split long lines

doc/chapters/advanced-examples.texi

@@ -228,7 +228,8 @@ int vector[NX];
 starpu_data_handle_t handle;
 
 /* Declare data to StarPU */
-starpu_vector_data_register(&handle, 0, (uintptr_t)vector, NX, sizeof(vector[0]));
+starpu_vector_data_register(&handle, 0, (uintptr_t)vector,
+                            NX, sizeof(vector[0]));
 
 /* Partition the vector in PARTS sub-vectors */
 starpu_filter f =
@@ -630,7 +631,8 @@ instance, assuming that the index variable @code{i} was registered as handle
 starpu_insert_task(&which_index, STARPU_W, i_handle, 0);
 
 /* And submit the corresponding task */
-STARPU_DATA_ACQUIRE_CB(i_handle, STARPU_R, starpu_insert_task(&work, STARPU_RW, A_handle[i], 0));
+STARPU_DATA_ACQUIRE_CB(i_handle, STARPU_R,
+                       starpu_insert_task(&work, STARPU_RW, A_handle[i], 0));
 @end smallexample
 
 The @code{STARPU_DATA_ACQUIRE_CB} macro submits an asynchronous request for
@@ -769,7 +771,8 @@ which provides per-worker buffers without content consistency.
 @smallexample
 starpu_vector_data_register(&workspace, -1, 0, sizeof(float));
 for (i = 0; i < N; i++)
-    starpu_insert_task(&compute, STARPU_R, input[i], STARPU_SCRATCH, workspace, STARPU_W, output[i], 0);
+    starpu_insert_task(&compute, STARPU_R, input[i],
+                       STARPU_SCRATCH, workspace, STARPU_W, output[i], 0);
 @end smallexample
 
 StarPU will make sure that the buffer is allocated before executing the task,
@@ -1065,7 +1068,8 @@ for (workerid = 0; workerid < starpu_worker_get_count(); workerid++)
 cudaGraphicsResourceGetMappedPointer((void**)&output, &num_bytes, resource);
 
 /* And register it to StarPU */
-starpu_vector_data_register(&handle, starpu_worker_get_memory_node(workerid), output, num_bytes / sizeof(float4), sizeof(float4));
+starpu_vector_data_register(&handle, starpu_worker_get_memory_node(workerid),
+                            output, num_bytes / sizeof(float4), sizeof(float4));
 
 /* The handle can now be used as usual */
 starpu_insert_task(&cl, STARPU_RW, handle, 0);

doc/chapters/basic-examples.texi

@@ -739,7 +739,8 @@ extern "C" void scal_cuda_func(void *buffers[], void *_args)
     unsigned threads_per_block = 64;
     unsigned nblocks = (n + threads_per_block-1) / threads_per_block;
 
-@i{    vector_mult_cuda<<<nblocks,threads_per_block, 0, starpu_cuda_get_local_stream()>>>(val, n, *factor);}
+@i{    vector_mult_cuda<<<nblocks,threads_per_block, 0, starpu_cuda_get_local_stream()>>>}
+@i{                    (val, n, *factor);}
 
 @i{    cudaStreamSynchronize(starpu_cuda_get_local_stream());}
 @}
@@ -803,7 +804,8 @@ void scal_opencl_func(void *buffers[], void *_args)
 @i{    @{}
 @i{        size_t global=n;}
 @i{        size_t local=1;}
-@i{        err = clEnqueueNDRangeKernel(queue, kernel, 1, NULL, &global, &local, 0, NULL, &event);}
+@i{        err = clEnqueueNDRangeKernel(queue, kernel, 1, NULL,}
+@i{                                     &global, &local, 0, NULL, &event);}
 @i{        if (err != CL_SUCCESS) STARPU_OPENCL_REPORT_ERROR(err);}
 @i{    @}}
 

doc/chapters/perf-optimization.texi

@@ -276,7 +276,9 @@ void feed(void) @{
         starpu_data_handle_t handle;
 	starpu_vector_data_register(&handle, -1, 0, measure->size, sizeof(float));
 	task.handles[0] = handle;
-	starpu_perfmodel_update_history(&perf_model, &task, STARPU_CUDA_DEFAULT + measure->cudadev, 0, measure->implementation, measure->time);
+	starpu_perfmodel_update_history(&perf_model, &task,
+	                                STARPU_CUDA_DEFAULT + measure->cudadev, 0,
+	                                measure->implementation, measure->time);
 	starpu_task_clean(&task);
 	starpu_data_unregister(handle);
     @}

doc/chapters/vector_scal_cuda.texi

@@ -1,7 +1,7 @@
 @c -*-texinfo-*-
 
 @c This file is part of the StarPU Handbook.
-@c Copyright (C) 2009-2011  Université de Bordeaux 1
+@c Copyright (C) 2009-2012  Université de Bordeaux 1
 @c Copyright (C) 2010, 2011, 2012  Centre National de la Recherche Scientifique
 @c See the file starpu.texi for copying conditions.
 
@@ -27,7 +27,8 @@ extern "C" void scal_cuda_func(void *buffers[], void *_args)
         unsigned threads_per_block = 64;
         unsigned nblocks = (n + threads_per_block-1) / threads_per_block;
 
-        vector_mult_cuda<<<nblocks,threads_per_block, 0, starpu_cuda_get_local_stream()>>>(val, n, *factor);
+        vector_mult_cuda<<<nblocks,threads_per_block, 0, starpu_cuda_get_local_stream()>>>
+	                (val, n, *factor);
 
         cudaStreamSynchronize(starpu_cuda_get_local_stream());
 @}