CPU Init
GPU Init
There are 4 GPUs
Device 0:
	name:         Tesla C1060
	capability:   1.3
	mem global:   4096 Mb
	mem const:    64 Kb
	mem shared:   16 Kb
	clock:        1.296 GHz
	processors:   30
	cores:        240
	warp:         32
	max thr/blk:  512
	max blk size: 512x512x64
	max grd size: 65535x65535
Device 1:
	name:         Tesla C1060
	capability:   1.3
	mem global:   4096 Mb
	mem const:    64 Kb
	mem shared:   16 Kb
	clock:        1.296 GHz
	processors:   30
	cores:        240
	warp:         32
	max thr/blk:  512
	max blk size: 512x512x64
	max grd size: 65535x65535
Device 2:
	name:         Tesla C1060
	capability:   1.3
	mem global:   4096 Mb
	mem const:    64 Kb
	mem shared:   16 Kb
	clock:        1.296 GHz
	processors:   30
	cores:        240
	warp:         32
	max thr/blk:  512
	max blk size: 512x512x64
	max grd size: 65535x65535
Device 3:
	name:         Tesla C1060
	capability:   1.3
	mem global:   4096 Mb
	mem const:    64 Kb
	mem shared:   16 Kb
	clock:        1.296 GHz
	processors:   30
	cores:        240
	warp:         32
	max thr/blk:  512
	max blk size: 512x512x64
	max grd size: 65535x65535


Set size:   4 Mfloats
Data size:  16 Mb
Iterations: 100
Block size: 512
Grid  size: 8192

CPU ==============================================
CPU Alloc:          0.01 ms
CPU Run:         5951.11 ms
CPU Free:           1.38 ms
CPU ==============================================

GPU 0 ============================================
GPU Model:    Tesla C1060
GPU Alloc:          1.42 ms
  GPU Load:        15.72 ms, 0.993897 GB/s
  GPU Filter:     191.29 ms
  GPU Unload:      11.97 ms, 1.304818 GB/s
GPU Run:          219.08 ms
GPU Free:           1.77 ms
GPU ==============================================

GPU 1 ============================================
GPU Model:    Tesla C1060
GPU Alloc:          1.36 ms
  GPU Load:        10.07 ms, 1.551177 GB/s
  GPU Filter:     184.20 ms
  GPU Unload:       9.75 ms, 1.602243 GB/s
GPU Run:          204.12 ms
GPU Free:           1.23 ms
GPU ==============================================

GPU 2 ============================================
GPU Model:    Tesla C1060
GPU Alloc:          3.14 ms
  GPU Load:        12.36 ms, 1.263648 GB/s
  GPU Filter:     186.31 ms
  GPU Unload:      10.21 ms, 1.530808 GB/s
GPU Run:          208.95 ms
GPU Free:           1.22 ms
GPU ==============================================

GPU 3 ============================================
GPU Model:    Tesla C1060
GPU Alloc:          1.32 ms
  GPU Load:        14.46 ms, 1.080862 GB/s
  GPU Filter:     185.25 ms
  GPU Unload:      10.48 ms, 1.490521 GB/s
GPU Run:          210.26 ms
GPU Free:           1.20 ms
GPU ==============================================

CPU Fini
GPU Fini