Other DC (boinc) projects [e.g., Amicable numbers] which potentially tie up all the CPUs on one's PC have a mechanism where the max number of CPUs that can be used by any task is set by the user... and this is a straight-forward option within the Project preferences without any monkeying around:

Preferences for this project	Amicable Numbers preferences
                         ^ You can set a limit on the number of CPU cores used

LLP

Yes, I believe the highest number of cpus a wu can use right now is 16

---

Everything stays
But it still changes
Ever so slightly
Daily and nightly
In little ways
When everything stays...

Other DC (boinc) projects [e.g., Amicable numbers] which potentially tie up all the CPUs on one's PC have a mechanism where the max number of CPUs that can be used by any task is set by the user... and this is a straight-forward option within the Project preferences without any monkeying around:

Preferences for this project	Amicable Numbers preferences
                         ^ You can set a limit on the number of CPU cores used

LLP

I use this app_config.xml file to make mine only use 2 cpu's per task

<app_config>


<app_version>
<app_name>milkyway_nbody</app_name>
<plan_class>mt</plan_class>
<avg_ncpus>2</avg_ncpus>
<cmdline>--nthreads 2</cmdline>
</app_version>

<project_max_concurrent>2</project_max_concurrent>

</app_config>

It tells the pc to only use 2 cpu's per task and then to only run 2 tasks max, I adjust the last line based on the pc it's on, this one is from my laptop but my 5950X is running 15 tasks at a time when it runs them.

Thanks, I've set mine to also run multiple lower CPU count WUs. Is there any performance increase you see for doing this?

---

Everything stays
But it still changes
Ever so slightly
Daily and nightly
In little ways
When everything stays...

Thanks, I've set mine to also run multiple lower CPU count WUs. Is there any performance increase you see for doing this?

No I do it because MilkyWay isn't my prime focus right now and I can adjust the tasks up and down easily and quickly depending on when my other projects have the tasks I want.

Finn the Human wrote:

Thanks, I've set mine to also run multiple lower CPU count WUs. Is there any performance increase you see for doing this?

CPU utilization at high thread counts per task is not very good, therefore it occurs to me that host utilization is better with lower thread counts per task and higher number of concurrent tasks on a host. I am considering to eventually measure whether or not there is merit to my assumption, but haven't taken the time yet to set up a respective experiment, which would involve running a fixed workunit outside of BOINC for hopefully direct and precise comparison of different threads/tasks settings.

Just eyeballing the numbers, I see higher CPU utilization and more WUs being crunched. Probably because now I can run 6x (4core) WUs and saturate all 24 threads of my CPU. Individual WUs suffer less run time increase than the number of cores removed per WU.

---

Everything stays
But it still changes
Ever so slightly
Daily and nightly
In little ways
When everything stays...

Finn the Human wrote:

Thanks, I've set mine to also run multiple lower CPU count WUs. Is there any performance increase you see for doing this?

CPU utilization at high thread counts per task is not very good, therefore it occurs to me that host utilization is better with lower thread counts per task and higher number of concurrent tasks on a host. I am considering to eventually measure whether or not there is merit to my assumption, but haven't taken the time yet to set up a respective experiment, which would involve running a fixed workunit outside of BOINC for hopefully direct and precise comparison of different threads/tasks settings.

I have also noticed that.
On my 16core CPU I had to use 3x15Threads to get around 100% CPU load.
Now I try with 4x10Threads which is also running fine.
I have told my CPU to be a 45core via cc_config.xml.

With 2x16Threads I only saw about 50% load. The first minute only one Thread is under load and the second minute 12 Threads were loaded. This is really bad efficiency.