perf_zen0_3070ti_cuda112

Performance timing on 3070Ti, CUDA 11.2, GCC 9.3.1

./nvCuda01.bin

n		ngpu	tcpu	gfcpu	tgpu	gfgpu
100k	1		0.80135	174.705	0.12671	1104.89


./nvCuda02.bin

n		ngpu	tcpu	gfcpu	tgpu	gfgpu
200k	1		0.54205	1033.11	0.13963	4010.5


./nvCuda03.bin

n		ngpu	tcpu	gfcpu	tgpu	gfgpu
200k	1		0.54110	1034.92	0.04961	11286.4
400k	1		2.20395	1016.36	0.19609	11422.8
800k	1		15.3438	583.951	0.77454	11568.1


./nvCuda04.bin

n		ngpu	tcpu	gfcpu	tgpu	gfgpu
400k	1		35.3261	86.0555	0.29090	10450