elpa issueshttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues2017-07-14T13:33:45Zhttps://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/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/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/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.https://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/38C macros for ELPA1 auxillary2023-06-30T12:22:51ZAndreas MarekC macros for ELPA1 auxillaryPavel KusPavel Kushttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/37C macros in ELPA2 complex case missing2017-05-21T22:14:18ZAndreas MarekC macros in ELPA2 complex case missingPavel KusPavel Kushttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/36Consistent name of C macros2017-05-21T22:14:18ZAndreas MarekConsistent name of C macrosIn the real case macro names start with "M_" in the complex case not. Make this consistnentIn the real case macro names start with "M_" in the complex case not. Make this consistnentPavel KusPavel Kushttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/35cuda memcpy types2017-08-24T11:59:56ZPavel Kuscuda memcpy typeschange integer(C_SIZE_T) to normal integer in cuda memcpy wrappers.change integer(C_SIZE_T) to normal integer in cuda memcpy wrappers.Pavel KusPavel Kushttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/34ELP2 test real QR-decomposition does not work on KNL2017-05-21T22:14:18ZAndreas MarekELP2 test real QR-decomposition does not work on KNLhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/33AVX512 complex kernels do not work2017-05-21T22:14:19ZAndreas MarekAVX512 complex kernels do not workhttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/32module precision.mod is not allowed to be private2017-05-21T22:14:19ZAndreas Marekmodule precision.mod is not allowed to be privatehttps://gitlab.mpcdf.mpg.de/elpa/elpa/-/issues/31OpenMP version in branches ELPA_GPU and ELPA_KNL2017-05-21T22:14:19ZAndreas MarekOpenMP version in branches ELPA_GPU and ELPA_KNLin the branches ELPA_GPU and ELPA_KNL the openmp version is buggy: depending on the matrix and block size, the results are wrong.
The master branch does NOT show this issuesin the branches ELPA_GPU and ELPA_KNL the openmp version is buggy: depending on the matrix and block size, the results are wrong.
The master branch does NOT show this issues