- 05 Nov, 2015 3 commits
-
-
Andreas Marek authored
-
Andreas Marek authored
Point more clearly to the usage of ELPA under the terms of the LGPL.
-
Andreas Marek authored
-
- 04 Nov, 2015 1 commit
-
-
Andreas Marek authored
Intel (thanks, especially A.Heinecke from Intel) there exists an optimized version of ELPA with AVX2 support. This merge includes all the optimizations done by Intel plus some smaller changes which were necessary to incorperate these modifications.
-
- 03 Nov, 2015 2 commits
-
-
Andreas Marek authored
A build without autotools is not officially supported anymore. Thus this --- broken since long time --- Makefile.example is removed
-
Andreas Marek authored
The examples, how to invoke ELPA from a c program have been updated. There are now examples for ELPA1 and ELPA2 both real and complex case. The test cases are still with less functionality than their Fortran counter parts, they are just ment as a "proof-of-concept".
-
- 28 Oct, 2015 1 commit
-
-
Alexander Heinecke authored
- enabling fusing iterations of stage 5 in ELPA2 for every configuration - Changed reduction bandwidth in ELPA2 to be at least 64 - partial OpenMP parallelization of the QR factorization in bandred_real - OpenMP parallelization of SYMM - OpenMP parallelization of SYR2K in bandred_real - OpenMP parallelization for elpa1_reduce_add_vectors and elpa1_transpose_vectors - AVX2 support in backtransformation elpa2_kernels (FMA3 instructions introduced with Haswell microarchitecture)
-
- 24 Aug, 2015 1 commit
-
-
Andreas Marek authored
Inge Gutheil from FZ Juelich pointed out, that the configure test for BGQ failed due to typos. These are corrected now
-
- 16 Jun, 2015 3 commits
-
-
Andreas Marek authored
complex cases Create automatically two independent routines for real and complex valued matrices
-
Andreas Marek authored
This commit is not ABI compatible
-
Andreas Marek authored
This commit is not ABI compatible, since it changes the interfaces of some routines Also, introduce type checking for transpose and reduce_add routines
-
- 28 May, 2015 3 commits
-
-
Lorenz Huedepohl authored
These files are always automatically generated by autooconf and should not be in version control.
-
Lorenz Huedepohl authored
-
Lorenz Huedepohl authored
-
- 26 May, 2015 3 commits
-
-
Andreas Marek authored
-
Andreas Marek authored
-
Andreas Marek authored
Andreas Gloess informed us about a memory leak in ELPA, which was introduced in version 2013.11.008. This memory leak is removed now again. Note, that older versions of ELPA will not be fixed right now.
-
- 19 May, 2015 3 commits
-
-
Andreas Marek authored
-
Andreas Marek authored
An "dangling" fi has been removed
-
Andreas Marek authored
-
- 29 Apr, 2015 2 commits
-
-
Andreas Marek authored
Remove variables which are not needed (anymore)
-
Andreas Marek authored
The macros which define the functionality to test for - a specific real/complex kernel (not all available kernels) are now defined in files in the m4 directory
-
- 28 Apr, 2015 4 commits
-
-
Andreas Marek authored
-
Andreas Marek authored
-
Andreas Marek authored
-
Andreas Marek authored
Just polishing of text Signed-off-by:
Andreas Marek <amarek@rzg.mpg.de>
-
- 27 Apr, 2015 2 commits
-
-
Lorenz Huedepohl authored
There was an inconsistency when the OpenMP flag was different for the Fortran and C compiler (e.g. -openmp for ifort and -fopenmp for gcc). This led to strange errors when linking the example program with the C main() routine when using Intel Fortran, Intel MPI, and GCC together, a typical error message was /usr/bin/ld: MPIR_Thread: TLS definition in [...]/intel64/lib/libmpi_dbg_mt.so section .tbss mismatches non-TLS definition in [...]/intel64/lib/libmpi_dbg.so section .bss [...]/intel64/lib/libmpi_dbg_mt.so: could not read symbols: Bad value The reason seems to be that the various MPI wrapper shell scripts (mpicc, mpiifort) need the correct OpenMP option to select the thread-safe Intel MPI debug library. Previously, always OPENMP_FCFLAGS was appended to LDFLAGS, which did not trigger this when linking a C main program with mpicc.
-
Lorenz Huedepohl authored
Sourcecode in AC_LINK_IFELSE must now be guarded by AC_LANG_SOURCE statements.
-
- 23 Mar, 2015 3 commits
-
-
Lorenz Huedepohl authored
Just adding -maxv works on many systems which have compiler that can produce AVX code but do not necessarily have processors with AVX support.
-
Lorenz Huedepohl authored
If not, abort with an #error (this means that configure failed to detect the lack of AVX support for C++)
-
Lorenz Huedepohl authored
-
- 19 Mar, 2015 1 commit
-
-
Lorenz Huedepohl authored
The flag -mavx was not removed from C/CXXFLAGS again if AVX is unusable
-
- 18 Mar, 2015 1 commit
-
-
- provide C interface for ELPA Library - correct an error in the test case for QR-decomposition
-
- 16 Mar, 2015 5 commits
-
-
Lorenz Huedepohl authored
-
Lorenz Huedepohl authored
-
Lorenz Huedepohl authored
-
Lorenz Huedepohl authored
-
Lorenz Huedepohl authored
-
- 11 Mar, 2015 2 commits
-
-
Lorenz Huedepohl authored
Some compilers detected the static out-of-bounds condition present in the test code and refused to compile it.
-
Andreas Marek authored
C interfaces are now available and definied in the header elpa.h
-