Skip to content

Instantly share code, notes, and snippets.

@danilaml
Created September 30, 2018 01:34
Show Gist options
  • Save danilaml/d46d766f0fa5260fb169a3065afd4b82 to your computer and use it in GitHub Desktop.
Save danilaml/d46d766f0fa5260fb169a3065afd4b82 to your computer and use it in GitHub Desktop.
GPGPU Task2 (3?)
OpenCL devices:
Device #0: CPU. Intel(R) Core(TM) i5-4210U CPU @ 1.70GHz. Intel(R) Corporation. Total memory: 6067 Mb
Device #1: CPU. Intel(R) Core(TM) i5-4210U CPU @ 1.70GHz. Intel(R) Corporation. Total memory: 6067 Mb
Device #2: GPU. Intel(R) HD Graphics 4400. Total memory: 1629 Mb
Using device #2: GPU. Intel(R) HD Graphics 4400. Total memory: 1629 Mb
CPU: 1.3125+-0.0199478 s
CPU: 8.18089 GFlops
Real iterations fraction: 56.2638%
Недопустимый параметр: 100
GPU: 0.075+-0 s
GPU: 143.166 GFlops
Real iterations fraction: 56.2638%
Недопустимый параметр: 100
GPU vs CPU average results difference: 0%
OpenCL devices:
Device #0: CPU. Intel(R) Core(TM) i5-4210U CPU @ 1.70GHz. Intel(R) Corporation. Total memory: 6067 Mb
Device #1: CPU. Intel(R) Core(TM) i5-4210U CPU @ 1.70GHz. Intel(R) Corporation. Total memory: 6067 Mb
Device #2: GPU. Intel(R) HD Graphics 4400. Total memory: 1629 Mb
Using device #2: GPU. Intel(R) HD Graphics 4400. Total memory: 1629 Mb
______________________________________________
n=2 values in range: [-1023; 1023]
Max prefix sum: 0 on prefix [0; 0)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.00233333+-0.000471405 s
GPU: 0.000857143 millions/s
______________________________________________
n=4 values in range: [-1023; 1023]
Max prefix sum: 776 on prefix [0; 1)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.002+-0 s
GPU: 0.002 millions/s
______________________________________________
n=8 values in range: [-1023; 1023]
Max prefix sum: 0 on prefix [0; 0)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.002+-0 s
GPU: 0.004 millions/s
______________________________________________
n=16 values in range: [-1023; 1023]
Max prefix sum: 1562 on prefix [0; 6)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.002+-0 s
GPU: 0.008 millions/s
______________________________________________
n=32 values in range: [-1023; 1023]
Max prefix sum: 6550 on prefix [0; 22)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.002+-0 s
GPU: 0.016 millions/s
______________________________________________
n=64 values in range: [-1023; 1023]
Max prefix sum: 0 on prefix [0; 0)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.0025+-0.0005 s
GPU: 0.0256 millions/s
______________________________________________
n=128 values in range: [-1023; 1023]
Max prefix sum: 4191 on prefix [0; 34)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.00233333+-0.000471405 s
GPU: 0.0548571 millions/s
______________________________________________
n=256 values in range: [-1023; 1023]
Max prefix sum: 1093 on prefix [0; 4)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.002+-0 s
GPU: 0.128 millions/s
______________________________________________
n=512 values in range: [-1023; 1023]
Max prefix sum: 7395 on prefix [0; 316)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.002+-0 s
GPU: 0.256 millions/s
______________________________________________
n=1024 values in range: [-1023; 1023]
Max prefix sum: 4662 on prefix [0; 323)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.003+-4.1159e-11 s
GPU: 0.341333 millions/s
______________________________________________
n=2048 values in range: [-1023; 1023]
Max prefix sum: 3486 on prefix [0; 55)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.00266667+-0.000471405 s
GPU: 0.768 millions/s
______________________________________________
n=4096 values in range: [-1023; 1023]
Max prefix sum: 6013 on prefix [0; 208)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.00283333+-0.000372678 s
GPU: 1.44565 millions/s
______________________________________________
n=8192 values in range: [-1023; 1023]
Max prefix sum: 75294 on prefix [0; 6579)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.00333333+-0.000471405 s
GPU: 2.4576 millions/s
______________________________________________
n=16384 values in range: [-1023; 1023]
Max prefix sum: 92146 on prefix [0; 12399)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.003+-4.1159e-11 s
GPU: 5.46133 millions/s
______________________________________________
n=32768 values in range: [-1023; 1023]
Max prefix sum: 78744 on prefix [0; 3221)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.003+-4.1159e-11 s
GPU: 10.9227 millions/s
______________________________________________
n=65536 values in range: [-1023; 1023]
Max prefix sum: 56352 on prefix [0; 8758)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.00333333+-0.000471405 s
GPU: 19.6608 millions/s
______________________________________________
n=131072 values in range: [-1023; 1023]
Max prefix sum: 114622 on prefix [0; 10080)
CPU: 0+-0 s
CPU: inf millions/s
GPU: 0.004+-0 s
GPU: 32.768 millions/s
______________________________________________
n=262144 values in range: [-1023; 1023]
Max prefix sum: 228982 on prefix [0; 97875)
CPU: 0.000333333+-0.000471405 s
CPU: 786.432 millions/s
GPU: 0.005+-0 s
GPU: 52.4288 millions/s
______________________________________________
n=524288 values in range: [-1023; 1023]
Max prefix sum: 771285 on prefix [0; 524288)
CPU: 0.0005+-0.0005 s
CPU: 1048.58 millions/s
GPU: 0.00733333+-0.000471405 s
GPU: 71.4938 millions/s
______________________________________________
n=1048576 values in range: [-1023; 1023]
Max prefix sum: 378485 on prefix [0; 836658)
CPU: 0.00116667+-0.000372678 s
CPU: 898.779 millions/s
GPU: 0.00966667+-0.000471405 s
GPU: 108.473 millions/s
______________________________________________
n=2097152 values in range: [-1023; 1023]
Max prefix sum: 1625146 on prefix [0; 1558997)
CPU: 0.002+-0 s
CPU: 1048.58 millions/s
GPU: 0.0163333+-0.000745356 s
GPU: 128.397 millions/s
______________________________________________
n=4194304 values in range: [-511; 511]
Max prefix sum: 315064 on prefix [0; 4115605)
CPU: 0.00533333+-0.000942809 s
CPU: 786.432 millions/s
GPU: 0.0251667+-0.000372678 s
GPU: 166.661 millions/s
______________________________________________
n=8388608 values in range: [-255; 255]
Max prefix sum: 55893 on prefix [0; 20879)
CPU: 0.00916667+-0.000372678 s
CPU: 915.121 millions/s
GPU: 0.0461667+-0.00167498 s
GPU: 181.703 millions/s
______________________________________________
n=16777216 values in range: [-127; 127]
Max prefix sum: 118369 on prefix [0; 652799)
CPU: 0.017+-0.001 s
CPU: 986.895 millions/s
GPU: 0.0858333+-0.00260875 s
GPU: 195.463 millions/s
CPU: 0.0656667+-0.00298142 s
CPU: 1522.84 millions/s
CPU OMP: 0.0423333+-0.00512076 s
CPU OMP: 2362.2 millions/s
OpenCL devices:
Device #0: CPU. Intel(R) Core(TM) i5-4210U CPU @ 1.70GHz. Intel(R) Corporation. Total memory: 6067 Mb
Device #1: CPU. Intel(R) Core(TM) i5-4210U CPU @ 1.70GHz. Intel(R) Corporation. Total memory: 6067 Mb
Device #2: GPU. Intel(R) HD Graphics 4400. Total memory: 1629 Mb
Using device #2: GPU. Intel(R) HD Graphics 4400. Total memory: 1629 Mb
GPU OCL: 0.0755+-0.0005 s
GPU OCL: 1324.5 millions/s
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment