Simulations of Complex and Microscopic Models of Cardiac Electrophysiology Powered by Multi-GPU Platforms

Table 1

Average execution time and speedup of parallel implementations for a tissue of 0.5 cm × 0.5 cm. The execution times are presented in seconds.

Parallel implementation	Cores	Total Time	ODE time	PDE time	Speedup
Cluster	1	137,964	132,590	5,264	—
Cluster	8	18,492	17,210	1,262	7.5
Cluster	16	9,922	9,316	595	13.9
Cluster	32	4,198	3,884	311	32.9
Cluster	64	2,283	2,087	191	60.4
Multi-GPU	64 + 16 GPUs	401.84	209.4	187	343