cuda-samples/bin/x86_64/linux/release/APM_scan.txt

./scan Starting...

GPU Device 0: "Hopper" with compute capability 9.0

Allocating and initializing host arrays...
Allocating and initializing CUDA arrays...
Initializing CUDA-C scan...

*** Running GPU scan for short arrays (100 identical iterations)...

Running scan for 4 elements (1703936 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 8 elements (851968 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 16 elements (425984 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 32 elements (212992 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 64 elements (106496 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 128 elements (53248 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 256 elements (26624 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 512 elements (13312 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 1024 elements (6656 arrays)...
Validating the results...
...reading back GPU results
 ...scanExclusiveHost()
 ...comparing the results
 ...Results Match


scan, Throughput = 35.1769 MElements/s, Time = 0.00003 s, Size = 1024 Elements, NumDevsUsed = 1, Workgroup = 256

***Running GPU scan for large arrays (100 identical iterations)...

Running scan for 2048 elements (3328 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 4096 elements (1664 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 8192 elements (832 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 16384 elements (416 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 32768 elements (208 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 65536 elements (104 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 131072 elements (52 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match

Running scan for 262144 elements (26 arrays)...
Validating the results...
...reading back GPU results
...scanExclusiveHost()
 ...comparing the results
 ...Results Match


scan, Throughput = 5146.1328 MElements/s, Time = 0.00005 s, Size = 262144 Elements, NumDevsUsed = 1, Workgroup = 256

Shutting down...