Skip to main content

Table 8 Speedup of single GPU code v.s. CPU code running with 28 MPI tasks

From: Effects of mesh loop modes on performance of unstructured finite volume GPU simulations

mesh size

Mesh 1

Mesh 2

Mesh 3

Mesh 4

Mesh 5

speedup

21.7

15.7

13.0

11.5

8.5