search

marekandreas / elpa

A scalable eigensolver for dense, symmetric (hermitian) matrices (fork of https://gitlab.mpcdf.mpg.de/elpa/elpa.git)
Other
27 stars 13 forks source link

Error in executing copy_double_complex_a_tmatc_kernel #35

Closed toxa81 closed 1 year ago

toxa81 commented 1 year ago

Dear @marekandreas ! I'm running latest release of ELPA on GPUs and I'm getting this error message

Error in executing copy_double_complex_a_tmatc_kernel: invalid configuration argument

However it seems to be harmless as the calculation runs fine and all the data seems to be properly copied. This happens on 4x4 and 2x2 BLACS grids and different matrix sizes.

With kind regards, Anton.

marekandreas commented 1 year ago

Dear @toxa81, can you please provide your configure command line?

toxa81 commented 1 year ago

Hi @marekandreas I'm not using command line; I'm installing ELPA via spack. The 'spec' is quite simple: elpa@gcc+cuda. Here is the full spec

elpa@2022.11.001%gcc@11.3.0~autotune+cuda+mpi+openmp~rocm build_system=autotools cuda_arch=60 arch=linux-ubuntu22.04-broadwell
    ^cuda@11.8.0%gcc@11.3.0~allow-unsupported-compilers~dev build_system=generic arch=linux-ubuntu22.04-broadwell
        ^libxml2@2.10.3%gcc@11.3.0~python build_system=autotools arch=linux-ubuntu22.04-broadwell
            ^libiconv@1.17%gcc@11.3.0 build_system=autotools libs=shared,static arch=linux-ubuntu22.04-broadwell
            ^xz@5.2.5%gcc@11.3.0~pic build_system=autotools libs=shared,static arch=linux-ubuntu22.04-broadwell
            ^zlib@1.2.13%gcc@11.3.0+optimize+pic+shared build_system=makefile arch=linux-ubuntu22.04-broadwell
    ^intel-oneapi-mkl@2023.0.0%gcc@11.3.0+cluster+envmods~ilp64+shared build_system=generic arch=linux-ubuntu22.04-broadwell
        ^intel-oneapi-tbb@2021.8.0%gcc@11.3.0+envmods build_system=generic arch=linux-ubuntu22.04-broadwell
    ^libtool@2.4.7%gcc@11.3.0 build_system=autotools arch=linux-ubuntu22.04-broadwell
        ^m4@1.4.18%gcc@11.3.0+sigsegv build_system=autotools patches=3877ab5,fc9b616 arch=linux-ubuntu22.04-broadwell
    ^mpich@3.4.3%gcc@11.3.0~argobots~cuda+fortran+hwloc+hydra+libxml2+pci~rocm+romio~slurm~two_level_namespace~verbs+wrapperrpath build_system=autotools datatype-engine=auto device=ch4 netmod=ofi patches=7326028 pmi=pmi arch=linux-ubuntu22.04-broadwell
        ^findutils@4.8.0%gcc@11.3.0 build_system=autotools patches=440b954 arch=linux-ubuntu22.04-broadwell
        ^hwloc@2.9.0%gcc@11.3.0~cairo~cuda~gl~libudev+libxml2~netloc~nvml~oneapi-level-zero~opencl+pci~rocm build_system=autotools libs=shared,static arch=linux-ubuntu22.04-broadwell
            ^ncurses@6.4%gcc@11.3.0~symlinks+termlib abi=none build_system=autotools arch=linux-ubuntu22.04-broadwell
        ^libfabric@1.16.1%gcc@11.3.0~debug~kdreg build_system=autotools fabrics=sockets,tcp,udp arch=linux-ubuntu22.04-broadwell
        ^libpciaccess@0.17%gcc@11.3.0 build_system=autotools arch=linux-ubuntu22.04-broadwell
            ^util-macros@1.19.3%gcc@11.3.0 build_system=autotools arch=linux-ubuntu22.04-broadwell
        ^pkg-config@0.29.2%gcc@11.3.0+internal_glib build_system=autotools arch=linux-ubuntu22.04-broadwell
    ^python@3.10.6%gcc@11.3.0+bz2+crypt+ctypes+dbm~debug+libxml2+lzma+nis~optimizations+pic+pyexpat~pythoncmd+readline+shared+sqlite3+ssl~tkinter+uuid+zlib build_system=generic patches=0d98e93,7d40923,f2fd060 arch=linux-ubuntu22.04-broadwell
marekandreas commented 1 year ago

Hello @toxa81 ,

with the new release candidate the problem should be fixed.