Page 4 of 4
Re: Mousetester graphs
Posted: 20 Aug 2023, 11:54
by ayukreizi
widow13 wrote: ↑20 Aug 2023, 11:51
Yeah it seems like it. CPU ports are usually better but that's not 100% of the time.
How is your frequency vs time looking ?
i just edited my post to answer your question - forgot it the first time around.
my results that i posted earlier and now are without any core affinity. assigning the cores usually improve my results when it comes to "periodical" jitter but not by much.
this periodical jitter mostly comes from nvidias drivers if i am correct in my testing.
interval vs time and frequency vs time will in my experince will almost always look 99% identical but here you go.
Re: Mousetester graphs
Posted: 20 Aug 2023, 12:03
by widow13
ayukreizi wrote: ↑20 Aug 2023, 11:54
widow13 wrote: ↑20 Aug 2023, 11:51
Yeah it seems like it. CPU ports are usually better but that's not 100% of the time.
i just edited my post to answer your question - forgot it the first time around.
my results that i posted earlier and now are without any core affinity. assigning the cores usually improve my results when it comes to "periodical" jitter but not by much.
this periodical jitter mostly comes from nvidias drivers if i am correct in my testing.
I wonder what I'm missing and my graphs are nowhere close to "perfect".
Damn that's kinda clean.
Re: Mousetester graphs
Posted: 20 Aug 2023, 12:38
by Slender
ayukreizi wrote: ↑20 Aug 2023, 11:49
Slender wrote: ↑20 Aug 2023, 09:53
your graphs looks like stable but anyway you have jitter 960-1040, what system you use, amd?
if you use amd try to disable GPU driver in Dev.man and retest mousetester
as mentioned, 7800X3D with a 4090.
by GPU driver you mean oem0.inf?
because that would make it a synthetic result as you need it to run for gaming if i'm not mistaken? but you're correct that the residual jitters are mostly from nvidia drivers.
here are "synthetic results" in safemode with gpu driver obviously disabled.
Chipset results:
CPU results:
widow13 wrote: ↑20 Aug 2023, 11:07
Do you use any affinity on chipset/cpu usbs or running default ?
doesn't matter that much in my case and for my specific question. it slightly reduces jitter but the results remain the same mostly. my results are without any core affinity.
so yeah, do those results indicate that the CPU port is inheritently worse than my Chipset port?
or am i mistakenly ignoring something?
if you have that graphs in safe mode you have issue with your bios, try diff pci usb controller / bios / cpu settings / usb settings (disable argb usb controller, sound usb, bluetooth, etc)
Re: Mousetester graphs
Posted: 20 Aug 2023, 12:57
by ayukreizi
widow13 wrote: ↑20 Aug 2023, 11:51
Yeah it seems like it. CPU ports are usually better but that's not 100% of the time.
i'm aware that CPU ports aren't always better but it seems like with these results I am missing a piece of the puzzle.
these CPU port results are ridiculously consistent and not prone to any interference. while enabling /useplatformclock negatively impacts the measurings on the chipset port, they remain the same and just more aligned on the CPU port.
i don't want to bring in the argument "it feels better" into the discussion because it has no place in professional benchmarking but each month i return to retesting and trying to figure out this port.
thus i come here for any more insights as to what i could be missing.
Slender wrote: ↑20 Aug 2023, 12:38
if you have that graphs in safe mode you have issue with your bios, try diff pci usb controller / bios / cpu settings / usb settings (disable argb usb controller, sound usb, bluetooth, etc)
i've tested all of the suggestions mentioned by you in the previous motnhs extensively and comparing them A/B.
- all usb ports not in use are disabled in BIOS/OS.
- CPU settings have been tested at current OC vs stock.
- BIOS: RGB completely disabled on everything, disabled internal audio, external DAC only, disabled bluetooth
while this has generally helped me in lowering the jitter and overall results on the chipset port... it simply reduced the jitter on the CPU port
without lowering the
1.008 wall.
i can further disable services and interferences to lower my chipset readout to 1.0001 but whatever i do - i cannot lower it on the CPU port.
Re: Mousetester graphs
Posted: 20 Aug 2023, 13:11
by Slender
ayukreizi wrote: ↑20 Aug 2023, 12:57
widow13 wrote: ↑20 Aug 2023, 11:51
Yeah it seems like it. CPU ports are usually better but that's not 100% of the time.
i'm aware that CPU ports aren't always better but it seems like with these results I am missing a piece of the puzzle.
these CPU port results are ridiculously consistent and not prone to any interference. while enabling /useplatformclock negatively impacts the measurings on the chipset port, they remain the same and just more aligned on the CPU port.
i don't want to bring in the argument "it feels better" into the discussion because it has no place in professional benchmarking but each month i return to retesting and trying to figure out this port.
thus i come here for any more insights as to what i could be missing.
Slender wrote: ↑20 Aug 2023, 12:38
if you have that graphs in safe mode you have issue with your bios, try diff pci usb controller / bios / cpu settings / usb settings (disable argb usb controller, sound usb, bluetooth, etc)
i've tested all of the suggestions mentioned by you in the previous motnhs extensively and comparing them A/B.
- all usb ports not in use are disabled in BIOS/OS.
- CPU settings have been tested at current OC vs stock.
- BIOS: RGB completely disabled on everything, disabled internal audio, external DAC only, disabled bluetooth
while this has generally helped me in lowering the jitter and overall results on the chipset port... it simply reduced the jitter on the CPU port
without lowering the
1.008 wall.
i can further disable services and interferences to lower my chipset readout to 1.0001 but whatever i do - i cannot lower it on the CPU port.
SA voltage?
Re: Mousetester graphs
Posted: 20 Aug 2023, 13:17
by widow13
ayukreizi wrote: ↑20 Aug 2023, 12:57
widow13 wrote: ↑20 Aug 2023, 11:51
Yeah it seems like it. CPU ports are usually better but that's not 100% of the time.
i'm aware that CPU ports aren't always better but it seems like with these results I am missing a piece of the puzzle.
these CPU port results are ridiculously consistent and not prone to any interference. while enabling /useplatformclock negatively impacts the measurings on the chipset port, they remain the same and just more aligned on the CPU port.
i don't want to bring in the argument "it feels better" into the discussion because it has no place in professional benchmarking but each month i return to retesting and trying to figure out this port.
thus i come here for any more insights as to what i could be missing.
Slender wrote: ↑20 Aug 2023, 12:38
if you have that graphs in safe mode you have issue with your bios, try diff pci usb controller / bios / cpu settings / usb settings (disable argb usb controller, sound usb, bluetooth, etc)
i've tested all of the suggestions mentioned by you in the previous motnhs extensively and comparing them A/B.
- all usb ports not in use are disabled in BIOS/OS.
- CPU settings have been tested at current OC vs stock.
- BIOS: RGB completely disabled on everything, disabled internal audio, external DAC only, disabled bluetooth
while this has generally helped me in lowering the jitter and overall results on the chipset port... it simply reduced the jitter on the CPU port
without lowering the
1.008 wall.
i can further disable services and interferences to lower my chipset readout to 1.0001 but whatever i do - i cannot lower it on the CPU port.
Yeah honestly I can't really help on this topic. Because my graphs are bad and I haven't managed to fix them at all.
If you have any ideas that could help me tho, I'm all ears.
Re: Mousetester graphs
Posted: 21 Aug 2023, 02:08
by widow13
By the way this is what I get with nvidia driver enabled/disabled.
Enabled
- 1.png (81.5 KiB) Viewed 4619 times
Disabled
- 2.png (33.63 KiB) Viewed 4619 times
Re: Mousetester graphs
Posted: 25 Apr 2026, 08:23
by Jonelkingas
Is this suppose too be bad graph!? what?? this is a absoule beautiful graph... look at mine on windows 11 and new mouse i just bought with nordic and pixar 3950: