Changes between Version 8 and Version 9 of krg_performance


Ignore:
Timestamp:
Mar 27, 2008, 12:34:27 AM (17 years ago)
Author:
rider
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • krg_performance

    v8 v9  
    1919case4: 8192 x 6144[[BR]]
    2020
    21 '''MPI + Kerrighed enabled - MPI Only'''[[BR]]
     21'''MPI-POVRAY - MPI Only'''[[BR]]
     22
     23Machinefile:[[BR]]
     24#MPI Machinefile [[BR]]
     25node1:4 [[BR]]
     26node2:4 [[BR]]
     27node3:4 [[BR]]
     28node4:4 [[BR]]
     29node5:4 [[BR]]
     30node6:4 [[BR]]
     31node7:4 [[BR]]
     32# End of Machinefile [[BR]]
    2233
    2334case1.1: Resolution 1024 x 768: Running 5 *.pov continuously with np7 takes '''16''' secs to finish rendering[[BR]]
    … …  
    3647case4.3: Resolution 8192 x 6144: Running 5 *.pov continuously with np28 takes '''695''' secs to finish rendering[[BR]]
    3748
    38 '''Kerrighed enabled - Using Kerrighed'''[[BR]]
     49'''MPI-POVRAY - MPI + Kerrighed'''[[BR]]
    3950
    40 case1.1: Resolution 1024 x 768: Running 5 *.pov continuously with np7 takes '''''' secs to finish rendering[[BR]]
    41 case2.1: Resolution 2048 x 1536: Running 5 *.pov continuously with np7 takes '''''' secs to finish rendering[[BR]]
    42 case3.1: Resolution 4096 x 3072: Running 5 *.pov continuously with np7 takes '''''' secs to finish rendering[[BR]]
    43 case4.1: Resolution 8192 x 6144: Running 5 *.pov continuously with np7 takes '''''' secs to finish rendering[[BR]]
     51#MPI+Kerrighed Machinefile [[BR]]
     52node1:4 [[BR]]
     53node1:4 [[BR]]
     54node1:4 [[BR]]
     55node1:4 [[BR]]
     56node1:4 [[BR]]
     57node1:4 [[BR]]
     58node1:4 [[BR]]
     59# End of Machinefile [[BR]]
    4460
    45 case1.2: Resolution 1024 x 768: Running 5 *.pov continuously with np14 takes '''''' secs to finish rendering[[BR]]
    46 case2.2: Resolution 2048 x 1536: Running 5 *.pov continuously with np14 takes '''''' secs to finish rendering[[BR]]
    47 case3.2: Resolution 4096 x 3072: Running 5 *.pov continuously with np14 takes '''''' secs to finish rendering[[BR]]
    48 case4.2: Resolution 8192 x 6144: Running 5 *.pov continuously with np14 takes '''''' secs to finish rendering[[BR]]
     61Result: Using this machinefile,we only get one node running povary process by 4 CPUs and the others are nothing to do. [[BR]]
    4962
    50 case1.3: Resolution 1024 x 768: Running 5 *.pov continuously with np28 takes '''''' secs to finish rendering[[BR]]
    51 case2.3: Resolution 2048 x 1536: Running 5 *.pov continuously with np28 takes '''''' secs to finish rendering[[BR]]
    52 case3.3: Resolution 4096 x 3072: Running 5 *.pov continuously with np28 takes '''''' secs to finish rendering[[BR]]
    53 case4.3: Resolution 8192 x 6144: Running 5 *.pov continuously with np28 takes '''''' secs to finish rendering[[BR]]
     63Step1: rider@node101:~$ krg_capset -e +CAN_MIGRATE [[BR]]
     64Step2: rider@node101:~$ migrate pid nodeid [[BR]]
    5465
    55 @Example:For the attached file: mpi-povray performance_result.odt
     66Failure: Running-povray process can not be divided to several process for kerrighed to migrate. [[BR]]
     67
     68Solution: OpenMP + POVRAY (Testing) : 2~4 Days
     69
     70@Performance Report: For the attached file: mpi-povray performance_result.odt