Commit bead45bd authored by petros.anastasiadis's avatar petros.anastasiadis
Browse files

Update 03/10/2017 - gitignore changes

parent bf61a5c4
......@@ -3,4 +3,6 @@
**/*.out
**/*.err
**/*.debug
**/*.compute
**/*.taskp
MPI Version(N=25000, M=25000, Tasks=2, Nodes=2, Tasks/Node=1, threads=1): comp_t= 194.178829 ms, comm_t= 1332.824230 ms
MPI Version(N=25000, M=25000, Tasks=2, Nodes=2, Tasks/Node=1, threads=2): comp_t= 110.103779 ms, comm_t= 1798.905134 ms
MPI Version(N=25000, M=25000, Tasks=2, Nodes=2, Tasks/Node=1, threads=5): comp_t= 47.298059 ms, comm_t= 1719.721079 ms
MPI Version(N=25000, M=25000, Tasks=2, Nodes=2, Tasks/Node=1, threads=10): comp_t= 30.680361 ms, comm_t= 1669.413805 ms
MPI Version(N=25000, M=25000, Tasks=2, Nodes=2, Tasks/Node=1, threads=20): comp_t= 27.329772 ms, comm_t= 1805.709839 ms
MPI Version(N=25000, M=25000, Tasks=4, Nodes=4, Tasks/Node=1, threads=1): comp_t= 97.456789 ms, comm_t= 1045.057058 ms
MPI Version(N=25000, M=25000, Tasks=4, Nodes=4, Tasks/Node=1, threads=2): comp_t= 55.045478 ms, comm_t= 1212.171316 ms
MPI Version(N=25000, M=25000, Tasks=4, Nodes=4, Tasks/Node=1, threads=5): comp_t= 23.733768 ms, comm_t= 1144.655228 ms
MPI Version(N=25000, M=25000, Tasks=4, Nodes=4, Tasks/Node=1, threads=10): comp_t= 15.427949 ms, comm_t= 1174.911976 ms
MPI Version(N=25000, M=25000, Tasks=4, Nodes=4, Tasks/Node=1, threads=20): comp_t= 13.703361 ms, comm_t= 1173.395872 ms
MPI Version(N=25000, M=25000, Tasks=8, Nodes=8, Tasks/Node=1, threads=1): comp_t= 48.671141 ms, comm_t= 909.532785 ms
MPI Version(N=25000, M=25000, Tasks=8, Nodes=8, Tasks/Node=1, threads=2): comp_t= 27.521832 ms, comm_t= 966.041803 ms
MPI Version(N=25000, M=25000, Tasks=8, Nodes=8, Tasks/Node=1, threads=5): comp_t= 11.969309 ms, comm_t= 951.106071 ms
MPI Version(N=25000, M=25000, Tasks=8, Nodes=8, Tasks/Node=1, threads=10): comp_t= 7.720699 ms, comm_t= 964.529991 ms
MPI Version(N=25000, M=25000, Tasks=8, Nodes=8, Tasks/Node=1, threads=20): comp_t= 6.873391 ms, comm_t= 965.454817 ms
MPI Version(N=25000, M=25000, Tasks=16, Nodes=16, Tasks/Node=1, threads=1): comp_t= 24.376562 ms, comm_t= 851.062775 ms
MPI Version(N=25000, M=25000, Tasks=16, Nodes=16, Tasks/Node=1, threads=2): comp_t= 13.838730 ms, comm_t= 876.939058 ms
MPI Version(N=25000, M=25000, Tasks=16, Nodes=16, Tasks/Node=1, threads=5): comp_t= 6.032262 ms, comm_t= 869.652748 ms
MPI Version(N=25000, M=25000, Tasks=16, Nodes=16, Tasks/Node=1, threads=10): comp_t= 3.906670 ms, comm_t= 872.004032 ms
MPI Version(N=25000, M=25000, Tasks=16, Nodes=16, Tasks/Node=1, threads=20): comp_t= 3.491812 ms, comm_t= 880.733728 ms
MPI Version(N=25000, M=25000, Tasks=32, Nodes=32, Tasks/Node=1, threads=1): comp_t= 12.220020 ms, comm_t= 817.686081 ms
MPI Version(N=25000, M=25000, Tasks=32, Nodes=32, Tasks/Node=1, threads=2): comp_t= 6.964960 ms, comm_t= 830.610991 ms
MPI Version(N=25000, M=25000, Tasks=32, Nodes=32, Tasks/Node=1, threads=5): comp_t= 3.068931 ms, comm_t= 823.021889 ms
MPI Version(N=25000, M=25000, Tasks=32, Nodes=32, Tasks/Node=1, threads=10): comp_t= 2.005892 ms, comm_t= 833.809614 ms
MPI Version(N=25000, M=25000, Tasks=32, Nodes=32, Tasks/Node=1, threads=20): comp_t= 1.813321 ms, comm_t= 825.877905 ms
MPI Version(N=25000, M=25000, Tasks=64, Nodes=64, Tasks/Node=1, threads=1): comp_t= 6.891279 ms, comm_t= 866.112232 ms
MPI Version(N=25000, M=25000, Tasks=64, Nodes=64, Tasks/Node=1, threads=2): comp_t= 4.050031 ms, comm_t= 875.716925 ms
MPI Version(N=25000, M=25000, Tasks=64, Nodes=64, Tasks/Node=1, threads=5): comp_t= 2.180080 ms, comm_t= 858.268976 ms
MPI Version(N=25000, M=25000, Tasks=64, Nodes=64, Tasks/Node=1, threads=10): comp_t= 1.726201 ms, comm_t= 859.513044 ms
MPI Version(N=25000, M=25000, Tasks=64, Nodes=64, Tasks/Node=1, threads=20): comp_t= 1.600821 ms, comm_t= 858.101845 ms
MPI Version(N=25000, M=25000, Tasks=128, Nodes=128, Tasks/Node=1, threads=1): comp_t= 4.468169 ms, comm_t= 943.107128 ms
MPI Version(N=25000, M=25000, Tasks=128, Nodes=128, Tasks/Node=1, threads=2): comp_t= 2.670059 ms, comm_t= 945.677042 ms
MPI Version(N=25000, M=25000, Tasks=128, Nodes=128, Tasks/Node=1, threads=5): comp_t= 2.082241 ms, comm_t= 911.346912 ms
MPI Version(N=25000, M=25000, Tasks=128, Nodes=128, Tasks/Node=1, threads=10): comp_t= 1.830890 ms, comm_t= 911.675930 ms
MPI Version(N=25000, M=25000, Tasks=128, Nodes=128, Tasks/Node=1, threads=20): comp_t= 1.749771 ms, comm_t= 910.978079 ms
MPI Version(N=25000, M=25000, Tasks=256, Nodes=256, Tasks/Node=1, threads=1): comp_t= 4.194009 ms, comm_t= 1117.182970 ms
MPI Version(N=25000, M=25000, Tasks=256, Nodes=256, Tasks/Node=1, threads=2): comp_t= 3.712251 ms, comm_t= 1114.975691 ms
MPI Version(N=25000, M=25000, Tasks=256, Nodes=256, Tasks/Node=1, threads=5): comp_t= 3.382900 ms, comm_t= 1045.048952 ms
MPI Version(N=25000, M=25000, Tasks=256, Nodes=256, Tasks/Node=1, threads=10): comp_t= 3.307860 ms, comm_t= 1047.138929 ms
MPI Version(N=25000, M=25000, Tasks=256, Nodes=256, Tasks/Node=1, threads=20): comp_t= 3.285811 ms, comm_t= 1047.061920 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=1, Nodes=1, Tasks/Node=1): comp_t= 57.144990 ms, comm_t= 351.879835 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=2, Nodes=1, Tasks/Node=2): comp_t= 28.931930 ms, comm_t= 335.523844 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=5, Nodes=1, Tasks/Node=5): comp_t= 14.414470 ms, comm_t= 325.868130 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=10, Nodes=1, Tasks/Node=10): comp_t= 9.026849 ms, comm_t= 332.774162 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=20, Nodes=1, Tasks/Node=20): comp_t= 8.623710 ms, comm_t= 327.397108 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=10, Nodes=2, Tasks/Node=5): comp_t= 8.081260 ms, comm_t= 228.461981 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=20, Nodes=2, Tasks/Node=10): comp_t= 7.472110 ms, comm_t= 217.247009 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=40, Nodes=2, Tasks/Node=20): comp_t= 6.232049 ms, comm_t= 262.038231 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=60, Nodes=3, Tasks/Node=20): comp_t= 5.085628 ms, comm_t= 254.292250 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=80, Nodes=4, Tasks/Node=20): comp_t= 2.516110 ms, comm_t= 238.667011 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=100, Nodes=5, Tasks/Node=20): comp_t= 2.122738 ms, comm_t= 250.440121 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=200, Nodes=10, Tasks/Node=20): comp_t= 1.367218 ms, comm_t= 344.570160 ms
MPI Version(Iter=100, N=10000, M=10000, Tasks=400, Nodes=20, Tasks/Node=20): comp_t= 1.246841 ms, comm_t= 560.771704 ms
MPI Version(N=10000, M=10000, Tasks=40): t= 5.110400 ms
Multi GPU CUDA-MPI Version(N=25000, M=12500, GPUs/Node=2, Nodes=1, Tasks/Node=2): comp_t= 13.342609 ms, comm_t= 1756.819963 ms
Multi GPU CUDA-MPI Version(N=25000, M=6250, GPUs/Node=2, Nodes=2, Tasks/Node=2): comp_t= 6.707978 ms, comm_t= 1122.361183 ms
Multi GPU CUDA-MPI Version(N=25000, M=3125, GPUs/Node=2, Nodes=4, Tasks/Node=2): comp_t= 3.318169 ms, comm_t= 955.436945 ms
Multi GPU CUDA-MPI Version(N=25000, M=1563, GPUs/Node=2, Nodes=8, Tasks/Node=2): comp_t= 3.125570 ms, comm_t= 966.177940 ms
Multi GPU CUDA-MPI Version(N=25000, M=782, GPUs/Node=2, Nodes=16, Tasks/Node=2): comp_t= 2.513990 ms, comm_t= 871.755123 ms
Multi GPU CUDA-MPI Version(N=25000, M=25000, GPUs/Node=1, Nodes=1, Tasks/Node=1): comp_t= 26.672130 ms, comm_t= 1808.822870 ms
OpenMP Version(N=25000, M=25000, Threads=1): t= 1170.268281 ms
OpenMP Version(N=25000, M=25000, Threads=2): t= 462.748051 ms
OpenMP Version(N=25000, M=25000, Threads=5): t= 233.253169 ms
OpenMP Version(N=25000, M=25000, Threads=10): t= 180.470340 ms
OpenMP Version(N=25000, M=25000, Threads=20): t= 189.864190 ms
OpenMP Version(N=25000, M=25000, Threads=40): t= 186.259170 ms
OpenMP Version(N=25000, M=25000, Threads=1): t= 456.858909 ms
OpenMP Version(N=25000, M=25000, Threads=2): t= 228.760691 ms
OpenMP Version(N=25000, M=25000, Threads=5): t= 94.036951 ms
OpenMP Version(N=25000, M=25000, Threads=10): t= 49.852111 ms
OpenMP Version(N=25000, M=25000, Threads=20): t= 30.018451 ms
OpenMP Version(N=25000, M=25000, Threads=40): t= 27.299979 ms
Serial Version(N=10000, M=10000): t= 55.129669 ms
Single GPU CUDA Version(N=25000, M=25000): t= 26.747921 ms
Single GPU CUDA Version(N=10000, M=10000): t= 25.496180 ms
Single GPU CUDA Coalesced Version(N=10000, M=10000): t= 6.006391 ms
Single GPU CUDA shmem Version(N=10000, M=10000): t= 4.535849 ms
Single GPU CUDA Version(N=25000, M=25000): t= 1775.153432 ms
Single GPU CUDA Coalesced Version(N=25000, M=25000): t= 31.531191 ms
Single GPU CUDA shmem Version(N=25000, M=25000): t= 26.186922 ms
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment