February 2014 - discuss - mailman3.cels.anl.gov

Re: [mpich-discuss] dynamic 2D array creation error
by Kenneth Raffenetti 18 Feb '14

18 Feb '14

This list is for asking questions about the usage of mpich. General programming questions like the below are better suited for a forum like Stackoverflow. On 02/18/2014 12:44 AM, Soheil Hooshdaran wrote: > Hello. What's wrong with this code snippet? > > |1 > 2 > 3 > 4 > 5 > 6 > | > > > > | int **lBucket; > > lBucket =new int*[iWorldSize];//iWorldSize is the nummber of processors > > for(i=0;i<iWorldSize;++i) > lBucket[i] =new int[m];| > > > > Thanks in advance > > > > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss >

1 0

Communication Error when installing MPICH on multi HOSTS.
by 维洛逐风 18 Feb '14

18 Feb '14

HI. My environment: Two Vmware VMs with ubuntu-server12.04 OS, called mpimaster,mpislaver1 they both linked to a virtual network 10.0.0.1; they can ssh to each other without password; I have disabled the fire walls with "sudo ufw disable" I install mpich3.0.4 on a NFS servered by mpimaster. I installed mpich3.0.4 follow the "readme.txt", it has Communication problem when progresses from different host comunicate with each other. From picture above we can see it's ok to run "cpi" on both hosts separately. If you can't see the picture,plz see the shell's below. ailab@mpimaster:~/Downloads/mpich-3.0.4$ mpiexec -n 4 ./examples/cpi Process 0 of 4 is on mpimaster Process 1 of 4 is on mpimaster Process 2 of 4 is on mpimaster Process 3 of 4 is on mpimaster pi is approximately 3.1415926544231239, Error is 0.0000000008333307 wall clock time = 0.028108 ailab@mpimaster:~/Downloads/mpich-3.0.4$ mpiexec -hosts mpimaster -n 4 ./examples/cpi Process 2 of 4 is on mpimaster Process 0 of 4 is on mpimaster Process 1 of 4 is on mpimaster Process 3 of 4 is on mpimaster pi is approximately 3.1415926544231239, Error is 0.0000000008333307 wall clock time = 0.027234 ailab@mpimaster:~/Downloads/mpich-3.0.4$ mpiexec -hosts mpislaver1 -n 4 ./examples/cpi Process 0 of 4 is on mpislaver1 pi is approximately 3.1415926544231239, Error is 0.0000000008333307 wall clock time = 0.000093 Process 1 of 4 is on mpislaver1 Process 2 of 4 is on mpislaver1 Process 3 of 4 is on mpislaver1 ailab@mpimaster:~/Downloads/mpich-3.0.4$ mpiexec -hosts mpimaster,mpislaver1 -n 4 ./examples/cpi Process 0 of 4 is on mpimaster Process 2 of 4 is on mpimaster Fatal error in PMPI_Reduce: A process has failed, error stack: PMPI_Reduce(1217)...............: MPI_Reduce(sbuf=0x7fff73a51ce8, rbuf=0x7fff73a51cf0, count=1, MPI_DOUBLE, MPI_SUM, root=0, MPI_COMM_WORLD) failed MPIR_Reduce_impl(1029)..........: MPIR_Reduce_intra(779)..........: MPIR_Reduce_impl(1029)..........: MPIR_Reduce_intra(835)..........: MPIR_Reduce_binomial(144).......: MPIDI_CH3U_Recvq_FDU_or_AEP(667): Communication error with rank 1 MPIR_Reduce_intra(799)..........: MPIR_Reduce_impl(1029)..........: MPIR_Reduce_intra(835)..........: MPIR_Reduce_binomial(206).......: Failure during collective ================================================================================ = BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES = EXIT CODE: 1 = CLEANING UP REMAINING PROCESSES = YOU CAN IGNORE THE BELOW CLEANUP MESSAGES ================================================================================ [proxy:0:1@mpislaver1] HYD_pmcd_pmip_control_cmd_cb (./pm/pmiserv/pmip_cb.c:886) [proxy:0:1@mpislaver1] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c [proxy:0:1@mpislaver1] main (./pm/pmiserv/pmip.c:206): demux engine error waitin [mpiexec@mpimaster] HYDT_bscu_wait_for_completion (./tools/bootstrap/utils/bscu_ [mpiexec@mpimaster] HYDT_bsci_wait_for_completion (./tools/bootstrap/src/bsci_wa [mpiexec@mpimaster] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:21 [mpiexec@mpimaster] main (./ui/mpich/mpiexec.c:331): process manager error waiti ailab@mpimaster:~/Downloads/mpich-3.0.4$ plz help,THX! ------------------ Jie-Jun Wu Department of Computer Science, Sun Yat-sen University, Guangzhou, P.R. China

1 0

dynamic 2D array creation error
by Soheil Hooshdaran 18 Feb '14

18 Feb '14

Hello. What's wrong with this code snippet? 1 2 3 4 5 6 int **lBucket; lBucket = new int*[iWorldSize];//iWorldSize is the nummber of processors for(i=0;i<iWorldSize;++i) lBucket[i] = new int[m]; Thanks in advance

1 0

Re: [mpich-discuss] MPICH 3.0.3 fails to compile with gcc 4.7
by Reuti 17 Feb '14

17 Feb '14

Hi, Am 16.02.2014 um 22:51 schrieb Ondřej Čertík: > Hi, > > After compiling 3.0.3 from source using gcc 4.7: As a first approach I suggest to try with 3.0.4. With gcc 4.7.2 it compiles and tests fine, being it 3.0.3 or 3.0.4, for me. -- Reuti > ./configure --prefix=/panfs/scratch/vol1/certik/h/bld/mpich/webn36mjzfb3 > --enable-shared > > (Full log is here: https://gist.github.com/certik/9041130) > > It fails with: > > [mpich] CC src/mpi/topo/nhb_allgather.lo > [mpich] CC src/mpi/topo/nhb_allgatherv.lo > [mpich] CC src/mpi/topo/nhb_alltoall.lo > [mpich] CC src/mpi/topo/nhb_alltoallv.lo > [mpich] CC src/mpi/topo/nhb_alltoallw.lo > [mpich] CC src/binding/f90/create_f90_int.lo > [mpich] CC src/binding/f90/create_f90_real.lo > [mpich] src/binding/f90/create_f90_real.c: In function > 'PMPI_Type_create_f90_real': > [mpich] src/binding/f90/create_f90_real.c:73:23: error: expected > expression before ',' token > [mpich] src/binding/f90/create_f90_real.c:74:25: error: expected > expression before ',' token > [mpich] make[2]: *** [src/binding/f90/create_f90_real.lo] Error 1 > [mpich] make[2]: Leaving directory > `/panfs/scratch/vol1/certik/h/tmp/mpich-webn36mjzfb3-1' > [mpich] make[1]: *** [all-recursive] Error 1 > [mpich] make[1]: Leaving directory > `/panfs/scratch/vol1/certik/h/tmp/mpich-webn36mjzfb3-1' > [mpich] make: *** [all] Error 2 > > > > It compiles fine with gcc 4.4. > > Ondrej > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss

1 0

MPICH 3.0.3 fails to compile with gcc 4.7
by Ondřej Čertík 16 Feb '14

16 Feb '14

Hi, After compiling 3.0.3 from source using gcc 4.7: ./configure --prefix=/panfs/scratch/vol1/certik/h/bld/mpich/webn36mjzfb3 --enable-shared (Full log is here: https://gist.github.com/certik/9041130) It fails with: [mpich] CC src/mpi/topo/nhb_allgather.lo [mpich] CC src/mpi/topo/nhb_allgatherv.lo [mpich] CC src/mpi/topo/nhb_alltoall.lo [mpich] CC src/mpi/topo/nhb_alltoallv.lo [mpich] CC src/mpi/topo/nhb_alltoallw.lo [mpich] CC src/binding/f90/create_f90_int.lo [mpich] CC src/binding/f90/create_f90_real.lo [mpich] src/binding/f90/create_f90_real.c: In function 'PMPI_Type_create_f90_real': [mpich] src/binding/f90/create_f90_real.c:73:23: error: expected expression before ',' token [mpich] src/binding/f90/create_f90_real.c:74:25: error: expected expression before ',' token [mpich] make[2]: *** [src/binding/f90/create_f90_real.lo] Error 1 [mpich] make[2]: Leaving directory `/panfs/scratch/vol1/certik/h/tmp/mpich-webn36mjzfb3-1' [mpich] make[1]: *** [all-recursive] Error 1 [mpich] make[1]: Leaving directory `/panfs/scratch/vol1/certik/h/tmp/mpich-webn36mjzfb3-1' [mpich] make: *** [all] Error 2 It compiles fine with gcc 4.4. Ondrej

1 0

Re: [mpich-discuss] Can i use MPI_REDUCE(with MPI_MIN) to get a "min array"?
by Matthieu Dorier 16 Feb '14

16 Feb '14

You can use MPI_Op_create to create the appropriate operation (see here: http://www.mcs.anl.gov/research/projects/mpi/www/www3/MPI_Op_create.html ) then use it in MPI_Reduce (instead of MPI_MIN). Matthieu Dorier PhD student at ENS Rennes http://people.irisa.fr/Matthieu.Dorier ----- Mail original ----- > De: "Wesley B. Bland" <wbland(a)anl.gov> > À: discuss(a)mpich.org > Envoyé: Dimanche 16 Février 2014 06:43:25 > Objet: Re: [mpich-discuss] Can i use MPI_REDUCE(with MPI_MIN) to get > a "min array"? > It depends on how you define min array. Do you want to get the > minimum value at each index? The full array with the minimum sum? > Something else? > On Feb 15, 2014, at 6:22 AM, 维洛逐风 < wu_0317(a)qq.com > wrote: > > HI. > > > Say,I have 10 process，each one has a array called gbest, I want to > > get the min array(with a compare operation I want to define). > > > Is there a way to use MPI_REDUCE to do this?As I know, MPI_MIN > > specifies datatypes(without arrays). > > > ------------------ > > > Jie-Jun Wu > > > Department of Computer Science, > > > Sun Yat-sen University, > > > Guangzhou, > > > P.R. China > > > _______________________________________________ > > > discuss mailing list discuss(a)mpich.org > > > To manage subscription options or unsubscribe: > > > https://lists.mpich.org/mailman/listinfo/discuss > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] Several nodes and typewrite several password
by Balaji, Pavan 16 Feb '14

16 Feb '14

Hello, You need to setup passwordless ssh between the nodes. Please see the README for more instructions. Regards, — Pavan From: Ярослав Иванов <ivanov.jaroslaw(a)gmail.com<mailto:[email protected]>> Reply-To: "discuss(a)mpich.org<mailto:[email protected]>" <discuss(a)mpich.org<mailto:[email protected]>> Date: Sunday, February 16, 2014 at 4:48 AM To: "discuss(a)mpich.org<mailto:[email protected]>" <discuss(a)mpich.org<mailto:[email protected]>> Subject: [mpich-discuss] Several nodes and typewrite several password Hello! When I try to exec my program on several machines, there is some trouble: When I use one node, there is all right. Before starting, system ask me: mpiu@ub1's password: ... But, when I try with two nodes: mpiu@ub2's password: mpiu@ub1's password: ... On one line! I try to typewrite password, but there is just stop and don't work. Without any issues or errors messages. I use mpich 1.4.1 and Ubuntu 12. -- С уважением, Иванов Ярослав

1 0

Several nodes and typewrite several password
by Ярослав Иванов 16 Feb '14

16 Feb '14

Hello! When I try to exec my program on several machines, there is some trouble: When I use one node, there is all right. Before starting, system ask me: mpiu@ub1's password: ... But, when I try with two nodes: mpiu@ub2's password: mpiu@ub1's password: ... On one line! I try to typewrite password, but there is just stop and don't work. Without any issues or errors messages. I use mpich 1.4.1 and Ubuntu 12. -- С уважением, Иванов Ярослав

1 0

Re: [mpich-discuss] Can i use MPI_REDUCE(with MPI_MIN) to get a "min array"?
by Bland, Wesley B. 15 Feb '14

15 Feb '14

It depends on how you define min array. Do you want to get the minimum value at each index? The full array with the minimum sum? Something else? On Feb 15, 2014, at 6:22 AM, 维洛逐风 <wu_0317(a)qq.com<mailto:[email protected]>> wrote: HI. Say,I have 10 process，each one has a array called gbest, I want to get the min array(with a compare operation I want to define). Is there a way to use MPI_REDUCE to do this?As I know, MPI_MIN specifies datatypes(without arrays). ------------------ Jie-Jun Wu Department of Computer Science, Sun Yat-sen University, Guangzhou, P.R. China _______________________________________________ discuss mailing list discuss(a)mpich.org<mailto:[email protected]> To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss

1 0

Can i use MPI_REDUCE(with MPI_MIN) to get a "min array"?
by 维洛逐风 15 Feb '14

15 Feb '14

HI. Say,I have 10 process，each one has a array called gbest, I want to get the min array(with a compare operation I want to define). Is there a way to use MPI_REDUCE to do this?As I know, MPI_MIN specifies datatypes(without arrays). ------------------ Jie-Jun Wu Department of Computer Science, Sun Yat-sen University, Guangzhou, P.R. China

1 0