Free Access
Fig. 4
Speed-ups of the large 3D radiative transfer test calculation for the OpenCL, OpenMP, and MPI implementations relative to the serial CPU run. The MPI calculation was run on 4 cores (1 CPU), and the OpenMP run used 16 threads (8 cores, incl. hyperthreading) to be comparable to the OpenCL CPU run.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.