|
@@ -1329,6 +1329,10 @@ use on-line calibration. StarPU will automatically calibrate codelets
|
|
|
which have never been calibrated yet. To force continuing calibration, use
|
|
which have never been calibrated yet. To force continuing calibration, use
|
|
|
@code{export STARPU_CALIBRATE=1} . To drop existing calibration information
|
|
@code{export STARPU_CALIBRATE=1} . To drop existing calibration information
|
|
|
completely and re-calibrate from start, use @code{export STARPU_CALIBRATE=2}.
|
|
completely and re-calibrate from start, use @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.
|
|
|
|
|
|
|
|
@node Task distribution vs Data transfer
|
|
@node Task distribution vs Data transfer
|
|
|
@section Task distribution vs Data transfer
|
|
@section Task distribution vs Data transfer
|
