turbo multiplier is 30. That's the absolute maximum. The amount of turbo boost that you get can also be limited by the power consumption of the CPU. When the CPU goes over the turbo TDP power limit, the maximum amount of turbo boost decreases.

It gets more complicated because this TDP power limit changes over time. If you click on the ThrottleStop TPL button, you should see two different power TDP values. It can only run at the higher limit for typically about 28 seconds. The exact amount of time depends on the bios and CPU model. If Dell did not lock this register in the bios, you would be able to use ThrottleStop to increase the turbo power limit but with a non-Extreme CPU like your i5, you would still be very limited by the maximum power limits that Intel has set within the CPU at the factory.

The 31X multiplier should work on your CPU. If you set 31, that is the maximum but you will only ever see this when running a single threaded activity. A lean Windows system typically consists of 500+ threads that need to be constantly scheduled. When you are running your single threaded application, that activates one core and then all of the background junk running on your computer will constantly wake up the second core so it is impossible to obtain the single core multiplier for any significant length of time. A few milliseconds here and there as the second core constantly wakes up and goes back to sleep. ThrottleStop calculates and displays a very accurate average multiplier so you get a good idea what percentage of time the highest multiplier is being used.

If you want to do some testing, try running a single thread of TS Bench or Super PI mod or whatever your favorite test is. While the CPU is loaded, try adjusting the Set Multiplier value and see what multiplier ThrottleStop reports. You can also run a ThrottleStop log file so you have a record of what multipliers you are getting. I don't own a Sandy CPU to test with so any log files or other data is always appreciated.

I know this new feature works but due to hardware limitations imposed by Intel, it probably won't work like everyone would like it to work. Setting this to 27 won't lock your CPU multiplier to 27 100% of the time. It should limit the maximum multiplier when turbo boost is active to 27X. This new feature is great for users trying to control their overheating Sandy Bridge based laptops but won't make your CPU run faster than Intel designed it to run.

 

Any reason to update from v3.40 to 4 with the older 940XM?

 

Most of the new features are only useful for Sandy Bridge owners but there were also reports of the multiplier getting stuck and turbo boost not working correctly when using version 3.40 to version 3.50 on some CPUs. This might be a CPU specific bug and may not be a problem for everyone but I decided to go back to what I was doing previously to work around this issue. TS 4.00 should be OK. That's the main reason why I pulled a new version number out of my hat. It's a great way to encourage everyone to upgrade.

ThrottleStop is designed to work on a wide variety of Intel CPUs but unfortunately, I haven't been able to afford any new hardware for years so I have never owned or had access to any Core i processors to test and develop with. That probably sounds a little crazy when you start to fully understand what ThrottleStop can do with both generations of Core i. None of ThrottleStop's features would have been possible without all of the feedback I have received from NBR and Tech|Inferno members but development based on user feedback alone is very time consuming so TS 4.00 is likely the final version.

Some Core 2 owners are happy with TS 3.00 or previous versions. Use whatever version you can find that works for you and your CPU.

Check out ThrottleStop's humble Core 2 origins.

 

Thank you unclewebb for your explanation and for all your work !

 

just a quick update on my situation a few pages back, it was cause by the Razer Mamba Mouse configurator, which used up lots of resources, turned it off and the muliplier is back to normal again.

 

Hi I just tried the throttlestop last week. Ever since my com always at multiplier x7 when ever I start com. It won't go pass 900ghz can help me?

 

When I right click inside Throttlestop 4.00 after turning it on, I only get the following drop down lists:

When right clicking anywhere on the grey part of the screen:
Minimize
Exit

When right clicking inside CPU description/details box:
Undo
Cut
Copy
Paste
Delete



I need to unlock my 920XM (see my sig for full specs). I can't see Unlock Multiplier or any way to change the Multiplier above 15.0/Turbo.

I've changed TRL to 27/25/21/21 after I changed TPL to 80/72, but without changing the multipliers I'm kinda stuck. I added 'Extreme = 1' to the end of my .ini file, but that didn't change anything.

Help please :|

EDIT: Confirmed: everything is working. I'm running 27/25/21/21 at 80/72 with max 90 Celsius Prime 95 (stable so far at 10 minutes, I know that doesn't mean much lol). Since these CPUs are rated good up to 105 Celsius (125 is shutdown temp), this should be a fine OC. This is, however, my first try at an OC... I could test a lot more Just wanted to see if this thing will actually run higher multipliers, which it does!

 

This thread helped me a lot, thanks unclewebb.

 

Is there any difference between throttlestop and rmclock for undervolting? Which one should I use?

 

@seiyafan Throttlestop gives you higher performance, as it quickly switches from the lowest to the highest multiplier. RMClock is good, but the step-by-step transitions can affect performance slightly. I think Throttlestop is better, as in the end you'll still be running at the highest multiplier under load, so the intermediary transitions are pretty much useless.

 

No one can help you if you don't post any details about your problems. Put a load on your CPU and post a picture of what speed your CPU is running at. If you don't understand ThrottleStop or it is not working correctly for you to solve your problems then simply delete the ThrottleStop folder and reboot and your computer will be just like it was before.

That's what I like to hear. I didn't have any feedback from 920XM / 940XM users about version 4.00 so if there are any problems, let me know. You can also go back to version 3.30.1 in my sig that most of the XM users were happy with. It sounds like everything is OK now that you understand the default multiplier and the adjustable turbo multiplier on these CPUs. That's a little confusing at first compared to previous generation Intel CPUs.

You can't undervolt the Core i CPUs. If you have an early Core 2, you might be better off with RM Clock if you get RMC set up correctly. In terms of power savings, ThrottleStop accomplishes a lot of what RM Clock accomplishes but is less hassle to set up and in some situations can significantly outperform RM Clock. Try both programs and use whatever one works best for your CPU and your situation.

 

Unclewebb, I have a question that is indirectly related to TS, but i expect you're probably the person who has the best chance of knowing. I understand everything about TDP just fine, however does TDC actually do. I keep the TDP/TDC ratio constant when i overclock my 920xm, but i'm curious as to what the thermal design current does or mean aside that is a current having to do with the thermal design of the CPU. By the way, thanks for TS, it is awesome .

 

Version 4.00 works fine for me, thank you unclewebb

 

TDP and TDC in ThrottleStop refer to the turbo power limits and not the design limits. To be more accurate, I probably should have called these values Turbo Boost Power Limit (TBPL) and Turbo Boost Current Limit (TBCL) or something like that.

If you set TDP to 60W then the CPU gives you full turbo boost when it is consuming less than 60 watts and when it is consuming more than 60 watts, turbo boost is disabled. Intel's CPUs can cycle Turbo Boost on and off so rapidly that they can maintain themselves right at whatever limit you set. That's why the average multiplier that ThrottleStop reports is so handy. The data TS reports is coming from internal timers running at billions of cycles per second so you can precisely see in real time exactly how much turbo boost you are really getting. The slightest hint of throttling is reported immediately.

TDC refers to the current flowing through your CPU. If you set that to 50A then you will get full turbo boost when less than 50 amps of current are flowing through your CPU and turbo boost will be turned off when more than 50 amps is flowing through your CPU. The ThrottleStop TDP and TDC values only control Turbo Boost. You can't set TDP to 20 and turn your CPU into a low power 20 watt CPU.

In theory, these two limits should follow the basic power formula:

Power = Current x Voltage

or

Voltage = Power / Current

Voltage stays fairly constant in a fully loaded CPU so that's why the turbo TDP and TDC ratio needs to stay fairly constant. If you raise turbo TDP without raising TDC then it is likely that the TDC limit will be what limits the amount of turbo boost you are getting. If you only raise TDC then you should find that the TDP limit will be what controls the maximum amount of turbo boost.

As the core temperature of a CPU varies while doing some full load testing, this changes the power consumption of a CPU so you will usually need to increase your turbo TDP and TDC values in ThrottleStop to maintain the same amount of Turbo Boost before turbo throttling begins. That's the theory at least.

schockie: Thanks for the feedback.

 

Thanks for the explanation .

 

Ok, so you can change limits, but you still can't overclock? For example my i5 520M @ 2.4Ghz? Or is there a way to get an overclock, or is this only for UM cpu's?
I changed TDP and TDC values from 25/21 to 35/30 but no result changes when i run wprime. It shows me 2660mhz (normal frequency). Is it normal the last few procent of the TS bench the cpu goes up to 2800mhz but becomes single threaded??

 

You cannot OC non extreme edition CPUs with Throttlestop. You'll need a utility like SetFSB, note that SetFSB isn't to be used with Sandy Bridge CPUs.

 

but setFSB requires to know the PLL, which I don't have>

 

Well, you'll have to look for it or forget about overclocking, the only way you can OC is by changing the PLL in your case.

 

version 4.00 running great here
thanks