website/tutorials/2014-05-PATC: add solution for vector_scal filer

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/starpu/website@12976 176f6dd6-97d6-42f4-bd05-d3db9ad07c7a

tutorials/2014-05-PATC/files/vector_scal_task_insert_filter.c

+/* StarPU --- Runtime system for heterogeneous multicore architectures.
+ *
+ * Copyright (C) 2010, 2011, 2012, 2013, 2014  Centre National de la Recherche Scientifique
+ * Copyright (C) 2010-2012, 2014  Université de Bordeaux 1
+ *
+ * StarPU is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation; either version 2.1 of the License, or (at
+ * your option) any later version.
+ *
+ * StarPU is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ * See the GNU Lesser General Public License in COPYING.LGPL for more details.
+ */
+
+/*
+ * This example demonstrates how to use StarPU to scale an array by a factor.
+ * It shows how to manipulate data with StarPU's data management library.
+ *  1- how to declare a piece of data to StarPU (starpu_vector_data_register)
+ *  2- how to submit a task to StarPU
+ *  3- how a kernel can manipulate the data (buffers[0].vector.ptr)
+ */
+#include <starpu.h>
+
+#define    NX    2048
+
+extern void vector_scal_cpu(void *buffers[], void *_args);
+extern void vector_scal_cuda(void *buffers[], void *_args);
+extern void vector_scal_opencl(void *buffers[], void *_args);
+
+static struct starpu_codelet cl = {
+	/* CPU implementation of the codelet */
+	.cpu_funcs = {vector_scal_cpu, NULL},
+#ifdef STARPU_USE_CUDA
+	/* CUDA implementation of the codelet */
+	.cuda_funcs = {vector_scal_cuda, NULL},
+#endif
+#ifdef STARPU_USE_OPENCL
+	/* OpenCL implementation of the codelet */
+	.opencl_funcs = {vector_scal_opencl, NULL},
+#endif
+	.nbuffers = 1,
+	.modes = {STARPU_RW}
+};
+
+#ifdef STARPU_USE_OPENCL
+struct starpu_opencl_program programs;
+#endif
+
+int main(int argc, char **argv)
+{
+	/* We consider a vector of float that is initialized just as any of C
+	 * data */
+	float *vector;
+	unsigned i;
+
+	starpu_malloc((void**)&vector, NX * sizeof(vector[0]));
+
+	for (i = 0; i < NX; i++)
+		vector[i] = 1.0f;
+
+	fprintf(stderr, "BEFORE : First element was %f\n", vector[0]);
+
+	/* Initialize StarPU with default configuration */
+	int ret = starpu_init(NULL);
+	STARPU_CHECK_RETURN_VALUE(ret, "starpu_init");
+
+#ifdef STARPU_USE_OPENCL
+	starpu_opencl_load_opencl_from_file("vector_scal_opencl_kernel.cl", &programs, NULL);
+#endif
+
+	/* Tell StaPU to associate the "vector" vector with the "vector_handle"
+	 * identifier. When a task needs to access a piece of data, it should
+	 * refer to the handle that is associated to it.
+	 * In the case of the "vector" data interface:
+	 *  - the first argument of the registration method is a pointer to the
+	 *    handle that should describe the data
+	 *  - the second argument is the memory node where the data (ie. "vector")
+	 *    resides initially: 0 stands for an address in main memory, as
+	 *    opposed to an adress on a GPU for instance.
+	 *  - the third argument is the adress of the vector in RAM
+	 *  - the fourth argument is the number of elements in the vector
+	 *  - the fifth argument is the size of each element.
+	 */
+	starpu_data_handle_t vector_handle;
+	starpu_vector_data_register(&vector_handle, 0, (uintptr_t)vector,
+				    NX, sizeof(vector[0]));
+
+#define N 10
+	struct starpu_data_filter filter;
+	memset(&filter, 0, sizeof(filter));
+	filter.filter_func = starpu_vector_filter_block;
+	filter.nchildren = N;
+
+	starpu_data_partition(vector_handle, &filter);
+
+	float factor = 3.14;
+
+    for (i = 0; i < N; i++)
+    {
+	ret = starpu_insert_task(&cl,
+				 /* an argument is passed to the codelet, beware that this is a
+				  * READ-ONLY buffer and that the codelet may be given a pointer to a
+				  * COPY of the argument */
+				 STARPU_VALUE, &factor, sizeof(factor),
+				 /* the codelet manipulates one buffer in RW mode */
+				 STARPU_RW, starpu_data_get_sub_data(vector_handle, 1, i),
+				 0);
+	STARPU_CHECK_RETURN_VALUE(ret, "starpu_insert_task");
+    }
+
+	/* Wait for tasks completion */
+	starpu_task_wait_for_all();
+
+	/* StarPU does not need to manipulate the array anymore so we can stop
+	 * monitoring it */
+	starpu_data_unpartition(vector_handle, 0);
+	starpu_data_unregister(vector_handle);
+
+#ifdef STARPU_USE_OPENCL
+	starpu_opencl_unload_opencl(&programs);
+#endif
+
+	/* terminate StarPU, no task can be submitted after */
+	starpu_shutdown();
+
+	fprintf(stderr, "AFTER First element is %f\n", vector[0]);
+
+	return 0;
+}

tutorials/2014-05-PATC/index.html

@@ -414,8 +414,10 @@ have been easily ported to StarPU by simply using <tt>starpu_insert_task</tt>.
 <p>
 Take the vector example again, and add partitioning support to it, using the
 matrix-matrix multiplication as an example. Here we will use the
-<tt>starpu_vector_filter_block</tt> filter. Try to run it with various numbers
-of tasks.
+<a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/group__API__Data__Partition.html#ga212189d3b83dfa4e225609b5f2bf8461"><tt>starpu_vector_filter_block()</tt></a> filter function. You can see the list of
+predefined filters provided by
+StarPU <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/starpu__data__filters_8h.html">here</a>.
+Try to run it with various numbers of tasks.
 </p>
 </div>
 </div>