Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Thanks for the trick. We can prepare the example script for Lonestar6 and mention it. --Junchao Zhang On Fri, Apr 19, 2024 at 11:55 AM Sreeram R Venkat wrote: > I talked to the MVAPICH people, and they told me to try adding > /path/to/mvapich2-gdr/lib64/libmpi.so to LD_PRELOAD (apparently, the

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

I talked to the MVAPICH people, and they told me to try adding /path/to/mvapich2-gdr/lib64/libmpi.so to LD_PRELOAD (apparently, they've had this issue before). This seemed to do the trick; I can build everything with MVAPICH2-GDR and run with it now. Not sure if this is something you want to add to

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

I looked at it before and checked again, and still see https://urldefense.us/v3/__https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/mpi.html*inter-gpu-communication-with-cuda-aware-mpi__;Iw!!G_uCfscf7eWS!aoebw25LunX6PlUYyVIti_VNLojOyz8MwWS3U-t5NHMMb4GnFUFV-nGq1LbjnigF72oKfDjmLXk9vUwkcYZpFTq

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Yes, I saw this paper https://urldefense.us/v3/__https://www.sciencedirect.com/science/article/abs/pii/S016781912100079X__;!!G_uCfscf7eWS!dHsBib5l9Muy07HNhTdWzjZYUUlhkMkHrO7blcUjZQbwvChOEe0pDb5zyW-3qjEF78R3JHlcfjthtoxJY5VolUpbQw$ that mentioned it, and I heard in Barry's talk at SIAM PP this year

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

On Wed, Apr 17, 2024 at 7:51 AM Sreeram R Venkat wrote: > Do you know if there are plans for NCCL support in PETSc? > What is your need? Do you mean using NCCL for the MPI communication? > > On Tue, Apr 16, 2024, 10:41 PM Junchao Zhang > wrote: > >> Glad to hear you found a way. Did you use

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Victor, through the SMART PETSc project, I do have access to Frontera and Lonestar6. --Junchao Zhang On Wed, Apr 17, 2024 at 3:55 AM Victor Eijkhout wrote: > > > > >- Did you use Frontera at TACC? If yes, I could have a try. > > > > If you’re interested in access to other TACC machines

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Do you know if there are plans for NCCL support in PETSc? On Tue, Apr 16, 2024, 10:41 PM Junchao Zhang wrote: > Glad to hear you found a way. Did you use Frontera at TACC? If yes, I > could have a try. > > --Junchao Zhang > > > On Tue, Apr 16, 2024 at 8:35 PM Sreeram R Venkat > wrote: > >> I

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

*Did you use Frontera at TACC? If yes, I could have a try. If you’re interested in access to other TACC machines that can be arranged. I once set up a project for PETSc access to TACC. I think that was for a github CI but we never actually set that up. Victor.

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Glad to hear you found a way. Did you use Frontera at TACC? If yes, I could have a try. --Junchao Zhang On Tue, Apr 16, 2024 at 8:35 PM Sreeram R Venkat wrote: > I finally figured out a way to make it work. I had to build PETSc and my > application using the (non GPU-aware) Intel MPI. Then,

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

I finally figured out a way to make it work. I had to build PETSc and my application using the (non GPU-aware) Intel MPI. Then, before running, I switch to the MVAPICH2-GDR. I'm not sure why that works, but it's the only way I've found to compile and run successfully without throwing any errors abo

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

You may need to set some env variables. This can be system specific so you might want to look at docs or ask TACC how to run with GPU-aware MPI. Mark On Fri, Dec 8, 2023 at 5:17 PM Sreeram R Venkat wrote: > Actually, when I compile my program with this build of PETSc and run, I > still get the

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Actually, when I compile my program with this build of PETSc and run, I still get the error: PETSC ERROR: PETSc is configured with GPU support, but your MPI is not GPU-aware. For better performance, please use a GPU-aware MPI. I have the mvapich2-gdr module loaded and MV2_USE_CUDA=1. Is there an

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Thank you, changing to CUDA 11.4 fixed the issue. The mvapich2-gdr module didn't require CUDA 11.4 as a dependency, so I was using 12.0 On Fri, Dec 8, 2023 at 1:15 PM Satish Balay wrote: > Executing: mpicc -show > stdout: icc -I/opt/apps/cuda/11.4/include -I/opt/apps/cuda/11.4/include > -lcuda -

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

Executing: mpicc -show stdout: icc -I/opt/apps/cuda/11.4/include -I/opt/apps/cuda/11.4/include -lcuda -L/opt/apps/cuda/11.4/lib64/stubs -L/opt/apps/cuda/11.4/lib64 -lcudart -lrt -Wl,-rpath,/opt/apps/cuda/11.4/lib64 -Wl,-rpath,XORIGIN/placeholder -Wl,--build-id -L/opt/apps/cuda/11.4/lib64/ -lm -

Re: [petsc-users] Configure error while building PETSc with CUDA/MVAPICH2-GDR

On Fri, Dec 8, 2023 at 1:54 PM Sreeram R Venkat wrote: > I am trying to build PETSc with CUDA using the CUDA-Aware MVAPICH2-GDR. > > Here is my configure command: > > ./configure PETSC_ARCH=linux-c-debug-mvapich2-gdr --download-hypre > --with-cuda=true --cuda-dir=$TACC_CUDA_DIR --with-hdf5=true

Re: [petsc-users] Configure error with PETSc 3.17.4 on Ubuntu 22.04

Thanks for this suggestion, using --download-mpich got it working! Thanks, David On Fri, Aug 12, 2022 at 1:25 PM Satish Balay wrote: > We've seen issues with Ubuntu built MPI. Can you try --download-mpich and > see if that helps? > > Also you don't need --with-clanguage=cxx for complex. PETS

Re: [petsc-users] Configure error with PETSc 3.17.4 on Ubuntu 22.04

On Fri, Aug 12, 2022 at 1:32 PM David Knezevic wrote: > Regarding 1.: We're using --download-mumps, so this is the mumps that was > installed during config. There was no mumps build prior to that. Does that > change anything? > I did not see the build in the log. Can you try removing and reconfi

Re: [petsc-users] Configure error with PETSc 3.17.4 on Ubuntu 22.04

Regarding 1.: We're using --download-mumps, so this is the mumps that was installed during config. There was no mumps build prior to that. Does that change anything? Regarding 2.: We need --with-clanguage=cxx since we're also using an external C++ library (libMesh). We've been using --with-clangua

Re: [petsc-users] Configure error with PETSc 3.17.4 on Ubuntu 22.04

We've seen issues with Ubuntu built MPI. Can you try --download-mpich and see if that helps? Also you don't need --with-clanguage=cxx for complex. PETSc can be built with c99 compilex - i.e "--with-clanguage=c --with-scalar-type=complex" should work. Satish On Fri, 12 Aug 2022, David Knezevic

Re: [petsc-users] Configure error with PETSc 3.17.4 on Ubuntu 22.04

On Fri, Aug 12, 2022 at 1:14 PM David Knezevic via petsc-users < petsc-users@mcs.anl.gov> wrote: > I get a configure error when building PETSc 3.17.4 on Ubuntu 22.04. The > configure.log is attached. > > This error seems to only occur when we use --with-clanguage=cxx. We need > to use that object

Re: [petsc-users] configure error with fftw and without mpi

Thank you Barry! Backported the patch to 3.16.0 and tested! I'll try to integrate downstream in Gentoo (https://bugs.gentoo.org/827185). Fabio > Il 26/11/2021 05:15 Barry Smith ha scritto: > > > > I have made a branch barry/2021-11-25/feature-fftw-seq  > https://gitlab.com/petsc/petsc/-/mer

Re: [petsc-users] configure error with fftw and without mpi

I have made a branch barry/2021-11-25/feature-fftw-seq https://gitlab.com/petsc/petsc/-/merge_requests/4604 that provides support for using FFTW without MPI, please let us know if you have difficulties with it. Barry > On Nov 25, 20

Re: [petsc-users] configure error with fftw and without mpi

On Thu, Nov 25, 2021 at 2:29 PM Fabio Rossi via petsc-users < petsc-users@mcs.anl.gov> wrote: > Thanks for the reply. > > I am using the system fftw which is provided by the distribution so I am > not going to install it by using PETSC's install scripts. > > I am sorry but I am not confident with

Re: [petsc-users] configure error with fftw and without mpi

Thanks for the reply. I am using the system fftw which is provided by the distribution so I am not going to install it by using PETSC's install scripts. I am sorry but I am not confident with the PETSC building system. What happens if mpi is installed but the user prefers to compile PETSC with

Re: [petsc-users] configure error with fftw and without mpi

PETSc's install and use of fftw always requires MPI. The code in config/BuildSystem/config/packages/fftw.py and src/mat/impls/fft/fftw/fftw.c could relatively easily be "fixed" to also support building and using FFTW without MPI. Just change the fftw.py to conditionally pass in args

[petsc-users] configure error with fftw and without mpi

I am trying to compile petsc with the following options (Gentoo build system): ./configure --prefix=/usr --build=x86_64-pc-linux-gnu --host=x86_64-pc-linux-gnu --mandir=/usr/share/man --infodir=/usr/share/info --datadir=/usr/share --sysconfdir=/etc --localstatedir=/var/lib --libdir=/usr/lib64/p

Re: [petsc-users] configure error

configure prints the information about CUDA at the end of the run, you can check that information to see which was actually used. I have a new MR where PETSc records the gencodearch it was built with and then when your program starts up CUDA it verifies that the hardware supports the genc

Re: [petsc-users] configure error

*'--with-cuda-gencodearch=70',* --Junchao Zhang On Tue, May 18, 2021 at 6:29 AM Mark Adams wrote: > Damn, I am getting this problem on Summit and did a clean configure. > I removed the Kokkos arch=70 line and added > '--with-cudac-gencodearch=70', > > Any ideas? > > < Number of SNES it

Re: [petsc-users] configure error

I thought I did a clean make but I made a clean one now and it seems to be working now. Also, I am trying to fix this error message that I get on Cori with 'make check'. I set mpiexec='srun -G 2 -c 20' and get an interactive shell with these parameters, but I get error messages on Kokkos: Possibl

Re: [petsc-users] configure error

Could still be a gencode arch issue. Is it possible that Kokkos was built with the 80 arch and when you reran configure with 70 it did not rebuild Kokkos because it didn't know it needed to? Sorry, but this may require another rm -rf arch* and running ./configure again. https://docs.nvidia.com

Re: [petsc-users] configure error

I now get this error. A blas error from VecAXPBYPCZ ... Any ideas? terminate called after throwing an instance of 'std::runtime_error' what(): cudaFuncGetAttributes(&attr_tmp, base_t::get_kernel_func()) error( cudaErrorInvalidDeviceFunction): invalid device function /global/u2/m/madams/petsc/a

Re: [petsc-users] configure error

Mark, The kokkos-kernels did not get rebuilt so they will likely have a different geodearch. I think you need to rm -rf arch-cori-gpu-opt-kokkos-gcc but was --with-mpi-dir=/usr/common/software/sles15_cgpu/openmpi/4.0.3/gcc built with CUDA aware MPI and a different gencodarch th

Re: [petsc-users] configure error

> On May 16, 2021, at 7:37 AM, Junchao Zhang wrote: > > Remove --with-kokkos-cuda-arch=VOLTA70 from your configure Yes, I think it should be removed. > > Barry: It seems we should either disable this option, or rename it to > --with-cuda-arch and get it accepted by both kokkos.py and cuda

Re: [petsc-users] configure error

Check the meaning of 'srun: error: Unable to create step for job 1921749: More processors requested than permitted' --Junchao Zhang On Sun, May 16, 2021 at 7:58 AM Mark Adams wrote: > Whoops, between scp'ing and soft links I gave you the wrong log file. I > removed this already. > > On Sun, Ma

Re: [petsc-users] configure error

Remove --with-kokkos-cuda-arch=VOLTA70 from your configure Barry: It seems we should either disable this option, or rename it to --with-cuda-arch and get it accepted by both kokkos.py and cuda.py --Junchao Zhang On Sun, May 16, 2021 at 6:15 AM Mark Adams wrote: > progress: > > 04:08 cgpu11 ada

Re: [petsc-users] configure error

Looks like nvcc_wrapper gets confused when both -arch and -gencode are used. But handles either of them separately correctly. Mark, PETSc configure now handles the -arch and --with-kokkos-cuda-arch= business automatically so you do not, and generally shouldn't pass -arch sm_70 in -

Re: [petsc-users] configure error

Add --show to the failing nvcc_wrapper command and see how nvcc_wrapper parses the options PATH=/global/common/sw/cray/sles15/x86_64/zlib/1.2.11/gcc/8.2.0/pep2pal/bin:/global/common/sw/cray/cnl7/haswell/cmake/3.18.2/bin:/opt/cray/rca/2.2.20-7.0.1.1_4.62__g8e3fb5b.ari/bin:/opt/cray/alps/6.6.58-7.0.

Re: [petsc-users] configure error

Bitbucket is off-line. Do you need fortran stubs at this moment? If not use --with-fortran-interface=0 > On May 15, 2021, at 2:51 PM, Mark Adams wrote: > > I can build a non-kokkos PETSc here (Cori/GPU) but I get this error with > Kokkos. > Any suggestions? > Thanks, > Mark > >

Re: [petsc-users] configure error

Thanks, Inexplicably, it says the project software directories are read-only on KNL (compute) nodes on Cori, which does not make sense to me, but maybe it's just my permissions. I can build on the login nodes with-batch=0 now. I guess that got fixed (executing a program) or maybe Hypre was instal

Re: [petsc-users] configure error

Configure Options: --configModules=PETSc.Configure --optionsModule=config.compilerOptions --with-cc=cc --with-cxx=CC --with-fc=ftn COPTFLAGS=" -g -O2" CXXOPTFLAGS="-g -O2" FOPTFLAGS=" -g -O2" --download-fblaslapack=1 --download-hypre=0 --download-metis=1 --download-parmetis=1 --with-debugging

Re: [petsc-users] configure error

It is reporting ld: cannot find -lmkl_intel_ilp64 Please send the output from ls /mnt/disks/intel-2018-3-222-blade-runtime-env-2018-1-07-08-2018-132838/2019.3/intel/compilers_and_libraries_2019.3.199/linux/mkl ls /mnt/disks/intel-2018-3-222-blade-runtime-env-2018-1-07-08-2018-132

Re: [petsc-users] configure error

On Mon, Jun 15, 2020 at 12:13 PM Kun Jiao via petsc-users < petsc-users@mcs.anl.gov> wrote: > Hi, > > > > Lately I run into a configure error with intel compiler+openmpi+lapack, > > > > Error message as: > > === > TESTING:

Re: [petsc-users] Configure error after upgrading GCC

The fix for petsc build error with openmpi-4.0.0 is in branch 'barry/remove-mpi-handler-function/maint' You can always get petsc to build mpich or openmpi - with --download-mpich or --download-openmpi Satish On Mon, 10 Dec 2018, Amneet Bhalla via petsc-users wrote: > That still caused the sam

Re: [petsc-users] Configure error after upgrading GCC

That still caused the same problem. But I have resolved the issue. I removed system mpich and built a local version of openmpi. That made it work. It appears that apt-get install mpich installs default GCC-5 headers even when I made GCC-7 the default complier. By the way, I built openmpi 4.0.0 an

Re: [petsc-users] Configure error after upgrading GCC

> Configure Options: --configModules=PETSc.Configure > --optionsModule=config.compilerOptions --CC=mpicc --FC=mpif90 > --with-debugging=1 --download-hypre=1 --with-x=0 --PETSC_ARCH=linux-dbg If specifying compilers - also specify a C++ compiler. --CC=mpicc --FC=mpif90 --CXX=mpicxx Satish On

Re: [petsc-users] configure error

Ok, nuking worked, thanks On Mon, Jul 23, 2018 at 4:22 PM Mark Adams wrote: > Yea, I have done this twice, once with just the git.hypre directory. I > will try again. > > > > On Mon, Jul 23, 2018 at 4:20 PM Smith, Barry F. > wrote: > >> >> delete $PETSC_ARCH and >> /global/homes/m/madams/pet

Re: [petsc-users] configure error

Yea, I have done this twice, once with just the git.hypre directory. I will try again. On Mon, Jul 23, 2018 at 4:20 PM Smith, Barry F. wrote: > > delete $PETSC_ARCH and > /global/homes/m/madams/petsc_install/petsc-xc30-opt-intel and run again. > > You may have run with some different opti

Re: [petsc-users] configure error

delete $PETSC_ARCH and /global/homes/m/madams/petsc_install/petsc-xc30-opt-intel and run again. You may have run with some different options before; it thinks hypre is installed but when checked found it is not. Barry > On Jul 23, 2018, at 3:47 PM, Mark Adams wrote: > > This is

Re: [petsc-users] configure error

Thanks, I can not find the damn (PGI) c++ compiler (on SUMMIT) but this is for a Fortran code so I just set it to =0 and it seems to be chugging along. On Thu, May 3, 2018 at 3:14 PM, Smith, Barry F. wrote: > > Mark, > > You pass the C and C++ compiler names to ./configure with > --with-cc

Re: [petsc-users] configure error

Mark, You pass the C and C++ compiler names to ./configure with --with-cc=mpicc --with-fc=mpif90 but do not pass a C++ compiler hence it defaults to g++ which does not know about MPI. Barry > On May 3, 2018, at 2:02 PM, Mark Adams wrote: > > I am getting this configure error on t

Re: [petsc-users] configure error

>>> Configure Options: --configModules=PETSc.Configure --optionsModule=config.compilerOptions --COPTFLAGS=-O2 --CXXOPTFLAGS=-O2 --FOPTFLAGS=-O2 --with-ssl=0 --with-batch=0 --prefix=/ccs/proj/env003/petscv3.9-opt64-summit-pgi --download-metis --with-hwloc=0 --download-parmetis --download-cma

Re: [petsc-users] configure error with --with-shared-libraries=0 --download-elemental

George, Thanks for letting us know. Now fixed in maint, master, next and will be in our next patch release Barry commit 5219fea8a3666c8b7c80c852d85e563864a43d28 Author: Barry Smith Date: Tue Aug 4 14:33:41 2015 -0500 Turn off elemental shared libraries if --with-shared-librarie

Re: [petsc-users] configure error with --with-shared-libraries=0 --download-elemental

Barry, Thanks. The patch works. George On Tue, Aug 4, 2015 at 12:33 PM, Barry Smith wrote: > > Aghh, looks like CMake does not have a universal standard for indicating > shared libraries or not. > > Please try the attached elemental.py file and see if that resolves your > difficulties. >

Re: [petsc-users] configure error with --with-shared-libraries=0 --download-elemental

Aghh, looks like CMake does not have a universal standard for indicating shared libraries or not. Please try the attached elemental.py file and see if that resolves your difficulties. import config.package class Configure(config.package.CMakePackage): def __init__(self, framework): c

Re: [petsc-users] configure error on Titan with Intel

On Tue, 12 May 2015, Mark Adams wrote: > > > > Notes: ./configure ran fine and detected -lhwloc in some standard system > > install location under normal circumstances it couldn't just disappear for > > a different example. > > > > > I configured in an interactive shell, so on a compute node. I

Re: [petsc-users] configure error on Titan with Intel

> > Notes: ./configure ran fine and detected -lhwloc in some standard system > install location under normal circumstances it couldn't just disappear for > a different example. > > I configured in an interactive shell, so on a compute node. I tried to 'make ex56' on a login node, as usual. So I

Re: [petsc-users] configure error on Titan with Intel

> On May 11, 2015, at 6:55 PM, Mark Adams wrote: > > More Titan fun. I have built for PGI on Titan but tests are failing to > build: -lhwloc? Mark, What test is this? Did "make tests" run correctly? How did you run this thing below, remember if you cut and paste everything including wh

Re: [petsc-users] configure error on Titan with Intel

On Mon, May 11, 2015 at 7:35 PM, Mark Adams wrote: > I did a fresh build again. No luck. Is this how I turn it off? > > '--download-hwloc=0', > --with-hwloc=0 Matt > On Mon, May 11, 2015 at 5:14 PM, Matthew Knepley > wrote: > >> On Mon, May 11, 2015 at 7:06 PM, Mark Adams wrote: >> >>

Re: [petsc-users] configure error on Titan with Intel

I did a fresh build again. No luck. Is this how I turn it off? '--download-hwloc=0', On Mon, May 11, 2015 at 5:14 PM, Matthew Knepley wrote: > On Mon, May 11, 2015 at 7:06 PM, Mark Adams wrote: > >> I think I did a super clean build... I will try again. >> > > I did not look at the confi

Re: [petsc-users] configure error on Titan with Intel

On Mon, May 11, 2015 at 7:06 PM, Mark Adams wrote: > I think I did a super clean build... I will try again. > I did not look at the configure.log. If this is master, it should not download hwloc automatically. If its not, turn it off. Matt > On Mon, May 11, 2015 at 5:04 PM, Matthew Kneple

Re: [petsc-users] configure error on Titan with Intel

I think I did a super clean build... I will try again. On Mon, May 11, 2015 at 5:04 PM, Matthew Knepley wrote: > On Mon, May 11, 2015 at 6:55 PM, Mark Adams wrote: > >> More Titan fun. I have built for PGI on Titan but tests are failing to >> build: -lhwloc? >> >> cc -mp -fast -o ex56 ex56.o

Re: [petsc-users] configure error on Titan with Intel

On Mon, May 11, 2015 at 6:55 PM, Mark Adams wrote: > More Titan fun. I have built for PGI on Titan but tests are failing to > build: -lhwloc? > > cc -mp -fast -o ex56 ex56.o > -L/autofs/na3_home1/adams/petsc_master_opt64idx_pgi/lib -lpetsc > -Wl,-rpath,/opt/pgi/14.2.0/linux86/5.1/lib > -L/opt/

Re: [petsc-users] configure error on Titan with Intel

On Fri, May 8, 2015 at 3:17 PM, Satish Balay wrote: > >> > Executing: cc -c -o /tmp/petsc-8S0Qxp/config.setCompilers/conftest.o > -I/tmp/petsc-8S0Qxp/config.setCompilers > /tmp/petsc-8S0Qxp/config.setCompilers/conftest.c > > Executing: cc -o /tmp/petsc-8S0Qxp/config.setCompilers/conftest >

Re: [petsc-users] configure error on Titan with Intel

Satish Balay writes: > Also - Perhaps with intel compilers - the recommended blas is > something other than ACML? [like MKL?]. Something to check.. MKL (and anything built using the Intel compiler) has the "run slower on AMD" feature. For any given operation, ACML won't necessarily be faster, b

Re: [petsc-users] configure error on Titan with Intel

>> Executing: cc -c -o /tmp/petsc-8S0Qxp/config.setCompilers/conftest.o -I/tmp/petsc-8S0Qxp/config.setCompilers /tmp/petsc-8S0Qxp/config.setCompilers/conftest.c Executing: cc -o /tmp/petsc-8S0Qxp/config.setCompilers/conftest /tmp/petsc-8S0Qxp/config.setCompilers/conftest.o -lstdc++ Ex

Re: [petsc-users] configure error on Titan with Intel

On Fri, 8 May 2015, David Trebotich wrote: > This has all come up because I cannot build Chombo-crunch using gnu > prgenv---cannot find mkl anymore. If this is a PETSc issue - send us logs - and I can look at it. With gnu compilers one can use gfortran compiled blas/lapack [MKL should also work

Re: [petsc-users] configure error on Titan with Intel

I added the LD path stuff and that seems to have fixed this problem ... but there are still problems. On Fri, May 8, 2015 at 1:23 PM, David Trebotich wrote: > This has all come up because I cannot build Chombo-crunch using gnu > prgenv---cannot find mkl anymore. So olcf consultants advised Inte

Re: [petsc-users] configure error on Titan with Intel

This has all come up because I cannot build Chombo-crunch using gnu prgenv---cannot find mkl anymore. So olcf consultants advised Intel prgenv. I am not sure yet what form of libs are used, that is mkl, blas, I don't know. David Trebotich sent from mobile (510) 384-6868 On May 8, 2015 9:22 AM, "

Re: [petsc-users] configure error on Titan with Intel

On Fri, 8 May 2015, Ed D'Azevedo wrote: > Is petsc using ACML specific routines? > If not, perhaps MKL provides the lapack/blas and ACML is not needed? > > Just a thought. yup PETSc can use whatever blas/lapck user provides. In this case PETSc was not seeking acml - but the 'module' env was pre

Re: [petsc-users] configure error on Titan with Intel

Also - Perhaps with intel compilers - the recommended blas is something other than ACML? [like MKL?]. Something to check.. Satish On Fri, 8 May 2015, Satish Balay wrote: > On Fri, 8 May 2015, Mark Adams wrote: > > > ACML seems to be there and Ed D'Azevedo gave me a module load script that I > >

Re: [petsc-users] configure error on Titan with Intel

Is petsc using ACML specific routines? If not, perhaps MKL provides the lapack/blas and ACML is not needed? Just a thought. Ed On 05/08/2015 12:03 PM, Mark Adams wrote: ACML seems to be there and Ed D'Azevedo gave me a module load script that I tried. I see: /usr/bin/ld: cannot find -lpets

Re: [petsc-users] configure error on Titan with Intel

On Fri, 8 May 2015, Mark Adams wrote: > ACML seems to be there and Ed D'Azevedo gave me a module load script that I > tried. I see: > > /usr/bin/ld: cannot find -lpetsc-ufod4vtr9mqHvKIQiVAm This is expected behavior [this test is checking for broken compilers that don't give errors here..] Sat

Re: [petsc-users] configure error on Titan with Intel

ACML seems to be there and Ed D'Azevedo gave me a module load script that I tried. I see: /usr/bin/ld: cannot find -lpetsc-ufod4vtr9mqHvKIQiVAm And I also still get the failure to find libacml.so I will try your LD_LIBRARY_PATH suggestion. On Fri, May 8, 2015 at 11:46 AM, Satish Balay wrote:

Re: [petsc-users] configure error on Titan with Intel

On Fri, 8 May 2015, Mark Adams wrote: > I am getting this error on Titan with Intel programming env. > > I run this from an interactive batch shell to avoid the batch business. > > This workflow seemed to work for pgi & gnu programming envs. > > Any ideas? > ERROR while running executable:

[petsc-users] configure error on Titan with Intel

I am getting this error on Titan with Intel programming env. I run this from an interactive batch shell to avoid the batch business. This workflow seemed to work for pgi & gnu programming envs. Any ideas? Thanks, Mark configure.log Description: Binary data

Re: [petsc-users] configure error

Remove the entire arch-eos-opt-intel directory and start again. If something fails then email configure.log immediately, do not fiddle around trying other things. Barry Somehow the previously build library is not correct. ipo: warning #11060: /autofs/na3_home1/adams/petsc_public/arch-

Re: [petsc-users] configure error

On Wed, Dec 10, 2014 at 4:32 PM, Mark Adams wrote: > > This is the error: Executing: cc -o /tmp/petsc-uxG_YZ/config.libraries/conftest-wd1572 -fast -openmp -traceback /tmp/petsc-uxG_YZ/config.libraries/conftest.o -Wl,-rpath,/autofs/na3_home1/adams/petsc_public/arch-eos-opt-intel/lib64 -L/a

[petsc-users] configure error with netcdf

>On Sep 9, 2012, at 12:02 PM, Satish Balay wrote: >> On Sun, 9 Sep 2012, Barry Smith wrote: > > >> > >> >On Sep 9, 2012, at 7:55 AM, Matthew Knepley wrote: >>> >>> >On Sun, Sep 9, 2012 at 12:31 AM, Satish Balay wrote: > ncgentab.c:(.text+0x1e2): undefined reference to `yyunput' >> > >> >

[petsc-users] configure error with netcdf

On Sep 9, 2012, at 12:02 PM, Satish Balay wrote: > On Sun, 9 Sep 2012, Barry Smith wrote: > >> >> On Sep 9, 2012, at 7:55 AM, Matthew Knepley wrote: >> >>> On Sun, Sep 9, 2012 at 12:31 AM, Satish Balay wrote: ncgentab.c:(.text+0x1e2): undefined reference to `yyunput' >> >> Satish, >

[petsc-users] configure error with netcdf

On Sun, 9 Sep 2012, Barry Smith wrote: > > On Sep 9, 2012, at 7:55 AM, Matthew Knepley wrote: > > > On Sun, Sep 9, 2012 at 12:31 AM, Satish Balay wrote: > > > ncgentab.c:(.text+0x1e2): undefined reference to `yyunput' > >Satish, > > Weird undefined symbols like yyunput are always a res

[petsc-users] configure error with netcdf

On Sep 9, 2012, at 7:55 AM, Matthew Knepley wrote: > On Sun, Sep 9, 2012 at 12:31 AM, Satish Balay wrote: > > ncgentab.c:(.text+0x1e2): undefined reference to `yyunput' Satish, Weird undefined symbols like yyunput are always a result of flex issues. Could you please make the same c

[petsc-users] configure error with netcdf

On Sun, Sep 9, 2012 at 12:31 AM, Satish Balay wrote: > > ncgentab.c:(.text+0x1e2): undefined reference to `yyunput' > > I don't know whats going on here. I don't see lex/flex invoked. > lex is invoked right above. Barry did not paste it. > Perhaps you can try the attached patch and see if it w

[petsc-users] configure error with netcdf

> ncgentab.c:(.text+0x1e2): undefined reference to `yyunput' I don't know whats going on here. I don't see lex/flex invoked. Perhaps you can try the attached patch and see if it works. Its attempting to use the latest netcdf tarball. cd config/BuidSystem patch -Np1 < netcdf.patch Matt - If the

[petsc-users] configure error with netcdf

Thank you Matt. I added MPI shared libraries to my LD_LIBRARY_PATH. The error disappeared. But other errors happened. Please find the attached files! -- Original -- From: "knepley"; Date: Sat, Sep 8, 2012 12:30 PM To: "fdkong"; Cc: "petsc-users"; Subj

[petsc-users] configure error with netcdf

This is likely the same flex problem you say with ptscotch: ncgen.l:142: warning: passing argument 1 of ?ncgerror? discards qualifiers from pointer target type ncgentab.o: In function `ignore': ncgentab.c:(.text+0x1e2): undefined reference to `yyunput' collect2: ld returned 1 exit status ma

[petsc-users] configure error with netcdf

>> Hi all, >> >> There are anyone who know how to install netcdf with cross compile? I >> configured petsc with netcdf, but got error below: >> >Send externalpackages./netcdf*/config.log > Thanks, > Matt I attached the file config.log. >> >> >===

[petsc-users] configure error with netcdf

Hi all, There are anyone who know how to install netcdf with cross compile? I configured petsc with netcdf, but got error below: === Configuring PETSc to compile on your system ===

[petsc-users] configure error with netcdf

On Fri, Sep 7, 2012 at 11:28 PM, fdkong wrote: > >> Hi all, > >> > >> There are anyone who know how to install netcdf with cross compile? I > >> configured petsc with netcdf, but got error below: > >> > > >Send externalpackages./netcdf*/config.log > > > Thanks, > > > Matt > > I attached the fil

[petsc-users] configure error with netcdf

On Fri, Sep 7, 2012 at 6:41 PM, fdkong wrote: > Hi all, > > There are anyone who know how to install netcdf with cross compile? I > configured petsc with netcdf, but got error below: > Send externalpackages./netcdf*/config.log Thanks, Matt > > ==

[petsc-users] Configure error

I solve the configure problem, I just post what I did for future reference. I re-installed Win SDK 7.0 and MSVC 2008 Express. I added the variable LIB C:\Program Files\Microsoft SDKs\Windows\v7.0\Lib;C:\Program Files\Microsoft SDKs\Windows\v7.0\Lib\x86 to the system and user environmental variabl

[petsc-users] Configure error

A simple test.cpp complains about kernel32.lib. My bad, I didn't mean to waste your time. Can I add all the linker option in --with-cc='win32fe cl all-options-VC-need' or I should do it some other way? Fabio 2012/8/10 Matthew Knepley : > On Fri, Aug 10, 2012 at 10:34 AM, Fabio wrote: >> >> 2012/

[petsc-users] Configure error

2012/8/10 Satish Balay : > Executing: /cygdrive/d/Workspace/PETSc/petsc-3.3-p2/bin/win32fe/win32fe cl > -o /tmp/petsc-_yEt5c/config.setCompilers/conftest.exe > /tmp/petsc-_yEt5c/config.setCompilers/conftest.o > sh: LINK : fatal error LNK1104: cannot open file 'kernel32.lib'^M > <<< > > O

[petsc-users] Configure error

Without using the wiht-mpi-dir option the code start testing but it stops saying the "C compiler associated with mpi-cc win32fe cl does not work" (configure.log is its log) If I use a link to another directory without space in the name I get the same error (provided that the link has been done in

[petsc-users] Configure error

I updated to the last version of Petsc then I used again PETSC_DIR=`pwd`; export PETSC_DIR then in the petsc directory ./configure --with-cc='win32fe cl' --with-fc=0 --download-f2cblas-lapack --with-mpi-dir=/cygdrive/c/Program\ Files\ \(x86\)/MPICH2 Now I have an error, "Nonexistent directory /c

[petsc-users] Configure error

On Fri, 10 Aug 2012, Fabio wrote: > A simple test.cpp complains about kernel32.lib. My bad, I didn't mean > to waste your time. > Can I add all the linker option in --with-cc='win32fe cl > all-options-VC-need' or I should do it some other way? Perhaps you need to reinstall your compiler. Satish

[petsc-users] Configure error

On Fri, 10 Aug 2012, Fabio wrote: > 2012/8/10 Satish Balay : > > > Executing: /cygdrive/d/Workspace/PETSc/petsc-3.3-p2/bin/win32fe/win32fe cl > > -o /tmp/petsc-_yEt5c/config.setCompilers/conftest.exe > > /tmp/petsc-_yEt5c/config.setCompilers/conftest.o > > sh: LINK : fatal error LNK1104

[petsc-users] Configure error

On Fri, Aug 10, 2012 at 10:34 AM, Fabio wrote: > 2012/8/10 Satish Balay : > > > Executing: /cygdrive/d/Workspace/PETSc/petsc-3.3-p2/bin/win32fe/win32fe > cl -o /tmp/petsc-_yEt5c/config.setCompilers/conftest.exe > /tmp/petsc-_yEt5c/config.setCompilers/conftest.o > > sh: LINK : fatal error L

[petsc-users] Configure error

>>> Executing: /cygdrive/d/Workspace/PETSc/petsc-3.3-p2/bin/win32fe/win32fe cl -o /tmp/petsc-_yEt5c/config.setCompilers/conftest.exe /tmp/petsc-_yEt5c/config.setCompilers/conftest.o sh: LINK : fatal error LNK1104: cannot open file 'kernel32.lib'^M <<< Ok configure failing with compiler check

[petsc-users] Configure error

On Fri, 10 Aug 2012, Fabio wrote: > I updated to the last version of Petsc then I used again > > PETSC_DIR=`pwd`; export PETSC_DIR > > then in the petsc directory > ./configure --with-cc='win32fe cl' --with-fc=0 > --download-f2cblas-lapack --with-mpi-dir=/cygdrive/c/Program\ Files\ > \(x86\)/MPI

[petsc-users] Configure error

On Fri, Aug 10, 2012 at 7:24 AM, Fabio wrote: > I updated to the last version of Petsc then I used again > > PETSC_DIR=`pwd`; export PETSC_DIR > > then in the petsc directory > ./configure --with-cc='win32fe cl' --with-fc=0 > --download-f2cblas-lapack --with-mpi-dir=/cygdrive/c/Program\ Files\ >

  1   2   >