|
|
@@ -1487,12 +1487,32 @@ to configure a performance model for the codelets of the application (see
|
|
|
@ref{Performance model example} for instance). History-based performance models
|
|
|
use on-line calibration. StarPU will automatically calibrate codelets
|
|
|
which have never been calibrated yet. To force continuing calibration, use
|
|
|
-@code{export STARPU_CALIBRATE=1} . To drop existing calibration information
|
|
|
-completely and re-calibrate from start, use @code{export STARPU_CALIBRATE=2}.
|
|
|
+@code{export STARPU_CALIBRATE=1} . This may be necessary if your application
|
|
|
+have not-so-stable performance. Details on the current performance model status
|
|
|
+can be obtained from the @code{starpu_perfmodel_display} command: the @code{-l}
|
|
|
+option lists the available performance models, and the @code{-s} option permits
|
|
|
+to choose the performance model to be displayed. The result looks like:
|
|
|
+
|
|
|
+@example
|
|
|
+€ starpu_perfmodel_display -s starpu_dlu_lu_model_22
|
|
|
+performance model for cpu
|
|
|
+# hash size mean dev n
|
|
|
+5c6c3401 1572864 1.216300e+04 2.277778e+03 1240
|
|
|
+@end example
|
|
|
+
|
|
|
+Which shows that for the LU 22 kernel with a 1.5MiB matrix, the average
|
|
|
+execution time on CPUs was about 12ms, with a 2ms standard deviation, over
|
|
|
+1240 samples. It is a good idea to check this before doing actual performance
|
|
|
+measurements.
|
|
|
+
|
|
|
+If a kernel source code was modified (e.g. performance improvement), the
|
|
|
+calibration information is stale and should be dropped, to re-calibrate from
|
|
|
+start. This can be done by using @code{export STARPU_CALIBRATE=2}.
|
|
|
+
|
|
|
Note: due to CUDA limitations, to be able to measure kernel duration,
|
|
|
calibration mode needs to disable asynchronous data transfers. Calibration thus
|
|
|
disables data transfer / computation overlapping, and should thus not be used
|
|
|
-for eventual benchmarks. Note 2: history-based performance model get calibrated
|
|
|
+for eventual benchmarks. Note 2: history-based performance models get calibrated
|
|
|
only if a performance-model-based scheduler is chosen.
|
|
|
|
|
|
@node Task distribution vs Data transfer
|
|
|
@@ -1514,7 +1534,7 @@ the good results that a precise estimation would give.
|
|
|
@node Data prefetch
|
|
|
@section Data prefetch
|
|
|
|
|
|
-The heft scheduling policy performs data prefetch (see @ref{STARPU_PREFETCH}):
|
|
|
+The heft, dmda and pheft scheduling policies perform data prefetch (see @ref{STARPU_PREFETCH}):
|
|
|
as soon as a scheduling decision is taken for a task, requests are issued to
|
|
|
transfer its required data to the target processing unit, if needeed, so that
|
|
|
when the processing unit actually starts the task, its data will hopefully be
|
