elpa merge requestshttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests2017-03-26T17:49:38Zhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/4Unify GPU/CPU compute_hh_trafo2017-03-26T17:49:38ZAndreas MarekUnify GPU/CPU compute_hh_trafoAndreas MarekAndreas Marekhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/5Loh/spectest2017-05-26T06:09:03ZLorenz HuedepohlLoh/spectestSpec file is now ready, but please have a look at the warnings in the build logs at https://build.opensuse.org/package/show/home:lorenz:ELPA/elpa_unstableSpec file is now ready, but please have a look at the warnings in the build logs at https://build.opensuse.org/package/show/home:lorenz:ELPA/elpa_unstablehttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/6Fix some typos in the documentation and examples2018-02-22T11:52:52ZSebastian OhlmannFix some typos in the documentation and exampleshttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/7Fix automake to include headers for generalized solver2018-11-08T20:21:03ZSebastian OhlmannFix automake to include headers for generalized solverprecision_typedefs.h is needed by the generalized methods, but only included when built with MPI. Thus the normal distcheck does not catch this.
This MR adds precision_typedefs.h to Makefile.am and adds a distcheck test with MPIprecision_typedefs.h is needed by the generalized methods, but only included when built with MPI. Thus the normal distcheck does not catch this.
This MR adds precision_typedefs.h to Makefile.am and adds a distcheck test with MPIhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/8Add python interface for ELPA2018-11-14T20:42:10ZSebastian OhlmannAdd python interface for ELPAThe ELPA C API is wrapped by cython code that can be called from python. Python classes for convenience access are provided. Tests are included and activated in CI.
The interface is built when --enable-python is given to configure. The ...The ELPA C API is wrapped by cython code that can be called from python. Python classes for convenience access are provided. Tests are included and activated in CI.
The interface is built when --enable-python is given to configure. The requirements then are then python, numpy, mpi4py, cython. The tests can be enabled with --enable-python-tests; then, an additional requirement is pytest.
Currently, the interface is only tested with the MPI version of ELPA.https://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/9Fix problem in elpa2_print_kernels with GPU kernel2019-01-06T08:04:58ZAndreas MarekFix problem in elpa2_print_kernels with GPU kernelThe GPU kernel can only be set, if e%set("use_gpu",1) has been set
before and GPU usage was thus requested.
In the elpa2_print_kernels, this was not reflected, and the GPU kernels
were checked via can_set method without activating G...The GPU kernel can only be set, if e%set("use_gpu",1) has been set
before and GPU usage was thus requested.
In the elpa2_print_kernels, this was not reflected, and the GPU kernels
were checked via can_set method without activating GPU usage
=> GPU kernels were always reported as non exisitentAndreas MarekAndreas Marekhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/10loh/fix elpa index2019-02-05T13:36:23ZLorenz Huedepohlloh/fix elpa indexFix bug in elpa_index.c as discovered during to the porting onto the NEC vector cardFix bug in elpa_index.c as discovered during to the porting onto the NEC vector cardAndreas MarekAndreas Marekhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/11loh/python3 compat2019-04-16T08:06:14ZLorenz Huedepohlloh/python3 compatSimple fix for python 3 in "remove_xcompiler" wrapper script.
Based on "loh/fix_elpa_index" which also should be merged at some point...Simple fix for python 3 in "remove_xcompiler" wrapper script.
Based on "loh/fix_elpa_index" which also should be merged at some point...Andreas MarekAndreas Marekhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/12Fix omp2019-04-24T08:13:23ZAndreas MarekFix omphttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/13Pkus/devel2019-05-03T05:38:36ZPavel KusPkus/devel2 changes in the elpa_index2 changes in the elpa_indexhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/14improving forgotten precision macros2019-05-08T12:39:27ZPavel Kusimproving forgotten precision macrosmaster_pre_stage (even though it did not solve the issue)master_pre_stage (even though it did not solve the issue)https://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/15adding test which splits communicator at the beginning2019-05-08T12:40:39ZPavel Kusadding test which splits communicator at the beginningand runs several elpas (still mpi-based) in parallel. Each elpa
"instance" then splits its communicator to row and column communicator,
as it is always done. This is actually often done in FHI-aims and was
previously leading to issues wh...and runs several elpas (still mpi-based) in parallel. Each elpa
"instance" then splits its communicator to row and column communicator,
as it is always done. This is actually often done in FHI-aims and was
previously leading to issues when using OmniPath. Hopefully was solved
by Intel MPI 2019.3. Keeping the test for future reference.https://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/16Likwid2019-05-23T12:16:59ZPavel KusLikwidHi Andi,
please look into the commit "replacing two instances of AC_RUN_IFELSE" whether you are OK with thatHi Andi,
please look into the commit "replacing two instances of AC_RUN_IFELSE" whether you are OK with thathttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/18Neon2019-06-21T05:42:10ZAndreas MarekNeonAndreas MarekAndreas Marekhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/19New fix2019-06-26T05:57:48ZAndreas MarekNew fixhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/20Auto detect2019-10-11T05:47:35ZAndreas MarekAuto detecthttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/21Seperate the variable type definition of the library and the test programs2019-10-11T15:54:28ZAndreas MarekSeperate the variable type definition of the library and the test programsAndreas MarekAndreas Marekhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/22Add support for NVTX profiling2019-10-23T10:03:12ZSebastian OhlmannAdd support for NVTX profilingWhen profiling the GPU version, NVTX can be used to highlight the corresponding regions of the code in the timeline of the profiling tool (nvvp or nsight systems). This is very useful to correlate what happens on the GPU with what part o...When profiling the GPU version, NVTX can be used to highlight the corresponding regions of the code in the timeline of the profiling tool (nvvp or nsight systems). This is very useful to correlate what happens on the GPU with what part of the code we are in.
Currently, the regions are only defined in the elpa1 solver.https://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/23Long int scalapack2019-10-26T14:18:02ZAndreas MarekLong int scalapackAndreas MarekAndreas Marekhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/merge_requests/24Gitlab CI: Test for 64bit blas and 32bit MPI2019-10-30T06:01:56ZAndreas MarekGitlab CI: Test for 64bit blas and 32bit MPIAndreas MarekAndreas Marek