I've got BOINC running R@h on a Raspberry Pi 4, the newest board w/ 8GB of RAM. I decided to overclock the Pi CPU so I updated /boot/config.txt:

over_voltage=6
arm_freq=2000

In other words: I took the CPU clock speed up from the default of 1.5 GHz to 2.0 GHz. It's been running on this config for several days, no issues with under-voltage:

$ vcgencmd get_throttled
throttled=0x0

While everything is running fine I haven't noticed any meaningful improvement in R@h tasks completion times. Before the overclock my tasks were completing in ~28,800s (i.e., 8 hours). After the overclock completion times are pretty much exactly the same, albeit I occasionally see tasks finish up in just under 28,000s (i.e., 7:45 hours).

So despite a 33% boost in clock speed for the CPU I'm not seeing any meaningful improvement in R@h performance. My questions are:
1) Is there anything else I need to do with either R@h setting or BOINC settings to recognize this increased CPU clock speed?
2) Or is R@h sending bigger WUs to this machine that fit within a ~8 hour processing window? I have not modified the "Target CPU run time" setting from the default of 8 hours. I'd assume if this were the case I'd be seeing higher daily point totals, but that doesn't seem to be happening.

Thanks in advance.

R@h works differently than many other BOINC projects. There is a user preference for how long you would prefer the tasks to run. The setting is more of an objective than a hard rule.

You should look to compare credit per CPU hour. Credit is your best indication of how much work your machine completed.

Basically what is happening is that your machine is now completing more models in the 8 hours than it would without the overclock.

The Number Crunching board would be best place to post additional performance questions.

---

Rosetta Moderator: Mod.Sense

Thanks for the info, that gives me a much better picture of how things work with Rosetta.