DoZator wrote on 2025-06-20, 19:14:

...
All that's left is to figure out a way to reset the multiplier to "40" under Windows XP (installed on the same PC, on a separate partition). CrystalCPUID, in principle, allows you to change the multiplier on a given processor (using the /Fxx parameter), but it hasn't been updated for a while, and it doesn't seem to fully support the 4th generation. It has some internal limitations that prevent the multiplier from exceeding a certain value (based on my rough estimates based on benchmarks, it's around "31"), even if you use the "/F99" parameter (which should theoretically increase the multiplier to its maximum allowed value). Unfortunately, I haven't found any other XP-compatible tools (CPUSPD doesn't officially support XP).

Older versions of ThrottleStop work with Windows XP. I have just shared a proven to work version of it (ThrottleStop_600) in another topic here:
Re: x86 microarchitecture benchmark (MandelX)

Falcosoft wrote on 2025-06-20, 19:35:

DoZator wrote on 2025-06-20, 19:14:

...
All that's left is to figure out a way to reset the multiplier to "40" under Windows XP (installed on the same PC, on a separate partition). CrystalCPUID, in principle, allows you to change the multiplier on a given processor (using the /Fxx parameter), but it hasn't been updated for a while, and it doesn't seem to fully support the 4th generation. It has some internal limitations that prevent the multiplier from exceeding a certain value (based on my rough estimates based on benchmarks, it's around "31"), even if you use the "/F99" parameter (which should theoretically increase the multiplier to its maximum allowed value). Unfortunately, I haven't found any other XP-compatible tools (CPUSPD doesn't officially support XP).

Older versions of ThrottleStop work with Windows XP. I have just shared a proven to work version of it (ThrottleStop_600) in another topic here:
Re: x86 microarchitecture benchmark (MandelX)

All right, I figured it out. In fact, my mistake was that I changed not only the multiplier to "8" in the BIOS, but also the "Uncore Ratio" to the same "8" (assuming that these two settings should change synchronously). However, this is not the case. As a result, the performance did not return to its previous level. In fact, there is no need to adjust the "Uncore Ratio" at all. I've returned the "Uncore Ratio" to its default value. In general, both "ThrottleStop" and "CrystalCPUID" (with the /F99 parameter) correctly return the multiplier to the "40" value, and the performance is now fully restored. And those of my assumptions that you quoted above, regarding "CrystalCPUID" - NOT TRUE (CrystalCPUID, when launched with the parameter "/F99", quite correctly returns the multiplier back to the value "40", in combination with this processor, which is confirmed by the readings "ThrottleStop" and benchmark results). The problem is completely solved. Thank you for your help.

Hi All,

Long time no see, hope all is well.

Attached is a spreadsheet that might be of interest to you. I used it to automatically look up the equivalent cpu according to the DOOM realticks when developing CPUSPD. It also has the results for some of the CPUs I tested and recorded.

Just plug in the DOOM realticks from your test into column L, and column M ("Equivalent CPU", blue) will look it up from the "Reference" sheet and show you the results. The "Reference" sheet contains the results posted by one member on Vogons (sorry it was too long ago and I've forgotten who). Note that DOOM can't really run on 286 and below so the realticks for those cpus are interpolated.

Cheers!

For K10 does this depend on Bios/MB or just the CPU? Was planning to put together a AMD build for 98/XP/7 with something like a Phenom II X4, but even for 95/98 Windows there are a number of speed sensitive games so even getting down to a Pentium 1 alone would make me happy. I'm leaning towards the Asus M5A97 since it's confirmed working with 98, its socket AM3+ but like I said, a Phenom II or even an Athlon II will be better if it can be slowed all the way down like in the screenshots a few pages back. Thanks.

AaronS wrote on 2025-07-11, 03:26:

For K10 does this depend on Bios/MB or just the CPU? Was planning to put together a AMD build for 98/XP/7 with something like a Phenom II X4, but even for 95/98 Windows there are a number of speed sensitive games so even getting down to a Pentium 1 alone would make me happy. I'm leaning towards the Asus M5A97 since it's confirmed working with 98, its socket AM3+ but like I said, a Phenom II or even an Athlon II will be better if it can be slowed all the way down like in the screenshots a few pages back. Thanks.

The ability to scale down CPU cores to even 100 MHz is a CPU feature and BIOS independent.

kalohimal wrote on 2025-06-26, 12:16:

Hi All, […]
Show full quote

Hi All,

Long time no see, hope all is well.

Attached is a spreadsheet that might be of interest to you. I used it to automatically look up the equivalent cpu according to the DOOM realticks when developing CPUSPD. It also has the results for some of the CPUs I tested and recorded.

Just plug in the DOOM realticks from your test into column L, and column M ("Equivalent CPU", blue) will look it up from the "Reference" sheet and show you the results. The "Reference" sheet contains the results posted by one member on Vogons (sorry it was too long ago and I've forgotten who). Note that DOOM can't really run on 286 and below so the realticks for those cpus are interpolated.

Cheers!

The attachment cpuspd test sheet.png is no longer available

The attachment cpuspd_test.xls is no longer available

Hi I just came across this thread recently and I want to say THANK YOU for this great program.

I'm finally able to run Interstate 76 exactly right on my P4 retro PC. I'm running Windows ME on a 3.4 Northwood and using your utility to set the CPU to Throttle 2 makes the game function exactly as it should.

Thank you again!