From bfp at purdue.edu Wed Nov 4 16:09:47 2009 From: bfp at purdue.edu (Bryan Putnam) Date: Wed Nov 4 16:10:31 2009 Subject: [mvapich-discuss] mvapich2 and RDMA CM Address error Message-ID: We've been seeing with both mvapich2-1.4rc2 and mvapich2-1.4 the following error when attempting to use a large number of processors, for example 256 processors; 8 processors on each of 32 nodes. coates-a029 1005% mpiexec -np 256 ./helloc Hello from process 0! Hello from process 1! Hello from process 2! Hello from process 3! Hello from process 4! Hello from process 5! Hello from process 6! Hello from process 7! Hello from process 8! Hello from process 9! Hello from process 10! Hello from process 11! Hello from process 12! [247] Abort: RDMA CM Address error: rdma cma event 1, error -110 at line 341 in file rdma_cm.c I just wanted to check and see if this was a know problem with a solution. Thanks! Bryan From panda at cse.ohio-state.edu Wed Nov 4 16:39:54 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Wed Nov 4 16:40:32 2009 Subject: [mvapich-discuss] mvapich2 and RDMA CM Address error In-Reply-To: Message-ID: Hi Bryan, I believe you are still using the MPD/mpiexec environment. We are going away from that environment because it is not scalable. Please start using the new mpirun-rsh-based framwork which provides fast and scalable job startup. Let us know if you see any issues when using the mpirun-rsh-based framework. Thanks, DK On Wed, 4 Nov 2009, Bryan Putnam wrote: > We've been seeing with both mvapich2-1.4rc2 and mvapich2-1.4 the following > error when attempting to use a large number of processors, for example > 256 processors; 8 processors on each of 32 nodes. > > coates-a029 1005% mpiexec -np 256 ./helloc > Hello from process 0! > Hello from process 1! > Hello from process 2! > Hello from process 3! > Hello from process 4! > Hello from process 5! > Hello from process 6! > Hello from process 7! > Hello from process 8! > Hello from process 9! > Hello from process 10! > Hello from process 11! > Hello from process 12! > [247] Abort: RDMA CM Address error: rdma cma event 1, error -110 > at line 341 in file rdma_cm.c > > > I just wanted to check and see if this was a know problem with a solution. > > Thanks! > Bryan > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From bron.c.nelson at nasa.gov Wed Nov 4 17:07:36 2009 From: bron.c.nelson at nasa.gov (Nelson, Bron C. (ARC-TNE)[SILICON GRAPHICS]) Date: Wed Nov 4 17:08:19 2009 Subject: [mvapich-discuss] non-uniform IB connectivity Message-ID: I'm new to this list, so sorry if this has been discussed before. My site has two different clusters, each of which has dual fabrics of connectivity, i.e. the IB cards have 2 ports, and each cluster has 2 separate fabrics: ib0 (connected to the first port), and ib1 (connected to the second port), connecting the nodes within each cluster. We are now connecting the two clusters together, but for various reasons, the inter-cluster connections are only available over the ib1 fabric from each of the sub-clusters. I have been able to get mvapich2 1.4 to run across the two clusters, but only by disabling the first port on the IB cards, so that all the processes uniformly use only the ib1 fabrics. Is there some way to launch a single job across both clusters, and have mvapich use both fabrics for communications within a sub-cluster, but only a single fabric for communications across the sub-clusters? It looks to me as if when the ibv_query_port function returns IBV_PORT_ACTIVE that the mvapich software assumes it can use that port to reach the target process. That is not true in my case, or rather it is only selectively true, depending on which target process we are talking about, on a case by case basis. Any thoughts/advice welcome .. advTHANKSance ! -- Bron Campbell Nelson bron.c.nelson@nasa.gov With the first link, the chain is forged. The first speech censored, the first thought forbidden, the first freedom denied, chains us all irrevocably... The first time any man's freedom is trodden on, we're all damaged. Captain Jean-Luc Picard, Star Trek TNG, "The Drumhead" From bfp at purdue.edu Wed Nov 4 17:33:18 2009 From: bfp at purdue.edu (Bryan Putnam) Date: Wed Nov 4 17:34:02 2009 Subject: [mvapich-discuss] mvapich2 and RDMA CM Address error In-Reply-To: References: Message-ID: On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > Hi Bryan, > > I believe you are still using the MPD/mpiexec environment. We are going > away from that environment because it is not scalable. Please start using > the new mpirun-rsh-based framwork which provides fast and scalable job > startup. Let us know if you see any issues when using the mpirun-rsh-based > framework. Hi DK, Actually, I'm not using MPD/mpiexec, but am using mpiexec.hydra from the mpich2 distribution. The mpirun_rsh (from mvapich2) does not work on our Chelsio cluster. I had reported the mpirun_rsh problem earlier, but I'll go ahead and send that in again. Thanks, Bryan > > Thanks, > > DK > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > We've been seeing with both mvapich2-1.4rc2 and mvapich2-1.4 the following > > error when attempting to use a large number of processors, for example > > 256 processors; 8 processors on each of 32 nodes. > > > > coates-a029 1005% mpiexec -np 256 ./helloc > > Hello from process 0! > > Hello from process 1! > > Hello from process 2! > > Hello from process 3! > > Hello from process 4! > > Hello from process 5! > > Hello from process 6! > > Hello from process 7! > > Hello from process 8! > > Hello from process 9! > > Hello from process 10! > > Hello from process 11! > > Hello from process 12! > > [247] Abort: RDMA CM Address error: rdma cma event 1, error -110 > > at line 341 in file rdma_cm.c > > > > > > I just wanted to check and see if this was a know problem with a solution. > > > > Thanks! > > Bryan > > _______________________________________________ > > mvapich-discuss mailing list > > mvapich-discuss@cse.ohio-state.edu > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > From panda at cse.ohio-state.edu Wed Nov 4 17:39:53 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Wed Nov 4 17:40:30 2009 Subject: [mvapich-discuss] mvapich2 and RDMA CM Address error In-Reply-To: Message-ID: > > Hi Bryan, > > > > I believe you are still using the MPD/mpiexec environment. We are going > > away from that environment because it is not scalable. Please start using > > the new mpirun-rsh-based framwork which provides fast and scalable job > > startup. Let us know if you see any issues when using the mpirun-rsh-based > > framework. > > Hi DK, > > Actually, I'm not using MPD/mpiexec, but am using mpiexec.hydra from the > mpich2 distribution. The mpirun_rsh (from mvapich2) does not work on our > Chelsio cluster. I had reported the mpirun_rsh problem earlier, but I'll > go ahead and send that in again. We have not tested mpiexec.hydra. Let us know what issues you are facing with the mpirun_rsh framework on your Chelsio cluster. We use this in our Chelsio set-up here without any problem. Thanks, DK > Thanks, > Bryan > > > > > Thanks, > > > > DK > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > We've been seeing with both mvapich2-1.4rc2 and mvapich2-1.4 the following > > > error when attempting to use a large number of processors, for example > > > 256 processors; 8 processors on each of 32 nodes. > > > > > > coates-a029 1005% mpiexec -np 256 ./helloc > > > Hello from process 0! > > > Hello from process 1! > > > Hello from process 2! > > > Hello from process 3! > > > Hello from process 4! > > > Hello from process 5! > > > Hello from process 6! > > > Hello from process 7! > > > Hello from process 8! > > > Hello from process 9! > > > Hello from process 10! > > > Hello from process 11! > > > Hello from process 12! > > > [247] Abort: RDMA CM Address error: rdma cma event 1, error -110 > > > at line 341 in file rdma_cm.c > > > > > > > > > I just wanted to check and see if this was a know problem with a solution. > > > > > > Thanks! > > > Bryan > > > _______________________________________________ > > > mvapich-discuss mailing list > > > mvapich-discuss@cse.ohio-state.edu > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > From bfp at purdue.edu Wed Nov 4 17:43:16 2009 From: bfp at purdue.edu (Bryan Putnam) Date: Wed Nov 4 17:43:57 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 Message-ID: Hi All, When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) on a Chelsio cluster, I get errors which are reproduced below. Note that I don't see these errors with mvapich2 when using MPD/mpiexec or the mpiexec.hydra launcher from the mpich2 distribution. Thanks, Bryan =============================================== coates-a012 1005% mpif90 hellof.f -o hellof coates-a012 1006% cat $PBS_NODEFILE coates-a012 coates-a012 coates-a012 coates-a012 coates-a040 coates-a040 coates-a040 coates-a040 coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof Fatal error in MPI_Init: Error message texts are not available Exit code -5 signaled from coates-a040 MPI process (rank: 4) terminated unexpectedly on coates-a040.rcac.purdue.edu Fatal error in MPI_Init: Error message texts are not available Fatal error in MPI_Init: Error message texts are not available MPI process (rank: 0) terminated unexpectedly on coates-a012.rcac.purdue.edu forrtl: error (69): process interrupted (SIGINT) Image PC Routine Line Source libc.so.6 000000341045492F Unknown Unknown Unknown libc.so.6 0000003410463C15 Unknown Unknown Unknown libc.so.6 000000341045EF68 Unknown Unknown Unknown libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown Unknown libibverbs.so.1 000000341180722C Unknown Unknown Unknown libibverbs.so.1 00000034118082A3 Unknown Unknown Unknown libibverbs.so.1 000000341180707B Unknown Unknown Unknown libmpich.so.1.1 00002B0009C76298 Unknown Unknown Unknown libmpich.so.1.1 00002B0009C3C992 Unknown Unknown Unknown libmpich.so.1.1 00002B0009C751DC Unknown Unknown Unknown libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown Unknown libmpich.so.1.1 00002B0009C4B715 Unknown Unknown Unknown libmpich.so.1.1 00002B0009C46116 Unknown Unknown Unknown libmpich.so.1.1 00002B0009C4566A Unknown Unknown Unknown libmpich.so.1.1 00002B0009C45560 Unknown Unknown Unknown hellof 0000000000400F61 Unknown Unknown Unknown hellof 0000000000400EFC Unknown Unknown Unknown libc.so.6 000000341041D994 Unknown Unknown Unknown hellof 0000000000400E09 Unknown Unknown Unknown forrtl: error (69): process interrupted (SIGINT) Image PC Routine Line Source libpthread.so.0 0000003410C0D590 Unknown Unknown Unknown libibverbs.so.1 00000034118090D4 Unknown Unknown Unknown libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown Unknown libibverbs.so.1 000000341180722C Unknown Unknown Unknown libibverbs.so.1 00000034118082A3 Unknown Unknown Unknown libibverbs.so.1 000000341180707B Unknown Unknown Unknown libmpich.so.1.1 00002B74565E1298 Unknown Unknown Unknown libmpich.so.1.1 00002B74565A7992 Unknown Unknown Unknown libmpich.so.1.1 00002B74565E01DC Unknown Unknown Unknown libmpich.so.1.1 00002B7456566B6D Unknown Unknown Unknown libmpich.so.1.1 00002B74565B6715 Unknown Unknown Unknown libmpich.so.1.1 00002B74565B1116 Unknown Unknown Unknown libmpich.so.1.1 00002B74565B066A Unknown Unknown Unknown libmpich.so.1.1 00002B74565B0560 Unknown Unknown Unknown hellof 0000000000400F61 Unknown Unknown Unknown hellof 0000000000400EFC Unknown Unknown Unknown libc.so.6 000000341041D994 Unknown Unknown Unknown hellof 0000000000400E09 Unknown Unknown Unknown forrtl: error (69): process interrupted (SIGINT) Image PC Routine Line Source ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown Unknown ld-linux-x86-64.s 000000341000610F Unknown Unknown Unknown ld-linux-x86-64.s 0000003410007D33 Unknown Unknown Unknown ld-linux-x86-64.s 0000003410010C4D Unknown Unknown Unknown ld-linux-x86-64.s 000000341000CE96 Unknown Unknown Unknown ld-linux-x86-64.s 000000341001064C Unknown Unknown Unknown libdl.so.2 0000003410800F9A Unknown Unknown Unknown ld-linux-x86-64.s 000000341000CE96 Unknown Unknown Unknown libdl.so.2 000000341080150D Unknown Unknown Unknown libdl.so.2 0000003410800F11 Unknown Unknown Unknown libibverbs.so.1 0000003411807151 Unknown Unknown Unknown libibverbs.so.1 0000003411807410 Unknown Unknown Unknown libibverbs.so.1 000000341180825F Unknown Unknown Unknown libibverbs.so.1 000000341180707B Unknown Unknown Unknown libmpich.so.1.1 00002BA2E8701298 Unknown Unknown Unknown libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown Unknown libmpich.so.1.1 00002BA2E87001DC Unknown Unknown Unknown libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown Unknown libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown Unknown libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown Unknown libmpich.so.1.1 00002BA2E86D066A Unknown Unknown Unknown libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown Unknown hellof 0000000000400F61 Unknown Unknown Unknown hellof 0000000000400EFC Unknown Unknown Unknown libc.so.6 000000341041D994 Unknown Unknown Unknown hellof 0000000000400E09 Unknown Unknown Unknown coates-a012 1008% From panda at cse.ohio-state.edu Wed Nov 4 20:06:27 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Wed Nov 4 20:07:08 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: Message-ID: Bryan - Thanks for the report. This seems to be an issue when PBS is being used with mpirun_rsh of mvapich2. Are you able to launch jobs using mpirun_rsh directly as outlined in the mvapich2 user guide in the following section: http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 Thanks, DK On Wed, 4 Nov 2009, Bryan Putnam wrote: > Hi All, > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > on a Chelsio cluster, I get errors which are reproduced below. Note that I > don't see these errors with mvapich2 when using MPD/mpiexec or the > mpiexec.hydra launcher from the mpich2 distribution. > > Thanks, > Bryan > =============================================== > > coates-a012 1005% mpif90 hellof.f -o hellof > coates-a012 1006% cat $PBS_NODEFILE > coates-a012 > coates-a012 > coates-a012 > coates-a012 > coates-a040 > coates-a040 > coates-a040 > coates-a040 > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > Fatal error in MPI_Init: > Error message texts are not available > Exit code -5 signaled from coates-a040 > MPI process (rank: 4) terminated unexpectedly on > coates-a040.rcac.purdue.edu > Fatal error in MPI_Init: > Error message texts are not available > Fatal error in MPI_Init: > Error message texts are not available > MPI process (rank: 0) terminated unexpectedly on > coates-a012.rcac.purdue.edu > forrtl: error (69): process interrupted (SIGINT) > Image PC Routine Line Source > libc.so.6 000000341045492F Unknown Unknown > Unknown > libc.so.6 0000003410463C15 Unknown Unknown > Unknown > libc.so.6 000000341045EF68 Unknown Unknown > Unknown > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > Unknown > libibverbs.so.1 000000341180722C Unknown Unknown > Unknown > libibverbs.so.1 00000034118082A3 Unknown Unknown > Unknown > libibverbs.so.1 000000341180707B Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > Unknown > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > Unknown > hellof 0000000000400F61 Unknown Unknown > Unknown > hellof 0000000000400EFC Unknown Unknown > Unknown > libc.so.6 000000341041D994 Unknown Unknown > Unknown > hellof 0000000000400E09 Unknown Unknown > Unknown > forrtl: error (69): process interrupted (SIGINT) > Image PC Routine Line Source > libpthread.so.0 0000003410C0D590 Unknown Unknown > Unknown > libibverbs.so.1 00000034118090D4 Unknown Unknown > Unknown > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > Unknown > libibverbs.so.1 000000341180722C Unknown Unknown > Unknown > libibverbs.so.1 00000034118082A3 Unknown Unknown > Unknown > libibverbs.so.1 000000341180707B Unknown Unknown > Unknown > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > Unknown > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > Unknown > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > Unknown > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > Unknown > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > Unknown > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > Unknown > libmpich.so.1.1 00002B74565B066A Unknown Unknown > Unknown > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > Unknown > hellof 0000000000400F61 Unknown Unknown > Unknown > hellof 0000000000400EFC Unknown Unknown > Unknown > libc.so.6 000000341041D994 Unknown Unknown > Unknown > hellof 0000000000400E09 Unknown Unknown > Unknown > forrtl: error (69): process interrupted (SIGINT) > Image PC Routine Line Source > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > Unknown > ld-linux-x86-64.s 000000341000610F Unknown Unknown > Unknown > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > Unknown > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > Unknown > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > Unknown > ld-linux-x86-64.s 000000341001064C Unknown Unknown > Unknown > libdl.so.2 0000003410800F9A Unknown Unknown > Unknown > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > Unknown > libdl.so.2 000000341080150D Unknown Unknown > Unknown > libdl.so.2 0000003410800F11 Unknown Unknown > Unknown > libibverbs.so.1 0000003411807151 Unknown Unknown > Unknown > libibverbs.so.1 0000003411807410 Unknown Unknown > Unknown > libibverbs.so.1 000000341180825F Unknown Unknown > Unknown > libibverbs.so.1 000000341180707B Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > Unknown > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > Unknown > hellof 0000000000400F61 Unknown Unknown > Unknown > hellof 0000000000400EFC Unknown Unknown > Unknown > libc.so.6 000000341041D994 Unknown Unknown > Unknown > hellof 0000000000400E09 Unknown Unknown > Unknown > coates-a012 1008% > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From bfp at purdue.edu Wed Nov 4 20:31:20 2009 From: bfp at purdue.edu (Bryan Putnam) Date: Wed Nov 4 20:32:04 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: References: Message-ID: On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > Bryan - Thanks for the report. This seems to be an issue when PBS is being > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > mpirun_rsh directly as outlined in the mvapich2 user guide in the > following section: > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 DK, Yes, I see the same problem if I do mpirun_rsh -np 2 host1 host2 ./a.out Note that PBS is actually not involved at the point I was running the example. PBS simply set up the file $PBS_NODEFILE (which is a list of hosts). If I do cat $PBS_NODEFILE ./hostfile mpirun_rsh -hostfile ./hostfile -np 2 ./a.out I see the same problem. Note that mpirun_rsh does work as exepected on our other cluster which is Infiniband rather than iWARP. Both clusters are RHEL5. Please let me know if there is additional info you need. Thanks, Bryan > > Thanks, > > DK > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > Hi All, > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > mpiexec.hydra launcher from the mpich2 distribution. > > > > Thanks, > > Bryan > > =============================================== > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > coates-a012 1006% cat $PBS_NODEFILE > > coates-a012 > > coates-a012 > > coates-a012 > > coates-a012 > > coates-a040 > > coates-a040 > > coates-a040 > > coates-a040 > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > Fatal error in MPI_Init: > > Error message texts are not available > > Exit code -5 signaled from coates-a040 > > MPI process (rank: 4) terminated unexpectedly on > > coates-a040.rcac.purdue.edu > > Fatal error in MPI_Init: > > Error message texts are not available > > Fatal error in MPI_Init: > > Error message texts are not available > > MPI process (rank: 0) terminated unexpectedly on > > coates-a012.rcac.purdue.edu > > forrtl: error (69): process interrupted (SIGINT) > > Image PC Routine Line Source > > libc.so.6 000000341045492F Unknown Unknown > > Unknown > > libc.so.6 0000003410463C15 Unknown Unknown > > Unknown > > libc.so.6 000000341045EF68 Unknown Unknown > > Unknown > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > Unknown > > libibverbs.so.1 000000341180722C Unknown Unknown > > Unknown > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > Unknown > > libibverbs.so.1 000000341180707B Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > Unknown > > hellof 0000000000400F61 Unknown Unknown > > Unknown > > hellof 0000000000400EFC Unknown Unknown > > Unknown > > libc.so.6 000000341041D994 Unknown Unknown > > Unknown > > hellof 0000000000400E09 Unknown Unknown > > Unknown > > forrtl: error (69): process interrupted (SIGINT) > > Image PC Routine Line Source > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > Unknown > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > Unknown > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > Unknown > > libibverbs.so.1 000000341180722C Unknown Unknown > > Unknown > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > Unknown > > libibverbs.so.1 000000341180707B Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > Unknown > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > Unknown > > hellof 0000000000400F61 Unknown Unknown > > Unknown > > hellof 0000000000400EFC Unknown Unknown > > Unknown > > libc.so.6 000000341041D994 Unknown Unknown > > Unknown > > hellof 0000000000400E09 Unknown Unknown > > Unknown > > forrtl: error (69): process interrupted (SIGINT) > > Image PC Routine Line Source > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > Unknown > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > Unknown > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > Unknown > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > Unknown > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > Unknown > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > Unknown > > libdl.so.2 0000003410800F9A Unknown Unknown > > Unknown > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > Unknown > > libdl.so.2 000000341080150D Unknown Unknown > > Unknown > > libdl.so.2 0000003410800F11 Unknown Unknown > > Unknown > > libibverbs.so.1 0000003411807151 Unknown Unknown > > Unknown > > libibverbs.so.1 0000003411807410 Unknown Unknown > > Unknown > > libibverbs.so.1 000000341180825F Unknown Unknown > > Unknown > > libibverbs.so.1 000000341180707B Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > Unknown > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > Unknown > > hellof 0000000000400F61 Unknown Unknown > > Unknown > > hellof 0000000000400EFC Unknown Unknown > > Unknown > > libc.so.6 000000341041D994 Unknown Unknown > > Unknown > > hellof 0000000000400E09 Unknown Unknown > > Unknown > > coates-a012 1008% > > > > > > _______________________________________________ > > mvapich-discuss mailing list > > mvapich-discuss@cse.ohio-state.edu > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > From perkinjo at cse.ohio-state.edu Wed Nov 4 20:49:51 2009 From: perkinjo at cse.ohio-state.edu (Jonathan Perkins) Date: Wed Nov 4 20:50:36 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: References: Message-ID: <20091105014951.GA2843@cse.ohio-state.edu> On Wed, Nov 04, 2009 at 08:31:20PM -0500, Bryan Putnam wrote: > On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > > > Bryan - Thanks for the report. This seems to be an issue when PBS is being > > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > > mpirun_rsh directly as outlined in the mvapich2 user guide in the > > following section: > > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 > > DK, > > Yes, I see the same problem if I do > > mpirun_rsh -np 2 host1 host2 ./a.out > > Note that PBS is actually not involved at the point I was running the > example. PBS simply set up the file $PBS_NODEFILE (which is a list of > hosts). If I do > > cat $PBS_NODEFILE ./hostfile > mpirun_rsh -hostfile ./hostfile -np 2 ./a.out > > I see the same problem. Note that mpirun_rsh does work as exepected on our > other cluster which is Infiniband rather than iWARP. Both clusters are > RHEL5. Please let me know if there is additional info you need. I didn't realize that you were using iWARP the last time you posted this. I think the issue is related to a variable not being set on the mpirun_rsh command line. Try using... mpirun_rsh -np 2 host1 host2 MV2_USE_IWARP_MODE=1 ./a.out Please see the following link for more information: http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-220005.2.6 > > Thanks, > Bryan > > > > > Thanks, > > > > DK > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > Hi All, > > > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > > mpiexec.hydra launcher from the mpich2 distribution. > > > > > > Thanks, > > > Bryan > > > =============================================== > > > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > > coates-a012 1006% cat $PBS_NODEFILE > > > coates-a012 > > > coates-a012 > > > coates-a012 > > > coates-a012 > > > coates-a040 > > > coates-a040 > > > coates-a040 > > > coates-a040 > > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > > Fatal error in MPI_Init: > > > Error message texts are not available > > > Exit code -5 signaled from coates-a040 > > > MPI process (rank: 4) terminated unexpectedly on > > > coates-a040.rcac.purdue.edu > > > Fatal error in MPI_Init: > > > Error message texts are not available > > > Fatal error in MPI_Init: > > > Error message texts are not available > > > MPI process (rank: 0) terminated unexpectedly on > > > coates-a012.rcac.purdue.edu > > > forrtl: error (69): process interrupted (SIGINT) > > > Image PC Routine Line Source > > > libc.so.6 000000341045492F Unknown Unknown > > > Unknown > > > libc.so.6 0000003410463C15 Unknown Unknown > > > Unknown > > > libc.so.6 000000341045EF68 Unknown Unknown > > > Unknown > > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > Unknown > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > > Unknown > > > hellof 0000000000400F61 Unknown Unknown > > > Unknown > > > hellof 0000000000400EFC Unknown Unknown > > > Unknown > > > libc.so.6 000000341041D994 Unknown Unknown > > > Unknown > > > hellof 0000000000400E09 Unknown Unknown > > > Unknown > > > forrtl: error (69): process interrupted (SIGINT) > > > Image PC Routine Line Source > > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > > Unknown > > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > > Unknown > > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > Unknown > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > > Unknown > > > hellof 0000000000400F61 Unknown Unknown > > > Unknown > > > hellof 0000000000400EFC Unknown Unknown > > > Unknown > > > libc.so.6 000000341041D994 Unknown Unknown > > > Unknown > > > hellof 0000000000400E09 Unknown Unknown > > > Unknown > > > forrtl: error (69): process interrupted (SIGINT) > > > Image PC Routine Line Source > > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > > Unknown > > > libdl.so.2 0000003410800F9A Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > Unknown > > > libdl.so.2 000000341080150D Unknown Unknown > > > Unknown > > > libdl.so.2 0000003410800F11 Unknown Unknown > > > Unknown > > > libibverbs.so.1 0000003411807151 Unknown Unknown > > > Unknown > > > libibverbs.so.1 0000003411807410 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180825F Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > > Unknown > > > hellof 0000000000400F61 Unknown Unknown > > > Unknown > > > hellof 0000000000400EFC Unknown Unknown > > > Unknown > > > libc.so.6 000000341041D994 Unknown Unknown > > > Unknown > > > hellof 0000000000400E09 Unknown Unknown > > > Unknown > > > coates-a012 1008% > > > > > > > > > _______________________________________________ > > > mvapich-discuss mailing list > > > mvapich-discuss@cse.ohio-state.edu > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 197 bytes Desc: not available Url : http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091104/a87a73d0/attachment.bin From perkinjo at cse.ohio-state.edu Wed Nov 4 20:52:21 2009 From: perkinjo at cse.ohio-state.edu (Jonathan Perkins) Date: Wed Nov 4 20:53:00 2009 Subject: [mvapich-discuss] mvapich2 and RDMA CM Address error In-Reply-To: References: Message-ID: <20091105015221.GB2843@cse.ohio-state.edu> On Wed, Nov 04, 2009 at 04:09:47PM -0500, Bryan Putnam wrote: > We've been seeing with both mvapich2-1.4rc2 and mvapich2-1.4 the following > error when attempting to use a large number of processors, for example > 256 processors; 8 processors on each of 32 nodes. > > coates-a029 1005% mpiexec -np 256 ./helloc > Hello from process 0! > Hello from process 1! > Hello from process 2! > Hello from process 3! > Hello from process 4! > Hello from process 5! > Hello from process 6! > Hello from process 7! > Hello from process 8! > Hello from process 9! > Hello from process 10! > Hello from process 11! > Hello from process 12! > [247] Abort: RDMA CM Address error: rdma cma event 1, error -110 > at line 341 in file rdma_cm.c > > > I just wanted to check and see if this was a know problem with a solution. This doesn't look like a known issue. Is there a specific node that isn't functioning correctly? I see this error sometimes when opensm isn't running or the /etc/mv2.conf file doesn't point to the ip address of the interface that you're trying to use. Maybe you can try using subsets of your nodes to isolate where the problem is located. > > Thanks! > Bryan > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 197 bytes Desc: not available Url : http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091104/4caadc44/attachment.bin From panda at cse.ohio-state.edu Wed Nov 4 20:58:52 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Wed Nov 4 20:59:30 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: Message-ID: > On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > > > Bryan - Thanks for the report. This seems to be an issue when PBS is being > > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > > mpirun_rsh directly as outlined in the mvapich2 user guide in the > > following section: > > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 > > DK, > > Yes, I see the same problem if I do > > mpirun_rsh -np 2 host1 host2 ./a.out > > Note that PBS is actually not involved at the point I was running the > example. PBS simply set up the file $PBS_NODEFILE (which is a list of > hosts). If I do > > cat $PBS_NODEFILE ./hostfile > mpirun_rsh -hostfile ./hostfile -np 2 ./a.out > > I see the same problem. Note that mpirun_rsh does work as exepected on our > other cluster which is Infiniband rather than iWARP. Both clusters are > RHEL5. Please let me know if there is additional info you need. You need to use MV2_USE_iWARP_MODE=1 in the mpirun_rsh command. You also need to create the file /etc/MV2.conf with the local IP address to be used by RDMA_CM. Section 5.2.6 of MVAPICH2 1.4 user guide indicates how to use mpirun_rsh with iWARP devices. http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-220005.2.6 Let us know whether the steps indicated in this section help you. Thanks, DK > Thanks, > Bryan > > > > > Thanks, > > > > DK > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > Hi All, > > > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > > mpiexec.hydra launcher from the mpich2 distribution. > > > > > > Thanks, > > > Bryan > > > =============================================== > > > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > > coates-a012 1006% cat $PBS_NODEFILE > > > coates-a012 > > > coates-a012 > > > coates-a012 > > > coates-a012 > > > coates-a040 > > > coates-a040 > > > coates-a040 > > > coates-a040 > > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > > Fatal error in MPI_Init: > > > Error message texts are not available > > > Exit code -5 signaled from coates-a040 > > > MPI process (rank: 4) terminated unexpectedly on > > > coates-a040.rcac.purdue.edu > > > Fatal error in MPI_Init: > > > Error message texts are not available > > > Fatal error in MPI_Init: > > > Error message texts are not available > > > MPI process (rank: 0) terminated unexpectedly on > > > coates-a012.rcac.purdue.edu > > > forrtl: error (69): process interrupted (SIGINT) > > > Image PC Routine Line Source > > > libc.so.6 000000341045492F Unknown Unknown > > > Unknown > > > libc.so.6 0000003410463C15 Unknown Unknown > > > Unknown > > > libc.so.6 000000341045EF68 Unknown Unknown > > > Unknown > > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > Unknown > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > > Unknown > > > hellof 0000000000400F61 Unknown Unknown > > > Unknown > > > hellof 0000000000400EFC Unknown Unknown > > > Unknown > > > libc.so.6 000000341041D994 Unknown Unknown > > > Unknown > > > hellof 0000000000400E09 Unknown Unknown > > > Unknown > > > forrtl: error (69): process interrupted (SIGINT) > > > Image PC Routine Line Source > > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > > Unknown > > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > > Unknown > > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > Unknown > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > > Unknown > > > hellof 0000000000400F61 Unknown Unknown > > > Unknown > > > hellof 0000000000400EFC Unknown Unknown > > > Unknown > > > libc.so.6 000000341041D994 Unknown Unknown > > > Unknown > > > hellof 0000000000400E09 Unknown Unknown > > > Unknown > > > forrtl: error (69): process interrupted (SIGINT) > > > Image PC Routine Line Source > > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > > Unknown > > > libdl.so.2 0000003410800F9A Unknown Unknown > > > Unknown > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > Unknown > > > libdl.so.2 000000341080150D Unknown Unknown > > > Unknown > > > libdl.so.2 0000003410800F11 Unknown Unknown > > > Unknown > > > libibverbs.so.1 0000003411807151 Unknown Unknown > > > Unknown > > > libibverbs.so.1 0000003411807410 Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180825F Unknown Unknown > > > Unknown > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > > Unknown > > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > > Unknown > > > hellof 0000000000400F61 Unknown Unknown > > > Unknown > > > hellof 0000000000400EFC Unknown Unknown > > > Unknown > > > libc.so.6 000000341041D994 Unknown Unknown > > > Unknown > > > hellof 0000000000400E09 Unknown Unknown > > > Unknown > > > coates-a012 1008% > > > > > > > > > _______________________________________________ > > > mvapich-discuss mailing list > > > mvapich-discuss@cse.ohio-state.edu > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From bfp at purdue.edu Wed Nov 4 21:30:16 2009 From: bfp at purdue.edu (Bryan Putnam) Date: Wed Nov 4 21:30:59 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: <20091105014951.GA2843@cse.ohio-state.edu> References: <20091105014951.GA2843@cse.ohio-state.edu> Message-ID: On Wed, 4 Nov 2009, Jonathan Perkins wrote: > On Wed, Nov 04, 2009 at 08:31:20PM -0500, Bryan Putnam wrote: > > On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > > > > > Bryan - Thanks for the report. This seems to be an issue when PBS is being > > > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > > > mpirun_rsh directly as outlined in the mvapich2 user guide in the > > > following section: > > > > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 > > > > DK, > > > > Yes, I see the same problem if I do > > > > mpirun_rsh -np 2 host1 host2 ./a.out > > > > Note that PBS is actually not involved at the point I was running the > > example. PBS simply set up the file $PBS_NODEFILE (which is a list of > > hosts). If I do > > > > cat $PBS_NODEFILE ./hostfile > > mpirun_rsh -hostfile ./hostfile -np 2 ./a.out > > > > I see the same problem. Note that mpirun_rsh does work as exepected on our > > other cluster which is Infiniband rather than iWARP. Both clusters are > > RHEL5. Please let me know if there is additional info you need. > > I didn't realize that you were using iWARP the last time you posted > this. I think the issue is related to a variable not being set on the > mpirun_rsh command line. > > Try using... > mpirun_rsh -np 2 host1 host2 MV2_USE_IWARP_MODE=1 ./a.out OK that's interesting. That did appear to fix the problem. I knew that I needed to have MV2_USE_IWARP_MODE=1, but I had it in the environement as coates-adm 1012% env | grep MV MVAPICH2_HOME=/apps/rhel5/mvapich2-1.4/64/ib-intel-11.1.038 MV2_USE_SHMEM_COLL=0 MV2_USE_RDMA_CM=1 MV2_USE_IWARP_MODE=1 So, it appears that it actually needs to be on the mpirun_rsh command line as well? Thanks, Bryan > > Please see the following link for more information: > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-220005.2.6 > > > > > Thanks, > > Bryan > > > > > > > > Thanks, > > > > > > DK > > > > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > > > Hi All, > > > > > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > > > mpiexec.hydra launcher from the mpich2 distribution. > > > > > > > > Thanks, > > > > Bryan > > > > =============================================== > > > > > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > > > coates-a012 1006% cat $PBS_NODEFILE > > > > coates-a012 > > > > coates-a012 > > > > coates-a012 > > > > coates-a012 > > > > coates-a040 > > > > coates-a040 > > > > coates-a040 > > > > coates-a040 > > > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > > > Fatal error in MPI_Init: > > > > Error message texts are not available > > > > Exit code -5 signaled from coates-a040 > > > > MPI process (rank: 4) terminated unexpectedly on > > > > coates-a040.rcac.purdue.edu > > > > Fatal error in MPI_Init: > > > > Error message texts are not available > > > > Fatal error in MPI_Init: > > > > Error message texts are not available > > > > MPI process (rank: 0) terminated unexpectedly on > > > > coates-a012.rcac.purdue.edu > > > > forrtl: error (69): process interrupted (SIGINT) > > > > Image PC Routine Line Source > > > > libc.so.6 000000341045492F Unknown Unknown > > > > Unknown > > > > libc.so.6 0000003410463C15 Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341045EF68 Unknown Unknown > > > > Unknown > > > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400F61 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400EFC Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400E09 Unknown Unknown > > > > Unknown > > > > forrtl: error (69): process interrupted (SIGINT) > > > > Image PC Routine Line Source > > > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > > > Unknown > > > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400F61 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400EFC Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400E09 Unknown Unknown > > > > Unknown > > > > forrtl: error (69): process interrupted (SIGINT) > > > > Image PC Routine Line Source > > > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > > > Unknown > > > > libdl.so.2 0000003410800F9A Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > Unknown > > > > libdl.so.2 000000341080150D Unknown Unknown > > > > Unknown > > > > libdl.so.2 0000003410800F11 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 0000003411807151 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 0000003411807410 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180825F Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400F61 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400EFC Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400E09 Unknown Unknown > > > > Unknown > > > > coates-a012 1008% > > > > > > > > > > > > _______________________________________________ > > > > mvapich-discuss mailing list > > > > mvapich-discuss@cse.ohio-state.edu > > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > > > > > > > > _______________________________________________ > > mvapich-discuss mailing list > > mvapich-discuss@cse.ohio-state.edu > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > -- > Jonathan Perkins > http://www.cse.ohio-state.edu/~perkinjo > From bfp at purdue.edu Wed Nov 4 21:35:10 2009 From: bfp at purdue.edu (Bryan Putnam) Date: Wed Nov 4 21:36:18 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: References: Message-ID: On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > > On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > > > > > Bryan - Thanks for the report. This seems to be an issue when PBS is being > > > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > > > mpirun_rsh directly as outlined in the mvapich2 user guide in the > > > following section: > > > > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 > > > > DK, > > > > Yes, I see the same problem if I do > > > > mpirun_rsh -np 2 host1 host2 ./a.out > > > > Note that PBS is actually not involved at the point I was running the > > example. PBS simply set up the file $PBS_NODEFILE (which is a list of > > hosts). If I do > > > > cat $PBS_NODEFILE ./hostfile > > mpirun_rsh -hostfile ./hostfile -np 2 ./a.out > > > > I see the same problem. Note that mpirun_rsh does work as exepected on our > > other cluster which is Infiniband rather than iWARP. Both clusters are > > RHEL5. Please let me know if there is additional info you need. > > You need to use MV2_USE_iWARP_MODE=1 in the mpirun_rsh command. You also > need to create the file /etc/MV2.conf with the local IP address to be used > by RDMA_CM. Section 5.2.6 of MVAPICH2 1.4 user guide indicates how to use > mpirun_rsh with iWARP devices. > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-220005.2.6 > > Let us know whether the steps indicated in this section help you. DK, Thanks, we do already have the /etc/mv2.conf file set up. It was the fact that the MV2_USE_IWARP_MODE variable needed to be set on the command line rather than in the env that seemed to cause the problems. Thanks, Bryan > > Thanks, > > DK > > > > Thanks, > > Bryan > > > > > > > > Thanks, > > > > > > DK > > > > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > > > Hi All, > > > > > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > > > mpiexec.hydra launcher from the mpich2 distribution. > > > > > > > > Thanks, > > > > Bryan > > > > =============================================== > > > > > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > > > coates-a012 1006% cat $PBS_NODEFILE > > > > coates-a012 > > > > coates-a012 > > > > coates-a012 > > > > coates-a012 > > > > coates-a040 > > > > coates-a040 > > > > coates-a040 > > > > coates-a040 > > > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > > > Fatal error in MPI_Init: > > > > Error message texts are not available > > > > Exit code -5 signaled from coates-a040 > > > > MPI process (rank: 4) terminated unexpectedly on > > > > coates-a040.rcac.purdue.edu > > > > Fatal error in MPI_Init: > > > > Error message texts are not available > > > > Fatal error in MPI_Init: > > > > Error message texts are not available > > > > MPI process (rank: 0) terminated unexpectedly on > > > > coates-a012.rcac.purdue.edu > > > > forrtl: error (69): process interrupted (SIGINT) > > > > Image PC Routine Line Source > > > > libc.so.6 000000341045492F Unknown Unknown > > > > Unknown > > > > libc.so.6 0000003410463C15 Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341045EF68 Unknown Unknown > > > > Unknown > > > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400F61 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400EFC Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400E09 Unknown Unknown > > > > Unknown > > > > forrtl: error (69): process interrupted (SIGINT) > > > > Image PC Routine Line Source > > > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > > > Unknown > > > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400F61 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400EFC Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400E09 Unknown Unknown > > > > Unknown > > > > forrtl: error (69): process interrupted (SIGINT) > > > > Image PC Routine Line Source > > > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > > > Unknown > > > > libdl.so.2 0000003410800F9A Unknown Unknown > > > > Unknown > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > Unknown > > > > libdl.so.2 000000341080150D Unknown Unknown > > > > Unknown > > > > libdl.so.2 0000003410800F11 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 0000003411807151 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 0000003411807410 Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180825F Unknown Unknown > > > > Unknown > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > > > Unknown > > > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400F61 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400EFC Unknown Unknown > > > > Unknown > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > Unknown > > > > hellof 0000000000400E09 Unknown Unknown > > > > Unknown > > > > coates-a012 1008% > > > > > > > > > > > > _______________________________________________ > > > > mvapich-discuss mailing list > > > > mvapich-discuss@cse.ohio-state.edu > > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > > > > > > > > _______________________________________________ > > mvapich-discuss mailing list > > mvapich-discuss@cse.ohio-state.edu > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > From subramon at cse.ohio-state.edu Wed Nov 4 22:11:22 2009 From: subramon at cse.ohio-state.edu (Hari Subramoni) Date: Wed Nov 4 22:12:04 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: Message-ID: For mpirun_rsh , all the environment variables must be passed on the command line or through the parameters file. It will not take it from the environment like mpiexec/mpd will. Thx, Hari. On Wed, 4 Nov 2009, Bryan Putnam wrote: > On Wed, 4 Nov 2009, Jonathan Perkins wrote: > > > On Wed, Nov 04, 2009 at 08:31:20PM -0500, Bryan Putnam wrote: > > > On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > > > > > > > Bryan - Thanks for the report. This seems to be an issue when PBS is being > > > > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > > > > mpirun_rsh directly as outlined in the mvapich2 user guide in the > > > > following section: > > > > > > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 > > > > > > DK, > > > > > > Yes, I see the same problem if I do > > > > > > mpirun_rsh -np 2 host1 host2 ./a.out > > > > > > Note that PBS is actually not involved at the point I was running the > > > example. PBS simply set up the file $PBS_NODEFILE (which is a list of > > > hosts). If I do > > > > > > cat $PBS_NODEFILE ./hostfile > > > mpirun_rsh -hostfile ./hostfile -np 2 ./a.out > > > > > > I see the same problem. Note that mpirun_rsh does work as exepected on our > > > other cluster which is Infiniband rather than iWARP. Both clusters are > > > RHEL5. Please let me know if there is additional info you need. > > > > I didn't realize that you were using iWARP the last time you posted > > this. I think the issue is related to a variable not being set on the > > mpirun_rsh command line. > > > > Try using... > > mpirun_rsh -np 2 host1 host2 MV2_USE_IWARP_MODE=1 ./a.out > > OK that's interesting. That did appear to fix the problem. I knew that I > needed to have MV2_USE_IWARP_MODE=1, but I had it in the environement as > > coates-adm 1012% env | grep MV > MVAPICH2_HOME=/apps/rhel5/mvapich2-1.4/64/ib-intel-11.1.038 > MV2_USE_SHMEM_COLL=0 > MV2_USE_RDMA_CM=1 > MV2_USE_IWARP_MODE=1 > > So, it appears that it actually needs to be on the mpirun_rsh command line > as well? > > Thanks, > Bryan > > > > > > Please see the following link for more information: > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-220005.2.6 > > > > > > > > Thanks, > > > Bryan > > > > > > > > > > > Thanks, > > > > > > > > DK > > > > > > > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > > > > > Hi All, > > > > > > > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > > > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > > > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > > > > mpiexec.hydra launcher from the mpich2 distribution. > > > > > > > > > > Thanks, > > > > > Bryan > > > > > =============================================== > > > > > > > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > > > > coates-a012 1006% cat $PBS_NODEFILE > > > > > coates-a012 > > > > > coates-a012 > > > > > coates-a012 > > > > > coates-a012 > > > > > coates-a040 > > > > > coates-a040 > > > > > coates-a040 > > > > > coates-a040 > > > > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > > > > Fatal error in MPI_Init: > > > > > Error message texts are not available > > > > > Exit code -5 signaled from coates-a040 > > > > > MPI process (rank: 4) terminated unexpectedly on > > > > > coates-a040.rcac.purdue.edu > > > > > Fatal error in MPI_Init: > > > > > Error message texts are not available > > > > > Fatal error in MPI_Init: > > > > > Error message texts are not available > > > > > MPI process (rank: 0) terminated unexpectedly on > > > > > coates-a012.rcac.purdue.edu > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > Image PC Routine Line Source > > > > > libc.so.6 000000341045492F Unknown Unknown > > > > > Unknown > > > > > libc.so.6 0000003410463C15 Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341045EF68 Unknown Unknown > > > > > Unknown > > > > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > Unknown > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > Image PC Routine Line Source > > > > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > > > > Unknown > > > > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > Unknown > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > Image PC Routine Line Source > > > > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > > > > Unknown > > > > > libdl.so.2 0000003410800F9A Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > > Unknown > > > > > libdl.so.2 000000341080150D Unknown Unknown > > > > > Unknown > > > > > libdl.so.2 0000003410800F11 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 0000003411807151 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 0000003411807410 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180825F Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > Unknown > > > > > coates-a012 1008% > > > > > > > > > > > > > > > _______________________________________________ > > > > > mvapich-discuss mailing list > > > > > mvapich-discuss@cse.ohio-state.edu > > > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > > > > > > > > > > > > > > _______________________________________________ > > > mvapich-discuss mailing list > > > mvapich-discuss@cse.ohio-state.edu > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > -- > > Jonathan Perkins > > http://www.cse.ohio-state.edu/~perkinjo > > > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From balaji at mcs.anl.gov Wed Nov 4 22:33:44 2009 From: balaji at mcs.anl.gov (Pavan Balaji) Date: Wed Nov 4 22:34:30 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: References: <20091105014951.GA2843@cse.ohio-state.edu> Message-ID: <4AF24798.4050109@mcs.anl.gov> On 11/04/2009 08:30 PM, Bryan Putnam wrote: > OK that's interesting. That did appear to fix the problem. I knew that I > needed to have MV2_USE_IWARP_MODE=1, but I had it in the environement as > > coates-adm 1012% env | grep MV > MVAPICH2_HOME=/apps/rhel5/mvapich2-1.4/64/ib-intel-11.1.038 > MV2_USE_SHMEM_COLL=0 > MV2_USE_RDMA_CM=1 > MV2_USE_IWARP_MODE=1 > > So, it appears that it actually needs to be on the mpirun_rsh command line > as well? How a process manager passes along environment information to each MPI process is implementation dependent. MPD and Hydra send out environment variables they inherit from their shell to the application processes by default. It looks like OSU's mpirun_rsh doesn't do that. In general, it's always a good idea to pass the environment you care about on all process managers (irrespective of what they do by default). -- Pavan -- Pavan Balaji http://www.mcs.anl.gov/~balaji From panda at cse.ohio-state.edu Wed Nov 4 22:38:25 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Wed Nov 4 22:39:07 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: Message-ID: > > > > Bryan - Thanks for the report. This seems to be an issue when PBS is being > > > > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > > > > mpirun_rsh directly as outlined in the mvapich2 user guide in the > > > > following section: > > > > > > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 > > > > > > DK, > > > > > > Yes, I see the same problem if I do > > > > > > mpirun_rsh -np 2 host1 host2 ./a.out > > > > > > Note that PBS is actually not involved at the point I was running the > > > example. PBS simply set up the file $PBS_NODEFILE (which is a list of > > > hosts). If I do > > > > > > cat $PBS_NODEFILE ./hostfile > > > mpirun_rsh -hostfile ./hostfile -np 2 ./a.out > > > > > > I see the same problem. Note that mpirun_rsh does work as exepected on our > > > other cluster which is Infiniband rather than iWARP. Both clusters are > > > RHEL5. Please let me know if there is additional info you need. > > > > I didn't realize that you were using iWARP the last time you posted > > this. I think the issue is related to a variable not being set on the > > mpirun_rsh command line. > > > > Try using... > > mpirun_rsh -np 2 host1 host2 MV2_USE_IWARP_MODE=1 ./a.out > > OK that's interesting. That did appear to fix the problem. I knew that I > needed to have MV2_USE_IWARP_MODE=1, but I had it in the environement as > > coates-adm 1012% env | grep MV > MVAPICH2_HOME=/apps/rhel5/mvapich2-1.4/64/ib-intel-11.1.038 > MV2_USE_SHMEM_COLL=0 > MV2_USE_RDMA_CM=1 > MV2_USE_IWARP_MODE=1 > > So, it appears that it actually needs to be on the mpirun_rsh command line > as well? Bryan, Very good to know that the problem got resolved. I will also suggest to remove the `MV2_USE_SHMEM_COLL=0' restriction to get best performance for collectives and applications on large-scale clusters. By default, SHMEM_COLL is on (1) and you should use it. Let us know if you encounter any additional problems. Thanks, DK > Thanks, > Bryan > > > > > > Please see the following link for more information: > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-220005.2.6 > > > > > > > > Thanks, > > > Bryan > > > > > > > > > > > Thanks, > > > > > > > > DK > > > > > > > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > > > > > Hi All, > > > > > > > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > > > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > > > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > > > > mpiexec.hydra launcher from the mpich2 distribution. > > > > > > > > > > Thanks, > > > > > Bryan > > > > > =============================================== > > > > > > > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > > > > coates-a012 1006% cat $PBS_NODEFILE > > > > > coates-a012 > > > > > coates-a012 > > > > > coates-a012 > > > > > coates-a012 > > > > > coates-a040 > > > > > coates-a040 > > > > > coates-a040 > > > > > coates-a040 > > > > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > > > > Fatal error in MPI_Init: > > > > > Error message texts are not available > > > > > Exit code -5 signaled from coates-a040 > > > > > MPI process (rank: 4) terminated unexpectedly on > > > > > coates-a040.rcac.purdue.edu > > > > > Fatal error in MPI_Init: > > > > > Error message texts are not available > > > > > Fatal error in MPI_Init: > > > > > Error message texts are not available > > > > > MPI process (rank: 0) terminated unexpectedly on > > > > > coates-a012.rcac.purdue.edu > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > Image PC Routine Line Source > > > > > libc.so.6 000000341045492F Unknown Unknown > > > > > Unknown > > > > > libc.so.6 0000003410463C15 Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341045EF68 Unknown Unknown > > > > > Unknown > > > > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > Unknown > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > Image PC Routine Line Source > > > > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > > > > Unknown > > > > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > Unknown > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > Image PC Routine Line Source > > > > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > > > > Unknown > > > > > libdl.so.2 0000003410800F9A Unknown Unknown > > > > > Unknown > > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > > Unknown > > > > > libdl.so.2 000000341080150D Unknown Unknown > > > > > Unknown > > > > > libdl.so.2 0000003410800F11 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 0000003411807151 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 0000003411807410 Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180825F Unknown Unknown > > > > > Unknown > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > > > > Unknown > > > > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > Unknown > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > Unknown > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > Unknown > > > > > coates-a012 1008% > > > > > > > > > > > > > > > _______________________________________________ > > > > > mvapich-discuss mailing list > > > > > mvapich-discuss@cse.ohio-state.edu > > > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > > > > > > > > > > > > > > _______________________________________________ > > > mvapich-discuss mailing list > > > mvapich-discuss@cse.ohio-state.edu > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > -- > > Jonathan Perkins > > http://www.cse.ohio-state.edu/~perkinjo > > > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From bfp at purdue.edu Thu Nov 5 08:36:26 2009 From: bfp at purdue.edu (Bryan Putnam) Date: Thu Nov 5 08:37:08 2009 Subject: [mvapich-discuss] mpirun_rsh and Chelsio cluster running RHEL5 In-Reply-To: References: Message-ID: On Wed, 4 Nov 2009, Dhabaleswar Panda wrote: > > > > > Bryan - Thanks for the report. This seems to be an issue when PBS is being > > > > > used with mpirun_rsh of mvapich2. Are you able to launch jobs using > > > > > mpirun_rsh directly as outlined in the mvapich2 user guide in the > > > > > following section: > > > > > > > > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-170005.2.1 > > > > > > > > DK, > > > > > > > > Yes, I see the same problem if I do > > > > > > > > mpirun_rsh -np 2 host1 host2 ./a.out > > > > > > > > Note that PBS is actually not involved at the point I was running the > > > > example. PBS simply set up the file $PBS_NODEFILE (which is a list of > > > > hosts). If I do > > > > > > > > cat $PBS_NODEFILE ./hostfile > > > > mpirun_rsh -hostfile ./hostfile -np 2 ./a.out > > > > > > > > I see the same problem. Note that mpirun_rsh does work as exepected on our > > > > other cluster which is Infiniband rather than iWARP. Both clusters are > > > > RHEL5. Please let me know if there is additional info you need. > > > > > > I didn't realize that you were using iWARP the last time you posted > > > this. I think the issue is related to a variable not being set on the > > > mpirun_rsh command line. > > > > > > Try using... > > > mpirun_rsh -np 2 host1 host2 MV2_USE_IWARP_MODE=1 ./a.out > > > > OK that's interesting. That did appear to fix the problem. I knew that I > > needed to have MV2_USE_IWARP_MODE=1, but I had it in the environement as > > > > coates-adm 1012% env | grep MV > > MVAPICH2_HOME=/apps/rhel5/mvapich2-1.4/64/ib-intel-11.1.038 > > MV2_USE_SHMEM_COLL=0 > > MV2_USE_RDMA_CM=1 > > MV2_USE_IWARP_MODE=1 > > > > So, it appears that it actually needs to be on the mpirun_rsh command line > > as well? > > Bryan, > > Very good to know that the problem got resolved. I will also suggest to > remove the `MV2_USE_SHMEM_COLL=0' restriction to get best performance for > collectives and applications on large-scale clusters. By default, > SHMEM_COLL is on (1) and you should use it. > > Let us know if you encounter any additional problems. Thanks DK et al for all the help. Actually, I had to set MV2_USE_SHMEM_COLL=0 in order to get the Intel MPI benchmarks to complete successfully (when using mpiexec/mpd and mpiexec.hydra). I found this to be the case on both our IB cluster and our iWARP cluster. Anyway, I'll do some experimenting with mpirun_rsh for wide jobs and let you know what I see. Thanks! Bryan > > Thanks, > > DK > > > Thanks, > > Bryan > > > > > > > > > > Please see the following link for more information: > > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-220005.2.6 > > > > > > > > > > > Thanks, > > > > Bryan > > > > > > > > > > > > > > Thanks, > > > > > > > > > > DK > > > > > > > > > > > > > > > On Wed, 4 Nov 2009, Bryan Putnam wrote: > > > > > > > > > > > Hi All, > > > > > > > > > > > > When attempting to use "mpirun_rsh" (from mvapich2-1.4 or mvapich2-1.4rc2) > > > > > > on a Chelsio cluster, I get errors which are reproduced below. Note that I > > > > > > don't see these errors with mvapich2 when using MPD/mpiexec or the > > > > > > mpiexec.hydra launcher from the mpich2 distribution. > > > > > > > > > > > > Thanks, > > > > > > Bryan > > > > > > =============================================== > > > > > > > > > > > > coates-a012 1005% mpif90 hellof.f -o hellof > > > > > > coates-a012 1006% cat $PBS_NODEFILE > > > > > > coates-a012 > > > > > > coates-a012 > > > > > > coates-a012 > > > > > > coates-a012 > > > > > > coates-a040 > > > > > > coates-a040 > > > > > > coates-a040 > > > > > > coates-a040 > > > > > > coates-a012 1007% mpirun_rsh -hostfile $PBS_NODEFILE -np 8 ./hellof > > > > > > Fatal error in MPI_Init: > > > > > > Error message texts are not available > > > > > > Exit code -5 signaled from coates-a040 > > > > > > MPI process (rank: 4) terminated unexpectedly on > > > > > > coates-a040.rcac.purdue.edu > > > > > > Fatal error in MPI_Init: > > > > > > Error message texts are not available > > > > > > Fatal error in MPI_Init: > > > > > > Error message texts are not available > > > > > > MPI process (rank: 0) terminated unexpectedly on > > > > > > coates-a012.rcac.purdue.edu > > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > > Image PC Routine Line Source > > > > > > libc.so.6 000000341045492F Unknown Unknown > > > > > > Unknown > > > > > > libc.so.6 0000003410463C15 Unknown Unknown > > > > > > Unknown > > > > > > libc.so.6 000000341045EF68 Unknown Unknown > > > > > > Unknown > > > > > > libmthca-rdmav2.s 00002B000ADB7C26 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009C76298 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009C3C992 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009C751DC Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009BFBB6D Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009C4B715 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009C46116 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009C4566A Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B0009C45560 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > > Unknown > > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > > Unknown > > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > > Image PC Routine Line Source > > > > > > libpthread.so.0 0000003410C0D590 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 00000034118090D4 Unknown Unknown > > > > > > Unknown > > > > > > libcxgb3-rdmav2.s 00002B7457929C78 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 000000341180722C Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 00000034118082A3 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B74565E1298 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B74565A7992 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B74565E01DC Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B7456566B6D Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B74565B6715 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B74565B1116 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B74565B066A Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002B74565B0560 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > > Unknown > > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > > Unknown > > > > > > forrtl: error (69): process interrupted (SIGINT) > > > > > > Image PC Routine Line Source > > > > > > ld-linux-x86-64.s 0000003410014BA6 Unknown Unknown > > > > > > Unknown > > > > > > ld-linux-x86-64.s 000000341000610F Unknown Unknown > > > > > > Unknown > > > > > > ld-linux-x86-64.s 0000003410007D33 Unknown Unknown > > > > > > Unknown > > > > > > ld-linux-x86-64.s 0000003410010C4D Unknown Unknown > > > > > > Unknown > > > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > > > Unknown > > > > > > ld-linux-x86-64.s 000000341001064C Unknown Unknown > > > > > > Unknown > > > > > > libdl.so.2 0000003410800F9A Unknown Unknown > > > > > > Unknown > > > > > > ld-linux-x86-64.s 000000341000CE96 Unknown Unknown > > > > > > Unknown > > > > > > libdl.so.2 000000341080150D Unknown Unknown > > > > > > Unknown > > > > > > libdl.so.2 0000003410800F11 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 0000003411807151 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 0000003411807410 Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 000000341180825F Unknown Unknown > > > > > > Unknown > > > > > > libibverbs.so.1 000000341180707B Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E8701298 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E86C7992 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E87001DC Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E8686B6D Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E86D6715 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E86D1116 Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E86D066A Unknown Unknown > > > > > > Unknown > > > > > > libmpich.so.1.1 00002BA2E86D0560 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400F61 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400EFC Unknown Unknown > > > > > > Unknown > > > > > > libc.so.6 000000341041D994 Unknown Unknown > > > > > > Unknown > > > > > > hellof 0000000000400E09 Unknown Unknown > > > > > > Unknown > > > > > > coates-a012 1008% > > > > > > > > > > > > > > > > > > _______________________________________________ > > > > > > mvapich-discuss mailing list > > > > > > mvapich-discuss@cse.ohio-state.edu > > > > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > > > > > > > > > > > > > > > > > > > > > > > _______________________________________________ > > > > mvapich-discuss mailing list > > > > mvapich-discuss@cse.ohio-state.edu > > > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > > > -- > > > Jonathan Perkins > > > http://www.cse.ohio-state.edu/~perkinjo > > > > > > > > > _______________________________________________ > > mvapich-discuss mailing list > > mvapich-discuss@cse.ohio-state.edu > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > > From panda at cse.ohio-state.edu Fri Nov 6 08:46:36 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Fri Nov 6 08:47:15 2009 Subject: [mvapich-discuss] non-uniform IB connectivity In-Reply-To: Message-ID: Hi Bron, Thanks for your note. > I'm new to this list, so sorry if this has been discussed before. > My site has two different clusters, each of which has dual > fabrics of connectivity, i.e. the IB cards have 2 ports, and > each cluster has 2 separate fabrics: ib0 (connected to the first > port), and ib1 (connected to the second port), connecting the > nodes within each cluster. > > We are now connecting the two clusters together, but for various > reasons, the inter-cluster connections are only available over the > ib1 fabric from each of the sub-clusters. > > I have been able to get mvapich2 1.4 to run across the two > clusters, but only by disabling the first port on the IB cards, > so that all the processes uniformly use only the ib1 fabrics. Good. MVAPICH2 has support for multi-rail. You can use both ports. However, you are indicating that inter-cluster connectivity is not there for both clusters on your fabric using both ports. In this case, you can not use the multi-rail feature. > Is there some way to launch a single job across both clusters, > and have mvapich use both fabrics for communications within > a sub-cluster, but only a single fabric for communications > across the sub-clusters? It looks to me as if when the > ibv_query_port function returns IBV_PORT_ACTIVE that > the mvapich software assumes it can use that port to reach > the target process. That is not true in my case, or rather it > is only selectively true, depending on which target process > we are talking about, on a case by case basis. It is not as easy as you are indicating. All underlying MPI protocols (pt-to-pt, collectives, etc.) need to be modified to take care of such assymetric connections. I think what you are doing (using ib1 port only) sounds good to me. If you can get your inter-cluster network to work on both ports, you can use the multi-rail features of MVAPICH2. Thanks, DK > Any thoughts/advice welcome .. advTHANKSance ! > > -- > Bron Campbell Nelson bron.c.nelson@nasa.gov > > With the first link, the chain is forged. The first speech censored, > the first thought forbidden, the first freedom denied, chains us all > irrevocably... The first time any man's freedom is trodden on, > we're all damaged. > Captain Jean-Luc Picard, Star Trek TNG, "The Drumhead" > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From niftycluster at niftyegg.com Sat Nov 7 19:26:40 2009 From: niftycluster at niftyegg.com (NiftyCluster Tom Mitchell) Date: Sat Nov 7 19:27:19 2009 Subject: [mvapich-discuss] non-uniform IB connectivity In-Reply-To: References: Message-ID: <7dddca9e0911071626l77803992qf738a4d0961f22a9@mail.gmail.com> On 11/6/09, Dhabaleswar Panda wrote: > Hi Bron, > > Thanks for your note. > >> I'm new to this list, so sorry if this has been discussed before. >> My site has two different clusters, each of which has dual >> fabrics of connectivity, i.e. the IB cards have 2 ports, and >> each cluster has 2 separate fabrics: ib0 (connected to the first >> port), and ib1 (connected to the second port), connecting the >> nodes within each cluster. >> >> We are now connecting the two clusters together, but for various >> reasons, the inter-cluster connections are only available over the >> ib1 fabric from each of the sub-clusters. Do check your TCP/IP Ethernet connectivity. netmasks and host names etc. It is possible that your previous two fabrics were isolated in part by the way that jobs were launched from the tcp/ip connections on the nodes. It only takes a single IB cable between two fabrics to merge them. As soon as duplicate LIDs are eliminated by the subnet manager you have a single IB fabric. Make sure the subnet manager is healthy. In some cases with too many nodes managed by an imbedded manager the SM can choke. Merging two fabrics might take things beyond the one too many line. i.e. the management tools and configurations that once kept the two clusters healthy or separated may still be getting in the way. -- NiftyCluster T o m M i t c h e l l From onunix at digitalhenge.com Mon Nov 9 10:22:36 2009 From: onunix at digitalhenge.com (=?ks_c_5601-1987?B?wMwguc7B1g==?=) Date: Mon Nov 9 10:57:38 2009 Subject: [mvapich-discuss] MVAPICH 1.2.0 and Intel compiler 10 Message-ID: <8FA329826573164DA1E5C72B0CE981D4E012EE@hns1.digitalhenge.com> Hi, When I compile MVAPICH 1.2.0-3054 with intel compiler 10.1, there is a condition which stops. checking whether icpc returns correct error code... => icpc -c conftest.cc>conftest.out .... Is this intel compiler or MVAPICH 1.2.0 bugs ? --------------------------------------------------------------------- [ ??? ] (?)????? | SI??? | ?? (152-790) ??? ??? ??3? 212-8 ??????? 1? 8? (305-806) ????? ??? ??? 52-11 ??????????? Eoeun-dong 52-11, Yuseong-gu, Daejeon city, Korea(South) KISTI Tel. +82-42-869-0646 / Cel. +82-10-7100-8220 / Fax. +82-42-862-0984 onunix@digitalhenge.com / onunix@gmail.com / openunix@kisti.re.kr --------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091110/97747c11/attachment.html From perkinjo at cse.ohio-state.edu Mon Nov 9 12:11:01 2009 From: perkinjo at cse.ohio-state.edu (Jonathan Perkins) Date: Mon Nov 9 12:11:41 2009 Subject: [mvapich-discuss] MVAPICH 1.2.0 and Intel compiler 10 In-Reply-To: <8FA329826573164DA1E5C72B0CE981D4E012EE@hns1.digitalhenge.com> References: <8FA329826573164DA1E5C72B0CE981D4E012EE@hns1.digitalhenge.com> Message-ID: <20091109171101.GM2371@cse.ohio-state.edu> On Tue, Nov 10, 2009 at 12:22:36AM +0900, ?? ???? wrote: > Hi, > > When I compile MVAPICH 1.2.0-3054 with intel compiler 10.1, there is a condition which stops. > > checking whether icpc returns correct error code... > > => icpc -c conftest.cc>conftest.out .... > > Is this intel compiler or MVAPICH 1.2.0 bugs ? It's hard to tell without the config logs. It looks like you're saying the configuration step stops after outputting this message. We'll need the config.log file to see why its failing this test. You can send this directly to me as an attachment if you'd like. -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 197 bytes Desc: not available Url : http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091109/37dee9c6/attachment.bin From kubota at cray.com Mon Nov 9 21:30:36 2009 From: kubota at cray.com (Yutaka Kubota) Date: Mon Nov 9 21:31:19 2009 Subject: [mvapich-discuss] RE: Could you upgrade "mpirun_rsh" command In-Reply-To: <20091026154130.GJ3972@cse.ohio-state.edu> References: <20091026154130.GJ3972@cse.ohio-state.edu> Message-ID: TO: Professor Panda CC: Jonathan This is Yutaka Kubota from Cray Japan Inc. Thank you for answer and your idea. We have a favor to ask you. In fact, we strongly need function of "mpirun_rsh" new option of keeping Group ID to compute nodes. Because our users having some group executed "newgrp" submit job using MVAPICH2. So if they execute "newgrp" command for change other group, their put files posses original group. It is problem for our system. I guess such user is more exist in the MVAPICH2 users. Could you discuss to add this function on the MVAPICH2. For example: $ mpirun_rsh -np 64 -hostfile hostfile.txt -g $GROUP_ID ./a.out Best regards Yutaka Kubota -----Original Message----- From: Jonathan Perkins [mailto:perkinjo@cse.ohio-state.edu] Sent: Tuesday, October 27, 2009 12:42 AM To: Yutaka Kubota Cc: mvapich-discuss@cse.ohio-state.edu Subject: Re: [mvapich-discuss] RE: Could you upgrade "mpirun_rsh" command Sorry for the delay in replying. We spent some time reviewing the options for satisfying this request. At first glance this issue seems like it can be better suited to be handled by other mechanisms but I haven't found any that handles the dynamic setting of a user's effective group id on a remote machine. It also doesn't seem trivial to setup the requested behavior using wrapper script(s) while being friendly enough for the general user. Because of this, I think that it may be warranted to provide a command line option to mpirun_rsh that tells mpispawn to change its gid to that provided. I'm not sure if this will make it into our upcoming release. If not, we can release this as a patch to you in the meantime and make it generally available in the next minor or patch release for those who are interested. On Sun, Oct 25, 2009 at 07:53:33PM -0500, Yutaka Kubota wrote: > Dear MVAPICH2 discussion Mailing list, > > This is Yutaka Kubota from Cray Japan Inc. > > We don't receive your reply about it yet. We guess that this problem is not MPI, so you might decide low priority about this symptom. However this problem is high priority for us. So if you don't have much time for fix the symptom. Please let me know who should I ask. If we have to fix this symptom for own coding. We are afraid that we have to fix mpirun_rsh command every MVAPICH2 version up. > > Yutaka Kubota, Cray Japan inc. > > > -----Original Message----- > From: owner-tokyocsd@cray.com [mailto:owner-tokyocsd@cray.com] On > Behalf Of Yutaka Kubota > Sent: Wednesday, October 21, 2009 12:24 PM > To: mvapich-discuss@cse.ohio-state.edu > Subject: Could you upgrade "mpirun_rsh" command > > Dear MVAPICH2 discussion Mailing list, > > This is Yutaka Kubota from Cray Japan. > > I always appreciate your support. Our Satoshi Isono had asked that we had confirmed that all putting files owner were changed before group when change the Liux group using newgrp command and submit job using "mpirun_rsh" command. Bill in university of Texas had answered that insert "/usr/bin/sg `id -gn`" command line in between MPI option and execution binary name. We had confirmed that most patter submission was resolved on this way. However some submission patter using "sg" command affected to user program. > > Could you fix "mpirun_rsh" command for newgrp user put files before owner changed symptom? > > Best regards > > Yutaka Kubota, Cray Japan. > > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo From perkinjo at cse.ohio-state.edu Tue Nov 10 11:57:13 2009 From: perkinjo at cse.ohio-state.edu (Jonathan Perkins) Date: Tue Nov 10 11:57:54 2009 Subject: [mvapich-discuss] RE: Could you upgrade "mpirun_rsh" command In-Reply-To: References: <20091026154130.GJ3972@cse.ohio-state.edu> Message-ID: <20091110165713.GB2437@cse.ohio-state.edu> Yes, we've decided to add this option for our next release. We'll have a patch prepared for you in about 2 or 3 weeks so you don't have to wait until then. On Mon, Nov 09, 2009 at 08:30:36PM -0600, Yutaka Kubota wrote: > TO: Professor Panda > CC: Jonathan > > This is Yutaka Kubota from Cray Japan Inc. > > Thank you for answer and your idea. > > We have a favor to ask you. In fact, we strongly need function of "mpirun_rsh" new option of keeping Group ID to compute nodes. Because our users having some group executed "newgrp" submit job using MVAPICH2. So if they execute "newgrp" command for change other group, their put files posses original group. It is problem for our system. I guess such user is more exist in the MVAPICH2 users. Could you discuss to add this function on the MVAPICH2. > > For example: > $ mpirun_rsh -np 64 -hostfile hostfile.txt -g $GROUP_ID ./a.out > > Best regards > > Yutaka Kubota > > -----Original Message----- > From: Jonathan Perkins [mailto:perkinjo@cse.ohio-state.edu] > Sent: Tuesday, October 27, 2009 12:42 AM > To: Yutaka Kubota > Cc: mvapich-discuss@cse.ohio-state.edu > Subject: Re: [mvapich-discuss] RE: Could you upgrade "mpirun_rsh" command > > Sorry for the delay in replying. We spent some time reviewing the options for satisfying this request. At first glance this issue seems like it can be better suited to be handled by other mechanisms but I haven't found any that handles the dynamic setting of a user's effective group id on a remote machine. It also doesn't seem trivial to setup the requested behavior using wrapper script(s) while being friendly enough for the general user. Because of this, I think that it may be warranted to provide a command line option to mpirun_rsh that tells mpispawn to change its gid to that provided. > > I'm not sure if this will make it into our upcoming release. If not, we can release this as a patch to you in the meantime and make it generally available in the next minor or patch release for those who are interested. > > On Sun, Oct 25, 2009 at 07:53:33PM -0500, Yutaka Kubota wrote: > > Dear MVAPICH2 discussion Mailing list, > > > > This is Yutaka Kubota from Cray Japan Inc. > > > > We don't receive your reply about it yet. We guess that this problem is not MPI, so you might decide low priority about this symptom. However this problem is high priority for us. So if you don't have much time for fix the symptom. Please let me know who should I ask. If we have to fix this symptom for own coding. We are afraid that we have to fix mpirun_rsh command every MVAPICH2 version up. > > > > Yutaka Kubota, Cray Japan inc. > > > > > > -----Original Message----- > > From: owner-tokyocsd@cray.com [mailto:owner-tokyocsd@cray.com] On > > Behalf Of Yutaka Kubota > > Sent: Wednesday, October 21, 2009 12:24 PM > > To: mvapich-discuss@cse.ohio-state.edu > > Subject: Could you upgrade "mpirun_rsh" command > > > > Dear MVAPICH2 discussion Mailing list, > > > > This is Yutaka Kubota from Cray Japan. > > > > I always appreciate your support. Our Satoshi Isono had asked that we had confirmed that all putting files owner were changed before group when change the Liux group using newgrp command and submit job using "mpirun_rsh" command. Bill in university of Texas had answered that insert "/usr/bin/sg `id -gn`" command line in between MPI option and execution binary name. We had confirmed that most patter submission was resolved on this way. However some submission patter using "sg" command affected to user program. > > > > Could you fix "mpirun_rsh" command for newgrp user put files before owner changed symptom? > > > > Best regards > > > > Yutaka Kubota, Cray Japan. > > > > > > > > _______________________________________________ > > mvapich-discuss mailing list > > mvapich-discuss@cse.ohio-state.edu > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > -- > Jonathan Perkins > http://www.cse.ohio-state.edu/~perkinjo -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 197 bytes Desc: not available Url : http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091110/1844be74/attachment-0001.bin From kallies at zib.de Tue Nov 10 15:37:56 2009 From: kallies at zib.de (Bernd Kallies) Date: Tue Nov 10 15:39:15 2009 Subject: [mvapich-discuss] mvapich2 1.4.0 and MPI_Comm_Spawn fatal errors Message-ID: <1257885476.3491.64.camel@kallies.zib.de> Dear mvapich2 dev team, I'm currently playing with dynamic process creation with mvapich2 1.4.0. Note that there is a funny bug in src/mpid/ch3/src/ch3u_comm_spawn_multiple.c line 195: if (mpi_errno != PMI_SUCCESS) { must read if (pmi_errno != PMI_SUCCESS) { otherwise fatal spawn errors cannot be handled correctly, when using pmi. My question: will you fix this in the mpich2 sources distributed with mvapich2, or will you update to a more recent mpich2? Sincerely, BK -- Dr. Bernd Kallies Konrad-Zuse-Zentrum f?r Informationstechnik Berlin Takustr. 7 14195 Berlin Tel: +49-30-84185-270 Fax: +49-30-84185-311 e-mail: kallies@zib.de From panda at cse.ohio-state.edu Tue Nov 10 16:11:08 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Tue Nov 10 16:11:48 2009 Subject: [mvapich-discuss] mvapich2 1.4.0 and MPI_Comm_Spawn fatal errors In-Reply-To: <1257885476.3491.64.camel@kallies.zib.de> Message-ID: Dr. Kallies - Thanks for reporting this error in the mpich2 sources distributed with mvapich2. We will examine this and make this change in the MVAPICH2 branch version. For our next mvapich2 release, we are working on updating to the latest MPICH2 1.2.1 release. Thanks, DK On Tue, 10 Nov 2009, Bernd Kallies wrote: > Dear mvapich2 dev team, > > I'm currently playing with dynamic process creation with mvapich2 1.4.0. > > Note that there is a funny bug in > src/mpid/ch3/src/ch3u_comm_spawn_multiple.c line 195: > > if (mpi_errno != PMI_SUCCESS) { > > must read > > if (pmi_errno != PMI_SUCCESS) { > > otherwise fatal spawn errors cannot be handled correctly, when using > pmi. > > My question: will you fix this in the mpich2 sources distributed with > mvapich2, or will you update to a more recent mpich2? > > Sincerely, BK > > -- > Dr. Bernd Kallies > Konrad-Zuse-Zentrum für Informationstechnik Berlin > Takustr. 7 > 14195 Berlin > Tel: +49-30-84185-270 > Fax: +49-30-84185-311 > e-mail: kallies@zib.de > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From balaji at mcs.anl.gov Tue Nov 10 16:12:23 2009 From: balaji at mcs.anl.gov (Pavan Balaji) Date: Tue Nov 10 16:13:06 2009 Subject: [mvapich-discuss] mvapich2 1.4.0 and MPI_Comm_Spawn fatal errors In-Reply-To: <1257885476.3491.64.camel@kallies.zib.de> References: <1257885476.3491.64.camel@kallies.zib.de> Message-ID: <4AF9D737.4070405@mcs.anl.gov> This is already fixed in the MPICH2 source. But that probably happened after MPICH2-1.0.8p1, that the MVAPICH2 release is based on. -- Pavan On 11/10/2009 02:37 PM, Bernd Kallies wrote: > Dear mvapich2 dev team, > > I'm currently playing with dynamic process creation with mvapich2 1.4.0. > > Note that there is a funny bug in > src/mpid/ch3/src/ch3u_comm_spawn_multiple.c line 195: > > if (mpi_errno != PMI_SUCCESS) { > > must read > > if (pmi_errno != PMI_SUCCESS) { > > otherwise fatal spawn errors cannot be handled correctly, when using > pmi. > > My question: will you fix this in the mpich2 sources distributed with > mvapich2, or will you update to a more recent mpich2? > > Sincerely, BK > -- Pavan Balaji http://www.mcs.anl.gov/~balaji From kubota at cray.com Tue Nov 10 19:43:23 2009 From: kubota at cray.com (Yutaka Kubota) Date: Tue Nov 10 19:44:06 2009 Subject: [mvapich-discuss] RE: Could you upgrade "mpirun_rsh" command In-Reply-To: <20091110165713.GB2437@cse.ohio-state.edu> References: <20091026154130.GJ3972@cse.ohio-state.edu> <20091110165713.GB2437@cse.ohio-state.edu> Message-ID: Hi Jonathan, Thank you for replying and letting me know such plan. Of course I can wait it. I am looking forward to receive your patch. Best regards Yutaka Kubota -----Original Message----- From: Jonathan Perkins [mailto:perkinjo@cse.ohio-state.edu] Sent: Wednesday, November 11, 2009 1:57 AM To: Yutaka Kubota Cc: Dhabaleswar Panda; mvapich-discuss@cse.ohio-state.edu Subject: Re: [mvapich-discuss] RE: Could you upgrade "mpirun_rsh" command Yes, we've decided to add this option for our next release. We'll have a patch prepared for you in about 2 or 3 weeks so you don't have to wait until then. On Mon, Nov 09, 2009 at 08:30:36PM -0600, Yutaka Kubota wrote: > TO: Professor Panda > CC: Jonathan > > This is Yutaka Kubota from Cray Japan Inc. > > Thank you for answer and your idea. > > We have a favor to ask you. In fact, we strongly need function of "mpirun_rsh" new option of keeping Group ID to compute nodes. Because our users having some group executed "newgrp" submit job using MVAPICH2. So if they execute "newgrp" command for change other group, their put files posses original group. It is problem for our system. I guess such user is more exist in the MVAPICH2 users. Could you discuss to add this function on the MVAPICH2. > > For example: > $ mpirun_rsh -np 64 -hostfile hostfile.txt -g $GROUP_ID ./a.out > > Best regards > > Yutaka Kubota > > -----Original Message----- > From: Jonathan Perkins [mailto:perkinjo@cse.ohio-state.edu] > Sent: Tuesday, October 27, 2009 12:42 AM > To: Yutaka Kubota > Cc: mvapich-discuss@cse.ohio-state.edu > Subject: Re: [mvapich-discuss] RE: Could you upgrade "mpirun_rsh" > command > > Sorry for the delay in replying. We spent some time reviewing the options for satisfying this request. At first glance this issue seems like it can be better suited to be handled by other mechanisms but I haven't found any that handles the dynamic setting of a user's effective group id on a remote machine. It also doesn't seem trivial to setup the requested behavior using wrapper script(s) while being friendly enough for the general user. Because of this, I think that it may be warranted to provide a command line option to mpirun_rsh that tells mpispawn to change its gid to that provided. > > I'm not sure if this will make it into our upcoming release. If not, we can release this as a patch to you in the meantime and make it generally available in the next minor or patch release for those who are interested. > > On Sun, Oct 25, 2009 at 07:53:33PM -0500, Yutaka Kubota wrote: > > Dear MVAPICH2 discussion Mailing list, > > > > This is Yutaka Kubota from Cray Japan Inc. > > > > We don't receive your reply about it yet. We guess that this problem is not MPI, so you might decide low priority about this symptom. However this problem is high priority for us. So if you don't have much time for fix the symptom. Please let me know who should I ask. If we have to fix this symptom for own coding. We are afraid that we have to fix mpirun_rsh command every MVAPICH2 version up. > > > > Yutaka Kubota, Cray Japan inc. > > > > > > -----Original Message----- > > From: owner-tokyocsd@cray.com [mailto:owner-tokyocsd@cray.com] On > > Behalf Of Yutaka Kubota > > Sent: Wednesday, October 21, 2009 12:24 PM > > To: mvapich-discuss@cse.ohio-state.edu > > Subject: Could you upgrade "mpirun_rsh" command > > > > Dear MVAPICH2 discussion Mailing list, > > > > This is Yutaka Kubota from Cray Japan. > > > > I always appreciate your support. Our Satoshi Isono had asked that we had confirmed that all putting files owner were changed before group when change the Liux group using newgrp command and submit job using "mpirun_rsh" command. Bill in university of Texas had answered that insert "/usr/bin/sg `id -gn`" command line in between MPI option and execution binary name. We had confirmed that most patter submission was resolved on this way. However some submission patter using "sg" command affected to user program. > > > > Could you fix "mpirun_rsh" command for newgrp user put files before owner changed symptom? > > > > Best regards > > > > Yutaka Kubota, Cray Japan. > > > > > > > > _______________________________________________ > > mvapich-discuss mailing list > > mvapich-discuss@cse.ohio-state.edu > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > -- > Jonathan Perkins > http://www.cse.ohio-state.edu/~perkinjo -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo From Terry.Dontje at Sun.COM Wed Nov 11 11:17:49 2009 From: Terry.Dontje at Sun.COM (Terry Dontje) Date: Wed Nov 11 11:19:52 2009 Subject: [mvapich-discuss] [Fwd: strong ordering for data registered memory] Message-ID: <4AFAE3AD.7080507@sun.com> Forgive me if this is the wrong email alias to send this email, please direct me to the correct alias if this isn't the right one. Sun's IB group has asked me to forward the following email to MPI implementors to see if anyone have any comments on this email. thanks, --td > Subject: > strong ordering for data registered memory > From: > David Brean > Date: > Tue, 10 Nov 2009 15:19:26 -0500 > > To: > linux-rdma > > > Some time ago there was an email sent to this group with the subject > "weak ordering for data registered memory". I don't recall any action > resulting from this thread. So, I have a question. If a bit were > defined to specify "strong ordering", perhaps as a "access" flag (see > ibv_access_flags) and used with ibv_reg_mr(), would that be sufficient > for (1) client applications that need a HW "guarantee" of writing the > last byte of an RDMA last and (2) platform implementations that need > to deliver that feature? > > -David > > -- > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html From kubota at cray.com Thu Nov 12 21:53:38 2009 From: kubota at cray.com (Yutaka Kubota) Date: Thu Nov 12 21:54:27 2009 Subject: [mvapich-discuss] LS-DYNA with MVAPICH2 job is hung up in the one of condition Message-ID: Dear MVAPICH2 Discuss team, This is Yutaka Kubota from Cray Japan. We have executed LS-DYNA and topcrunch data with MVAPICH2 environment. However This job is always hung up on "3 cars collision" of topcrunch that is over 256 cores and 2 or 4 rails. Could you investigate about this symptom? I am waiting for sending me email from charger. If I know charger of this problem, I will send only charger to download URL of execution environment tarball file. because I would not like to broadcast download URL other member. By the way, this tarball file size is 3.1GB, please pay attention to download. Explanation of word Topcrunch http://www.topcrunch.org/ LS-DYNA http://www.lstc.com/ Explanation of Directory - LS-DYNA In LS-DYNA execution files - 3cars_0256_MV12 MVAPICH2 1.2 environment, result was SEGV - 3cars_0256_MV14 MVAPICH2 1.4 environment, result was HUNG-UP Best regards Yutaka Kubota From divad at digitus.itk.ppke.hu Sun Nov 15 14:49:28 2009 From: divad at digitus.itk.ppke.hu (=?ISO-8859-2?Q?Div=E1k_=C1d=E1m?=) Date: Sun Nov 15 14:50:33 2009 Subject: [mvapich-discuss] Compiling MVAPICH2 on FC9 Message-ID: <4B005B48.4060805@digitus.itk.ppke.hu> Dear Members, I would like to compile MVAPICH2 (1.4) under Fedora Core9 on an x86_64 machine but I run into a compiler-related error I can't figure out. (I know FC9 is rather old but unfortunately I'm not the administrator of the system) Running configure --prefix=`pwd` in the source directory yields: [...] checking for C compiler default output file name... a.out checking whether the C compiler works... configure: error: in `/home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/common/locks': configure: error: cannot run C compiled programs. If you meant to cross compile, use `--host'. See `config.log' for more details. configure: error: Configure of src/mpid/common/locks failed! I've attached config.log for more information. I've also attached config.out (which is the output of configure) because as far as I can see it provides more information than the log for some strange reason. I would like to emphasise that this is not the first "checking whether the C compiler works" test in the configure procedure (the previous ones run wihtout any error) and that I can compile other programs without any problems. The libs required by MVAPICH2 were installed from the standard Fedora repositories except for libibumad which was compiled locally as it was not available from the repo. As I've not encountered this behaviout with any other program I think it might be relevant to this list. make --version GNU Make 3.81 This program built for x86_64-redhat-linux-gnu gcc --version gcc (GCC) 4.3.0 20080428 (Red Hat 4.3.0-8) Any ideas would be greatly appreciated. Thanks, Adam -------------- next part -------------- This file contains any messages produced by compilers while running configure, to aid debugging if configure makes a mistake. It was created by configure, which was generated by GNU Autoconf 2.63. Invocation command line was $ ./configure --prefix=/home/eperfa/mvapich2/mvapich2-1.4-src ## --------- ## ## Platform. ## ## --------- ## hostname = blade14 uname -m = x86_64 uname -r = 2.6.27.25-78.2.56.fc9.x86_64 uname -s = Linux uname -v = #1 SMP Thu Jun 18 12:24:37 EDT 2009 /usr/bin/uname -p = unknown /bin/uname -X = unknown /bin/arch = x86_64 /usr/bin/arch -k = unknown /usr/convex/getsysinfo = unknown /usr/bin/hostinfo = unknown /bin/machine = unknown /usr/bin/oslevel = unknown /bin/universe = unknown PATH: /root/jdk1.6.0_13/bin PATH: /usr/lib64/qt-3.3/bin PATH: /usr/kerberos/bin PATH: /root/jdk1.6.0_13/bin PATH: /usr/lib64/ccache PATH: /usr/local/bin PATH: /bin PATH: /usr/bin PATH: /sbin PATH: /usr/lib64 PATH: /usr/lib PATH: /usr/local/lib PATH: /usr/local/lib64 PATH: /home/eperfa/bin PATH: /home/eperfa/mpich2/bin PATH: /home/eperfa/mpich2/etc PATH: /home/eperfa/mpich2/include PATH: /home/eperfa/mpich2/lib PATH: /home/eperfa/mpich2/sbin PATH: /home/eperfa/mpich2/share PATH: /home/eperfa/genesis PATH: /home/eperfa/neuron/nrn/x86_64/bin PATH: /sbin PATH: /usr/lib64 PATH: /usr/lib PATH: /usr/local/lib PATH: /usr/local/lib64 PATH: /home/eperfa/bin PATH: /home/eperfa/mpich2/bin PATH: /home/eperfa/mpich2/etc PATH: /home/eperfa/mpich2/include PATH: /home/eperfa/mpich2/lib PATH: /home/eperfa/mpich2/sbin PATH: /home/eperfa/mpich2/share PATH: /home/eperfa/genesis PATH: /home/eperfa/neuron/nrn/x86_64/bin ## ----------- ## ## Core tests. ## ## ----------- ## configure:2470: checking build system type configure:2488: result: x86_64-unknown-linux-gnu configure:2820: checking for gcc configure:2836: found /usr/lib64/ccache/gcc configure:2847: result: gcc configure:3079: checking for C compiler version configure:3087: gcc --version >&5 gcc (GCC) 4.3.0 20080428 (Red Hat 4.3.0-8) Copyright (C) 2008 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. configure:3091: $? = 0 configure:3098: gcc -v >&5 Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) configure:3102: $? = 0 configure:3109: gcc -V >&5 gcc: '-V' option must have argument configure:3113: $? = 1 configure:3136: checking for C compiler default output file name configure:3158: gcc conftest.c >&5 configure:3162: $? = 0 configure:3200: result: a.out configure:3219: checking whether the C compiler works configure:3229: ./a.out configure:3233: $? = 0 configure:3252: result: yes configure:3259: checking whether we are cross compiling configure:3261: result: no configure:3264: checking for suffix of executables configure:3271: gcc -o conftest conftest.c >&5 configure:3275: $? = 0 configure:3301: result: configure:3307: checking for suffix of object files configure:3333: gcc -c conftest.c >&5 configure:3337: $? = 0 configure:3362: result: o configure:3366: checking whether we are using the GNU C compiler configure:3395: gcc -c conftest.c >&5 configure:3402: $? = 0 configure:3419: result: yes configure:3428: checking whether gcc accepts -g configure:3458: gcc -c -g conftest.c >&5 configure:3465: $? = 0 configure:3566: result: yes configure:3583: checking for gcc option to accept ISO C89 configure:3657: gcc -c -g -O2 conftest.c >&5 configure:3664: $? = 0 configure:3687: result: none needed configure:3706: checking for pthread_spinlock_t configure:3735: gcc -c -g -O2 conftest.c >&5 configure:3742: $? = 0 configure:3770: gcc -c -g -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:13: error: expected expression before ')' token configure:3777: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | /* end confdefs.h. */ | #include | | int | main () | { | if (sizeof ((pthread_spinlock_t))) | return 0; | ; | return 0; | } configure:3800: result: yes configure:5059: checking for gcc configure:5086: result: gcc configure:5318: checking for C compiler version configure:5326: gcc --version >&5 gcc (GCC) 4.3.0 20080428 (Red Hat 4.3.0-8) Copyright (C) 2008 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. configure:5330: $? = 0 configure:5337: gcc -v >&5 Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) configure:5341: $? = 0 configure:5348: gcc -V >&5 gcc: '-V' option must have argument configure:5352: $? = 1 configure:5355: checking whether we are using the GNU C compiler configure:5408: result: yes configure:5417: checking whether gcc accepts -g configure:5555: result: yes configure:5572: checking for gcc option to accept ISO C89 configure:5676: result: none needed configure:6163: checking whether C compiler accepts option -O2 configure:6173: result: yes configure:6175: checking whether routines compiled with -O2 can be linked with ones compiled without -O2 configure:6183: result: yes configure:6406: checking for type of weak symbol support configure:6440: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:6447: $? = 0 configure:6646: result: pragma weak configure:6673: checking whether __attribute__ ((weak)) allowed configure:6700: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:6707: $? = 0 configure:6722: result: yes configure:6736: checking for multiple weak symbol support configure:6777: result: yes configure:6896: checking for g77 configure:6926: result: no configure:6896: checking for xlf configure:6926: result: no configure:6896: checking for f77 configure:6926: result: no configure:6896: checking for frt configure:6926: result: no configure:6896: checking for pgf77 configure:6926: result: no configure:6896: checking for cf77 configure:6926: result: no configure:6896: checking for fort77 configure:6926: result: no configure:6896: checking for fl32 configure:6926: result: no configure:6896: checking for af77 configure:6926: result: no configure:6896: checking for xlf90 configure:6926: result: no configure:6896: checking for f90 configure:6926: result: no configure:6896: checking for pgf90 configure:6926: result: no configure:6896: checking for pghpf configure:6926: result: no configure:6896: checking for epcf90 configure:6926: result: no configure:6896: checking for gfortran configure:6912: found /usr/bin/gfortran configure:6923: result: gfortran configure:6949: checking for Fortran 77 compiler version configure:6957: gfortran --version >&5 GNU Fortran (GCC) 4.3.0 20080428 (Red Hat 4.3.0-8) Copyright (C) 2008 Free Software Foundation, Inc. GNU Fortran comes with NO WARRANTY, to the extent permitted by law. You may redistribute copies of GNU Fortran under the terms of the GNU General Public License. For more information about these matters, see the file named COPYING configure:6961: $? = 0 configure:6968: gfortran -v >&5 Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) configure:6972: $? = 0 configure:6979: gfortran -V >&5 gfortran: '-V' option must have argument configure:6983: $? = 1 configure:6991: checking whether we are using the GNU Fortran 77 compiler configure:7010: gfortran -c -DNDEBUG conftest.F >&5 configure:7017: $? = 0 configure:7034: result: yes configure:7040: checking whether gfortran accepts -g configure:7057: gfortran -c -g conftest.f >&5 configure:7064: $? = 0 configure:7080: result: yes configure:7390: checking whether Fortran 77 compiler accepts option -O2 configure:7406: gfortran -DNDEBUG -o conftest conftest.f >conftest.bas 2>&1 configure:7409: $? = 0 configure:7411: gfortran -O2 -DNDEBUG -o conftest conftest.f >conftest.out 2>&1 configure:7414: $? = 0 configure:7417: result: yes configure:7419: checking whether routines compiled with -O2 can be linked with ones compiled without -O2 configure:7425: gfortran -c -DNDEBUG conftest2.f >conftest2.out 2>&1 configure:7428: $? = 0 configure:7430: gfortran -O2 -DNDEBUG -o conftest conftest2.o conftest.f >conftest.bas 2>&1 configure:7433: $? = 0 configure:7472: result: yes configure:7660: checking how to get verbose linking output from gfortran configure:7676: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:7683: $? = 0 configure:7705: gfortran -o conftest -DNDEBUG -O2 -v conftest.f Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) /usr/libexec/gcc/x86_64-redhat-linux/4.3.0/f951 conftest.f -ffixed-form -quiet -dumpbase conftest.f -mtune=generic -auxbase conftest -O2 -version -fintrinsic-modules-path /usr/lib/gcc/x86_64-redhat-linux/4.3.0/finclude -o /tmp/ccPSKgpi.s GNU F95 (GCC) version 4.3.0 20080428 (Red Hat 4.3.0-8) (x86_64-redhat-linux) compiled by GNU C version 4.3.0 20080428 (Red Hat 4.3.0-8), GMP version 4.2.2, MPFR version 2.3.0-p2. warning: MPFR header version 2.3.0-p2 differs from library version 2.3.1. GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072 as -V -Qy -o /tmp/cckstsqp.o /tmp/ccPSKgpi.s GNU assembler version 2.18.50.0.6 (x86_64-redhat-linux) using BFD version version 2.18.50.0.6-7.fc9 20080403 /usr/libexec/gcc/x86_64-redhat-linux/4.3.0/collect2 --eh-frame-hdr --build-id -m elf_x86_64 --hash-style=gnu -dynamic-linker /lib64/ld-linux-x86-64.so.2 -o conftest /usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64/crt1.o /usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64/crti.o /usr/lib/gcc/x86_64-redhat-linux/4.3.0/crtbegin.o -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. /tmp/cckstsqp.o -lgfortranbegin -lgfortran -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-redhat-linux/4.3.0/crtend.o /usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64/crtn.o configure:7774: result: -v configure:7776: checking for Fortran 77 libraries of gfortran configure:7799: gfortran -o conftest -DNDEBUG -O2 -v conftest.f Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) /usr/libexec/gcc/x86_64-redhat-linux/4.3.0/f951 conftest.f -ffixed-form -quiet -dumpbase conftest.f -mtune=generic -auxbase conftest -O2 -version -fintrinsic-modules-path /usr/lib/gcc/x86_64-redhat-linux/4.3.0/finclude -o /tmp/ccK4VQBd.s GNU F95 (GCC) version 4.3.0 20080428 (Red Hat 4.3.0-8) (x86_64-redhat-linux) compiled by GNU C version 4.3.0 20080428 (Red Hat 4.3.0-8), GMP version 4.2.2, MPFR version 2.3.0-p2. warning: MPFR header version 2.3.0-p2 differs from library version 2.3.1. GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072 as -V -Qy -o /tmp/ccs1c2ok.o /tmp/ccK4VQBd.s GNU assembler version 2.18.50.0.6 (x86_64-redhat-linux) using BFD version version 2.18.50.0.6-7.fc9 20080403 /usr/libexec/gcc/x86_64-redhat-linux/4.3.0/collect2 --eh-frame-hdr --build-id -m elf_x86_64 --hash-style=gnu -dynamic-linker /lib64/ld-linux-x86-64.so.2 -o conftest /usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64/crt1.o /usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64/crti.o /usr/lib/gcc/x86_64-redhat-linux/4.3.0/crtbegin.o -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. /tmp/ccs1c2ok.o -lgfortranbegin -lgfortran -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc /usr/lib/gcc/x86_64-redhat-linux/4.3.0/crtend.o /usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64/crtn.o configure:7976: result: -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm configure:7992: checking whether gfortran accepts the FLIBS found by autoconf configure:8004: gfortran -o conftest -DNDEBUG -O2 conftest.f >&5 configure:8007: $? = 0 configure:8015: result: yes configure:8053: checking whether C can link with -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm configure:8079: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm >&5 configure:8086: $? = 0 configure:8106: result: yes configure:8210: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:8217: $? = 0 configure:8235: checking for linker for Fortran main programs configure:8245: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:8248: $? = 0 configure:8267: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:8270: $? = 0 configure:8278: result: Use Fortran to link programs configure:8303: checking for Fortran 77 name mangling configure:8330: gfortran -c -DNDEBUG -O2 conftest.f 1>&5 configure:8333: $? = 0 configure:8371: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c fconftestf.o -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm >&5 /tmp/ccebFKTq.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:27: undefined reference to `my_name' collect2: ld returned 1 exit status configure:8378: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | /* end confdefs.h. */ | extern void my_name(int); | int | main () | { | my_name(0); | ; | return 0; | } configure:8419: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c fconftestf.o -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm >&5 configure:8426: $? = 0 configure:9111: result: lower underscore configure:9204: checking what libraries are needed to link Fortran programs with C routines that use stdio configure:9225: gcc -c -g -O2 -DNDEBUG -O2 conftestc.c 1>&5 configure:9228: $? = 0 configure:9237: gfortran -DNDEBUG -O2 -o conftest conftest.f conftestc.o 1>&5 configure:9240: $? = 0 configure:9265: result: none configure:9382: checking for f90 configure:9412: result: no configure:9382: checking for xlf90 configure:9412: result: no configure:9382: checking for pgf90 configure:9412: result: no configure:9382: checking for ifort configure:9412: result: no configure:9382: checking for epcf90 configure:9412: result: no configure:9382: checking for f95 configure:9398: found /usr/bin/f95 configure:9409: result: f95 configure:9435: checking that f works as the extension for Fortran 90 program configure:9441: f95 -c -DNDEBUG conftest.f >&5 configure:9444: $? = 0 configure:9446: result: yes configure:9498: checking for Fortran 90 compiler version configure:9501: f95 --version &5 GNU Fortran (GCC) 4.3.0 20080428 (Red Hat 4.3.0-8) Copyright (C) 2008 Free Software Foundation, Inc. GNU Fortran comes with NO WARRANTY, to the extent permitted by law. You may redistribute copies of GNU Fortran under the terms of the GNU General Public License. For more information about these matters, see the file named COPYING configure:9504: $? = 0 configure:9506: f95 -v &5 Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) configure:9509: $? = 0 configure:9511: f95 -V &5 f95: '-V' option must have argument configure:9514: $? = 1 configure:9522: checking whether we are using the GNU Fortran 90 compiler configure:9541: f95 -c -DNDEBUG conftest.F >&5 configure:9548: $? = 0 configure:9565: result: yes configure:9572: checking whether f95 accepts -g configure:9589: f95 -c -g conftest.f >&5 configure:9596: $? = 0 configure:9612: result: yes configure:9922: checking for extension for Fortran 90 programs configure:9930: f95 -c -DNDEBUG conftest.f90 1>&5 configure:9933: $? = 0 configure:9935: result: f90 configure:9958: checking whether the Fortran 90 compiler (f95 -DNDEBUG ) works configure:9975: f95 -o conftest -DNDEBUG conftest.f90 1>&5 configure:9978: $? = 0 configure:10002: result: yes configure:10008: checking whether the Fortran 90 compiler (f95 -DNDEBUG ) is a cross-compiler configure:10010: result: no configure:10015: checking whether Fortran 90 works with Fortran 77 configure:10050: gfortran -c -DNDEBUG -O2 conftest2.f 1>&5 configure:10053: $? = 0 configure:10055: f95 -o conftest -DNDEBUG conftest1.f90 conftest2.o 1>&5 configure:10058: $? = 0 configure:10078: result: yes configure:10120: checking whether Fortran accepts ! for comments configure:10143: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:10150: $? = 0 configure:10171: result: yes configure:10181: checking for include directory flag for Fortran configure:10201: gfortran -c -DNDEBUG -O2 -Isrc conftest.f 1>&5 configure:10204: $? = 0 configure:10216: result: -I configure:10234: checking for Fortran 77 flag for library directories configure:10252: gfortran -c -DNDEBUG -O2 conftest1.f 1>&5 configure:10255: $? = 0 configure:10263: ar cr conftest2/libconftest.a conftest1.o configure:10266: $? = 0 configure:10269: ranlib conftest2/libconftest.a configure:10272: $? = 0 configure:10276: gfortran -o conftest -DNDEBUG -O2 -Lconftest2 conftest.f -lconftest 1>&5 configure:10279: $? = 0 configure:10295: result: -L configure:10372: checking for which Fortran libraries are needed to link C with Fortran configure:10385: gfortran -c -DNDEBUG -O2 conftest.f 1>&5 configure:10388: $? = 0 configure:10429: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c mconftestf.o >&5 configure:10436: $? = 0 configure:10605: result: none configure:10703: checking whether Fortran compiler processes .F files with C preprocessor configure:10714: gfortran -c -DNDEBUG -O2 conftest.F 1>&5 configure:10717: $? = 0 configure:10739: result: yes configure:10899: checking that f works as the extension for Fortran 90 program configure:10905: f95 -c -DNDEBUG conftest.f >&5 configure:10908: $? = 0 configure:10910: result: yes configure:10962: checking for Fortran 90 compiler version configure:10965: f95 --version &5 GNU Fortran (GCC) 4.3.0 20080428 (Red Hat 4.3.0-8) Copyright (C) 2008 Free Software Foundation, Inc. GNU Fortran comes with NO WARRANTY, to the extent permitted by law. You may redistribute copies of GNU Fortran under the terms of the GNU General Public License. For more information about these matters, see the file named COPYING configure:10968: $? = 0 configure:10970: f95 -v &5 Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) configure:10973: $? = 0 configure:10975: f95 -V &5 f95: '-V' option must have argument configure:10978: $? = 1 configure:10986: checking whether we are using the GNU Fortran 90 compiler configure:11029: result: yes configure:11036: checking whether f95 accepts -g configure:11076: result: yes configure:11099: checking for extension for Fortran 90 programs configure:11107: f95 -c -DNDEBUG conftest.f90 1>&5 configure:11110: $? = 0 configure:11112: result: f90 configure:11135: checking whether the Fortran 90 compiler (f95 -DNDEBUG ) works configure:11152: f95 -o conftest -DNDEBUG conftest.f90 1>&5 configure:11155: $? = 0 configure:11178: result: yes configure:11184: checking whether the Fortran 90 compiler (f95 -DNDEBUG ) is a cross-compiler configure:11186: result: no configure:11215: checking for Fortran 90 module extension configure:11234: f95 -c -DNDEBUG conftest.f >&5 configure:11237: $? = 0 configure:11291: result: mod configure:11301: checking for Fortran 90 module include flag configure:11326: f95 -c -DNDEBUG conftest.f >&5 configure:11329: $? = 0 configure:11405: result: -I configure:11444: checking whether Fortran 90 accepts f90 suffix configure:11468: f95 -c -DNDEBUG conftest.f90 >&5 configure:11475: $? = 0 configure:11496: result: yes configure:11511: checking whether Fortran 90 compiler accepts option -O2 configure:11527: f95 -DNDEBUG -o conftest conftest.f90 >conftest.bas 2>&1 configure:11530: $? = 0 configure:11532: f95 -O2 -DNDEBUG -o conftest conftest.f90 >conftest.out 2>&1 configure:11535: $? = 0 configure:11538: result: yes configure:11540: checking whether routines compiled with -O2 can be linked with ones compiled without -O2 configure:11546: f95 -c -DNDEBUG conftest2.f90 >conftest2.out 2>&1 configure:11549: $? = 0 configure:11551: f95 -O2 -DNDEBUG -o conftest conftest2.o conftest.f90 >conftest.bas 2>&1 configure:11554: $? = 0 configure:11593: result: yes configure:11777: checking whether Fortran 90 compiler processes .F90 files with C preprocessor configure:11788: f95 -c -DNDEBUG -O2 conftest.F90 1>&5 configure:11791: $? = 0 configure:11813: result: yes configure:11843: checking what libraries are needed to link Fortran90 programs with C routines that use stdio configure:11865: gcc -c -g -O2 -DNDEBUG -O2 conftestc.c 1>&5 configure:11868: $? = 0 configure:11877: f95 -DNDEBUG -O2 -o conftest conftest.f90 conftestc.o 1>&5 configure:11880: $? = 0 configure:11905: result: none configure:11925: checking for f90 compiler vendor configure:11965: result: gnu configure:12041: checking for c++ configure:12057: found /usr/lib64/ccache/c++ configure:12068: result: c++ configure:12205: checking for C++ compiler version configure:12213: c++ --version >&5 c++ (GCC) 4.3.0 20080428 (Red Hat 4.3.0-8) Copyright (C) 2008 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. configure:12217: $? = 0 configure:12224: c++ -v >&5 Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --enable-libgcj-multifile --enable-java-maintainer-mode --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --disable-libjava-multilib --with-cpu=generic --build=x86_64-redhat-linux Thread model: posix gcc version 4.3.0 20080428 (Red Hat 4.3.0-8) (GCC) configure:12228: $? = 0 configure:12235: c++ -V >&5 c++: '-V' option must have argument configure:12239: $? = 1 configure:12242: checking whether we are using the GNU C++ compiler configure:12271: c++ -c -DNDEBUG conftest.cpp >&5 configure:12278: $? = 0 configure:12295: result: yes configure:12304: checking whether c++ accepts -g configure:12334: c++ -c -g conftest.cpp >&5 configure:12341: $? = 0 configure:12442: result: yes configure:12486: checking whether the C++ compiler c++ can build an executable configure:12526: c++ -o conftest -DNDEBUG conftest.cpp >&5 configure:12533: $? = 0 configure:12559: result: yes configure:12568: checking whether C++ compiler works with string configure:12602: c++ -c -DNDEBUG conftest.cpp >&5 configure:12609: $? = 0 configure:12630: result: yes configure:12643: checking whether the compiler supports exceptions configure:12676: c++ -c -DNDEBUG conftest.cpp >&5 configure:12683: $? = 0 configure:12705: result: yes configure:12715: checking whether the compiler recognizes bool as a built-in type configure:12752: c++ -c -DNDEBUG conftest.cpp >&5 configure:12759: $? = 0 configure:12781: result: yes configure:12791: checking whether the compiler implements namespaces configure:12824: c++ -c -DNDEBUG conftest.cpp >&5 configure:12831: $? = 0 configure:12853: result: yes configure:12874: checking whether available configure:12903: c++ -c -DNDEBUG conftest.cpp >&5 configure:12910: $? = 0 configure:12925: result: yes configure:12931: checking whether the compiler implements the namespace std configure:12968: c++ -c -DNDEBUG conftest.cpp >&5 configure:12975: $? = 0 configure:12998: result: yes configure:13012: checking whether available configure:13041: c++ -c -DNDEBUG conftest.cpp >&5 conftest.cpp:30:16: error: math: No such file or directory configure:13048: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | /* end confdefs.h. */ | | #include | | int | main () | { | using namespace std; | ; | return 0; | } configure:13063: result: no configure:13126: checking for GNU g++ version configure:13164: c++ -o conftest -DNDEBUG conftest.cpp >&5 configure:13168: $? = 0 configure:13174: ./conftest configure:13178: $? = 0 configure:13195: result: 4 . 3 configure:13243: checking whether C++ compiler accepts option -O2 configure:13253: result: yes configure:13255: checking whether routines compiled with -O2 can be linked with ones compiled without -O2 configure:13263: result: yes configure:13516: checking for perl configure:13534: found /usr/bin/perl configure:13546: result: /usr/bin/perl configure:13559: checking for ar configure:13575: found /usr/bin/ar configure:13586: result: ar configure:13608: checking for ranlib configure:13624: found /usr/bin/ranlib configure:13635: result: ranlib configure:13658: checking for etags configure:13688: result: no configure:13738: checking for killall configure:13754: found /usr/bin/killall configure:13765: result: killall configure:13812: checking for a BSD-compatible install configure:13880: result: /usr/bin/install -c configure:13900: checking whether install works configure:13908: result: yes configure:14016: checking whether install breaks libraries configure:14061: result: no configure:14083: checking whether mkdir -p works configure:14099: result: yes configure:14117: checking for make configure:14133: found /usr/bin/make configure:14144: result: make configure:14158: checking whether clock skew breaks make configure:14183: result: no configure:14193: checking whether make supports include configure:14217: result: yes configure:14226: checking whether make allows comments in actions configure:14249: result: yes configure:14263: checking for virtual path format configure:14306: result: VPATH configure:14316: checking whether make sets CFLAGS configure:14338: result: no configure:14387: checking for bash configure:14405: found /bin/bash configure:14417: result: /bin/bash configure:14440: checking whether /bin/bash supports arrays configure:14449: result: yes configure:15798: checking for doctext configure:15829: result: false configure:15839: checking for location of doctext style files configure:15856: result: unavailable configure:15868: checking for an ANSI C-conforming const configure:15943: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:15950: $? = 0 configure:15965: result: yes configure:15976: checking for volatile configure:16003: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:16010: $? = 0 configure:16025: result: yes configure:16036: checking for restrict configure:16063: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:35: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'a' conftest.c:35: error: 'a' undeclared (first use in this function) conftest.c:35: error: (Each undeclared identifier is reported only once conftest.c:35: error: for each function it appears in.) configure:16070: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | /* end confdefs.h. */ | | int | main () | { | int * restrict a; | ; | return 0; | } configure:16106: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:35: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'a' conftest.c:35: error: 'a' undeclared (first use in this function) conftest.c:35: error: (Each undeclared identifier is reported only once conftest.c:35: error: for each function it appears in.) configure:16113: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | /* end confdefs.h. */ | | int | main () | { | int * _Restrict a; | ; | return 0; | } configure:16150: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:16157: $? = 0 configure:16174: result: __restrict configure:16189: checking for inline configure:16215: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:16222: $? = 0 configure:16240: result: inline configure:16263: checking whether __attribute__ allowed configure:16290: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:16297: $? = 0 configure:16312: result: yes configure:16314: checking whether __attribute__((format)) allowed configure:16341: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:16348: $? = 0 configure:16363: result: yes configure:16388: checking for grep that handles long lines and -e configure:16448: result: /bin/grep configure:16453: checking for egrep configure:16517: result: /bin/grep -E configure:16522: checking for ANSI C header files configure:16552: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:16559: $? = 0 ./configure: line 16585: conftest.c: command not found configure:16690: result: no configure:16714: checking for sys/types.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for sys/stat.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for stdlib.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for string.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for memory.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for strings.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for inttypes.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for stdint.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16714: checking for unistd.h configure:16735: conftest.c ./configure: line 16737: conftest.c: command not found configure:16742: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | /* end confdefs.h. */ | #include configure:16766: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:16769: $? = 0 configure:16789: result: yes configure:16803: checking whether byte ordering is bigendian configure:16828: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:43: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'a' configure:16835: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | /* end confdefs.h. */ | #ifndef __APPLE_CC__ | not a universal capable compiler | #endif | typedef int dummy; | configure:16885: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:16892: $? = 0 configure:16924: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:49: error: 'not' undeclared (first use in this function) conftest.c:49: error: (Each undeclared identifier is reported only once conftest.c:49: error: for each function it appears in.) conftest.c:49: error: expected ';' before 'big' configure:16931: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | /* end confdefs.h. */ | #include | #include | | int | main () | { | #if BYTE_ORDER != BIG_ENDIAN | not big endian | #endif | | ; | return 0; | } configure:17183: result: no configure:17230: checking whether C compiler allows unaligned doubles configure:17273: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:17277: $? = 0 configure:17283: ./conftest configure:17287: $? = 0 configure:17304: result: yes configure:17323: checking whether gcc supports __func__ configure:17349: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:17356: $? = 0 configure:17371: result: yes configure:17515: result: Using gcc to determine dependencies configure:17547: checking whether long double is supported configure:17574: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:17581: $? = 0 configure:17596: result: yes configure:17607: checking whether long long is supported configure:17634: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:17641: $? = 0 configure:17656: result: yes configure:17669: checking for max C struct integer alignment configure:17797: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:17801: $? = 0 configure:17807: ./conftest configure:17811: $? = 0 configure:17830: result: eight configure:17867: checking for max C struct floating point alignment configure:17979: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:17983: $? = 0 configure:17989: ./conftest configure:17993: $? = 0 configure:18012: result: sixteen configure:18047: checking for max C struct alignment of structs with doubles configure:18128: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:18132: $? = 0 configure:18138: ./conftest configure:18142: $? = 0 configure:18161: result: eight configure:18168: checking for max C struct floating point alignment with long doubles configure:18250: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:18254: $? = 0 configure:18260: ./conftest configure:18264: $? = 0 configure:18283: result: sixteen configure:18293: WARNING: Structures containing long doubles may be aligned differently from structures with floats or longs. MVAPICH2 does not handle this case automatically and you should avoid assumed extents for structures containing float types. configure:18328: checking if alignment of structs with doubles is based on position configure:18372: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:18376: $? = 0 configure:18382: ./conftest configure:18386: $? = 0 configure:18405: result: no configure:18421: checking if alignment of structs with long long ints is based on position configure:18467: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:18471: $? = 0 configure:18477: ./conftest configure:18481: $? = 0 configure:18500: result: no configure:18516: checking if double alignment breaks rules, find actual alignment configure:18573: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:18577: $? = 0 configure:18583: ./conftest configure:18587: $? = 0 configure:18606: result: no configure:18622: checking for alignment restrictions on pointers configure:18652: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:18656: $? = 0 configure:18662: ./conftest configure:18666: $? = 0 configure:18692: result: int or better configure:18704: checking size of char configure:19009: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:19013: $? = 0 configure:19019: ./conftest configure:19023: $? = 0 configure:19049: result: 1 configure:19063: checking size of unsigned char configure:19368: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:19372: $? = 0 configure:19378: ./conftest configure:19382: $? = 0 configure:19408: result: 1 configure:19422: checking size of short configure:19727: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:19731: $? = 0 configure:19737: ./conftest configure:19741: $? = 0 configure:19767: result: 2 configure:19781: checking size of unsigned short configure:20086: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:20090: $? = 0 configure:20096: ./conftest configure:20100: $? = 0 configure:20126: result: 2 configure:20140: checking size of int configure:20445: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:20449: $? = 0 configure:20455: ./conftest configure:20459: $? = 0 configure:20485: result: 4 configure:20499: checking size of unsigned int configure:20804: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:20808: $? = 0 configure:20814: ./conftest configure:20818: $? = 0 configure:20844: result: 4 configure:20858: checking size of long configure:21163: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:21167: $? = 0 configure:21173: ./conftest configure:21177: $? = 0 configure:21203: result: 8 configure:21217: checking size of unsigned long configure:21522: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:21526: $? = 0 configure:21532: ./conftest configure:21536: $? = 0 configure:21562: result: 8 configure:21576: checking size of long long configure:21881: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:21885: $? = 0 configure:21891: ./conftest configure:21895: $? = 0 configure:21921: result: 8 configure:21935: checking size of unsigned long long configure:22240: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:22244: $? = 0 configure:22250: ./conftest configure:22254: $? = 0 configure:22280: result: 8 configure:22294: checking size of float configure:22599: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:22603: $? = 0 configure:22609: ./conftest configure:22613: $? = 0 configure:22639: result: 4 configure:22653: checking size of double configure:22958: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:22962: $? = 0 configure:22968: ./conftest configure:22972: $? = 0 configure:22998: result: 8 configure:23012: checking size of long double configure:23317: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:23321: $? = 0 configure:23327: ./conftest configure:23331: $? = 0 configure:23357: result: 16 configure:23371: checking size of wchar_t configure:23676: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:23680: $? = 0 configure:23686: ./conftest configure:23690: $? = 0 configure:23716: result: 4 configure:23892: checking size of void * configure:24197: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24201: $? = 0 configure:24207: ./conftest configure:24211: $? = 0 configure:24237: result: 8 configure:24249: checking for size of float int configure:24280: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24284: $? = 0 configure:24290: ./conftest configure:24294: $? = 0 configure:24319: result: 8 configure:24325: checking for size of double int configure:24356: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24360: $? = 0 configure:24366: ./conftest configure:24370: $? = 0 configure:24395: result: 12 configure:24401: checking for size of long int configure:24432: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24436: $? = 0 configure:24442: ./conftest configure:24446: $? = 0 configure:24471: result: 12 configure:24477: checking for size of short int configure:24508: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24512: $? = 0 configure:24518: ./conftest configure:24522: $? = 0 configure:24547: result: 6 configure:24553: checking for size of 2 int configure:24584: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24588: $? = 0 configure:24594: ./conftest configure:24598: $? = 0 configure:24623: result: 8 configure:24629: checking for size of long double int configure:24660: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24664: $? = 0 configure:24670: ./conftest configure:24674: $? = 0 configure:24699: result: 20 configure:24708: checking for sys/bitypes.h configure:24729: conftest.c ./configure: line 24731: conftest.c: command not found configure:24736: $? = 127 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | /* end confdefs.h. */ | #include configure:24760: gcc -c -g -O2 -DNDEBUG -O2 conftest.c 1>&5 configure:24763: $? = 0 configure:24783: result: yes configure:24798: checking for inttypes.h configure:24873: result: yes configure:24884: checking for int8_t configure:24915: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:24922: $? = 0 configure:24951: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:103: error: size of array 'test_array' is negative configure:24958: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | /* end confdefs.h. */ | #include | #ifdef HAVE_SYS_TYPES_H | # include | #endif | #ifdef HAVE_SYS_STAT_H | # include | #endif | #ifdef STDC_HEADERS | # include | # include | #else | # ifdef HAVE_STDLIB_H | # include | # endif | #endif | #ifdef HAVE_STRING_H | # if !defined STDC_HEADERS && defined HAVE_MEMORY_H | # include | # endif | # include | #endif | #ifdef HAVE_STRINGS_H | # include | #endif | #ifdef HAVE_INTTYPES_H | # include | #endif | #ifdef HAVE_STDINT_H | # include | #endif | #ifdef HAVE_UNISTD_H | # include | #endif | int | main () | { | static int test_array [1 - 2 * !((int8_t) ((((int8_t) 1 << (8 - 2)) - 1) * 2 + 1) | < (int8_t) ((((int8_t) 1 << (8 - 2)) - 1) * 2 + 2))]; | test_array [0] = 0 | | ; | return 0; | } configure:24987: result: yes configure:25000: checking for int16_t configure:25031: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:25038: $? = 0 configure:25067: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:103: error: size of array 'test_array' is negative configure:25074: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | /* end confdefs.h. */ | #include | #ifdef HAVE_SYS_TYPES_H | # include | #endif | #ifdef HAVE_SYS_STAT_H | # include | #endif | #ifdef STDC_HEADERS | # include | # include | #else | # ifdef HAVE_STDLIB_H | # include | # endif | #endif | #ifdef HAVE_STRING_H | # if !defined STDC_HEADERS && defined HAVE_MEMORY_H | # include | # endif | # include | #endif | #ifdef HAVE_STRINGS_H | # include | #endif | #ifdef HAVE_INTTYPES_H | # include | #endif | #ifdef HAVE_STDINT_H | # include | #endif | #ifdef HAVE_UNISTD_H | # include | #endif | int | main () | { | static int test_array [1 - 2 * !((int16_t) ((((int16_t) 1 << (16 - 2)) - 1) * 2 + 1) | < (int16_t) ((((int16_t) 1 << (16 - 2)) - 1) * 2 + 2))]; | test_array [0] = 0 | | ; | return 0; | } configure:25103: result: yes configure:25116: checking for int32_t configure:25147: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:25154: $? = 0 configure:25183: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:103: warning: integer overflow in expression conftest.c:103: error: size of array 'test_array' is negative configure:25190: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | /* end confdefs.h. */ | #include | #ifdef HAVE_SYS_TYPES_H | # include | #endif | #ifdef HAVE_SYS_STAT_H | # include | #endif | #ifdef STDC_HEADERS | # include | # include | #else | # ifdef HAVE_STDLIB_H | # include | # endif | #endif | #ifdef HAVE_STRING_H | # if !defined STDC_HEADERS && defined HAVE_MEMORY_H | # include | # endif | # include | #endif | #ifdef HAVE_STRINGS_H | # include | #endif | #ifdef HAVE_INTTYPES_H | # include | #endif | #ifdef HAVE_STDINT_H | # include | #endif | #ifdef HAVE_UNISTD_H | # include | #endif | int | main () | { | static int test_array [1 - 2 * !((int32_t) ((((int32_t) 1 << (32 - 2)) - 1) * 2 + 1) | < (int32_t) ((((int32_t) 1 << (32 - 2)) - 1) * 2 + 2))]; | test_array [0] = 0 | | ; | return 0; | } configure:25219: result: yes configure:25232: checking for int64_t configure:25263: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:25270: $? = 0 configure:25299: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:103: warning: integer overflow in expression conftest.c:103: error: size of array 'test_array' is negative configure:25306: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | /* end confdefs.h. */ | #include | #ifdef HAVE_SYS_TYPES_H | # include | #endif | #ifdef HAVE_SYS_STAT_H | # include | #endif | #ifdef STDC_HEADERS | # include | # include | #else | # ifdef HAVE_STDLIB_H | # include | # endif | #endif | #ifdef HAVE_STRING_H | # if !defined STDC_HEADERS && defined HAVE_MEMORY_H | # include | # endif | # include | #endif | #ifdef HAVE_STRINGS_H | # include | #endif | #ifdef HAVE_INTTYPES_H | # include | #endif | #ifdef HAVE_STDINT_H | # include | #endif | #ifdef HAVE_UNISTD_H | # include | #endif | int | main () | { | static int test_array [1 - 2 * !((int64_t) ((((int64_t) 1 << (64 - 2)) - 1) * 2 + 1) | < (int64_t) ((((int64_t) 1 << (64 - 2)) - 1) * 2 + 2))]; | test_array [0] = 0 | | ; | return 0; | } configure:25335: result: yes configure:25381: checking for uint8_t configure:25412: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:25419: $? = 0 configure:25440: result: yes configure:25458: checking for uint16_t configure:25489: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:25496: $? = 0 configure:25517: result: yes configure:25531: checking for uint32_t configure:25562: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:25569: $? = 0 configure:25590: result: yes configure:25608: checking for uint64_t configure:25639: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:25646: $? = 0 configure:25667: result: yes configure:26032: checking for size of Fortran type integer configure:26068: gcc -c -g -O2 -DNDEBUG -O2 conftestc.c >&5 configure:26071: $? = 0 configure:26090: gfortran -o conftest -DNDEBUG -O2 conftest.f conftestc.o >&5 configure:26093: $? = 0 configure:26129: result: 4 configure:26140: checking for size of Fortran type real configure:26176: gcc -c -g -O2 -DNDEBUG -O2 conftestc.c >&5 configure:26179: $? = 0 configure:26198: gfortran -o conftest -DNDEBUG -O2 conftest.f conftestc.o >&5 configure:26201: $? = 0 configure:26237: result: 4 configure:26248: checking for size of Fortran type double precision configure:26284: gcc -c -g -O2 -DNDEBUG -O2 conftestc.c >&5 configure:26287: $? = 0 configure:26306: gfortran -o conftest -DNDEBUG -O2 conftest.f conftestc.o >&5 configure:26309: $? = 0 configure:26345: result: 8 configure:26364: checking whether integer*1 is supported configure:26381: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:26388: $? = 0 configure:26403: result: yes configure:26405: checking whether integer*2 is supported configure:26422: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:26429: $? = 0 configure:26444: result: yes configure:26446: checking whether integer*4 is supported configure:26463: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:26470: $? = 0 configure:26485: result: yes configure:26487: checking whether integer*8 is supported configure:26504: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:26511: $? = 0 configure:26526: result: yes configure:26528: checking whether integer*16 is supported configure:26545: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:26552: $? = 0 configure:26567: result: yes configure:26569: checking whether real*4 is supported configure:26586: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:26593: $? = 0 configure:26608: result: yes configure:26610: checking whether real*8 is supported configure:26627: gfortran -c -DNDEBUG -O2 conftest.f >&5 configure:26634: $? = 0 configure:26649: result: yes configure:26651: checking whether real*16 is supported configure:26668: gfortran -c -DNDEBUG -O2 conftest.f >&5 conftest.f:2.13: real*16 a 1 Error: Old-style type declaration REAL*16 not supported at (1) configure:26675: $? = 1 configure: failed program was: | program main | real*16 a | end configure:26690: result: no configure:27070: checking for C type matching Fortran integer configure:27077: result: int configure:27126: checking for size of MPI_Status configure:27169: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:27173: $? = 0 configure:27179: ./conftest configure:27183: $? = 0 configure:27201: result: 20 configure:27230: checking for values of Fortran logicals configure:27273: gcc -c -g -O2 -DNDEBUG -O2 conftestc.c >&5 configure:27276: $? = 0 configure:27286: gfortran -o conftest -DNDEBUG -O2 conftest.f conftestc.o >&5 configure:27289: $? = 0 configure:27327: result: True is 1 and False is 0 configure:27417: checking how to run the C preprocessor configure:27457: gcc -E conftest.c configure:27464: $? = 0 configure:27495: gcc -E conftest.c conftest.c:84:28: error: ac_nonexistent.h: No such file or directory configure:27502: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | /* end confdefs.h. */ | #include configure:27535: result: gcc -E configure:27564: gcc -E conftest.c configure:27571: $? = 0 configure:27602: gcc -E conftest.c conftest.c:84:28: error: ac_nonexistent.h: No such file or directory configure:27609: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | /* end confdefs.h. */ | #include configure:27670: gcc -E conftest.c >/dev/null 2>conftest.out configure:27673: $? = 0 configure:27772: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:27775: $? = 0 configure:27817: gfortran -o conftest -DNDEBUG -O2 conftest.f >&5 configure:27820: $? = 0 configure:27865: c++ -o conftest -DNDEBUG -O2 conftest.cpp >&5 configure:27868: $? = 0 configure:2324: f95 -o conftest -DNDEBUG -O2 conftest.f90 >&5 configure:27963: checking for Fortran 90 integer kind for 8-byte integers configure:27997: f95 -o conftest -DNDEBUG -O2 conftest.f90 >&5 configure:28000: $? = 0 configure:28013: result: 8 configure:28191: checking whether real*8 is supported in Fortran 90 configure:28208: f95 -c -DNDEBUG -O2 conftest.f90 >&5 configure:28215: $? = 0 configure:28230: result: yes configure:28376: checking size of bool configure:28681: c++ -o conftest -DNDEBUG -O2 conftest.cpp >&5 configure:28685: $? = 0 configure:28691: ./conftest configure:28695: $? = 0 configure:28721: result: 1 configure:28736: checking how to run the C++ preprocessor configure:28772: c++ -E conftest.cpp configure:28779: $? = 0 configure:28810: c++ -E conftest.cpp conftest.cpp:85:28: error: ac_nonexistent.h: No such file or directory configure:28817: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | /* end confdefs.h. */ | #include configure:28850: result: c++ -E configure:28879: c++ -E conftest.cpp configure:28886: $? = 0 configure:28917: c++ -E conftest.cpp conftest.cpp:85:28: error: ac_nonexistent.h: No such file or directory configure:28924: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | /* end confdefs.h. */ | #include configure:28965: checking for complex configure:28986: c++ -E conftest.cpp configure:28993: $? = 0 configure:29040: result: yes configure:29055: checking size of Complex configure:29390: c++ -o conftest -DNDEBUG -O2 conftest.cpp >&5 configure:29394: $? = 0 configure:29400: ./conftest configure:29404: $? = 0 configure:29430: result: 8 configure:29444: checking size of DoubleComplex configure:29779: c++ -o conftest -DNDEBUG -O2 conftest.cpp >&5 configure:29783: $? = 0 configure:29789: ./conftest configure:29793: $? = 0 configure:29819: result: 16 configure:29834: checking size of LongDoubleComplex configure:30169: c++ -o conftest -DNDEBUG -O2 conftest.cpp >&5 configure:30173: $? = 0 configure:30179: ./conftest configure:30183: $? = 0 configure:30209: result: 32 configure:30290: checking if char * pointers use byte addresses configure:30318: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:30322: $? = 0 configure:30328: ./conftest configure:30332: $? = 0 configure:30349: result: yes configure:30376: checking for alignment restrictions on configure:30420: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:30424: $? = 0 configure:30430: ./conftest configure:30434: $? = 0 configure:30452: result: no configure:30473: checking for alignment restrictions on int32_t configure:30517: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:30521: $? = 0 configure:30527: ./conftest configure:30531: $? = 0 configure:30549: result: no configure:30575: checking for size of MPI_BSEND_OVERHEAD configure:30627: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:30631: $? = 0 configure:30637: ./conftest configure:30641: $? = 0 configure:30659: result: 95 configure:30679: checking for gcc __asm__ and pentium cmpxchgl instruction configure:30713: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: Assembler messages: conftest.c:103: Error: Incorrect register `%rsi' used with `l' suffix configure:30717: $? = 1 configure: program exited with status 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | /* end confdefs.h. */ | | int main(int argc, char *argv[]) | { | long int compval = 10; | volatile long int *p = &compval; | long int oldval = 10; | long int newval = 20; | char ret; | long int readval; | __asm__ __volatile__ ("lock; cmpxchgl %3, %1; sete %0" | : "=q" (ret), "=m" (*p), "=a" (readval) | : "r" (newval), "m" (*p), "a" (oldval) : "memory"); | return (compval == 20) ? 0 : -1; | } | configure:30743: result: no configure:30762: checking for gcc __asm__ and AMD x86_64 cmpxchgq instruction configure:30796: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:30800: $? = 0 configure:30806: ./conftest configure:30810: $? = 0 configure:30812: result: yes configure:30835: checking for gcc __asm__ and IA64 xchg4 instruction configure:30870: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: Assembler messages: conftest.c:99: Error: no such instruction: `xchg4 %rax=[%rdi],%rsi' conftest.c:99: Error: no such instruction: `xchg4 %rax=[%rax],%rdx' configure:30874: $? = 1 configure: program exited with status 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | /* end confdefs.h. */ | | unsigned long _InterlockedExchange(volatile void *ptr, unsigned long x) | { | unsigned long result; | __asm__ __volatile ("xchg4 %0=[%1],%2" : "=r" (result) | : "r" (ptr), "r" (x) : "memory"); | return result; | } | int main(int argc, char *argv[]) | { | long val = 1; | volatile long *p = &val; | long oldval = _InterlockedExchange(p, (unsigned long)2); | return (oldval == 1 && val == 2) ? 0 : -1; | } | configure:30899: result: no configure:31122: checking for ANSI C header files configure:31290: result: no configure:31319: checking for stdlib.h configure:31394: result: yes configure:31319: checking for stdarg.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31319: checking for sys/types.h configure:31394: result: yes configure:31319: checking for inttypes.h configure:31394: result: yes configure:31319: checking for limits.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31319: checking for stddef.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31319: checking for errno.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31319: checking for sys/socket.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31319: checking for sys/time.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31319: checking for unistd.h configure:31394: result: yes configure:31319: checking for endian.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31319: checking for assert.h configure:31340: gcc -E conftest.c configure:31347: $? = 0 configure:31394: result: yes configure:31406: checking for sys/uio.h configure:31436: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:31443: $? = 0 configure:31458: result: yes configure:31469: checking for size_t configure:31497: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:31504: $? = 0 configure:31531: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c: In function 'main': conftest.c:144: error: expected expression before ')' token configure:31538: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | /* end confdefs.h. */ | #include | #ifdef HAVE_SYS_TYPES_H | # include | #endif | #ifdef HAVE_SYS_STAT_H | # include | #endif | #ifdef STDC_HEADERS | # include | # include | #else | # ifdef HAVE_STDLIB_H | # include | # endif | #endif | #ifdef HAVE_STRING_H | # if !defined STDC_HEADERS && defined HAVE_MEMORY_H | # include | # endif | # include | #endif | #ifdef HAVE_STRINGS_H | # include | #endif | #ifdef HAVE_INTTYPES_H | # include | #endif | #ifdef HAVE_STDINT_H | # include | #endif | #ifdef HAVE_UNISTD_H | # include | #endif | int | main () | { | if (sizeof ((size_t))) | return 0; | ; | return 0; | } configure:31561: result: yes configure:31580: checking for setitimer configure:31636: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:31643: $? = 0 configure:31665: result: yes configure:31580: checking for alarm configure:31636: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:31643: $? = 0 configure:31665: result: yes configure:31683: checking for vsnprintf configure:31739: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:133: warning: conflicting types for built-in function 'vsnprintf' configure:31746: $? = 0 configure:31768: result: yes configure:31683: checking for vsprintf configure:31739: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:134: warning: conflicting types for built-in function 'vsprintf' configure:31746: $? = 0 configure:31768: result: yes configure:31783: checking whether vsnprintf needs a declaration configure:31812: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:114: error: conflicting types for 'vsnprintf' configure:31819: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | /* end confdefs.h. */ | #include | #include | int vsnprintf(double, int, double, const char *); | int | main () | { | int a=vsnprintf(1.0,27,1.0,"foo"); | ; | return 0; | } configure:31834: result: no configure:31852: checking for strerror configure:31908: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:31915: $? = 0 configure:31937: result: yes configure:31955: checking for snprintf configure:32011: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:136: warning: conflicting types for built-in function 'snprintf' configure:32018: $? = 0 configure:32040: result: yes configure:32054: checking whether snprintf needs a declaration configure:32082: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:115: error: conflicting types for 'snprintf' configure:32089: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | /* end confdefs.h. */ | #include | int snprintf(double, int, double, const char *); | int | main () | { | int a=snprintf(1.0,27,1.0,"foo"); | ; | return 0; | } configure:32104: result: no configure:32122: checking for va_copy configure:32158: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:32165: $? = 0 configure:32185: result: yes configure:32273: checking for working alloca.h configure:32300: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:32307: $? = 0 configure:32327: result: yes configure:32337: checking for alloca configure:32384: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:32391: $? = 0 configure:32411: result: yes configure:32670: checking for strdup configure:32726: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:140: warning: conflicting types for built-in function 'strdup' configure:32733: $? = 0 configure:32755: result: yes configure:32770: checking whether strdup needs a declaration configure:32798: gcc -c -g -O2 -DNDEBUG -O2 conftest.c >&5 conftest.c:119:45: error: macro "strdup" passed 4 arguments, but takes just 1 conftest.c:119: error: 'strdup' redeclared as different kind of symbol conftest.c:123:30: error: macro "strdup" passed 4 arguments, but takes just 1 configure:32805: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | /* end confdefs.h. */ | #include | int strdup(double, int, double, const char *); | int | main () | { | int a=strdup(1.0,27,1.0,"foo"); | ; | return 0; | } configure:32820: result: no configure:33127: checking for clock_gettime configure:33183: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 /tmp/ccaNql3D.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:152: undefined reference to `clock_gettime' collect2: ld returned 1 exit status configure:33190: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | /* end confdefs.h. */ | /* Define clock_gettime to an innocuous variant, in case declares clock_gettime. | For example, HP-UX 11i declares gettimeofday. */ | #define clock_gettime innocuous_clock_gettime | | /* System header to define __stub macros and hopefully few prototypes, | which can conflict with char clock_gettime (); below. | Prefer to if __STDC__ is defined, since | exists even on freestanding compilers. */ | | #ifdef __STDC__ | # include | #else | # include | #endif | | #undef clock_gettime | | /* Override any GCC internal prototype to avoid an error. | Use char because int might match the return type of a GCC | builtin and then its argument prototype would still apply. */ | #ifdef __cplusplus | extern "C" | #endif | char clock_gettime (); | /* The GNU C library defines this for functions which it implements | to always fail with ENOSYS. Some functions are actually named | something starting with __ and the normal name is an alias. */ | #if defined __stub_clock_gettime || defined __stub___clock_gettime | choke me | #endif | | int | main () | { | return clock_gettime (); | ; | return 0; | } configure:33212: result: no configure:33127: checking for clock_getres configure:33183: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 /tmp/ccg8lw7V.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:152: undefined reference to `clock_getres' collect2: ld returned 1 exit status configure:33190: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | /* end confdefs.h. */ | /* Define clock_getres to an innocuous variant, in case declares clock_getres. | For example, HP-UX 11i declares gettimeofday. */ | #define clock_getres innocuous_clock_getres | | /* System header to define __stub macros and hopefully few prototypes, | which can conflict with char clock_getres (); below. | Prefer to if __STDC__ is defined, since | exists even on freestanding compilers. */ | | #ifdef __STDC__ | # include | #else | # include | #endif | | #undef clock_getres | | /* Override any GCC internal prototype to avoid an error. | Use char because int might match the return type of a GCC | builtin and then its argument prototype would still apply. */ | #ifdef __cplusplus | extern "C" | #endif | char clock_getres (); | /* The GNU C library defines this for functions which it implements | to always fail with ENOSYS. Some functions are actually named | something starting with __ and the normal name is an alias. */ | #if defined __stub_clock_getres || defined __stub___clock_getres | choke me | #endif | | int | main () | { | return clock_getres (); | ; | return 0; | } configure:33212: result: no configure:33127: checking for gethrtime configure:33183: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 /tmp/ccUCXIM8.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:152: undefined reference to `gethrtime' collect2: ld returned 1 exit status configure:33190: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | /* end confdefs.h. */ | /* Define gethrtime to an innocuous variant, in case declares gethrtime. | For example, HP-UX 11i declares gettimeofday. */ | #define gethrtime innocuous_gethrtime | | /* System header to define __stub macros and hopefully few prototypes, | which can conflict with char gethrtime (); below. | Prefer to if __STDC__ is defined, since | exists even on freestanding compilers. */ | | #ifdef __STDC__ | # include | #else | # include | #endif | | #undef gethrtime | | /* Override any GCC internal prototype to avoid an error. | Use char because int might match the return type of a GCC | builtin and then its argument prototype would still apply. */ | #ifdef __cplusplus | extern "C" | #endif | char gethrtime (); | /* The GNU C library defines this for functions which it implements | to always fail with ENOSYS. Some functions are actually named | something starting with __ and the normal name is an alias. */ | #if defined __stub_gethrtime || defined __stub___gethrtime | choke me | #endif | | int | main () | { | return gethrtime (); | ; | return 0; | } configure:33212: result: no configure:33127: checking for gettimeofday configure:33183: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 configure:33190: $? = 0 configure:33212: result: yes configure:34560: checking for pthread.h configure:34581: gcc -E conftest.c configure:34588: $? = 0 configure:34635: result: yes configure:34651: checking for pthread_yield configure:34707: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 /tmp/ccOlJdHZ.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:157: undefined reference to `pthread_yield' collect2: ld returned 1 exit status configure:34714: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | #define HAVE_GETTIMEOFDAY 1 | #define MPIR_Pint long | #define MPIR_Upint unsigned long | #define MPIU_SIZE_T unsigned long | #define HAVE_PTHREAD_H 1 | /* end confdefs.h. */ | /* Define pthread_yield to an innocuous variant, in case declares pthread_yield. | For example, HP-UX 11i declares gettimeofday. */ | #define pthread_yield innocuous_pthread_yield | | /* System header to define __stub macros and hopefully few prototypes, | which can conflict with char pthread_yield (); below. | Prefer to if __STDC__ is defined, since | exists even on freestanding compilers. */ | | #ifdef __STDC__ | # include | #else | # include | #endif | | #undef pthread_yield | | /* Override any GCC internal prototype to avoid an error. | Use char because int might match the return type of a GCC | builtin and then its argument prototype would still apply. */ | #ifdef __cplusplus | extern "C" | #endif | char pthread_yield (); | /* The GNU C library defines this for functions which it implements | to always fail with ENOSYS. Some functions are actually named | something starting with __ and the normal name is an alias. */ | #if defined __stub_pthread_yield || defined __stub___pthread_yield | choke me | #endif | | int | main () | { | return pthread_yield (); | ; | return 0; | } configure:34736: result: no configure:34750: checking for library containing pthread_key_create configure:34791: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c >&5 /tmp/ccUwh2Sc.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:134: undefined reference to `pthread_key_create' collect2: ld returned 1 exit status configure:34798: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | #define HAVE_GETTIMEOFDAY 1 | #define MPIR_Pint long | #define MPIR_Upint unsigned long | #define MPIU_SIZE_T unsigned long | #define HAVE_PTHREAD_H 1 | /* end confdefs.h. */ | | /* Override any GCC internal prototype to avoid an error. | Use char because int might match the return type of a GCC | builtin and then its argument prototype would still apply. */ | #ifdef __cplusplus | extern "C" | #endif | char pthread_key_create (); | int | main () | { | return pthread_key_create (); | ; | return 0; | } configure:34791: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 configure:34798: $? = 0 configure:34829: result: -lpthread configure:34986: checking for pthread_cleanup_push configure:35042: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 /tmp/ccsMlLXn.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:157: undefined reference to `pthread_cleanup_push' collect2: ld returned 1 exit status configure:35049: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | #define HAVE_GETTIMEOFDAY 1 | #define MPIR_Pint long | #define MPIR_Upint unsigned long | #define MPIU_SIZE_T unsigned long | #define HAVE_PTHREAD_H 1 | /* end confdefs.h. */ | /* Define pthread_cleanup_push to an innocuous variant, in case declares pthread_cleanup_push. | For example, HP-UX 11i declares gettimeofday. */ | #define pthread_cleanup_push innocuous_pthread_cleanup_push | | /* System header to define __stub macros and hopefully few prototypes, | which can conflict with char pthread_cleanup_push (); below. | Prefer to if __STDC__ is defined, since | exists even on freestanding compilers. */ | | #ifdef __STDC__ | # include | #else | # include | #endif | | #undef pthread_cleanup_push | | /* Override any GCC internal prototype to avoid an error. | Use char because int might match the return type of a GCC | builtin and then its argument prototype would still apply. */ | #ifdef __cplusplus | extern "C" | #endif | char pthread_cleanup_push (); | /* The GNU C library defines this for functions which it implements | to always fail with ENOSYS. Some functions are actually named | something starting with __ and the normal name is an alias. */ | #if defined __stub_pthread_cleanup_push || defined __stub___pthread_cleanup_push | choke me | #endif | | int | main () | { | return pthread_cleanup_push (); | ; | return 0; | } configure:35071: result: no configure:35084: checking whether pthread_cleanup_push is available (may be a macro in pthread.h) configure:35113: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 conftest.c: In function 'main': conftest.c:132: error: expected 'while' at end of input conftest.c:132: error: expected declaration or statement at end of input conftest.c:132: error: expected declaration or statement at end of input configure:35120: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | #define HAVE_GETTIMEOFDAY 1 | #define MPIR_Pint long | #define MPIR_Upint unsigned long | #define MPIU_SIZE_T unsigned long | #define HAVE_PTHREAD_H 1 | /* end confdefs.h. */ | | #include | void f1(void *a) { return; } | int | main () | { | pthread_cleanup_push( f1, (void *)0 ); | ; | return 0; | } configure:35140: result: no configure:35466: checking for sched_yield configure:35522: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 configure:35529: $? = 0 configure:35551: result: yes configure:35466: checking for yield configure:35522: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 /tmp/ccyM8WO4.o: In function `main': /home/eperfa/mvapich2/mvapich2-1.4-src/conftest.c:158: undefined reference to `yield' collect2: ld returned 1 exit status configure:35529: $? = 1 configure: failed program was: | /* confdefs.h. */ | #define PACKAGE_NAME "" | #define PACKAGE_TARNAME "" | #define PACKAGE_VERSION "" | #define PACKAGE_STRING "" | #define PACKAGE_BUGREPORT "" | #define _OSU_MVAPICH_ 1 | #define MPIDI_CH3_CHANNEL_RNDV 1 | #define MPID_USE_SEQUENCE_NUMBERS 1 | #define USE_HEADER_CACHING 1 | #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL | #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL | #define USE_LOGGING MPID_LOGGING_NONE | #define HAVE_RUNTIME_THREADCHECK 1 | #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE | #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX | #define HAVE_ROMIO 1 | #define HAVE_PRAGMA_WEAK 1 | #define USE_WEAK_SYMBOLS 1 | #define HAVE_MULTIPLE_PRAGMA_WEAK 1 | #define HAVE_LONG_LONG 1 | #define F77_NAME_LOWER_USCORE 1 | #define STDCALL | #define HAVE_FORTRAN_BINDING 1 | #define HAVE_CXX_EXCEPTIONS /**/ | #define HAVE_NAMESPACES /**/ | #define HAVE_NAMESPACE_STD /**/ | #define HAVE_CXX_BINDING 1 | #define HAVE_NAMEPUB_SERVICE 1 | #define restrict __restrict | #define HAVE_GCC_ATTRIBUTE 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_SYS_STAT_H 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STRING_H 1 | #define HAVE_MEMORY_H 1 | #define HAVE_STRINGS_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_STDINT_H 1 | #define HAVE_UNISTD_H 1 | #define WORDS_LITTLEENDIAN 1 | #define HAVE_LONG_DOUBLE 1 | #define HAVE_LONG_LONG_INT 1 | #define HAVE_MAX_INTEGER_ALIGNMENT 8 | #define HAVE_MAX_STRUCT_ALIGNMENT 8 | #define HAVE_MAX_FP_ALIGNMENT 16 | #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 | #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 | #define SIZEOF_CHAR 1 | #define SIZEOF_UNSIGNED_CHAR 1 | #define SIZEOF_SHORT 2 | #define SIZEOF_UNSIGNED_SHORT 2 | #define SIZEOF_INT 4 | #define SIZEOF_UNSIGNED_INT 4 | #define SIZEOF_LONG 8 | #define SIZEOF_UNSIGNED_LONG 8 | #define SIZEOF_LONG_LONG 8 | #define SIZEOF_UNSIGNED_LONG_LONG 8 | #define SIZEOF_FLOAT 4 | #define SIZEOF_DOUBLE 8 | #define SIZEOF_LONG_DOUBLE 16 | #define SIZEOF_WCHAR_T 4 | #define SIZEOF_VOID_P 8 | #define HAVE_SYS_BITYPES_H 1 | #define HAVE_INT16_T 1 | #define HAVE_INT32_T 1 | #define HAVE_INT64_T 1 | #define MPIR_REAL4_CTYPE float | #define MPIR_REAL8_CTYPE double | #define MPIR_REAL16_CTYPE long double | #define MPIR_INTEGER1_CTYPE char | #define MPIR_INTEGER2_CTYPE short | #define MPIR_INTEGER4_CTYPE int | #define MPIR_INTEGER8_CTYPE long | #define SIZEOF_F77_INTEGER 4 | #define SIZEOF_F77_REAL 4 | #define SIZEOF_F77_DOUBLE_PRECISION 8 | #define HAVE_AINT_LARGER_THAN_FINT 1 | #define HAVE_FINT_IS_INT 1 | #define F77_TRUE_VALUE_SET 1 | #define F77_TRUE_VALUE 1 | #define F77_FALSE_VALUE 0 | #define SIZEOF_BOOL 1 | #define SIZEOF_COMPLEX 8 | #define SIZEOF_DOUBLECOMPLEX 16 | #define SIZEOF_LONGDOUBLECOMPLEX 32 | #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 | #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 | #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 | #define HAVE_CXX_COMPLEX 1 | #define HAVE_ANY_INT64_T_ALIGNMENT 1 | #define HAVE_ANY_INT32_T_ALIGNMENT 1 | #define HAVE_GCC_AND_X86_64_ASM 1 | #define HAVE_STDLIB_H 1 | #define HAVE_STDARG_H 1 | #define HAVE_SYS_TYPES_H 1 | #define HAVE_INTTYPES_H 1 | #define HAVE_LIMITS_H 1 | #define HAVE_STDDEF_H 1 | #define HAVE_ERRNO_H 1 | #define HAVE_SYS_SOCKET_H 1 | #define HAVE_SYS_TIME_H 1 | #define HAVE_UNISTD_H 1 | #define HAVE_ENDIAN_H 1 | #define HAVE_ASSERT_H 1 | #define HAVE_SYS_UIO_H 1 | #define HAVE_SETITIMER 1 | #define HAVE_ALARM 1 | #define HAVE_VSNPRINTF 1 | #define HAVE_VSPRINTF 1 | #define HAVE_STRERROR 1 | #define HAVE_SNPRINTF 1 | #define HAVE_VA_COPY 1 | #define HAVE_ALLOCA_H 1 | #define HAVE_ALLOCA 1 | #define HAVE_STRDUP 1 | #define HAVE_GETTIMEOFDAY 1 | #define MPIR_Pint long | #define MPIR_Upint unsigned long | #define MPIU_SIZE_T unsigned long | #define HAVE_PTHREAD_H 1 | #define HAVE_SCHED_YIELD 1 | /* end confdefs.h. */ | /* Define yield to an innocuous variant, in case declares yield. | For example, HP-UX 11i declares gettimeofday. */ | #define yield innocuous_yield | | /* System header to define __stub macros and hopefully few prototypes, | which can conflict with char yield (); below. | Prefer to if __STDC__ is defined, since | exists even on freestanding compilers. */ | | #ifdef __STDC__ | # include | #else | # include | #endif | | #undef yield | | /* Override any GCC internal prototype to avoid an error. | Use char because int might match the return type of a GCC | builtin and then its argument prototype would still apply. */ | #ifdef __cplusplus | extern "C" | #endif | char yield (); | /* The GNU C library defines this for functions which it implements | to always fail with ENOSYS. Some functions are actually named | something starting with __ and the normal name is an alias. */ | #if defined __stub_yield || defined __stub___yield | choke me | #endif | | int | main () | { | return yield (); | ; | return 0; | } configure:35551: result: no configure:35466: checking for usleep configure:35522: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 configure:35529: $? = 0 configure:35551: result: yes configure:35466: checking for sleep configure:35522: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 configure:35529: $? = 0 configure:35551: result: yes configure:35466: checking for select configure:35522: gcc -o conftest -g -O2 -DNDEBUG -O2 conftest.c -lpthread >&5 configure:35529: $? = 0 configure:35551: result: yes configure:35770: error: Configure of src/mpid/common/locks failed! ## ---------------- ## ## Cache variables. ## ## ---------------- ## ac_cv_build=x86_64-unknown-linux-gnu ac_cv_c_bigendian=no ac_cv_c_compiler_gnu=yes ac_cv_c_const=yes ac_cv_c_inline=inline ac_cv_c_int16_t=yes ac_cv_c_int32_t=yes ac_cv_c_int64_t=yes ac_cv_c_int8_t=yes ac_cv_c_uint16_t=yes ac_cv_c_uint32_t=yes ac_cv_c_uint64_t=yes ac_cv_c_uint8_t=yes ac_cv_cxx_bool=yes ac_cv_cxx_compiler_gnu=yes ac_cv_cxx_exceptions=yes ac_cv_cxx_namespace_std=yes ac_cv_cxx_namespaces=yes ac_cv_env_CCC_set= ac_cv_env_CCC_value= ac_cv_env_CC_set= ac_cv_env_CC_value= ac_cv_env_CFLAGS_set= ac_cv_env_CFLAGS_value= ac_cv_env_CPPFLAGS_set= ac_cv_env_CPPFLAGS_value= ac_cv_env_CPP_set= ac_cv_env_CPP_value= ac_cv_env_CXXCPP_set= ac_cv_env_CXXCPP_value= ac_cv_env_CXXFLAGS_set= ac_cv_env_CXXFLAGS_value= ac_cv_env_CXX_set= ac_cv_env_CXX_value= ac_cv_env_F77_set= ac_cv_env_F77_value= ac_cv_env_F90FLAGS_set= ac_cv_env_F90FLAGS_value= ac_cv_env_F90_set= ac_cv_env_F90_value= ac_cv_env_FFLAGS_set= ac_cv_env_FFLAGS_value= ac_cv_env_LDFLAGS_set= ac_cv_env_LDFLAGS_value= ac_cv_env_LIBS_set= ac_cv_env_LIBS_value= ac_cv_env_MPICH2LIB_CFLAGS_set= ac_cv_env_MPICH2LIB_CFLAGS_value= ac_cv_env_MPICH2LIB_CXXFLAGS_set= ac_cv_env_MPICH2LIB_CXXFLAGS_value= ac_cv_env_MPICH2LIB_F90FLAGS_set= ac_cv_env_MPICH2LIB_F90FLAGS_value= ac_cv_env_MPICH2LIB_FFLAGS_set= ac_cv_env_MPICH2LIB_FFLAGS_value= ac_cv_env_build_alias_set= ac_cv_env_build_alias_value= ac_cv_env_host_alias_set= ac_cv_env_host_alias_value= ac_cv_env_target_alias_set= ac_cv_env_target_alias_value= ac_cv_f77_compiler_gnu=yes ac_cv_f77_libs=' -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm' ac_cv_f90_compiler_gnu=yes ac_cv_func_alarm=yes ac_cv_func_alloca_works=yes ac_cv_func_clock_getres=no ac_cv_func_clock_gettime=no ac_cv_func_gethrtime=no ac_cv_func_gettimeofday=yes ac_cv_func_pthread_cleanup_push=no ac_cv_func_pthread_yield=no ac_cv_func_sched_yield=yes ac_cv_func_select=yes ac_cv_func_setitimer=yes ac_cv_func_sleep=yes ac_cv_func_snprintf=yes ac_cv_func_strdup=yes ac_cv_func_strerror=yes ac_cv_func_usleep=yes ac_cv_func_vsnprintf=yes ac_cv_func_vsprintf=yes ac_cv_func_yield=no ac_cv_header_assert_h=yes ac_cv_header_complex=yes ac_cv_header_endian_h=yes ac_cv_header_errno_h=yes ac_cv_header_inttypes_h=yes ac_cv_header_limits_h=yes ac_cv_header_memory_h=yes ac_cv_header_pthread_h=yes ac_cv_header_stdarg_h=yes ac_cv_header_stdc=no ac_cv_header_stddef_h=yes ac_cv_header_stdint_h=yes ac_cv_header_stdlib_h=yes ac_cv_header_string_h=yes ac_cv_header_strings_h=yes ac_cv_header_sys_bitypes_h=yes ac_cv_header_sys_socket_h=yes ac_cv_header_sys_stat_h=yes ac_cv_header_sys_time_h=yes ac_cv_header_sys_types_h=yes ac_cv_header_sys_uio_h=yes ac_cv_header_unistd_h=yes ac_cv_objext=o ac_cv_path_BASH_SHELL=/bin/bash ac_cv_path_DOCTEXT=false ac_cv_path_EGREP='/bin/grep -E' ac_cv_path_GREP=/bin/grep ac_cv_path_PERL=/usr/bin/perl ac_cv_path_install='/usr/bin/install -c' ac_cv_prog_AR=ar ac_cv_prog_CPP='gcc -E' ac_cv_prog_CXX=c++ ac_cv_prog_CXXCPP='c++ -E' ac_cv_prog_KILLALL=killall ac_cv_prog_MAKE=make ac_cv_prog_RANLIB=ranlib ac_cv_prog_ac_ct_CC=gcc ac_cv_prog_ac_ct_F77=gfortran ac_cv_prog_ac_ct_F90=f95 ac_cv_prog_cc_c89= ac_cv_prog_cc_cross= ac_cv_prog_cc_g=yes ac_cv_prog_cc_works=yes ac_cv_prog_cxx_cross= ac_cv_prog_cxx_g=yes ac_cv_prog_cxx_works=yes ac_cv_prog_f77_cross= ac_cv_prog_f77_g=yes ac_cv_prog_f77_v=-v ac_cv_prog_f77_works=yes ac_cv_prog_f90_cross=no ac_cv_prog_f90_g=yes ac_cv_prog_f90_works=yes ac_cv_prog_install_breaks_libs=no ac_cv_search_pthread_key_create=-lpthread ac_cv_sizeof_Complex=8 ac_cv_sizeof_DoubleComplex=16 ac_cv_sizeof_LongDoubleComplex=32 ac_cv_sizeof_bool=1 ac_cv_sizeof_char=1 ac_cv_sizeof_double=8 ac_cv_sizeof_float=4 ac_cv_sizeof_int=4 ac_cv_sizeof_long=8 ac_cv_sizeof_long_double=16 ac_cv_sizeof_long_long=8 ac_cv_sizeof_short=2 ac_cv_sizeof_unsigned_char=1 ac_cv_sizeof_unsigned_int=4 ac_cv_sizeof_unsigned_long=8 ac_cv_sizeof_unsigned_long_long=8 ac_cv_sizeof_unsigned_short=2 ac_cv_sizeof_void_p=8 ac_cv_sizeof_wchar_t=4 ac_cv_type_pthread_spinlock_t=yes ac_cv_type_size_t=yes ac_cv_working_alloca_h=yes pac_cv_attr_weak=yes pac_cv_c_char_p_is_byte=yes pac_cv_c_double_alignment_exception=no pac_cv_c_double_pos_align=no pac_cv_c_fp_align_nr=16 pac_cv_c_llint_pos_align=no pac_cv_c_max_double_fp_align=eight pac_cv_c_max_fp_align=sixteen pac_cv_c_max_integer_align=eight pac_cv_c_max_longdouble_fp_align=sixteen pac_cv_c_restrict=__restrict pac_cv_c_struct_align_nr=8 pac_cv_c_volatile=yes pac_cv_cc_has___func__=yes pac_cv_cxx_builds_exe=yes pac_cv_cxx_compiles_string=yes pac_cv_cxx_has_iostream=yes pac_cv_cxx_has_math=no pac_cv_f77_flibs_valid=yes pac_cv_f77_sizeof_double_precision=8 pac_cv_f77_sizeof_integer=4 pac_cv_f77_sizeof_real=4 pac_cv_f90_accepts_F90=yes pac_cv_f90_and_f77=yes pac_cv_f90_ext=f90 pac_cv_f90_ext_f90=yes pac_cv_f90_module_case=lower pac_cv_f90_module_ext=mod pac_cv_f90_module_incflag=-I pac_cv_f90_vendor=gnu pac_cv_fort90_real8=yes pac_cv_fort_accepts_F=yes pac_cv_fort_integer16=yes pac_cv_fort_integer1=yes pac_cv_fort_integer2=yes pac_cv_fort_integer4=yes pac_cv_fort_integer8=yes pac_cv_fort_real16=no pac_cv_fort_real4=yes pac_cv_fort_real8=yes pac_cv_func_decl_snprintf=no pac_cv_func_decl_strdup=no pac_cv_func_decl_vsnprintf=no pac_cv_func_pthread_cleanup_push=no pac_cv_func_va_copy=yes pac_cv_gnu_attr_format=yes pac_cv_gnu_attr_pure=yes pac_cv_have_long_double=yes pac_cv_have_long_long=yes pac_cv_int32_t_alignment=no pac_cv_int64_t_alignment=no pac_cv_mkdir_p=yes pac_cv_mpi_bsend_overhead=95 pac_cv_my_conf_dir=/home/eperfa/mvapich2/mvapich2-1.4-src pac_cv_pointers_have_int_alignment=yes pac_cv_prog_TESTCPP='gcc -E' pac_cv_prog_c_multiple_weak_symbols=yes pac_cv_prog_c_unaligned_doubles=yes pac_cv_prog_c_weak_symbols='pragma weak' pac_cv_prog_f77_and_c_stdio_libs=none pac_cv_prog_f77_exclaim_comments=yes pac_cv_prog_f77_has_incdir=-I pac_cv_prog_f77_library_dir_flag=-L pac_cv_prog_f77_name_mangle='lower underscore' pac_cv_prog_f77_true_false_value='1 0' pac_cv_prog_f90_and_c_stdio_libs=none pac_cv_prog_f90_cross=no pac_cv_prog_f90_int_kind_16=8 pac_cv_prog_f90_works=yes pac_cv_prog_make_allows_comments=yes pac_cv_prog_make_found_clock_skew=no pac_cv_prog_make_include=yes pac_cv_prog_make_set_cflags=no pac_cv_prog_make_vpath=VPATH pac_cv_sizeof_2_int=8 pac_cv_sizeof_double_int=12 pac_cv_sizeof_float_int=8 pac_cv_sizeof_long_double_int=20 pac_cv_sizeof_long_int=12 pac_cv_sizeof_mpi_status=20 pac_cv_sizeof_short_int=6 pac_cv_test_stdcall= ## ----------------- ## ## Output variables. ## ## ----------------- ## ABIVERSION='1:1' ADDRESS_KIND='8' ALLOCA='' AR='ar' BASH_SHELL='/bin/bash' BSEND_OVERHEAD='95' BUILD_BASH_SCRIPTS='yes' BUILD_DLLS='no' BUILD_TVDLL='no' CC='gcc' CC_SHL='true' CC_SHL_DBG='' CFLAGS='-g -O2 -DNDEBUG -O2' CONFIGURE_ARGS_CLEAN='--prefix=/home/eperfa/mvapich2/mvapich2-1.4-src' CONFIGURE_ARGUMENTS=' '\''--prefix=/home/eperfa/mvapich2/mvapich2-1.4-src'\''' CPP='gcc -E' CPPFLAGS='' CREATESHLIB='false' CXX='c++' CXXCPP='c++ -E' CXXFLAGS=' -DNDEBUG -O2' CXX_DEFS=' -DHAVE_CXX_IOSTREAM -DHAVE_NAMESPACE_STD' CXX_LINKPATH_SHL='' CXX_SHL='false' C_LINKPATH_SHL='' C_LINK_SHL='true' C_LINK_SHL_DBG='' DBG_SHLIB_TYPE='' DEFS='' DEVICE='ch3:mrail' DEVICE_ARGS='' DEVICE_NAME='ch3' DLLIMPORT='' DOCTEXT='false' DOCTEXTSTYLE='' ECHO_C='' ECHO_N='-n' ECHO_T='' EGREP='/bin/grep -E' ENABLE_SHLIB='none' ETAGS='true' ETAGSADD='' EXEEXT='' EXTERNAL_SRC_DIRS='' EXTRA_STATUS_DECL='' F77='gfortran' F77CPP='' F77_COMPLEX16='1275072554' F77_COMPLEX32='1275076652' F77_COMPLEX8='1275070504' F77_INCDIR='-I' F77_INTEGER16='MPI_DATATYPE_NULL' F77_INTEGER1='1275068717' F77_INTEGER2='1275068975' F77_INTEGER4='1275069488' F77_INTEGER8='1275070513' F77_IN_C_LIBS='' F77_LIBDIR_LEADER='-L' F77_NAME_MANGLE='F77_NAME_LOWER_USCORE' F77_OTHER_LIBS='' F77_REAL16='1275072555' F77_REAL4='1275069479' F77_REAL8='1275070505' F90='f95' F90CPP='' F90EXT='f90' F90FLAGS=' -DNDEBUG -O2' F90INC='-I' F90INCFLAG='-I' F90MODEXT='mod' F90MODINCFLAG='-I' F90MODINCSPEC='' F90_LINKPATH_SHL='' F90_OTHER_LIBS='' F90_SHL='' F90_WORK_FILES_ARG='' FC='gfortran' FC_LINKPATH_SHL='' FC_SHL='false' FFLAGS=' -DNDEBUG -O2' FINCLUDES='-I/home/eperfa/mvapich2/mvapich2-1.4-src/src' FLIBS=' -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm' FORTRAN_BINDING='1' FORTRAN_MPI_OFFSET='' FWRAPNAME='fmpich' GCC='yes' GNUCXX_MINORVERSION='3' GNUCXX_VERSION='4' GREP='/bin/grep' HAVE_CXX_EXCEPTIONS='1' HAVE_ROMIO='#include "mpio.h"' INCLUDE_MPICXX_H='#include "mpicxx.h"' INCLUDE_MPIDDEFS_H='/* ... no device specific definitions ... */' INSTALL_DATA='${INSTALL} -m 644' INSTALL_PROGRAM='${INSTALL}' INSTALL_SCRIPT='${INSTALL}' KILLALL='killall' LDFLAGS=' ' LIBOBJS='' LIBS='-lpthread -lrdmacm -libverbs -libumad ' LIBTOOL='' LTLIBOBJS='' MAKE='make' MAKE_DEPEND_C='gcc -MM' MANY_PM='no' MKDIR_P='mkdir -p' MPE_THREAD_LIB_NAME='mpich' MPIBASEMODNAME='mpi_base' MPICC='' MPICH2LIB_CFLAGS='' MPICH2LIB_CXXFLAGS='' MPICH2LIB_F90FLAGS='' MPICH2LIB_FFLAGS='' MPICH_TIMER_KIND='USE_GETTIMEOFDAY' MPICONSTMODNAME='mpi_constants' MPICXX='' MPICXXLIBNAME='mpichcxx' MPID_TIMER_TYPE='struct timeval' MPIF77='' MPIF90='' MPIFLIBNAME='mpich' MPIFPMPI=',PMPI_WTIME,PMPI_WTICK' MPILIBNAME='mpich' MPIMODNAME='mpi' MPIR_CXX_BOOL='0x4c000133' MPIR_CXX_COMPLEX='0x4c000834' MPIR_CXX_DOUBLE_COMPLEX='0x4c001035' MPIR_CXX_LONG_DOUBLE_COMPLEX='0x4c002036' MPISIZEOFMODNAME='mpi_sizeofs' MPIU_DLL_SPEC_DEF='' MPI_2COMPLEX='1275072548' MPI_2DOUBLE_COMPLEX='1275076645' MPI_2DOUBLE_PRECISION='1275072547' MPI_2INT='0x4c000816' MPI_2INTEGER='1275070496' MPI_2REAL='1275070497' MPI_AINT='long' MPI_AINT_FMT_DEC_SPEC='%ld' MPI_AINT_FMT_HEX_SPEC='%lx' MPI_BYTE='0x4c00010d' MPI_CHAR='0x4c000101' MPI_CHARACTER='1275068698' MPI_COMPLEX16='0x4c00102a' MPI_COMPLEX32='0x4c00202c' MPI_COMPLEX8='0x4c000828' MPI_COMPLEX='1275070494' MPI_DOUBLE='0x4c00080b' MPI_DOUBLE_COMPLEX='1275072546' MPI_DOUBLE_INT='0x8c000001' MPI_DOUBLE_PRECISION='1275070495' MPI_F77_BYTE='1275068685' MPI_F77_LB='1275068432' MPI_F77_PACKED='1275068687' MPI_F77_UB='1275068433' MPI_FINT='int' MPI_FLOAT='0x4c00040a' MPI_FLOAT_INT='0x8c000000' MPI_INT='0x4c000405' MPI_INTEGER16='MPI_DATATYPE_NULL' MPI_INTEGER1='0x4c00012d' MPI_INTEGER2='0x4c00022f' MPI_INTEGER4='0x4c000430' MPI_INTEGER8='0x4c000831' MPI_INTEGER='1275069467' MPI_LB='0x4c000010' MPI_LOGICAL='1275069469' MPI_LONG='0x4c000807' MPI_LONG_DOUBLE='0x4c00100c' MPI_LONG_DOUBLE_INT='0x8c000004' MPI_LONG_INT='0x8c000002' MPI_LONG_LONG='0x4c000809' MPI_MAX_PROCESSOR_NAME='' MPI_OFFSET='' MPI_OFFSET_TYPEDEF='' MPI_PACKED='0x4c00010f' MPI_REAL16='0x4c00102b' MPI_REAL4='0x4c000427' MPI_REAL8='0x4c000829' MPI_REAL='1275069468' MPI_SHORT='0x4c000203' MPI_SHORT_INT='0x8c000003' MPI_SIGNED_CHAR='0x4c000118' MPI_STATUS_SIZE='5' MPI_UB='0x4c000011' MPI_UNSIGNED_CHAR='0x4c000102' MPI_UNSIGNED_INT='0x4c000406' MPI_UNSIGNED_LONG='0x4c000808' MPI_UNSIGNED_LONG_LONG='0x4c000819' MPI_UNSIGNED_SHORT='0x4c000204' MPI_WCHAR='0x4c00040e' NEEDSPLIB='no' NO_WEAK_SYM='' NO_WEAK_SYM_TARGET='build_proflib' NUMVERSION='10400300' OBJEXT='o' OFFSET_KIND='8' PACKAGE_BUGREPORT='' PACKAGE_NAME='' PACKAGE_STRING='' PACKAGE_TARNAME='' PACKAGE_VERSION='' PATH_SEPARATOR=':' PERL='/usr/bin/perl' PMPIFLIBNAME='pmpich' PMPILIBNAME='pmpich' PROFILE_DEF_MPI='' RANLIB='ranlib' RANLIB_AFTER_INSTALL='no' RELEASE_DATE='2009-10-29' REQD='' REQI1='' REQI2='' REQI8='' SET_CFLAGS='' SET_MAKE='MAKE=make' SHELL='/bin/sh' SHLIB_EXT='so' SHLIB_FROM_LO='no' SHLIB_INSTALL='$(INSTALL_PROGRAM)' SIZEOF_F90_CHARACTER='1' SIZEOF_F90_DOUBLE_PRECISION='8' SIZEOF_F90_INTEGER='4' SIZEOF_F90_REAL='4' SIZEOF_MPI_STATUS='20' TESTCPP='gcc -E' THR_CFLAGS=' -D_REENTRANT -D_THREAD_SAFE' THR_CPPFLAGS='' THR_DEFS='' THR_LDFLAGS='' THR_LIBS=' -lpthread' VERSION='1.4.0' VPATH='VPATH=.:${srcdir}' WRAPPER_CFLAGS='-g -O2' WRAPPER_CXXFLAGS='' WRAPPER_F90FLAGS='' WRAPPER_FFLAGS='' WRAPPER_LDFLAGS='' XARGS_NODATA_OPT='-r' ac_ct_CC='gcc' ac_ct_CXX='' ac_ct_F77='gfortran' ac_ct_F90='f95' bindings=' f77 f90 cxx' bindings_dirs=' src/binding/f77 src/binding/f90 src/binding/cxx' bindir='${exec_prefix}/bin' build='x86_64-unknown-linux-gnu' build_alias='' build_cpu='x86_64' build_os='linux-gnu' build_vendor='unknown' datadir='${datarootdir}' datarootdir='${prefix}/share' debugger_dir='' device_name='ch3' docdir='${datarootdir}/doc/${PACKAGE}' dvidir='${docdir}' exec_prefix='NONE' host_alias='' htmldir='${docdir}' includedir='${prefix}/include' infodir='${datarootdir}/info' libdir='${exec_prefix}/lib' libexecdir='${exec_prefix}/libexec' localedir='${datarootdir}/locale' localstatedir='${prefix}/var' logging_dir='' logging_name='none' logging_subdirs='' mandir='${datarootdir}/man' master_top_builddir='/home/eperfa/mvapich2/mvapich2-1.4-src' master_top_srcdir='/home/eperfa/mvapich2/mvapich2-1.4-src' modincdir='${prefix}/include' mpe_dir='mpe2' nameserv_name='mpd' oldincludedir='/usr/include' other_install_dirs=' src/pm/mpd src/mpe2' other_pm_names='' pac_prog='' pdfdir='${docdir}' pm_name='mpd' pmi_name='simple' prefix='/home/eperfa/mvapich2/mvapich2-1.4-src' program_transform_name='s,x,x,' psdir='${docdir}' romio_dir='romio' sbindir='${exec_prefix}/sbin' sharedstatedir='${prefix}/com' subdirs='' subsystems=' src/mpid/common/locks src/mpi/romio src/pmi/simple src/pm/mpd src/mpe2' sysconfdir='${prefix}/etc' target_alias='' ## ------------------- ## ## File substitutions. ## ## ------------------- ## MPE_THREAD_FUNCS='./src/util/thread/posix_funcs.i' MPE_THREAD_TYPEDEFS='./src/util/thread/posix_types.i' ## ----------- ## ## confdefs.h. ## ## ----------- ## #define PACKAGE_NAME "" #define PACKAGE_TARNAME "" #define PACKAGE_VERSION "" #define PACKAGE_STRING "" #define PACKAGE_BUGREPORT "" #define _OSU_MVAPICH_ 1 #define MPIDI_CH3_CHANNEL_RNDV 1 #define MPID_USE_SEQUENCE_NUMBERS 1 #define USE_HEADER_CACHING 1 #define HAVE_ERROR_CHECKING MPID_ERROR_LEVEL_ALL #define MPICH_ERROR_MSG_LEVEL MPICH_ERROR_MSG_ALL #define USE_LOGGING MPID_LOGGING_NONE #define HAVE_RUNTIME_THREADCHECK 1 #define MPICH_THREAD_LEVEL MPI_THREAD_MULTIPLE #define USE_THREAD_IMPL MPICH_THREAD_IMPL_GLOBAL_MUTEX #define HAVE_ROMIO 1 #define HAVE_PRAGMA_WEAK 1 #define USE_WEAK_SYMBOLS 1 #define HAVE_MULTIPLE_PRAGMA_WEAK 1 #define HAVE_LONG_LONG 1 #define F77_NAME_LOWER_USCORE 1 #define STDCALL #define HAVE_FORTRAN_BINDING 1 #define HAVE_CXX_EXCEPTIONS /**/ #define HAVE_NAMESPACES /**/ #define HAVE_NAMESPACE_STD /**/ #define HAVE_CXX_BINDING 1 #define HAVE_NAMEPUB_SERVICE 1 #define restrict __restrict #define HAVE_GCC_ATTRIBUTE 1 #define HAVE_SYS_TYPES_H 1 #define HAVE_SYS_STAT_H 1 #define HAVE_STDLIB_H 1 #define HAVE_STRING_H 1 #define HAVE_MEMORY_H 1 #define HAVE_STRINGS_H 1 #define HAVE_INTTYPES_H 1 #define HAVE_STDINT_H 1 #define HAVE_UNISTD_H 1 #define WORDS_LITTLEENDIAN 1 #define HAVE_LONG_DOUBLE 1 #define HAVE_LONG_LONG_INT 1 #define HAVE_MAX_INTEGER_ALIGNMENT 8 #define HAVE_MAX_STRUCT_ALIGNMENT 8 #define HAVE_MAX_FP_ALIGNMENT 16 #define HAVE_MAX_DOUBLE_FP_ALIGNMENT 8 #define HAVE_MAX_LONG_DOUBLE_FP_ALIGNMENT 16 #define SIZEOF_CHAR 1 #define SIZEOF_UNSIGNED_CHAR 1 #define SIZEOF_SHORT 2 #define SIZEOF_UNSIGNED_SHORT 2 #define SIZEOF_INT 4 #define SIZEOF_UNSIGNED_INT 4 #define SIZEOF_LONG 8 #define SIZEOF_UNSIGNED_LONG 8 #define SIZEOF_LONG_LONG 8 #define SIZEOF_UNSIGNED_LONG_LONG 8 #define SIZEOF_FLOAT 4 #define SIZEOF_DOUBLE 8 #define SIZEOF_LONG_DOUBLE 16 #define SIZEOF_WCHAR_T 4 #define SIZEOF_VOID_P 8 #define HAVE_SYS_BITYPES_H 1 #define HAVE_INT16_T 1 #define HAVE_INT32_T 1 #define HAVE_INT64_T 1 #define MPIR_REAL4_CTYPE float #define MPIR_REAL8_CTYPE double #define MPIR_REAL16_CTYPE long double #define MPIR_INTEGER1_CTYPE char #define MPIR_INTEGER2_CTYPE short #define MPIR_INTEGER4_CTYPE int #define MPIR_INTEGER8_CTYPE long #define SIZEOF_F77_INTEGER 4 #define SIZEOF_F77_REAL 4 #define SIZEOF_F77_DOUBLE_PRECISION 8 #define HAVE_AINT_LARGER_THAN_FINT 1 #define HAVE_FINT_IS_INT 1 #define F77_TRUE_VALUE_SET 1 #define F77_TRUE_VALUE 1 #define F77_FALSE_VALUE 0 #define SIZEOF_BOOL 1 #define SIZEOF_COMPLEX 8 #define SIZEOF_DOUBLECOMPLEX 16 #define SIZEOF_LONGDOUBLECOMPLEX 32 #define MPIR_CXX_COMPLEX_VALUE 0x4c000834 #define MPIR_CXX_DOUBLE_COMPLEX_VALUE 0x4c001035 #define MPIR_CXX_LONG_DOUBLE_COMPLEX_VALUE 0x4c002036 #define HAVE_CXX_COMPLEX 1 #define HAVE_ANY_INT64_T_ALIGNMENT 1 #define HAVE_ANY_INT32_T_ALIGNMENT 1 #define HAVE_GCC_AND_X86_64_ASM 1 #define HAVE_STDLIB_H 1 #define HAVE_STDARG_H 1 #define HAVE_SYS_TYPES_H 1 #define HAVE_INTTYPES_H 1 #define HAVE_LIMITS_H 1 #define HAVE_STDDEF_H 1 #define HAVE_ERRNO_H 1 #define HAVE_SYS_SOCKET_H 1 #define HAVE_SYS_TIME_H 1 #define HAVE_UNISTD_H 1 #define HAVE_ENDIAN_H 1 #define HAVE_ASSERT_H 1 #define HAVE_SYS_UIO_H 1 #define HAVE_SETITIMER 1 #define HAVE_ALARM 1 #define HAVE_VSNPRINTF 1 #define HAVE_VSPRINTF 1 #define HAVE_STRERROR 1 #define HAVE_SNPRINTF 1 #define HAVE_VA_COPY 1 #define HAVE_ALLOCA_H 1 #define HAVE_ALLOCA 1 #define HAVE_STRDUP 1 #define HAVE_GETTIMEOFDAY 1 #define MPIR_Pint long #define MPIR_Upint unsigned long #define MPIU_SIZE_T unsigned long #define HAVE_PTHREAD_H 1 #define HAVE_SCHED_YIELD 1 #define HAVE_USLEEP 1 #define HAVE_SLEEP 1 #define HAVE_SELECT 1 #define USE_THREAD_PKG MPICH_THREAD_PKG_POSIX configure: exit 1 -------------- next part -------------- Configuring MVAPICH2 1.4.0 with '--prefix=/home/eperfa/mvapich2/mvapich2-1.4-src' checking build system type... x86_64-unknown-linux-gnu checking for gcc... gcc checking for C compiler default output file name... a.out checking whether the C compiler works... yes checking whether we are cross compiling... no checking for suffix of executables... checking for suffix of object files... o checking whether we are using the GNU C compiler... yes checking whether gcc accepts -g... yes checking for gcc option to accept ISO C89... none needed checking for pthread_spinlock_t... yes Executing mpich2prereq in /home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/ch3 with Executing mpich2prereq in /home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/ch3/channels/mrail sourcing /home/eperfa/mvapich2/mvapich2-1.4-src/src/pm/mpd/mpich2prereq sourcing /home/eperfa/mvapich2/mvapich2-1.4-src/src/pm/mpd/setup_pm checking for gcc... (cached) gcc checking whether we are using the GNU C compiler... (cached) yes checking whether gcc accepts -g... (cached) yes checking for gcc option to accept ISO C89... (cached) none needed checking whether C compiler accepts option -O2... yes checking whether routines compiled with -O2 can be linked with ones compiled without -O2... yes checking for type of weak symbol support... pragma weak checking whether __attribute__ ((weak)) allowed... yes checking for multiple weak symbol support... yes checking for g77... no checking for xlf... no checking for f77... no checking for frt... no checking for pgf77... no checking for cf77... no checking for fort77... no checking for fl32... no checking for af77... no checking for xlf90... no checking for f90... no checking for pgf90... no checking for pghpf... no checking for epcf90... no checking for gfortran... gfortran checking whether we are using the GNU Fortran 77 compiler... yes checking whether gfortran accepts -g... yes checking whether Fortran 77 compiler accepts option -O2... yes checking whether routines compiled with -O2 can be linked with ones compiled without -O2... yes checking how to get verbose linking output from gfortran... -v checking for Fortran 77 libraries of gfortran... -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm checking whether gfortran accepts the FLIBS found by autoconf... yes checking whether C can link with -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../../../lib64 -L/lib/../lib64 -L/usr/lib/../lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.3.0/../../.. -lgfortranbegin -lgfortran -lm... yes checking for linker for Fortran main programs... Use Fortran to link programs checking for Fortran 77 name mangling... lower underscore checking what libraries are needed to link Fortran programs with C routines that use stdio... none checking for f90... no checking for xlf90... no checking for pgf90... no checking for ifort... no checking for epcf90... no checking for f95... f95 checking that f works as the extension for Fortran 90 program... yes checking whether we are using the GNU Fortran 90 compiler... yes checking whether f95 accepts -g... yes checking for extension for Fortran 90 programs... f90 checking whether the Fortran 90 compiler (f95 -DNDEBUG ) works... yes checking whether the Fortran 90 compiler (f95 -DNDEBUG ) is a cross-compiler... no checking whether Fortran 90 works with Fortran 77... yes checking whether Fortran accepts ! for comments... yes checking for include directory flag for Fortran... -I checking for Fortran 77 flag for library directories... -L checking for which Fortran libraries are needed to link C with Fortran... none checking whether Fortran compiler processes .F files with C preprocessor... yes checking that f works as the extension for Fortran 90 program... yes checking whether we are using the GNU Fortran 90 compiler... (cached) yes checking whether f95 accepts -g... (cached) yes checking for extension for Fortran 90 programs... f90 checking whether the Fortran 90 compiler (f95 -DNDEBUG ) works... yes checking whether the Fortran 90 compiler (f95 -DNDEBUG ) is a cross-compiler... no checking for Fortran 90 module extension... mod checking for Fortran 90 module include flag... -I checking whether Fortran 90 accepts f90 suffix... yes checking whether Fortran 90 compiler accepts option -O2... yes checking whether routines compiled with -O2 can be linked with ones compiled without -O2... yes checking whether Fortran 90 compiler processes .F90 files with C preprocessor... yes checking what libraries are needed to link Fortran90 programs with C routines that use stdio... none checking for f90 compiler vendor... gnu checking for c++... c++ checking whether we are using the GNU C++ compiler... yes checking whether c++ accepts -g... yes checking whether the C++ compiler c++ can build an executable... yes checking whether C++ compiler works with string... yes checking whether the compiler supports exceptions... yes checking whether the compiler recognizes bool as a built-in type... yes checking whether the compiler implements namespaces... yes checking whether available... yes checking whether the compiler implements the namespace std... yes checking whether available... no checking for GNU g++ version... 4 . 3 checking whether C++ compiler accepts option -O2... yes checking whether routines compiled with -O2 can be linked with ones compiled without -O2... yes checking for perl... /usr/bin/perl checking for ar... ar checking for ranlib... ranlib checking for etags... no checking for killall... killall checking for a BSD-compatible install... /usr/bin/install -c checking whether install works... yes checking whether install breaks libraries... no checking whether mkdir -p works... yes checking for make... make checking whether clock skew breaks make... no checking whether make supports include... yes checking whether make allows comments in actions... yes checking for virtual path format... VPATH checking whether make sets CFLAGS... no checking for bash... /bin/bash checking whether /bin/bash supports arrays... yes checking for doctext... false checking for location of doctext style files... unavailable checking for an ANSI C-conforming const... yes checking for volatile... yes checking for restrict... __restrict checking for inline... inline checking whether __attribute__ allowed... yes checking whether __attribute__((format)) allowed... yes checking for grep that handles long lines and -e... /bin/grep checking for egrep... /bin/grep -E checking for ANSI C header files... no checking for sys/types.h... yes checking for sys/stat.h... yes checking for stdlib.h... yes checking for string.h... yes checking for memory.h... yes checking for strings.h... yes checking for inttypes.h... yes checking for stdint.h... yes checking for unistd.h... yes checking whether byte ordering is bigendian... no checking whether C compiler allows unaligned doubles... yes checking whether gcc supports __func__... yes Using gcc to determine dependencies checking whether long double is supported... yes checking whether long long is supported... yes checking for max C struct integer alignment... eight checking for max C struct floating point alignment... sixteen checking for max C struct alignment of structs with doubles... eight checking for max C struct floating point alignment with long doubles... sixteen configure: WARNING: Structures containing long doubles may be aligned differently from structures with floats or longs. MVAPICH2 does not handle this case automatically and you should avoid assumed extents for structures containing float types. checking if alignment of structs with doubles is based on position... no checking if alignment of structs with long long ints is based on position... no checking if double alignment breaks rules, find actual alignment... no checking for alignment restrictions on pointers... int or better checking size of char... 1 checking size of unsigned char... 1 checking size of short... 2 checking size of unsigned short... 2 checking size of int... 4 checking size of unsigned int... 4 checking size of long... 8 checking size of unsigned long... 8 checking size of long long... 8 checking size of unsigned long long... 8 checking size of float... 4 checking size of double... 8 checking size of long double... 16 checking size of wchar_t... 4 checking size of void *... 8 checking for size of float int... 8 checking for size of double int... 12 checking for size of long int... 12 checking for size of short int... 6 checking for size of 2 int... 8 checking for size of long double int... 20 checking for sys/bitypes.h... yes checking for inttypes.h... (cached) yes checking for int8_t... yes checking for int16_t... yes checking for int32_t... yes checking for int64_t... yes checking for uint8_t... yes checking for uint16_t... yes checking for uint32_t... yes checking for uint64_t... yes checking for size of Fortran type integer... 4 checking for size of Fortran type real... 4 checking for size of Fortran type double precision... 8 checking whether integer*1 is supported... yes checking whether integer*2 is supported... yes checking whether integer*4 is supported... yes checking whether integer*8 is supported... yes checking whether integer*16 is supported... yes checking whether real*4 is supported... yes checking whether real*8 is supported... yes checking whether real*16 is supported... no checking for C type matching Fortran integer... int checking for size of MPI_Status... 20 checking for values of Fortran logicals... True is 1 and False is 0 checking how to run the C preprocessor... gcc -E checking for Fortran 90 integer kind for 8-byte integers... 8 checking whether real*8 is supported in Fortran 90... yes checking size of bool... 1 checking how to run the C++ preprocessor... c++ -E checking for complex... yes checking size of Complex... 8 checking size of DoubleComplex... 16 checking size of LongDoubleComplex... 32 checking if char * pointers use byte addresses... yes checking for alignment restrictions on ... no checking for alignment restrictions on int32_t... no checking for size of MPI_BSEND_OVERHEAD... 95 checking for gcc __asm__ and pentium cmpxchgl instruction... no checking for gcc __asm__ and AMD x86_64 cmpxchgq instruction... yes checking for gcc __asm__ and IA64 xchg4 instruction... no checking for ANSI C header files... (cached) no checking for stdlib.h... (cached) yes checking for stdarg.h... yes checking for sys/types.h... (cached) yes checking for inttypes.h... (cached) yes checking for limits.h... yes checking for stddef.h... yes checking for errno.h... yes checking for sys/socket.h... yes checking for sys/time.h... yes checking for unistd.h... (cached) yes checking for endian.h... yes checking for assert.h... yes checking for sys/uio.h... yes checking for size_t... yes checking for setitimer... yes checking for alarm... yes checking for vsnprintf... yes checking for vsprintf... yes checking whether vsnprintf needs a declaration... no checking for strerror... yes checking for snprintf... yes checking whether snprintf needs a declaration... no checking for va_copy... yes checking for working alloca.h... yes checking for alloca... yes checking for strdup... yes checking whether strdup needs a declaration... no checking for clock_gettime... no checking for clock_getres... no checking for gethrtime... no checking for gettimeofday... yes sourcing /home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/ch3/setup_device RUNNING SETUP_DEVICE FOR THE CH3 DEVICE sourcing /home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/ch3/channels/mrail/setup_channel RUNNING SETUP_CHANNEL FOR THE MRAIL CHANNEL checking for pthread.h... yes checking for pthread_yield... no checking for library containing pthread_key_create... -lpthread checking for pthread_cleanup_push... no checking whether pthread_cleanup_push is available (may be a macro in pthread.h)... no checking for sched_yield... yes checking for yield... no checking for usleep... yes checking for sleep... yes checking for select... yes RUNNING CONFIGURE FOR CH3 DEVICE checking for make... make checking whether clock skew breaks make... no checking whether make supports include... yes checking whether make allows comments in actions... yes checking for virtual path format... VPATH checking whether make sets CFLAGS... yes checking for gcc... gcc checking for C compiler default output file name... a.out checking whether the C compiler works... yes checking whether we are cross compiling... no checking for suffix of executables... checking for suffix of object files... o checking whether we are using the GNU C compiler... yes checking whether gcc accepts -g... yes checking for gcc option to accept ISO C89... none needed checking how to run the C preprocessor... gcc -E checking for assert.h... yes checking for limits.h... yes checking for string.h... yes checking for sys/types.h... yes checking for sys/uio.h... yes checking for uuid/uuid.h... yes checking for time.h... yes checking for ctype.h... yes checking for unistd.h... yes checking for arpa/inet.h... yes checking for sys/socket.h... yes checking for net/if.h... yes checking for grep that handles long lines and -e... /bin/grep checking for egrep... /bin/grep -E checking for ANSI C header files... yes checking for sys/types.h... (cached) yes checking for sys/stat.h... yes checking for stdlib.h... yes checking for string.h... (cached) yes checking for memory.h... yes checking for strings.h... yes checking for inttypes.h... yes checking for stdint.h... yes checking for unistd.h... (cached) yes checking for pid_t... yes checking for inet_pton... yes checking for gethostname... yes checking whether gethostname needs a declaration... no checking for CFUUIDCreate... no checking for uuid_generate... no checking for time... yes checking for library containing uuid_generate... -luuid checking whether CPP accepts variable length argument lists... yes checking whether byte ordering is bigendian... no checking whether we can use struct ifconf... yes checking size of int... 4 checking size of long... 8 checking size of long long... 8 checking size of void *... 8 checking for etags... true configure: creating ./config.status config.status: creating Makefile config.status: creating src/Makefile config.status: creating util/Makefile config.status: creating util/shm/Makefile config.status: creating util/shmbase/Makefile config.status: creating channels/Makefile config.status: creating localdefs config.status: creating include/mpid_thread.h config.status: creating include/mpidi_ch3_conf.h config.status: include/mpidi_ch3_conf.h is unchanged config.status: executing default-1 commands copying ./../common/thread/mpid_thread_mpe.c to src/mpid_thread.c === configuring in channels/mrail (/home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/ch3/channels/mrail) configure: running /bin/sh ./configure --disable-option-checking '--prefix=/home/eperfa/mvapich2/mvapich2-1.4-src' '--enable-header-caching' 'CC=gcc' 'CFLAGS=-g -O2 -DNDEBUG -O2' 'LIBS=-lpthread ' --cache-file=/dev/null --srcdir=. RUNNING CONFIGURE FOR THE MRAIL CHANNEL checking build system type... x86_64-unknown-linux-gnu checking for make... make checking whether clock skew breaks make... no checking whether make supports include... yes checking whether make allows comments in actions... yes checking for virtual path format... VPATH checking whether make sets CFLAGS... yes checking for gcc... gcc checking for C compiler default output file name... a.out checking whether the C compiler works... yes checking whether we are cross compiling... no checking for suffix of executables... checking for suffix of object files... o checking whether we are using the GNU C compiler... yes checking whether gcc accepts -g... yes checking for gcc option to accept ISO C89... none needed checking how to run the C preprocessor... gcc -E checking for errno.h... yes checking for stdlib.h... yes checking for unistd.h... yes checking for pthread.h... yes ./configure: line 3635: enable_ftb-cr=no: command not found checking for the InfiniBand includes path... default checking for the InfiniBand library path... default checking for library containing umad_init... -libumad checking for library containing ibv_open_device... -libverbs checking for infiniband/umad.h... yes checking for infiniband/verbs.h... yes checking whether to enable support for BLCR... no checking whether to enable support for FTB-CR... checking whether to enable support for XRC... no checking whether to enable support for RDMA CM... yes checking for library containing rdma_create_event_channel... -lrdmacm checking for rdma/rdma_cma.h... yes checking whether to enable header caching... yes checking whether to enable registration caching... yes checking for snprintf... yes checking whether snprintf needs a declaration... no configure: creating ./config.status config.status: creating Makefile config.status: creating src/Makefile config.status: creating src/rdma/Makefile config.status: creating src/plpa/Makefile config.status: creating src/memory/Makefile config.status: creating src/memory/ptmalloc2/Makefile config.status: creating src/gen2/Makefile config.status: creating localdefs config.status: creating include/mpidi_ch3i_rdma_conf.h config.status: include/mpidi_ch3i_rdma_conf.h is unchanged config.status: executing default-1 commands Updating dependency directories .deps configure: WARNING: unrecognized options: --enable-header-caching RUNNING CONFIGURE FOR LOCKS checking for make... make checking whether clock skew breaks make... no checking whether make supports include... yes checking whether make allows comments in actions... yes checking for virtual path format... VPATH checking whether make sets CFLAGS... yes checking for ar... ar checking for ranlib... ranlib checking for gcc... gcc checking for C compiler default output file name... a.out checking whether the C compiler works... configure: error: in `/home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/common/locks': configure: error: cannot run C compiled programs. If you meant to cross compile, use `--host'. See `config.log' for more details. configure: error: Configure of src/mpid/common/locks failed! From perkinjo at cse.ohio-state.edu Sun Nov 15 15:01:22 2009 From: perkinjo at cse.ohio-state.edu (Jonathan Perkins) Date: Sun Nov 15 15:02:03 2009 Subject: [mvapich-discuss] Compiling MVAPICH2 on FC9 In-Reply-To: <4B005B48.4060805@digitus.itk.ppke.hu> References: <4B005B48.4060805@digitus.itk.ppke.hu> Message-ID: <20091115200122.GC4458@cse.ohio-state.edu> On Sun, Nov 15, 2009 at 08:49:28PM +0100, Div?k ?d?m wrote: > Dear Members, > > I would like to compile MVAPICH2 (1.4) under Fedora Core9 on an x86_64 > machine but I run into a compiler-related error I can't figure out. (I > know FC9 is rather old but unfortunately I'm not the administrator of > the system) > > Running configure --prefix=`pwd` in the source directory yields: > [...] > checking for C compiler default output file name... a.out > checking whether the C compiler works... configure: error: in > `/home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/common/locks': > configure: error: cannot run C compiled programs. > If you meant to cross compile, use `--host'. > See `config.log' for more details. > configure: error: Configure of src/mpid/common/locks failed! Thanks for the report. It looks like you provided the top level config.log. Can you post (or send me) the config.log in the src/mpid/common/locks directory. -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 197 bytes Desc: not available Url : http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091115/d6eb9bff/attachment.bin From divad at digitus.itk.ppke.hu Sun Nov 15 17:37:16 2009 From: divad at digitus.itk.ppke.hu (=?ISO-8859-2?Q?Div=E1k_=C1d=E1m?=) Date: Sun Nov 15 17:38:16 2009 Subject: [mvapich-discuss] Compiling MVAPICH2 on FC9 In-Reply-To: <20091115200122.GC4458@cse.ohio-state.edu> References: <4B005B48.4060805@digitus.itk.ppke.hu> <20091115200122.GC4458@cse.ohio-state.edu> Message-ID: <4B00829C.10603@digitus.itk.ppke.hu> Jonathan Perkins wrote: > On Sun, Nov 15, 2009 at 08:49:28PM +0100, Div?k ?d?m wrote: > >> Dear Members, >> >> I would like to compile MVAPICH2 (1.4) under Fedora Core9 on an x86_64 >> machine but I run into a compiler-related error I can't figure out. (I >> know FC9 is rather old but unfortunately I'm not the administrator of >> the system) >> >> Running configure --prefix=`pwd` in the source directory yields: >> [...] >> checking for C compiler default output file name... a.out >> checking whether the C compiler works... configure: error: in >> `/home/eperfa/mvapich2/mvapich2-1.4-src/src/mpid/common/locks': >> configure: error: cannot run C compiled programs. >> If you meant to cross compile, use `--host'. >> See `config.log' for more details. >> configure: error: Configure of src/mpid/common/locks failed! >> > > Thanks for the report. It looks like you provided the top level > config.log. Can you post (or send me) the config.log in the > src/mpid/common/locks directory. > Thanks for your answer, it just showed me my mistake so the problem is solved. Right after the configure script failed I entered the directory and ran ./configure there, which ran without any problems but it has overwritten my original config.log Re-running the original (top level) config and examining that log showed the error itself, which was that the compiler couldn't find the libibumad library. (I fail to see why that happened, as earlier in the configuration process there is a direct test for that which didn't produce errors, and the library is accessible from my path, but anyway, moving the lib file from /usr/local/lib to /usr/lib solved the problem.) Excuse me for the noise. Regards, Adam From anthony.j.mayhall at nasa.gov Wed Nov 18 12:02:45 2009 From: anthony.j.mayhall at nasa.gov (Mayhall, Anthony J. (MSFC-ES53)[TBE-1]) Date: Wed Nov 18 12:05:06 2009 Subject: [mvapich-discuss] MPI_Bcast Message-ID: <76E49B2FF96CBE4CB1DB0C8D3E7D90173DB205CF3E@NDMSSCC06.ndc.nasa.gov> How is MPI_Bcast implemented in mvapich 1.4? Can it use IB multicast? If so, how do you turn that on? It is currently taking our apps a lot longer to broadcast using MPI_Bcast to 10 nodes (175us for 40K) vs. 2 (46us for 40K) nodes. We are only broadcasting to one executable on each node. A multicast should take the same amount of time regardless of number of nodes wouldn't it? I used the multicast_test.c code to test IB multicast and it seems to not matter much how many nodes are being used as far as the timing goes. Can the Bcast buffer be broken into multiple 2048 byte transfers in MPI_Bcast to use IB multicast? I thought I saw in a white paper that these methods were being taken advantage of in mvapich. Or are we just doing something wrong? Thanks, Anthony Mayhall Davidson Technologies, Inc. (256)544-7620 From kandalla at cse.ohio-state.edu Wed Nov 18 12:42:12 2009 From: kandalla at cse.ohio-state.edu (Krishna Chaitanya Kandalla) Date: Wed Nov 18 12:43:06 2009 Subject: [mvapich-discuss] MPI_Bcast In-Reply-To: <76E49B2FF96CBE4CB1DB0C8D3E7D90173DB205CF3E@NDMSSCC06.ndc.nasa.gov> References: <76E49B2FF96CBE4CB1DB0C8D3E7D90173DB205CF3E@NDMSSCC06.ndc.nasa.gov> Message-ID: <4B0431F4.4040809@cse.ohio-state.edu> Anthony, Previously, we had explored the IB multicast option to implement a few of the collectives in MVAPICH. However, we found that it was not a scalable option. In MVAPICH2, we implement all collective operations using either point-to-point or shared-memory based algorithms. Getting back to your question, for the message sizes that you have mentioned (40K), we are currently using a shared-memory based algorithm to implement the MPI_Bcast operation. Which earlier version of MVAPICH/MVAPICH2 are you comparing these results with and what is the performance difference that you are observing? Also, you mentioned having to broadcast to one executable on each node, does your job involve running different executables on each node? Or do you mean you are having just one process running on each node? Thanks, Krishna Mayhall, Anthony J. (MSFC-ES53)[TBE-1] wrote: > How is MPI_Bcast implemented in mvapich 1.4? Can it use IB multicast? If so, how do you turn that on? It is currently taking our apps a lot longer to broadcast using MPI_Bcast to 10 nodes (175us for 40K) vs. 2 (46us for 40K) nodes. We are only broadcasting to one executable on each node. A multicast should take the same amount of time regardless of number of nodes wouldn't it? I used the multicast_test.c code to test IB multicast and it seems to not matter much how many nodes are being used as far as the timing goes. Can the Bcast buffer be broken into multiple 2048 byte transfers in MPI_Bcast to use IB multicast? I thought I saw in a white paper that these methods were being taken advantage of in mvapich. > > Or are we just doing something wrong? > > Thanks, > > Anthony Mayhall > Davidson Technologies, Inc. > (256)544-7620 > > > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > > > From anthony.j.mayhall at nasa.gov Wed Nov 18 13:47:19 2009 From: anthony.j.mayhall at nasa.gov (Mayhall, Anthony J. (MSFC-ES53)[TBE-1]) Date: Wed Nov 18 13:49:21 2009 Subject: [mvapich-discuss] MPI_Bcast In-Reply-To: <4B0431F4.4040809@cse.ohio-state.edu> References: <76E49B2FF96CBE4CB1DB0C8D3E7D90173DB205CF3E@NDMSSCC06.ndc.nasa.gov> <4B0431F4.4040809@cse.ohio-state.edu> Message-ID: <9DEECB5A-FFB6-46D1-AF3A-5052F70DC038@nasa.gov> We have only one executable on each node that is executed by mpirun_rsh. The root broadcasts to only one executable on each of the other nodes. We have other executables that communicate with those via shared memory, but are not run using mpirun_rsh. The numbers we are seeing are not in comparison to other mvapich builds. We need a faster method of doing the broadcast. It looks like the mcast option may work better for our app. We will try it and see. Thanks, Anthony Mayhall 256-684-1094 On Nov 18, 2009, at 12:35 PM, "Krishna Chaitanya Kandalla" wrote: > Anthony, > Previously, we had explored the IB multicast option to > implement a few of the collectives in MVAPICH. However, we found > that it was not a scalable option. In MVAPICH2, we implement all > collective operations using either point-to-point or shared-memory > based algorithms. > Getting back to your question, for the message sizes that you > have mentioned (40K), we are currently using a shared-memory based > algorithm to implement the MPI_Bcast operation. Which earlier > version of MVAPICH/MVAPICH2 are you comparing these results with and > what is the performance difference that you are observing? Also, you > mentioned having to broadcast to one executable on each node, does > your job involve running different executables on each node? Or do > you mean you are having just one process running on each node? > > Thanks, > Krishna > > > > > Mayhall, Anthony J. (MSFC-ES53)[TBE-1] wrote: >> How is MPI_Bcast implemented in mvapich 1.4? Can it use IB >> multicast? If so, how do you turn that on? It is currently taking >> our apps a lot longer to broadcast using MPI_Bcast to 10 nodes >> (175us for 40K) vs. 2 (46us for 40K) nodes. We are only >> broadcasting to one executable on each node. A multicast should >> take the same amount of time regardless of number of nodes wouldn't >> it? I used the multicast_test.c code to test IB multicast and it >> seems to not matter much how many nodes are being used as far as >> the timing goes. Can the Bcast buffer be broken into multiple 2048 >> byte transfers in MPI_Bcast to use IB multicast? I thought I saw >> in a white paper that these methods were being taken advantage of >> in mvapich. >> >> Or are we just doing something wrong? >> >> Thanks, >> >> Anthony Mayhall >> Davidson Technologies, Inc. >> (256)544-7620 >> >> >> >> _______________________________________________ >> mvapich-discuss mailing list >> mvapich-discuss@cse.ohio-state.edu >> http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss >> >> >> From panda at cse.ohio-state.edu Wed Nov 18 15:49:08 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Wed Nov 18 15:49:48 2009 Subject: [mvapich-discuss] MPI_Bcast In-Reply-To: <9DEECB5A-FFB6-46D1-AF3A-5052F70DC038@nasa.gov> Message-ID: Anthony - Since you are using additional executables which are also communicating via shared memory, I am wondering whether the performance is getting degraded by concurrent communication over shared memory. As Krishna indicated, the latest version is using shared-memory broadcast. How many cores are per node on your system? Do you see this bahavior for less than 10 nodes? Please note that in MVAPICH2 1.4, we have introduced multiple runtime parameters to select the broadcast scheme for a given environment - pure pt-to-pt-based scheme vs. shared memory-based scheme. Details are available at the following location in MVAPICH2 user guide. You can try some of these options and let us know whether the problem gets resolved on your set-up. http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-8600010.8 Thanks, DK On Wed, 18 Nov 2009, Mayhall, Anthony J. (MSFC-ES53)[TBE-1] wrote: > We have only one executable on each node that is executed by > mpirun_rsh. The root broadcasts to only one executable on each of the > other nodes. We have other executables that communicate with those > via shared memory, but are not run using mpirun_rsh. The numbers we > are seeing are not in comparison to other mvapich builds. We need a > faster method of doing the broadcast. It looks like the mcast option > may work better for our app. We will try it and see. > > Thanks, > > > Anthony Mayhall > 256-684-1094 > > On Nov 18, 2009, at 12:35 PM, "Krishna Chaitanya Kandalla" > wrote: > > > Anthony, > > Previously, we had explored the IB multicast option to > > implement a few of the collectives in MVAPICH. However, we found > > that it was not a scalable option. In MVAPICH2, we implement all > > collective operations using either point-to-point or shared-memory > > based algorithms. > > Getting back to your question, for the message sizes that you > > have mentioned (40K), we are currently using a shared-memory based > > algorithm to implement the MPI_Bcast operation. Which earlier > > version of MVAPICH/MVAPICH2 are you comparing these results with and > > what is the performance difference that you are observing? Also, you > > mentioned having to broadcast to one executable on each node, does > > your job involve running different executables on each node? Or do > > you mean you are having just one process running on each node? > > > > Thanks, > > Krishna > > > > > > > > > > Mayhall, Anthony J. (MSFC-ES53)[TBE-1] wrote: > >> How is MPI_Bcast implemented in mvapich 1.4? Can it use IB > >> multicast? If so, how do you turn that on? It is currently taking > >> our apps a lot longer to broadcast using MPI_Bcast to 10 nodes > >> (175us for 40K) vs. 2 (46us for 40K) nodes. We are only > >> broadcasting to one executable on each node. A multicast should > >> take the same amount of time regardless of number of nodes wouldn't > >> it? I used the multicast_test.c code to test IB multicast and it > >> seems to not matter much how many nodes are being used as far as > >> the timing goes. Can the Bcast buffer be broken into multiple 2048 > >> byte transfers in MPI_Bcast to use IB multicast? I thought I saw > >> in a white paper that these methods were being taken advantage of > >> in mvapich. > >> > >> Or are we just doing something wrong? > >> > >> Thanks, > >> > >> Anthony Mayhall > >> Davidson Technologies, Inc. > >> (256)544-7620 > >> > >> > >> > >> _______________________________________________ > >> mvapich-discuss mailing list > >> mvapich-discuss@cse.ohio-state.edu > >> http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > >> > >> > >> > > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss > From anthony.j.mayhall at nasa.gov Wed Nov 18 15:55:30 2009 From: anthony.j.mayhall at nasa.gov (Mayhall, Anthony J. (MSFC-ES53)[TBE-1]) Date: Wed Nov 18 15:56:19 2009 Subject: [mvapich-discuss] MPI_Bcast In-Reply-To: References: Message-ID: We have 12 cores per system. No shared memory transfers occur until the broadcast completes. I have tried some of the options and haven't seen any real effect in the timing. Anthony Mayhall 256-684-1094 On Nov 18, 2009, at 2:49 PM, "Dhabaleswar Panda" wrote: > Anthony - Since you are using additional executables which are also > communicating via shared memory, I am wondering whether the > performance is > getting degraded by concurrent communication over shared memory. As > Krishna indicated, the latest version is using shared-memory > broadcast. > How many cores are per node on your system? Do you see this bahavior > for > less than 10 nodes? > > Please note that in MVAPICH2 1.4, we have introduced multiple runtime > parameters to select the broadcast scheme for a given environment - > pure > pt-to-pt-based scheme vs. shared memory-based scheme. Details are > available at the following location in MVAPICH2 user guide. You can > try some of these options and let us know whether the problem gets > resolved on your set-up. > > http://mvapich.cse.ohio-state.edu/support/user_guide_mvapich2-1.4.html#x1-8600010.8 > > Thanks, > > DK > > > > On Wed, 18 Nov 2009, Mayhall, Anthony J. (MSFC-ES53)[TBE-1] wrote: > >> We have only one executable on each node that is executed by >> mpirun_rsh. The root broadcasts to only one executable on each of >> the >> other nodes. We have other executables that communicate with those >> via shared memory, but are not run using mpirun_rsh. The numbers we >> are seeing are not in comparison to other mvapich builds. We need a >> faster method of doing the broadcast. It looks like the mcast option >> may work better for our app. We will try it and see. >> >> Thanks, >> >> >> Anthony Mayhall >> 256-684-1094 >> >> On Nov 18, 2009, at 12:35 PM, "Krishna Chaitanya Kandalla" >> wrote: >> >>> Anthony, >>> Previously, we had explored the IB multicast option to >>> implement a few of the collectives in MVAPICH. However, we found >>> that it was not a scalable option. In MVAPICH2, we implement all >>> collective operations using either point-to-point or shared-memory >>> based algorithms. >>> Getting back to your question, for the message sizes that you >>> have mentioned (40K), we are currently using a shared-memory based >>> algorithm to implement the MPI_Bcast operation. Which earlier >>> version of MVAPICH/MVAPICH2 are you comparing these results with and >>> what is the performance difference that you are observing? Also, you >>> mentioned having to broadcast to one executable on each node, does >>> your job involve running different executables on each node? Or do >>> you mean you are having just one process running on each node? >>> >>> Thanks, >>> Krishna >>> >>> >>> >>> >>> Mayhall, Anthony J. (MSFC-ES53)[TBE-1] wrote: >>>> How is MPI_Bcast implemented in mvapich 1.4? Can it use IB >>>> multicast? If so, how do you turn that on? It is currently taking >>>> our apps a lot longer to broadcast using MPI_Bcast to 10 nodes >>>> (175us for 40K) vs. 2 (46us for 40K) nodes. We are only >>>> broadcasting to one executable on each node. A multicast should >>>> take the same amount of time regardless of number of nodes wouldn't >>>> it? I used the multicast_test.c code to test IB multicast and it >>>> seems to not matter much how many nodes are being used as far as >>>> the timing goes. Can the Bcast buffer be broken into multiple 2048 >>>> byte transfers in MPI_Bcast to use IB multicast? I thought I saw >>>> in a white paper that these methods were being taken advantage of >>>> in mvapich. >>>> >>>> Or are we just doing something wrong? >>>> >>>> Thanks, >>>> >>>> Anthony Mayhall >>>> Davidson Technologies, Inc. >>>> (256)544-7620 >>>> >>>> >>>> >>>> _______________________________________________ >>>> mvapich-discuss mailing list >>>> mvapich-discuss@cse.ohio-state.edu >>>> http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss >>>> >>>> >>>> >> >> _______________________________________________ >> mvapich-discuss mailing list >> mvapich-discuss@cse.ohio-state.edu >> http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss >> > From bramesh at vt.edu Thu Nov 19 13:22:08 2009 From: bramesh at vt.edu (Bharath Ramesh) Date: Thu Nov 19 13:26:05 2009 Subject: [mvapich-discuss] MVAPICH2-1.4 build failure Message-ID: <20091119182207.GA25926@vt.edu> I am trying to build to MVAPICH2-1.4 and I am having a build failure. This occurs in both the stable version and the daily release on 2009-11-18. The build failure is: gcc -DHAVE_CONFIG_H -I. -I. -I../../include -I../../pm/smpd -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/pm/smpd -g -O2 -DNDEBUG -O2 -I/apps/packages/OFED-1.4.2/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock/poll -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock/poll -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/datatype -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/datatype -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/src/gen2 -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/src/gen2 -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -c smpd_pmi.c smpd_pmi.c: In function 'PMI_Init': smpd_pmi.c:114: warning: assignment from incompatible pointer type smpd_pmi.c:153: warning: assignment from incompatible pointer type smpd_pmi.c: At top level: smpd_pmi.c:349: error: conflicting types for 'PMI_Args_to_keyval' ../../include/pmi.h:753: error: previous declaration of 'PMI_Args_to_keyval' was here smpd_pmi.c: In function 'PMI_Args_to_keyval': smpd_pmi.c:356: warning: passing argument 2 of 'fn.PMI_Args_to_keyval' from incompatible pointer type make[3]: *** [smpd_pmi.o] Error 1 I configured mvapich using 77=gfortran F90=gfortran ./configure --prefix=/apps/packages/mvapich2-1.4_gnu --with-rdma=gen2 --with-ib-include=/apps/packages/OFED-1.4.2/include --with-ib-libpath=/apps/packages/OFED-1.4.2/lib64 --disable-romio --without-mpe --with-pm=smpd,mpirun --enable-sharedlibs=gcc --with-pmi=smpd --enable-error-messages=all --enable-rdma-cm --enable-header-caching Any help in fixing this build failure is appreciated. I am also not subscribed to this list, would appreciate it if I am copied during reply. Regards, Bharath -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/x-pkcs7-signature Size: 2245 bytes Desc: not available Url : http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091119/dd12068c/smime.bin From perkinjo at cse.ohio-state.edu Thu Nov 19 15:20:48 2009 From: perkinjo at cse.ohio-state.edu (Jonathan Perkins) Date: Thu Nov 19 15:21:30 2009 Subject: [mvapich-discuss] MVAPICH2-1.4 build failure In-Reply-To: <20091119182207.GA25926@vt.edu> References: <20091119182207.GA25926@vt.edu> Message-ID: <20091119202048.GH3487@cse.ohio-state.edu> Bharath: We'll take a look at this build failure. In the meantime, can you try using mpirun_rsh to see if it suites your needs. On Thu, Nov 19, 2009 at 01:22:08PM -0500, Bharath Ramesh wrote: > I am trying to build to MVAPICH2-1.4 and I am having a build failure. > This occurs in both the stable version and the daily release on > 2009-11-18. The build failure is: > > gcc -DHAVE_CONFIG_H -I. -I. -I../../include -I../../pm/smpd -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/pm/smpd -g -O2 -DNDEBUG -O2 -I/apps/packages/OFED-1.4.2/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock/poll -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/sock/poll -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/datatype -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/datatype -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/include -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/src/gen2 -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/ch3/channels/mrail/src/gen2 -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -I/home/bramesh/ARC/ithaca/mvapich2-1.4-2009-11-18/src/mpid/common/locks -c smpd_pmi.c > smpd_pmi.c: In function 'PMI_Init': > smpd_pmi.c:114: warning: assignment from incompatible pointer type > smpd_pmi.c:153: warning: assignment from incompatible pointer type > smpd_pmi.c: At top level: > smpd_pmi.c:349: error: conflicting types for 'PMI_Args_to_keyval' > ../../include/pmi.h:753: error: previous declaration of 'PMI_Args_to_keyval' was here > smpd_pmi.c: In function 'PMI_Args_to_keyval': > smpd_pmi.c:356: warning: passing argument 2 of 'fn.PMI_Args_to_keyval' from incompatible pointer type > make[3]: *** [smpd_pmi.o] Error 1 > > I configured mvapich using > > 77=gfortran F90=gfortran ./configure --prefix=/apps/packages/mvapich2-1.4_gnu --with-rdma=gen2 --with-ib-include=/apps/packages/OFED-1.4.2/include --with-ib-libpath=/apps/packages/OFED-1.4.2/lib64 --disable-romio --without-mpe --with-pm=smpd,mpirun --enable-sharedlibs=gcc --with-pmi=smpd --enable-error-messages=all --enable-rdma-cm --enable-header-caching > > Any help in fixing this build failure is appreciated. I am also not > subscribed to this list, would appreciate it if I am copied during > reply. > > Regards, > > Bharath > _______________________________________________ > mvapich-discuss mailing list > mvapich-discuss@cse.ohio-state.edu > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss -- Jonathan Perkins http://www.cse.ohio-state.edu/~perkinjo -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 197 bytes Desc: not available Url : http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091119/64ec4c06/attachment.bin From jsquyres at cisco.com Fri Nov 20 17:01:48 2009 From: jsquyres at cisco.com (Jeff Squyres) Date: Fri Nov 20 17:02:31 2009 Subject: [mvapich-discuss] MPI Forum community feedback survey Message-ID: The MPI Forum announced at its SC09 BOF that they are soliciting community feedback to help guide the MPI-3 standards process. A survey is available online at the following URL: http://mpi-forum.questionpro.com/ Password: mpi3 In this survey, the MPI Forum is asking as many people as possible for feedback on the MPI-3 process -- what features to include, what features to not include, etc. We encourage you to forward this survey on to as many interested and relevant parties as possible. It will take approximately 10 minutes to complete the questionnaire. No question in the survey is mandatory; feel free to only answer the questions which are relevant to you and your applications. Your answers will help the MPI Forum guide its process to create a genuinely useful MPI-3 standard. This survey closes December 31, 2009. Your survey responses will be strictly confidential and data from this research will be reported only in the aggregate. Your information will be coded and will remain confidential. If you have questions at any time about the survey or the procedures, you may contact the MPI Forum via email to mpi-comments@mpi-forum.org. Thank you very much for your time and support. -- Jeff Squyres jsquyres@cisco.com From mohammad.rashti at queensu.ca Mon Nov 23 11:14:19 2009 From: mohammad.rashti at queensu.ca (Mohammad Javad Rashti) Date: Mon Nov 23 11:18:57 2009 Subject: [mvapich-discuss] Scatter-gather list in MVAPICH Message-ID: <3aea68870911230814o15eb4f73o32110fdf97b9651f@mail.gmail.com> Hi Jonathan, Do you know whether or not scatter-gather list capability in IB/iWARP work requests are utilized anywhere in MVAPICH or MVAPICH2? Thanks Mohammad -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20091123/55e5c83c/attachment.html From panda at cse.ohio-state.edu Mon Nov 23 13:21:11 2009 From: panda at cse.ohio-state.edu (Dhabaleswar Panda) Date: Mon Nov 23 13:21:52 2009 Subject: [mvapich-discuss] Scatter-gather list in MVAPICH In-Reply-To: <3aea68870911230814o15eb4f73o32110fdf97b9651f@mail.gmail.com> Message-ID: Yes, it is utilized. Please feel free to take a look at the codebase. Thanks, DK On Mon, 23 Nov 2009, Mohammad Javad Rashti wrote: > Hi Jonathan, > Do you know whether or not scatter-gather list capability in IB/iWARP work > requests are utilized anywhere > in MVAPICH or MVAPICH2? > Thanks > Mohammad >