[ simpleStreams ]

Device synchronization method set to = 0 (Automatic Blocking)
Setting reps to 100 to demonstrate steady state

> GPU Device 0: "Hopper" with compute capability 9.0

Device: <NVIDIA H100 PCIe> canMapHostMemory: Yes
> CUDA Capable: SM 9.0 hardware
> 114 Multiprocessor(s) x 128 (Cores/Multiprocessor) = 14592 (Cores)
> scale_factor = 1.0000
> array_size   = 16777216

> Using CPU/GPU Device Synchronization method (cudaDeviceScheduleAuto)
> mmap() allocating 64.00 Mbytes (generic page-aligned system memory)
> cudaHostRegister() registering 64.00 Mbytes of generic allocated system memory

Starting Test
memcopy:	2.45
kernel:		0.12
non-streamed:	2.80
4 streams:	2.66
-------------------------------