reductionMultiBlockCG Starting...

GPU Device 0: "Hopper" with compute capability 9.0

33554432 elements
numThreads: 1024
numBlocks: 228

Launching SinglePass Multi Block Cooperative Groups kernel
Average time: 0.102750 ms
Bandwidth:    1306.254555 GB/s

GPU result = 1.992401599884
CPU result = 1.992401361465