<div>dear wien users:</div> <div>i met a confused about parallel calculation.</div> <div>i compile the wien2k codes in my clusters with out any errors.and the single calculation works well. but when i running programs in parallel mode, i met some puzzled problem. <EM>the .machines file as followed:</EM></div> <div>1:console <BR>1:c0101<BR>1:c0102<BR>1:c0103<BR>1:c0104<BR>1:c0105<BR>1:c0106<BR>1:c0107<BR>...............</div> <div>granularity:1<BR>extrafine:1<BR></div> <div><EM>the cycles seems to be nomal,which dayfile is :</EM></div> <div>running lapw0 in single mode<BR>15.949u 1.807s 0:19.06 93.0% 0+0k 0+0io 29pf+0w<BR>> lapw1 -p (22:31:08) starting parallel lapw1 at Wed Sep 17 22:31:08 CST 2008<BR>-> starting parallel LAPW1 jobs at Wed Sep 17 22:31:08 CST 2008<BR>running LAPW1 in parallel mode (using .machines)<BR>8 number_of_parallel_jobs<BR> console(79) 254.184u 16.657s 9:07.02
49.5% 0+0k 0+0io 38pf+0w<BR> c0101(79) 250.019u 16.482s 8:59.24 49.4% 0+0k 0+0io 27pf+0w<BR> c0102(79) 253.406u 16.350s 9:04.43 49.5% 0+0k 0+0io 9pf+0w<BR> c0103(79) 254.532u 17.161s 9:06.57 49.7% 0+0k 0+0io 0pf+0w<BR> c0104(79) 252.878u 15.813s 9:00.49 49.7% 0+0k 0+0io 0pf+0w<BR> c0105(79) 254.152u 15.739s 9:03.59 49.6% 0+0k 0+0io 0pf+0w<BR> c0106(79) 254.164u 15.906s 9:01.19 49.9% 0+0k 0+0io 0pf+0w<BR> c0107(79) 254.787u 16.461s 9:04.39 49.8% 0+0k 0+0io 0pf+0w<BR> c0101(1) 3.607u 0.272s 0:05.37 72.0% 0+0k 0+0io 0pf+0w<BR> c0102(1) 3.650u 0.242s 0:04.21 92.3% 0+0k 0+0io 0pf+0w<BR>
c0104(1) 3.270u 0.225s 0:03.64 95.8% 0+0k 0+0io 0pf+0w<BR> Summary of lapw1para:<BR> console k=79 user=254.184 wallclock=547.02<BR> c0101 k=80 user=253.626 wallclock=544.61<BR> c0102 k=80 user=257.056 wallclock=548.64<BR> c0103 k=79 user=254.532 wallclock=546.57<BR> c0104 k=80 user=256.148 wallclock=544.13<BR> c0105 k=79 user=254.152 wallclock=543.59<BR>
c0106 k=79 user=254.164 wallclock=541.19<BR> c0107 k=79 user=254.787 wallclock=544.39<BR>2039.101u 132.877s 9:14.54 391.6% 0+0k 0+0io 76pf+0w<BR>............................................</div> <div> </div> <div><EM>but when i check the ps of every <SPAN class=webtrans_meaning>Compute Node , there is no lapw1 in other nodes at all. all the lapw1(or lapw2)_1.def lapw1(or lapw2)_2.def are running in master nodes. did the parallel calculation take effect? apparently , i used "runsp_lapw -p"for parallel.</SPAN></EM></div> <div><SPAN class=webtrans_meaning></SPAN> </div> <div><SPAN class=webtrans_meaning><FONT color=#cc0033><EM>long for some suggestions.</EM></FONT></SPAN></div> <div><SPAN class=webtrans_meaning></SPAN> </div> <div><SPAN
class=webtrans_meaning>Appendix£º</SPAN></div> <div><SPAN class=webtrans_meaning>the details of my clusters' environment as following£º</SPAN></div> <div><SPAN class=webtrans_meaning></SPAN> </div> <div>the system: fedora 8 and intel ifort 9.1 and the detail of compile options:</div> <div>Current settings:<BR> O Compiler options: -O3 -FR -w -mp1 -prec_div -pad -ip -xP<BR> L Linker Flags: -L/export/mathlib/cmkl81/lib/em64t -lguide -lpthread -lsvml<BR> P Preprocessor flags '-DParallel'<BR> R R_LIB (LAPACK+BLAS): -L/export/mathlib/cmkl81/lib/em64t -lmkl_lapack64 -lmkl_em64t -lguide -lpthread<BR> <BR>Shared Memory Architecture? yes</div> <div> </div> <div>the MPI and Scalapack options:</div> <div> RP
RP_LIB(SCALAPACK+PBLAS): -L/export/mathlib/cmkl81/lib/em64t -lmkl_scalapack -lmkl_blacs_intelmpi20 -lmkl_lapack -lmkl_em64t -lguide -lpthread<BR> FP FPOPT(par.comp.options): -O3 -FR -w -mp1 -prec_div -pad -ip -xP<BR> MP MPIRUN commando : mpirun -np _NP_ -machinefile _HOSTS_ _EXEC_<BR></div><p> 
<hr size=1><a href="http://cn.mail.yahoo.com/"> ÑÅ»¢ÓÊÏ䣬ÄúµÄÖÕÉúÓÊÏ䣡</a>