You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
If we only want to wait for a very short amount of time, then at some point suspending a thread and thereby performing a context switch, becomes less efficient than busy waiting. I would guess that up to a few or maybe a couple dozen microseconds we should busy wait. This matches with what Prof. Montenegro told me in an E-Mail. They did some measurements with an STM32F4 (I don't know the clock rate they used) and found that switch from a thread to an interrupt and back takes < 6 µs.
The text was updated successfully, but these errors were encountered:
Description
If we only want to wait for a very short amount of time, then at some point suspending a thread and thereby performing a context switch, becomes less efficient than busy waiting. I would guess that up to a few or maybe a couple dozen microseconds we should busy wait. This matches with what Prof. Montenegro told me in an E-Mail. They did some measurements with an STM32F4 (I don't know the clock rate they used) and found that switch from a thread to an interrupt and back takes < 6 µs.
The text was updated successfully, but these errors were encountered: