Merge branch 'knobs' of git+ssh://scm.gforge.inria.fr/gitroot/starpu/starpu into knobs

AUTHORS

@@ -21,6 +21,7 @@ Khorsi Yanis, Inria, <yanis.khorsi@inria.fr>
 Lambert Thibaut, Inria, <thibaud.lambert@inria.fr>
 Leria Erwan, University of Bordeaux, <erwan.leria@etu.u-bordeaux.fr>
 Lizé Benoît, Airbus, <benoit.lize@gmail.com>
+Makni Mariem, Inria, <mariem.makni@inria.fr>
 Nakov Stojce, Inria, <stojce.nakov@inria.fr>
 Namyst Raymond, University of Bordeaux, <raymond.namyst@labri.fr>
 Nesi Lucas Leandro, Federal University of Rio Grande do Sul (UFRGS), <llnesi@inf.ufrgs.br>

doc/doxygen/chapters/101_building.doxy

@@ -504,8 +504,10 @@ multiplication using BLAS and cuBLAS. They output the obtained GFlops.
 It can also be convenient to try simulated benchmarks, if you want to give a try
 at CPU-GPU scheduling without actually having a GPU at hand. This can be done by
 using the simgrid version of StarPU: first install the simgrid simulator from
-http://simgrid.gforge.inria.fr/ (we tested with simgrid 3.11, 3.12 and 3.13, other versions
-may have compatibility issues), then configure StarPU with \ref enable-simgrid
+http://simgrid.gforge.inria.fr/ (we tested with simgrid from 3.11 to 3.16, and
+3.18 to 3.22, other versions may have compatibility issues, 3.17 notably does
+not build at all. MPI simulation does not work with version 3.22),
+then configure StarPU with \ref enable-simgrid
 "--enable-simgrid" and rebuild and install it, and then you can simulate the performance for a
 few virtualized systems shipped along StarPU: attila, mirage, idgraf, and sirocco.
 

doc/doxygen/chapters/320_scheduling.doxy

@@ -166,20 +166,34 @@ be obtained from the machine power supplier.
 The energy actually consumed by the total execution can be displayed by setting
 <c>export STARPU_PROFILING=1 STARPU_WORKER_STATS=1</c> .
 
-On-line task consumption measurement is currently only supported through the
+For OpenCL devices, on-line task consumption measurement is currently supported through the
 <c>CL_PROFILING_POWER_CONSUMED</c> OpenCL extension, implemented in the MoviSim
-simulator. Applications can however provide explicit measurements by
-using the function starpu_perfmodel_update_history() (examplified in \ref PerformanceModelExample
-with the <c>energy_model</c> performance model). Fine-grain
-measurement is often not feasible with the feedback provided by the hardware, so
-the user can for instance run a given task a thousand times, measure the global
+simulator.
+
+For CUDA devices, on-line task consumption measurement is supported on V100
+cards and beyond. This however only works for quite long tasks, since the
+measurement granularity is about 10ms.
+
+Applications can however provide explicit measurements by using the function
+starpu_perfmodel_update_history() (examplified in \ref PerformanceModelExample
+with the <c>energy_model</c> performance model). Fine-grain measurement
+is often not feasible with the feedback provided by the hardware, so the
+user can for instance run a given task a thousand times, measure the global
 consumption for that series of tasks, divide it by a thousand, repeat for
-varying kinds of tasks and task sizes, and eventually feed StarPU
-with these manual measurements through starpu_perfmodel_update_history().
-For instance, for CUDA devices, <c>nvidia-smi -q -d POWER</c> can be used to get
-the current consumption in Watt. Multiplying this value by the average duration
-of a single task gives the consumption of the task in Joules, which can be given
-to starpu_perfmodel_update_history().
+varying kinds of tasks and task sizes, and eventually feed StarPU with these
+manual measurements through starpu_perfmodel_update_history().  For instance,
+for CUDA devices, <c>nvidia-smi -q -d POWER</c> can be used to get the current
+consumption in Watt. Multiplying this value by the average duration of a
+single task gives the consumption of the task in Joules, which can be given to
+starpu_perfmodel_update_history().
+
+Another way to provide the energy performance is to define a
+perfmodel with starpu_perfmodel::type ::STARPU_PER_ARCH, and set the
+starpu_perfmodel::arch_cost_function field to a function which shall return the
+estimated consumption of the task in Joules. Such a function can for instance
+use starpu_task_expected_length() on the task (in µs), multiplied by the
+typical power consumption of the device, e.g. in W, and divided by 1000000. to
+get Joules.
 
 \section ExistingModularizedSchedulers Modularized Schedulers
 

doc/doxygen/chapters/470_simgrid.doxy

@@ -16,6 +16,10 @@
  * See the GNU Lesser General Public License in COPYING.LGPL for more details.
  */
 
+/*
+ * NOTE: XXX: also update simgrid versions in 101_building.doxy !!
+ */
+
 /*! \page SimGridSupport SimGrid Support
 
 StarPU can use Simgrid in order to simulate execution on an arbitrary

examples/mult/xgemm.c

@@ -1,6 +1,6 @@
 /* StarPU --- Runtime system for heterogeneous multicore architectures.
  *
- * Copyright (C) 2009-2017                                Université de Bordeaux
+ * Copyright (C) 2009-2017, 2019                                Université de Bordeaux
  * Copyright (C) 2012,2013                                Inria
  * Copyright (C) 2017                                     Erwan Leria
  * Copyright (C) 2010                                     Mehdi Juhoor
@@ -269,6 +269,12 @@ static void parse_args(int argc, char **argv)
 			xdim = strtol(argv[++i], &argptr, 10);
 		}
 
+		else if (strcmp(argv[i], "-xy") == 0)
+		{
+			char *argptr;
+			xdim = ydim = strtol(argv[++i], &argptr, 10);
+		}
+
 		else if (strcmp(argv[i], "-y") == 0)
 		{
 			char *argptr;
@@ -310,7 +316,7 @@ static void parse_args(int argc, char **argv)
 
 		else if (strcmp(argv[i], "-help") == 0 || strcmp(argv[i], "--help") == 0 || strcmp(argv[i], "-h") == 0)
 		{
-			fprintf(stderr,"Usage: %s [-nblocks n] [-nblocksx x] [-nblocksy y] [-x x] [-y y] [-z z] [-size size] [-iter iter] [-bound] [-check] [-spmd]\n", argv[0]);
+			fprintf(stderr,"Usage: %s [-nblocks n] [-nblocksx x] [-nblocksy y] [-x x] [-y y] [-xy n] [-z z] [-size size] [-iter iter] [-bound] [-check] [-spmd]\n", argv[0]);
 			fprintf(stderr,"Currently selected: %ux%u * %ux%u and %ux%u blocks, %u iterations\n", zdim, ydim, xdim, zdim, nslicesx, nslicesy, niter);
 			exit(EXIT_SUCCESS);
 		}

mpi/examples/user_datatype/my_interface.c

@@ -111,8 +111,6 @@ static void data_register_data_handle(starpu_data_handle_t handle, unsigned home
 {
 	struct starpu_my_data_interface *my_data_interface = (struct starpu_my_data_interface *) data_interface;
 
-	struct starpu_my_data *data = (struct starpu_my_data *)my_data_interface->ptr;
-
 	unsigned node;
 	for (node = 0; node < STARPU_MAXNODES; node++)
 	{

mpi/src/starpu_mpi_cache.c

@@ -98,7 +98,6 @@ void _starpu_mpi_cache_shutdown()
 	}
 	STARPU_PTHREAD_MUTEX_UNLOCK(&_cache_mutex);
 	STARPU_PTHREAD_MUTEX_DESTROY(&_cache_mutex);
-	free(_cache_data);
 	_starpu_mpi_cache_stats_shutdown();
 }
 

src/core/perfmodel/perfmodel_history.c

@@ -742,7 +742,7 @@ static void check_per_arch_model(struct starpu_perfmodel *model, int comb, unsig
 	struct starpu_perfmodel_history_list *ptr = NULL;
 	unsigned nentries = 0;
 
-	if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED)
+	if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED  || model->type == STARPU_REGRESSION_BASED)
 	{
 		/* Dump the list of all entries in the history */
 		ptr = per_arch_model->list;
@@ -760,7 +760,7 @@ static void check_per_arch_model(struct starpu_perfmodel *model, int comb, unsig
 	check_reg_model(model, comb, impl);
 
 	/* Dump the history into the model file in case it is necessary */
-	if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED)
+	if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED || model->type == STARPU_REGRESSION_BASED)
 	{
 		ptr = per_arch_model->list;
 		while (ptr)
@@ -779,7 +779,7 @@ static void dump_per_arch_model_file(FILE *f, struct starpu_perfmodel *model, in
 	struct starpu_perfmodel_history_list *ptr = NULL;
 	unsigned nentries = 0;
 
-	if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED)
+       if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED || model->type == STARPU_REGRESSION_BASED)
 	{
 		/* Dump the list of all entries in the history */
 		ptr = per_arch_model->list;
@@ -800,7 +800,7 @@ static void dump_per_arch_model_file(FILE *f, struct starpu_perfmodel *model, in
 	dump_reg_model(f, model, comb, impl);
 
 	/* Dump the history into the model file in case it is necessary */
-	if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED)
+       if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED || model->type == STARPU_REGRESSION_BASED)
 	{
 		fprintf(f, "# hash\t\tsize\t\tflops\t\tmean (us)\tdev (us)\tsum\t\tsum2\t\tn\n");
 		ptr = per_arch_model->list;
@@ -1046,7 +1046,7 @@ void starpu_perfmodel_dump_xml(FILE *f, struct starpu_perfmodel *model)
 		int nimpls = model->state->nimpls[comb];
 		for (impl = 0; impl < nimpls; impl++)
 		{
-			fprintf(f, "    <implementation id=\"%u\">\n", impl);
+			fprintf(f, "    <implementation id=\"%d\">\n", impl);
 			char archname[STR_SHORT_LENGTH];
 			starpu_perfmodel_get_arch_name(arch_combs[comb], archname,  sizeof(archname), impl);
 			fprintf(f, "      <!-- %s -->\n", archname);
@@ -1410,25 +1410,27 @@ int starpu_perfmodel_list(FILE *output)
 {
 #if !defined(_WIN32) || defined(__MINGW32__) || defined(__CYGWIN__)
         char *path;
-        DIR *dp;
+	struct dirent **list;
+	int n;
 
 	path = _starpu_get_perf_model_dir_codelet();
-        dp = opendir(path);
-        if (dp != NULL)
-	{
-		struct dirent *ep;
-                while ((ep = readdir(dp)))
-		{
-                        if (strcmp(ep->d_name, ".") && strcmp(ep->d_name, ".."))
-                                fprintf(output, "file: <%s>\n", ep->d_name);
-                }
-                closedir (dp);
-        }
-        else
+	n = scandir(path, &list, NULL, alphasort);
+	if (n < 0)
 	{
 		_STARPU_DISP("Could not open the perfmodel directory <%s>: %s\n", path, strerror(errno));
-        }
-	return 0;
+		return 1;
+	}
+	else
+	{
+		int i;
+		for (i = 0; i < n; i++) {
+			if (strcmp(list[i]->d_name, ".") && strcmp(list[i]->d_name, ".."))
+				fprintf(output, "file: <%s>\n", list[i]->d_name);
+			free(list[i]);
+		}
+		free(list);
+		return 0;
+	}
 #else
 	_STARPU_MSG("Listing perfmodels is not implemented on pure Windows yet\n");
 	return 1;
@@ -1859,7 +1861,7 @@ void _starpu_update_perfmodel_history(struct _starpu_job *j, struct starpu_perfm
 			model->state->per_arch_is_set[comb][impl] = 1;
 		}
 
-		if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED)
+		if (model->type == STARPU_HISTORY_BASED || model->type == STARPU_NL_REGRESSION_BASED || model->type == STARPU_REGRESSION_BASED)
 		{
 			struct starpu_perfmodel_history_entry *entry;
 			struct starpu_perfmodel_history_table *elt;

src/debug/traces/anim.c

@@ -409,10 +409,13 @@ void _starpu_fxt_component_push(FILE *output, struct starpu_fxt_options *options
 	}
 	else
 		nflowing++;
-	if (prio)
-		to_p->npriotasks++;
-	else
-		to_p->ntasks++;
+	if (to_p)
+	{
+		if (prio)
+			to_p->npriotasks++;
+		else
+			to_p->ntasks++;
+	}
 
 	// fprintf(stderr,"push from %s to %s\n", from_p?from_p->name:"none", to_p?to_p->name:"none");
 	fxt_component_print_step(output, options, timestamp, workerid, 1, from_p, to_p);
@@ -435,10 +438,13 @@ void _starpu_fxt_component_pull(FILE *output, struct starpu_fxt_options *options
 		COMPONENT_FIND(components, to, to_p);
 		STARPU_ASSERT(to_p);
 	}
-	if (prio)
-		from_p->npriotasks--;
-	else
-		from_p->ntasks--;
+	if (from_p)
+	{
+		if (prio)
+			from_p->npriotasks--;
+		else
+			from_p->ntasks--;
+	}
 	if (to_p)
 	{
 		if (prio)

src/util/starpu_task_insert.c

@@ -142,7 +142,7 @@ int _starpu_task_insert_v(struct starpu_codelet *cl, va_list varg_list)
 
 	if (STARPU_UNLIKELY(ret == -ENODEV))
 	{
-		_STARPU_MSG("submission of task %p wih codelet %p failed (symbol `%s') (err: ENODEV)\n",
+		_STARPU_MSG("submission of task %p with codelet %p failed (symbol `%s') (err: ENODEV)\n",
 			    task, task->cl,
 			    (cl == NULL) ? "none" :
 			    task->cl->name ? task->cl->name :

tests/datawizard/partition_init.c

@@ -27,7 +27,7 @@ void my_func(void *buffers[], void *cl_arg)
 	for(i=0 ; i<nb ; i++)
 	{
 		v[i] = i+42;
-		FPRINTF(stderr, "setting v[%d] to %d\n",i, v[i]);
+		FPRINTF(stderr, "setting v[%u] to %d\n",i, v[i]);
 	}
 }
 
@@ -44,7 +44,7 @@ void display_func(void *buffers[], void *cl_arg)
         int *v = (int *)STARPU_VECTOR_GET_PTR(buffers[0]);
 
 	unsigned i;
-	for(i=0 ; i<nb ; i++) FPRINTF(stderr, "v[%d] = %d\n", i, v[i]);
+	for(i=0 ; i<nb ; i++) FPRINTF(stderr, "v[%u] = %d\n", i, v[i]);
 }
 
 struct starpu_codelet display_codelet =

tests/parallel_tasks/parallel_kernels_trivial.c

@@ -94,8 +94,6 @@ int main(void)
 	starpu_malloc((void **)&v, VECTORSIZE*sizeof(unsigned));
 	starpu_vector_data_register(&v_handle, STARPU_MAIN_RAM, (uintptr_t)v, VECTORSIZE, sizeof(unsigned));
 
-	unsigned nworker = starpu_worker_get_count() + starpu_combined_worker_get_count();
-
 	/* First submit a sequential task */
 	ret = starpu_task_insert(&cl_seq, STARPU_R, v_handle, 0);
 	if (ret == -ENODEV) goto enodev;