A Performance Study of a Dual Xeon-Phi Cluster for the Forward Modelling of Gravitational Fields

Table 3

Errors of the L2 normal for different platforms with respect to the serial version.

Platform	Error L2 ()
CPU multicore (16 threads)
Dual Xeon-Phi (236 × 2 threads); Cluster CPU
multicore (16 threads, 10 nodes); Cluster Dual Xeon
Phi (236 × 2 threads, 10 nodes)