File sortreduce.cu compiled on Mar 23 2015 at 04:59:52
Device name: Quadro K2100M
CUDA Capability version: 3.0
CUDA Driver / Runtime Version: 7,000/7,000, CUDA_VERSION: 7,000
Thrust v1.8
TIME thru Starting                           : CPU:  0.007 (d= 0.007)
Some redundant ops are done for timing purposes.
N= 100,000,000

Comparing sort on 4 types of memory:
TIME thru Sync                               : CPU:  0.065 (d= 0.058)

Host:
TIME thru Create int vec on host             : CPU:  0.111 (d= 0.046)
TIME thru Transform rand int vec on host     : CPU:  0.508 (d= 0.397)
TIME thru Sort on host                       : CPU:  2.269 (d= 1.761)
TIME thru Sync                               : CPU:  2.269 (d= 0.000)

Device:
Before creating device vector: cuda_mem_tot= 2,147,287,040, cuda_mem_free= 1,283,903,488
TIME thru Before create int vec on device    : CPU:  2.270 (d= 0.000)
TIME thru Create int vec on device           : CPU:  2.270 (d= 0.001)
After creating device vector: cuda_mem_tot= 2,147,287,040, cuda_mem_free= 883,847,168
TIME thru Copy host to device                : CPU:  2.340 (d= 0.070)
TIME thru Transform rand int vec on device   : CPU:  2.340 (d= 0.000)
TIME thru Sort on device                     : CPU:  2.750 (d= 0.410)
TIME thru Copy device to host                : CPU:  2.812 (d= 0.062)

Mapped:
Starting mapped test: cuda_mem_tot= 2,147,287,040, cuda_mem_free= 1,283,854,336
TIME thru cudaHostAllocMapped                : CPU:  2.916 (d= 0.104)
TIME thru Transform mapped array             : CPU:  2.916 (d= 0.000)
TIME thru sort mapped array                  : CPU:  3.552 (d= 0.635)
TIME thru free and sync                      : CPU:  3.623 (d= 0.071)

Managed:
Starting managed test: cuda_mem_tot= 2,147,287,040, cuda_mem_free= 1,283,043,328
TIME thru cudaMallocManaged                  : CPU:  3.628 (d= 0.005)
after cudaMallocManaged: cuda_mem_tot= 2,147,287,040, cuda_mem_free= 882,712,576
TIME thru Transform managed array            : CPU:  3.628 (d= 0.000)
TIME thru Transform managed device array     : CPU:  3.628 (d= 0.000)
TIME thru sort managed array                 : CPU:  4.044 (d= 0.416)
TIME thru sort managed device array          : CPU:  4.439 (d= 0.395)
TIME thru free and sync                      : CPU:  4.440 (d= 0.001)

Comparing reduce on 4 types of memory:
TIME thru Starting testreduce                : CPU:  4.441 (d= 0.001)

Host:
TIME thru Create float vec on host           : CPU:  4.487 (d= 0.046)
TIME thru Transform rand float vec on host   : CPU:  4.950 (d= 0.463)
TIME thru Generate rand float vec on host    : CPU:  6.964 (d= 2.013)
sumh= 36,028,797,018,963,968.000
TIME thru Reduce on host                     : CPU:  7.077 (d= 0.113)

Device:
TIME thru Create float vec on device         : CPU:  7.077 (d= 0.001)
TIME thru Transform rand float vec on device : CPU:  7.077 (d= 0.000)
sumd= 4,994,873,019,072,512.000
TIME thru Reduce on device                   : CPU:  7.119 (d= 0.042)

Mapped:
TIME thru cudaHostAllocMapped                : CPU:  7.222 (d= 0.103)
TIME thru Transform rand float vec on mapped : CPU:  7.222 (d= 0.000)
sumd= 4,994,873,019,072,512.000
TIME thru Reduce on mapped                   : CPU:  7.292 (d= 0.070)

Managed:
Starting managed test: cuda_mem_tot= 2,147,287,040, cuda_mem_free= 1,273,700,352
TIME thru cudaMallocManaged                  : CPU:  7.293 (d= 0.001)
after cudaMallocManaged: cuda_mem_tot= 2,147,287,040, cuda_mem_free= 873,668,608
TIME thru Transform managed array            : CPU:  7.293 (d= 0.000)
TIME thru Transform managed device array     : CPU:  7.293 (d= 0.000)
sumd= 4,994,873,019,072,512.000
TIME thru Reduce on managed                  : CPU:  7.344 (d= 0.051)
TIME thru free and sync                      : CPU:  7.345 (d= 0.001)