GPU Device 0: "Hopper" with compute capability 9.0

16777216 elements
threads per block  = 512
Graph Launch iterations = 3

Num of nodes in the graph created manually = 7
[cudaGraphsManual] Host callback final reduced sum = 0.996214
[cudaGraphsManual] Host callback final reduced sum = 0.996214
[cudaGraphsManual] Host callback final reduced sum = 0.996214
Cloned Graph Output.. 
[cudaGraphsManual] Host callback final reduced sum = 0.996214
[cudaGraphsManual] Host callback final reduced sum = 0.996214
[cudaGraphsManual] Host callback final reduced sum = 0.996214

Num of nodes in the graph created using stream capture API = 7
[cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
[cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
[cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
Cloned Graph Output.. 
[cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
[cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
[cudaGraphsUsingStreamCapture] Host callback final reduced sum = 0.996214
