• Dukc (8/8) May 07 2020 Is there some way to measure the performance of a function so
• Simen =?UTF-8?B?S2rDpnLDpXM=?= (7/17) May 07 2020 If I understand correctly, you want to measure how many cycles
• Dukc (8/12) May 07 2020 Something like that. Well, I would also like to eliminate
• Dennis (7/12) May 07 2020 You can make a reference program that you use to get a measure
• Dukc (4/10) May 07 2020 I have to keep that in mind, but I'd prefer something that does

Dukc <ajieskola gmail.com> writes:

Is there some way to measure the performance of a function so 
that the results will be same in different computers (all x86, 
but otherwise different processors)? I'm thinking of making a 
test suite that could find performance regressions automatically.

I figured out Bochs[1] could be used for that, but it seems an 
overkill for me to install a whole virtual operating system just 
to benchmark functions. Does anybody know more lightweight way?

[1] http://bochs.sourceforge.net/

Simen =?UTF-8?B?S2rDpnLDpXM=?= <simen.kjaras gmail.com> writes:

On Thursday, 7 May 2020 at 10:21:07 UTC, Dukc wrote:
 Is there some way to measure the performance of a function so 
 that the results will be same in different computers (all x86, 
 but otherwise different processors)? I'm thinking of making a 
 test suite that could find performance regressions 
 automatically.

 I figured out Bochs[1] could be used for that, but it seems an 
 overkill for me to install a whole virtual operating system 
 just to benchmark functions. Does anybody know more lightweight 
 way?

 [1] http://bochs.sourceforge.net/

If I understand correctly, you want to measure how many cycles 
pass, rather than clock time?

If so, it seems perf can do that: 
https://perf.wiki.kernel.org/index.php/Tutorial

--
   Simen

Dukc <ajieskola gmail.com> writes:

On Thursday, 7 May 2020 at 10:51:27 UTC, Simen Kjærås wrote:
 If I understand correctly, you want to measure how many cycles 
 pass, rather than clock time?

Something like that. Well, I would also like to eliminate 
differences based on different memory caches between machines.

In addition, if the profiler could eliminate the randomness of 
the benchamrks that results from memory aligment, context 
switches and dunno, that would obviously be a big plus for 
automatic testing.

 If so, it seems perf can do that: 
 https://perf.wiki.kernel.org/index.php/Tutorial


Sounds worth a look. Thanks!

Dennis <dkorpel gmail.com> writes:

On Thursday, 7 May 2020 at 10:21:07 UTC, Dukc wrote:
 Is there some way to measure the performance of a function so 
 that the results will be same in different computers (all x86, 
 but otherwise different processors)? I'm thinking of making a 
 test suite that could find performance regressions 
 automatically.

You can make a reference program that you use to get a measure 
for how fast the computer is that you run the benchmark on. Then 
you can use that to scale your actual benchmark results.

When testing regressions there's a fairly obvious choice for this 
reference program: the old version. You can compare those results 
with the new version and report the relative difference.

Dukc <ajieskola gmail.com> writes:

On Thursday, 7 May 2020 at 11:06:17 UTC, Dennis wrote:
 You can make a reference program that you use to get a measure 
 for how fast the computer is that you run the benchmark on. 
 Then you can use that to scale your actual benchmark results.

 When testing regressions there's a fairly obvious choice for 
 this reference program: the old version. You can compare those 
 results with the new version and report the relative difference.

I have to keep that in mind, but I'd prefer something that does 
not require keeping old sources working, or floating their 
binaries around.