Thanks for the tip, it now works at least for serial calculation. Note furthermore that, using the xlf compiler from ibm, I also had to change -qrealsize=8 into -qautodbl=dbl4 in order to avoid a segmentation fault.<div><br>
</div><div>I am now trying to compile to it for parallel calculation, thus I specified mpxlf_r and mpcc_r in F77 and C fields in makenek. However I get the following message as soon as I start the compilation:</div><div>
<br>
</div><blockquote class="webkit-indent-blockquote" style="margin: 0 0 0 40px; border: none; padding: 0px;"><blockquote class="webkit-indent-blockquote" style="margin: 0 0 0 40px; border: none; padding: 0px;"><div><blockquote>
./makenek stenosis <br>makenek - automatic build tool for Nek5000<br>** test === End of Compilation 1 ===<br>1501-510 Compilation successful for file test_f77.f.<br>llsubmit: Processed command file through Submit Filter: "/usr/local/loadl/Fidris/llsubmit_exit".<br>
** underscore_test === End of Compilation 1 ===<br>1501-510 Compilation successful for file test_underscore.f.<br>ERROR: Unable to detect compiler!<br> - don't know how to promote datatype REAL to 8 bytes<br>
- don't know how to invoke the C pre-processor (CPP) before compilation<br> Please edit the makefile and specify the requested compiler flags using the P variable.</blockquote></div></blockquote></blockquote>
<div><div><br></div>I presume it is a fairly simple error to solve, but I am not familiar at all with such massively parallel calculators yet <img src="cid:33D@goomoji.gmail" style="margin-top: 0px; margin-right: 0.2ex; margin-bottom: 0px; margin-left: 0.2ex; vertical-align: middle; " goomoji="33D"></div>
<div><br></div><div>Best regards,</div><div>JC<br><div class="gmail_quote">On 24 May 2011 16:20, <span dir="ltr"><<a href="mailto:nek5000-users@lists.mcs.anl.gov">nek5000-users@lists.mcs.anl.gov</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><br>
Dear Jean-Christophe,<br>
<br>
etime is a fairly std. timer function, but obviously not<br>
supported with your compiler.<br>
<br>
When using mpi, it uses instead the mpi timer, so there is no<br>
issue.<br>
<br>
The quick fix here would be to edit mpi_dummy.f and change<br>
the etime() reference therein to the ibm timer function.<br>
<br>
You might also try setting it zero - but I'm not 100% certain<br>
that there are no divisions involving time in the denominator...<br>
It's worth a try, however.<br>
<br>
Paul<div><div></div><div class="h5"><br>
<br>
<br>
<br>
On Tue, 24 May 2011, <a href="mailto:nek5000-users@lists.mcs.anl.gov" target="_blank">nek5000-users@lists.mcs.anl.gov</a> wrote:<br>
<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi Nek's,<br>
<br>
Up to now I have compiled and run the code on the various workstations<br>
available in my lab. I am now trying to compile it (only in serial for the<br>
moment) on an IBM Power 6 (<br>
<a href="http://www.idris.fr/su/Scalaire/vargas/hw-vargas.html" target="_blank">http://www.idris.fr/su/Scalaire/vargas/hw-vargas.html</a>) but I encounter an<br>
error (which is the reason why I do not compile it using mpi support<br>
yet). Following is the outpost from the compilation:<br>
<br>
xlf_r -qsuppress=cmpmsg -o nek5000 obj/stenosis.o obj/drive.o obj/drive1.o<br>
obj/drive2.o obj/plan4.o obj/bdry.o obj/coef.o obj/conduct.o obj/connect1.o<br>
obj/connect2.o obj/dssum.o obj/edgec.o obj/eigsolv.o obj/gauss.o<br>
obj/genxyz.o obj/navier1.o obj/makeq.o obj/navier0.o obj/navier2.o<br>
obj/navier3.o obj/navier4.o obj/prepost.o obj/speclib.o obj/map2.o<br>
obj/turb.o obj/mvmesh.o obj/ic.o obj/ssolv.o obj/planx.o obj/math.o<br>
obj/mxm_wrapper.o obj/hmholtz.o obj/gfdm_par.o obj/gfdm_op.o<br>
obj/gfdm_solve.o obj/subs1.o obj/subs2.o obj/genbox.o obj/gmres.o obj/hsmg.o<br>
obj/convect.o obj/induct.o obj/perturb.o obj/navier5.o obj/navier6.o<br>
obj/navier7.o obj/navier8.o obj/fast3d.o obj/fasts.o obj/calcz.o obj/byte.o<br>
obj/chelpers.o obj/byte_mpi.o obj/postpro.o obj/cvode_driver.o<br>
obj/nek_comm.o obj/init_plugin.o obj/setprop.o obj/qthermal.o<br>
obj/cvode_aux.o obj/makeq_aux.o obj/papi.o obj/ssygv.o obj/dsygv.o<br>
obj/mxm_std.o obj/blas.o obj/comm_mpi.o obj/mpi_dummy.o obj/singlmesh.o<br>
obj/jl2_gs.o obj/jl2_sort.o obj/jl2_sarray_transfer.o obj/jl2_sarray_sort.o<br>
obj/jl2_gs_local.o obj/jl2_crystal.o obj/jl2_comm.o obj/jl2_tensor.o<br>
obj/jl2_fail.o obj/jl2_fcrystal.o obj/jl_tuple_list.o obj/jl_transfer.o<br>
obj/jl_sort.o obj/jl_fcrystal.o obj/jl_errmem.o obj/jl_crystal.o<br>
obj/jl2_findpts.o obj/jl2_findpts_local.o obj/jl2_obbox.o obj/jl2_poly.o<br>
obj/jl2_lob_bnd.o obj/jl2_findpts_el_3.o obj/jl2_findpts_el_2.o<br>
obj/jl2_sparse_cholesky.o obj/jl2_xxt.o obj/jl2_fcrs.o<br>
ld: 0711-317 ERROR: Undefined symbol: .etime<br>
ld: 0711-345 Use the -bloadmap or -bnoquiet option to obtain more<br>
information.<br>
gmake: *** [nek5000] Error 8<br>
<br>
Attached is the whole compiler.out file also. Does anyone have an idea?<br>
<br>
Regards,<br>
<br>
-- <br>
Jean-Christophe<br>
<br>
</blockquote></div></div>
_______________________________________________<br>
Nek5000-users mailing list<br>
<a href="mailto:Nek5000-users@lists.mcs.anl.gov" target="_blank">Nek5000-users@lists.mcs.anl.gov</a><br>
<a href="https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users</a><br>
</blockquote></div><br><br clear="all"><br>-- <br>Jean-Christophe<br>
</div>