|Efficient Execution Time Profiling ? email@example.com (1992-04-29)|
|Re: Efficient Execution Time Profiling ? firstname.lastname@example.org (1992-04-30)|
|Re: Efficient Execution Time Profiling ? email@example.com (1992-05-08)|
|Re: Efficient Execution Time Profiling ? firstname.lastname@example.org (1992-05-09)|
|Re: Efficient Execution Time Profiling ? email@example.com (1992-05-11)|
|Organization:||University of Colorado at Boulder|
|Date:||Fri, 8 May 1992 00:29:22 GMT|
firstname.lastname@example.org (David Keppel) said:
> Some specific systems have accurate clocks that can be accessed at low
> and/or predictable delay. ...
According to some asking around, SparcStations-1's and -2's have an
other-wise unused timer available. The other timer is used for the 100Hz
(or whatever) interrupt.
We're in trying to mmap this puppy into user memory to use for timing, but
I would imagine others have done this already.
If you have, please let us know how it went & if you can share the source
(yes, we have a license).
Return to the
Search the comp.compilers archives again.