elpa issueshttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues2017-08-31T10:24:59Zhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/60No GPU complex GPU version in elpa2_bandred2017-08-31T10:24:59ZAndreas MarekNo GPU complex GPU version in elpa2_bandredhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/59add scalapack test to gitlab CI2018-01-07T10:01:37ZPavel Kusadd scalapack test to gitlab CIThe scalapack tests are built only when --enable-scalapack-tests option is used with configure. We should test it in gitlab CI as well, but MKL 11.3 is strangely failing on buildtest. The problem seems to disappear when switching to MKL ...The scalapack tests are built only when --enable-scalapack-tests option is used with configure. We should test it in gitlab CI as well, but MKL 11.3 is strangely failing on buildtest. The problem seems to disappear when switching to MKL 2017 (even though it works on Hydra for both 11.3 and 2017). So we should return this test when we switch to MKL 2017 on buildtest.Pavel KusPavel Kushttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/58Port routines used in generalized eigenvalue problem to GPU2017-08-24T08:23:09ZPavel KusPort routines used in generalized eigenvalue problem to GPUPavel KusPavel Kushttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/57Missing: test_project for a C-code2018-01-07T10:24:24ZAndreas MarekMissing: test_project for a C-codeAnalogous to the already existing test projects, there should be some for a C program.Analogous to the already existing test projects, there should be some for a C program.Pavel KusPavel Kushttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/56Problem with ancient Ubuntu/Debian "mawk"2017-08-23T06:30:30ZLorenz HuedepohlProblem with ancient Ubuntu/Debian "mawk"Pavel discovered that on Ubuntu the system default awk is an 1996 "mawk" that does not properly understand `[[^,]]` constructions in a regex, which leads to errors in the generated `elpa/elpa_constants.h` filePavel discovered that on Ubuntu the system default awk is an 1996 "mawk" that does not properly understand `[[^,]]` constructions in a regex, which leads to errors in the generated `elpa/elpa_constants.h` fileLorenz HuedepohlLorenz Huedepohlhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/55PGI fortran has trouble with elpa_int_value_to_string()2017-07-14T13:33:45ZLorenz HuedepohlPGI fortran has trouble with elpa_int_value_to_string()It seems that the PGI compiler has problems with `elpa_int_value_to_string()`. The output of `elpa2_print_kernels` is consisting just of newlines:
```
[loh@miy01 build]$ ./elpa2_print_kernels
This program will give information on the ...It seems that the PGI compiler has problems with `elpa_int_value_to_string()`. The output of `elpa2_print_kernels` is consisting just of newlines:
```
[loh@miy01 build]$ ./elpa2_print_kernels
This program will give information on the ELPA2 kernels,
which are available with this library and it will give
information if (and how) the kernels can be choosen at
runtime
ELPA supports threads: no
Information on ELPA2 real case:
===============================
choice via environment variable: yes
environment variable name : ELPA_2STAGE_REAL_KERNEL
Available real kernels are:
Information on ELPA2 complex case:
===============================
choice via environment variable: yes
environment variable name : ELPA_2STAGE_COMPLEX_KERNEL
Available complex kernels are:
```Lorenz HuedepohlLorenz Huedepohlhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/54Trouble compiling ELPA with Intel 2018b2017-07-07T14:39:29ZLorenz HuedepohlTrouble compiling ELPA with Intel 2018bA user reported a problem compiling `elpa-2017.05.001.rc1` with the Intel 2018 Beta compiler, attached is his error message.
```
[KNL]$make
make all-am
make[1]: Entering directory `/home/elpauser/PCP/qe-6.1/qe-6.1_compilers_and_li...A user reported a problem compiling `elpa-2017.05.001.rc1` with the Intel 2018 Beta compiler, attached is his error message.
```
[KNL]$make
make all-am
make[1]: Entering directory `/home/elpauser/PCP/qe-6.1/qe-6.1_compilers_and_libraries_2018.0.061_VEC_xMIC-AVX512/elpa-2017.05.001.rc1-build_compilers_and_libraries_2018.0.061'
PPFC src/libelpa_onenode_openmp_private_la-elpa_impl.lo
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_SET_INTEGER]
manually_preprocessed__home_elpauser_PCP_qe-6.1_package_elpa-2017.05.001.rc1_src_elpa_impl.F90-src_.libs_libelpa_onenode_openmp_private_la-elpa_impl.o.F90(71): error #6136: Derived-type declared must be ABSTRACT [ELPA_IMPL_T]
type, extends(elpa_abstract_impl_t) :: elpa_impl_t
-----------------------------------------^
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_SET_DOUBLE]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_GET_INTEGER]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_GET_DOUBLE]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVECTORS_D]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVECTORS_F]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVECTORS_DC]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVECTORS_FC]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVALUES_D]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVALUES_F]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVALUES_DC]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_EIGENVALUES_FC]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_HERMITIAN_MULTIPLY_D]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_HERMITIAN_MULTIPLY_F]
/tmp/ifortTnMEgA.i90: error #8322: A deferred binding is inherited by non-abstract type; It must be overridden. [ELPA_HERMITIAN_MULTIPLY_DC]
/tmp/ifortTnMEgA.i90(1615): catastrophic error: Too many errors, exiting
compilation aborted for manually_preprocessed__home_elpauser_PCP_qe-6.1_package_elpa-2017.05.001.rc1_src_elpa_impl.F90-src_.libs_libelpa_onenode_openmp_private_la-elpa_impl.o.F90 (code 1)
Traceback (most recent call last):
File "/home/elpauser/PCP/qe-6.1/package/elpa-2017.05.001.rc1/manual_cpp", line 56, in <module>
check_call(args + [tmp_filename])
File "/home/elpauser/PCP/qe-6.1/package/elpa-2017.05.001.rc1/manual_cpp", line 16, in check_call
return subprocess.check_call(args, **kwargs)
File "/usr/lib64/python2.7/subprocess.py", line 542, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['mpiifort', '-DHAVE_CONFIG_H', '-I.', '-I/home/elpauser/PCP/qe-6.1/package/elpa-2017.05.001.rc1', '-L/opt/intel/compilers_and_libraries_2018.0.061/linux/mkl/lib/intel64', '-lmkl_scalapack_lp64', '-lmkl_intel_lp64',
'-lmkl_sequential', '-lmkl_core', '-lmkl_blacs_intelmpi_lp64', '-lpthread', '-I/opt/intel/compilers_and_libraries_2018.0.061/linux/mkl/include/intel64/lp64', '-Imodules', '-mod', 'private_modules', '-Iprivate_modules', '-fopenmp', '-g', '-c', '-fPIC', '-o',
'src/.libs/libelpa_onenode_openmp_private_la-elpa_impl.o', 'manually_preprocessed__home_elpauser_PCP_qe-6.1_package_elpa-2017.05.001.rc1_src_elpa_impl.F90-src_.libs_libelpa_onenode_openmp_private_la-elpa_impl.o.F90']' returned non-zero exit status 1
make[1]: *** [src/libelpa_onenode_openmp_private_la-elpa_impl.lo] Error 1
make[1]: Leaving directory `/home/elpauser/PCP/qe-6.1/qe-6.1_compilers_and_libraries_2018.0.061_VEC_xMIC-AVX512/elpa-2017.05.001.rc1-build_compilers_and_libraries_2018.0.061'
make: *** [all] Error 2
```Lorenz HuedepohlLorenz Huedepohlhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/53Investigate stripe_width issues for AVX512 kernels2017-09-06T19:06:07ZLorenz HuedepohlInvestigate stripe_width issues for AVX512 kernelsSee commit 565de5dSee commit 565de5dhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/52Dependencies for X90 files2017-08-24T11:58:02ZAndreas MarekDependencies for X90 filesIt would be nice to have makefile dependencies on the X90 filesIt would be nice to have makefile dependencies on the X90 filesLorenz HuedepohlLorenz Huedepohlhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/51complex gpu call in openmp region in elpa2_trans_ev_tridi_to_band_template.X902017-09-12T05:47:39ZAndreas Marekcomplex gpu call in openmp region in elpa2_trans_ev_tridi_to_band_template.X90https://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/50stripe_width in trans_ev_tridi_to_band2017-09-06T19:06:07ZAndreas Marekstripe_width in trans_ev_tridi_to_bandhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/49cleanup of THIS_REAL/COMPLEX_KERNEL2017-05-21T22:14:18ZAndreas Marekcleanup of THIS_REAL/COMPLEX_KERNELhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/48cleanup of size_of_PRECISION_real/complex2017-05-21T22:14:18ZAndreas Marekcleanup of size_of_PRECISION_real/complexhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/47check trans_ev_band_to_full row_group2017-09-05T16:56:15ZAndreas Marekcheck trans_ev_band_to_full row_grouphttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/46Check complex stripe_width factor of 22017-05-21T22:14:18ZAndreas MarekCheck complex stripe_width factor of 2https://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/45unify real/complex QR paths2017-07-16T17:31:50ZAndreas Marekunify real/complex QR pathshttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/44Tunable blocking in band_to_full2017-09-03T18:04:30ZAndreas MarekTunable blocking in band_to_fullAllow run-time choices whether blocking should be used, and which blocking parameters are optimalAllow run-time choices whether blocking should be used, and which blocking parameters are optimalhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/43Unify GPU path for real/complex version in band_to_full2017-08-28T20:00:37ZAndreas MarekUnify GPU path for real/complex version in band_to_fullBoth cases are handled slightly necessary. Confirm whether this is necessary or is just legacyBoth cases are handled slightly necessary. Confirm whether this is necessary or is just legacyhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/42Code divergence of real/complex CPU part in trans_ev_band_to_full2017-05-21T22:14:18ZAndreas MarekCode divergence of real/complex CPU part in trans_ev_band_to_fullThe real/complex CPU parts of trans_ev_band_to_full diverged:
The real code path uses blocking, the complex part does not!
To do:
- make blocking in real part an OPTION, i.e. a fall back to same code path as the complex version shoul...The real/complex CPU parts of trans_ev_band_to_full diverged:
The real code path uses blocking, the complex part does not!
To do:
- make blocking in real part an OPTION, i.e. a fall back to same code path as the complex version should be possible
- implement blocking for complex part also OPTIONAL.
In this way, we retain better tuning options for different architectureshttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/41Cleanup of trans_ev_tridi_to_band2017-05-21T22:14:18ZAndreas MarekCleanup of trans_ev_tridi_to_bandThe real/complex case have been unified in one file. Still some cleanup is necessary.The real/complex case have been unified in one file. Still some cleanup is necessary.