http://nb6mpi.pbwiki.com/ RecentChanges for nb6mpi http://nb6mpi.pbwiki.com/feedlogo.gif http://pbwiki.com/ PBwiki 3.7 support@pbwiki.com http://nb6mpi.pbwiki.com/BenchmarkResults email.hidden@example.com (Jose) Jose edited BenchmarkResults Relevant timings for N=50K:
c)
The optimal processor numbers
LRZ
Information about the hardware van be found in
]]> Mon, 16 Jun 2008 16:09:17 +0000 mod http://nb6mpi.pbwiki.com/BenchmarkResults email.hidden@example.com (Jose) Jose edited BenchmarkResults c)
The optimal processor numbers
A comparison of the plots of the b) type is now given
LRZ
Information about the hardware van be found in
]]> Mon, 16 Jun 2008 16:08:08 +0000 mod http://nb6mpi.pbwiki.com/BenchmarkResults email.hidden@example.com (Jose) Jose edited BenchmarkResults RZG
Information about the hardware van be found in http://www.rzg.mpg.de/computing/hardware/power4
The benchmarks were done by José with the Cambody version of Nbody6++.
a)b)
Relevant timings for N=50K:
c)
The optimal processor numbers
A comparison of the plots of the b) type is now given
LRZ
Information about the hardware van be found in
http://www.lrz-muenchen.de/services/compute/hlrb/
The benchmarks were done by José with the Cambody version of Nbody6++.
a)b)
]]> Mon, 16 Jun 2008 16:07:12 +0000 mod http://nb6mpi.pbwiki.com/f/LRZ.gif email.hidden@example.com (Jose) Jose uploaded LRZ.gif]]> Mon, 16 Jun 2008 16:06:55 +0000 upl http://nb6mpi.pbwiki.com/f/LRZ0050k.gif email.hidden@example.com (Jose) Jose uploaded LRZ0050k.gif]]> Mon, 16 Jun 2008 16:06:55 +0000 upl http://nb6mpi.pbwiki.com/Runtime+problems email.hidden@example.com (Andreas Ernst) Andreas Ernst edited Runtime problems 80 CONTINUE** Check whether membership range is acceptable.* Next statement commented (A. Ernst)* IF (NNB.EQ.1) GO TO 70*
A solution is to comment the above line. In principle, NLIST is deprecated and all references to this array should be removed anyway as Sverre says. (O.P./A.E.)
-O4 does not always work, seems to work in most cases, but -O3 seems to work in all cases so far with pgf. (A.E.)
]]> Sat, 15 Mar 2008 22:24:33 +0000 mod http://nb6mpi.pbwiki.com/Runtime+problems email.hidden@example.com (Andreas Ernst) Andreas Ernst edited Runtime problems 4) Segmentation fault directly after starting the code
5) Run hangs after output fpoly2 time
6) The energy is not equal to -0.25 or energy errors occur.
Solutions:
1) STDIO - Error 11: Resource temporarily unavailable: We were getting the following strange error on our Beowulf PC cluster Hydra @ ARI using PGI mpif77 / pgf77 while trying to restart the nbody6++ run:
80 CONTINUE** Check whether membership range is acceptable.* Next statement commented (A. Ernst)* IF (NNB.EQ.1) GO TO 70*
A solution is to comment the above line. In principle, NLIST is deprecated and all references to this array should be removed anyway as Sverre says. (O.P./A.E.)
6) The energy is not equal to -0.25 or energy errors occur. If you do a "grep ADJUST diagnosticsfile" you can see the value of the total energy. If it is not equal to -0.25 in the beginning or unreasonable energy errors occur the first thing to check is the compiler optimization option in the Makefile: -O4 does n]]> Sat, 15 Mar 2008 22:19:09 +0000 mod http://nb6mpi.pbwiki.com/Runtime+problems email.hidden@example.com (Andreas Ernst) Andreas Ernst edited Runtime problems 3) The run hangs in a KS regularization - what to do?
4) Segmentation fault directly after starting the code
5) Run hangs after output fpoly2 time
Solutions:
1) STDIO - Error 11: Resource temporarily unavailable: We were getting the following strange error on our Beowulf PC cluster Hydra @ ARI using PGI mpif77 / pgf77 while trying to restart the nbody6++ run:
This did not help me, i get the segfault in any case, shure that this is the solution? (José experienced the same problems). (O.P.)
Did you also rename the COMMON block CLOSE? (A.E.)
5) Run hangs after output fpoly2 time. The code hangs after the output
fpoly1 time= ... fpoly2 time= ...
appears in the diagnostics file. The problem is an infinite loop in start.F after label 80:
80 CONTINUE** Check whether membership range is acceptable.* Next statement commented (A. Ernst)* IF (NNB.EQ.1) GO TO 70*
A solution is to comment the above line. In principle, NLIST is deprecated and all references to]]> Thu, 13 Mar 2008 14:51:16 +0000 mod http://nb6mpi.pbwiki.com/Runtime+problems email.hidden@example.com (Jose) Jose renamed RZG-3.gif RZG.gif ]]> Wed, 12 Mar 2008 17:32:00 +0000 mvf http://nb6mpi.pbwiki.com/f/RZG-3.gif email.hidden@example.com (Jose) Jose uploaded RZG-3.gif]]> Wed, 12 Mar 2008 17:31:57 +0000 upl http://nb6mpi.pbwiki.com/Other+problems email.hidden@example.com (Andreas Ernst) Andreas Ernst edited Other problems Other problems
Problems:
1) I cannot read conf.3 on IBM PowerPC systems with XLF compiler.
]]> Wed, 12 Mar 2008 15:41:00 +0000 mod http://nb6mpi.pbwiki.com/Other+problems email.hidden@example.com (Andreas Ernst) Andreas Ernst added Other problems !! Problems:

1) I cannot read conf.3 on IBM PowerPC systems with XLF compiler.



!! Solutions:

**1) I cannot read conf.3 on IBM PowerPC systems with XLF compiler.** Try to modify all OPEN statements in file_init.F: Instead of ACCESS=\'APPEND\' use POSITION=\'APPEND\' for the XLF compiler. (A.E.)
]]> Wed, 12 Mar 2008 15:39:45 +0000 add http://nb6mpi.pbwiki.com/FrontPage email.hidden@example.com (Andreas Ernst) Andreas Ernst edited FrontPage Linking problems
Runtime problems
Other problems
Debugging
FAQ
]]> Wed, 12 Mar 2008 15:37:12 +0000 mod http://nb6mpi.pbwiki.com/FrontPage email.hidden@example.com (oliver) oliver renamed plot4_rzg-1.gif plot4_rzg.gif ]]> Wed, 12 Mar 2008 11:25:52 +0000 mvf http://nb6mpi.pbwiki.com/f/plot4_rzg-1.gif email.hidden@example.com (oliver) oliver uploaded plot4_rzg-1.gif]]> Wed, 12 Mar 2008 11:25:49 +0000 upl http://nb6mpi.pbwiki.com/f/plot4_rzg-1.gif email.hidden@example.com (oliver) oliver renamed NPEopt-1.gif NPEopt.gif ]]> Wed, 12 Mar 2008 11:25:36 +0000 mvf http://nb6mpi.pbwiki.com/f/NPEopt-1.gif email.hidden@example.com (oliver) oliver uploaded NPEopt-1.gif]]> Wed, 12 Mar 2008 11:25:32 +0000 upl http://nb6mpi.pbwiki.com/Runtime+problems email.hidden@example.com (Andreas Ernst) Andreas Ernst edited Runtime problems Restart the run with KSTART = 5 (see FAQ in this wiki) after you have modified one or more of the parameters ETAI, ETAR, ETAU, DTMIN, RMIN, NNBOPT in the third line of the restart input file
4) Segmentation fault directly after starting the code. This nasty bug appeard on SARA's Huygens system: A segfault right at the beginning before any output was written. Wim Rijks from SARA helped: There is a duplicate symbol "FCLOSE". Solution: Rename the routine fclose.f into something like myfclose.f and modify all calls to this routine by using sed. I have small script which does that for you. (A.E.)
problems).
(O.P.) (O.P.)
Did you also rename the COMMON block CLOSE? (A.E.)
]]> Tue, 11 Mar 2008 16:05:56 +0000 mod http://nb6mpi.pbwiki.com/Runtime+problems email.hidden@example.com (Jose) Jose renamed RZG-3.gif RZG.gif ]]> Wed, 05 Mar 2008 14:19:01 +0000 mvf http://nb6mpi.pbwiki.com/f/RZG-3.gif email.hidden@example.com (Jose) Jose uploaded RZG-3.gif]]> Wed, 05 Mar 2008 14:18:58 +0000 upl