Fig. 14

Download original image
Speedups of the OpenMP-parallelised FCFC with respect to the serial version on Haswell and Knights Landing CPUs with different numbers of OpenMP threads, measured using a periodic cubic random catalogue with Ν = 5 × 107, Lbox = 3 h−1 Gpc, and with 200 linear s bins in [0, 200) h−1 Mpc and 120 μ bins in [0, 1). The dashed line denotes the theoretical maximum speedup. SIMD is enabled in all cases.
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.