- Aug 21, 2018
-
-
Victor Lopez authored
-
- Apr 29, 2015
-
-
Victor Lopez authored
-
- Mar 10, 2015
-
-
Victor Lopez authored
-
- Mar 09, 2015
-
-
Victor Lopez authored
-
- Aug 04, 2014
-
-
Judit Planas authored
-
Judit Planas authored
By now, this approach is only used by CUDA.
-
- Oct 24, 2013
-
-
Judit Planas authored
- A new configuration option has been added to control whether we want to exploit the concurrent kernel execution feature and use N execution streams, or use just one. - Changing task execution's instrumentation: - Extrae events are emitted using CUDA events and callbacks. - A couple of functions have been added to Nanox's API to fit this change. - instrumentation_api family has been increased to 1001. - enableWDClosingEvents() function has no effect from now on for GPU Device. - This also implies a change in application's generated code that will call these API functions (Mercurium's DeviceProvider class basically). - Task number event (WorkDescriptor ID) is now emitted while the user code of GPU tasks is being executed. - WD's deferred events are flushed just before the GPU task is run.
-
Xavier Teruel authored
Closing burst events specifying type (using 0 in those events representing a value or an unspecifed value); close #882
-
- Oct 11, 2013
-
-
Xavier Teruel authored
-
Guillermo Miranda authored
-
- Aug 13, 2013
-
-
Xavier Teruel authored
-
- Aug 12, 2013
-
-
Xavier Teruel authored
-
Xavier Teruel authored
-
Xavier Teruel authored
-
- May 15, 2013
-
-
Javier Bueno Hedo authored
This reverts commit 072ac697, reversing changes made to 9a87a06f.
-
- Jan 31, 2013
-
-
Florentino Sainz authored
-
- Jan 15, 2013
-
-
- Nov 29, 2012
-
-
Xavier Teruel authored
-
- Oct 19, 2012
-
-
Xavier Teruel authored
Solving conflict between (e Event) and (e nanos_err_t) in instrumentation API; Error come from exception first implementation; see #18
-
Xavier Teruel authored
-
- Sep 25, 2012
-
-
Xavier Teruel authored
-
- Sep 07, 2012
-
-
Xavier Teruel authored
-
- Aug 22, 2012
-
-
Xavier Teruel authored
Simplifying instrumentation mechanism, reducing event size and removing some instrumentation calls; see #679
-
- Aug 16, 2012
-
-
Javier Bueno Hedo authored
-
- Feb 14, 2012
-
-
Judit authored
-
- Jan 13, 2012
-
-
Xavier Teruel authored
-
Xavier Teruel authored
-
- Oct 10, 2011
-
-
Xavier Teruel authored
Implementing enable/disable instrumentation pure virtual functions. Implementing these services in extrae plugin using Extrae_shutdown() and Extrae_restart() functions; see #563
-
- May 06, 2011
-
-
Judit Planas authored
-
- Dec 20, 2010
-
-
Xavier Teruel authored
-
- Nov 25, 2010
-
-
Judit Planas authored
-
- Nov 16, 2010
-
-
Judit Planas authored
-
- Oct 14, 2010
-
-
Judit Planas authored
As kernel calls are asynchronous, the event was actually raised inside the task outline, before the task had finished, giving an erroneous timestamp. Currently, this event is raised after the call to cudaThreadSynchronize().
-
- Sep 01, 2010
-
-
JAVIER TERUEL GARCIA authored
-
- Aug 31, 2010
-
-
JAVIER TERUEL GARCIA authored
-
- Jul 29, 2010
-
-
JAVIER TERUEL GARCIA authored
-
- Jul 21, 2010
-
-
JAVIER TERUEL GARCIA authored
-
- Jul 14, 2010
-
-
JAVIER TERUEL GARCIA authored
-
- Jul 02, 2010
-
-
Alex Duran authored
-
- Jul 01, 2010
-
-
JAVIER TERUEL GARCIA authored
-