Performance of parallel higher-order method of moments using 10K CPUs

The efficiency of parallel higher-order method of moments is illustrated using up to 10240 CPU cores on the platform form the National Supercomputing Center in Jinan. The scattering problem of an airplane is simulated to demonstrate the efficiency of the parallel algorithm. Numerical results show that one can achieve above 80% efficiency when the used memory to the total memory ratio is larger than 10%.