Skip to main content
. Author manuscript; available in PMC: 2023 Mar 1.
Published in final edited form as: IEEE Trans Parallel Distrib Syst. 2021 Jul 21;33(3):642–653. doi: 10.1109/tpds.2021.3098456

TABLE 5.

Estimated optimal MFLUPSmaxfrom LBM roofline performance model for a V100 GPU using direct addressing and equation 25.

Pattern Bytes/FLUP (B/F) D2Q9 B/F D2Q9 Roofline
AB 2Q*double 144 6250
MR 2M*double 96 9375