Changes between Version 16 and Version 17 of Public/User_Guide/Offloading_hybrid_apps

Timestamp:

Sep 17, 2019, 5:58:00 PM (5 years ago)

Author:

Kevin Sala

Comment:

—

Public/User_Guide/Offloading_hybrid_apps

@@ -38 +38 @@
 
 On the other hand, !OmpSs-2 proposes another approach targeting NVIDIA Unified Memory
-devices. CUDA kernels can be annotated as tasks declaring the corresponding data dependencies
-on the data buffers, so that, when all the dependencies of a task are satisfied, the CUDA
-kernel associated is offloaded to one of the available GPUs. In order to use that functionality,
-the user only has to allocate the buffers that CUDA kernels will access as a Unified Memory 
-buffers (using the `cudaMallocManaged()` function).
+devices. CUDA kernels can be annotated as regular tasks, and they can declare the 
+corresponding data dependencies on the data buffers. When all the dependencies of a CUDA task 
+are satisfied, the CUDA kernel associated to the task is offloaded to one of the available
+GPUs. To use that functionality, the user only has to allocate the buffers that CUDA kernels
+will access as Unified Memory buffers (i.e., using the `cudaMallocManaged()` function).
 
 == N-Body Benchmark ==