fftw3/fftw3.changes

336 lines
12 KiB
Plaintext
Raw Normal View History

-------------------------------------------------------------------
Tue Oct 17 13:23:12 UTC 2017 - eich@suse.com
- Add magic to limit the number of flavors built in the
in the OBS ring.
-------------------------------------------------------------------
Sat Oct 14 17:13:06 UTC 2017 - eich@suse.com
- For HPC build package static libraries as well.
-------------------------------------------------------------------
Thu Oct 12 05:46:35 UTC 2017 - eich@suse.com
- Generate baselib.conf dynamically and only for the non-HPC
build: this avoids issues with the source validator.
-------------------------------------------------------------------
Mon Sep 25 09:36:55 UTC 2017 - cgoll@suse.com
- removed unnedded dependency packages
-------------------------------------------------------------------
Thu Sep 7 07:46:53 UTC 2017 - cgoll@suse.com
- rewrote for hpc library support
* added environment modules
* reduced number of hpc realted packages to two
-------------------------------------------------------------------
Mon Aug 1 22:03:49 UTC 2016 - mardnh@gmx.de
- update to version 3.3.5
* New SIMD support:
- Power8 VSX instructions in single and double precision.
To use, add --enable-vsx to configure.
- Support for AVX2 (256-bit FMA instructions).
To use, add --enable-avx2 to configure.
- Experimental support for AVX512 and KCVI. (--enable-avx512, --enable-kcvi)
This code is expected to work but the FFTW maintainers do not have
hardware to test it.
- Support for AVX128/FMA (for some AMD machines) (--enable-avx128-fma)
- Double precision Neon SIMD for aarch64.
This code is expected to work but the FFTW maintainers do not have
hardware to test it.
- generic SIMD support using gcc vector intrinsics
* Add fftw_make_planner_thread_safe() API
* fix #18 (disable float128 for CUDACC)
* fix #19: missing Fortran interface for fftwq_alloc_real
* fix #21 (don't use float128 on Portland compilers, which pretend to be gcc)
* fix: Avoid segfaults due to double free in MPI transpose
-------------------------------------------------------------------
Sat Apr 19 19:16:23 UTC 2014 - mardnh@gmx.de
- add support for long-double precision
-------------------------------------------------------------------
Sat Apr 19 17:37:38 UTC 2014 - mardnh@gmx.de
- update to version 3.3.4
* New functions fftw_alignment_of (to check whether two arrays are equally
aligned for the purposes of applying a plan) and fftw_sprint_plan
(to output a description of plan to a string).
* Bugfix in fftw-wisdom-to-conf; thanks to Florian Oppermann for the bug report.
* Fixed manual to work with texinfo-5.
* Increased timing interval on x86_64 to reduce timing errors.
* Default to Win32 threads, not pthreads, if both are present.
* Various build-script fixes.
- Drop obsoleted 1_man_macro.patch
-------------------------------------------------------------------
Sun Dec 16 19:26:48 UTC 2012 - dhall@wustl.edu
- update to version 3.3.3
* Fix deadlock bug in MPI transforms (thanks to Michael Pippig for the bug
report and patch, and to Graham Dennis for the bug report).
* Use 128-bit ARM NEON instructions instead of 64-bit instructions. This
change appears to speed up even ARM processors with a 64-bit NEON pipe.
* Speed improvements for single-precision AVX.
* Speed up planner on machines without "official" cycle counters, such as ARM.
-------------------------------------------------------------------
Tue Jul 3 18:31:53 UTC 2012 - coolo@suse.com
- update to 3.3.2 to fix crashes with gcc 4.7
* Removed an archaic stack-alignment hack that was failing with
gcc-4.7/i386.
* Added stack-alignment hack necessary for gcc on Windows/i386. We
will regret this in ten years (see previous change).
* Fix incompatibility with Intel icc which pretends to be gcc
but does not support quad precision.
* make libfftw{threads,mpi} depend upon libfftw when using libtool;
this is consistent with most other libraries and simplifies the life
of various distributors of GNU/Linux.
-------------------------------------------------------------------
Tue May 29 14:43:58 CEST 2012 - tiwai@suse.de
- Enable AVX support (bnc#763657)
-------------------------------------------------------------------
Thu Apr 26 04:26:02 UTC 2012 - adrian@suse.de
- fix build on %arm
* disable neon it would require --enable-single (precision)
- enable openmpi for %arm
-------------------------------------------------------------------
Fri Mar 16 01:17:58 UTC 2012 - alinm.elena@gmail.com
- source the mpi environment
-------------------------------------------------------------------
Tue Mar 6 14:16:22 UTC 2012 - dhall@wustl.edu
- delete INSTALL file
-------------------------------------------------------------------
Tue Mar 6 10:35:15 UTC 2012 - dhall@wustl.edu
- patch macros in man files
-------------------------------------------------------------------
Tue Mar 6 00:32:24 UTC 2012 - dhall@wustl.edu
- add use of neon extensions on ARM
-------------------------------------------------------------------
Tue Mar 6 00:12:32 UTC 2012 - dhall@wustl.edu
- updated to version 3.3.1
* Reduced planning time in estimate mode for sizes with large prime factors.
* Added AVX autodetection under Visual Studio. Thanks Carsten Steger for submitting
the necessary code.
* Modern Fortran interface now uses a separate fftw3l.f03 interface file for the
long double interface, which is not supported by some Fortran compilers. Provided
new fftw3q.f03 interface file to access the quadruple-precision FFTW routines
with recent versions of gcc/gfortran.
* Added support for the NEON extensions to the ARM ISA.
* MPI code now compiles even if mpicc is a C++ compiler; thanks to Kyle Spyksma for
the bug report.
-------------------------------------------------------------------
Mon Nov 28 13:33:44 UTC 2011 - idoenmez@suse.de
- Ignore rpmlint fixed dependency errors
-------------------------------------------------------------------
Mon Nov 28 01:48:17 CET 2011 - ro@suse.de
- fix build on s390/s390x without openmpi
-------------------------------------------------------------------
Mon Nov 21 17:45:00 UTC 2011 - jengelh@medozas.de
- Remove redundant/unwanted tags/section (cf. specfile guidelines)
- Employ shlib naming (fftw3 -> libfftw3)
-------------------------------------------------------------------
Sun Oct 9 17:48:50 UTC 2011 - adrian@suse.de
- enable sse only on supported architectures
-------------------------------------------------------------------
Wed Sep 28 02:22:14 UTC 2011 - dhall@wustl.edu
- enable sse2 and sse code generation
-------------------------------------------------------------------
Fri Aug 5 22:44:51 UTC 2011 - dhall@wustl.edu
- specfile cleanup
* Remove authors from description
* use %makeinstall
- fix devel and mpi-devel to include proper header files
-------------------------------------------------------------------
Wed Aug 3 13:58:49 UTC 2011 - dhall@wustl.edu
- updated to version 3.3:
* Compiling OpenMP support (--enable-openmp) now installs a fftw3_omp
library, instead of fftw3_threads, so that OpenMP and POSIX threads
(--enable-threads) libraries can be built and installed at the same time.
* Add support for the AVX extensions to x86 and x86-64
* Added Fortran 2003 interface
* Added MPI distributed-memory transforms
* Add support for quad-precision __float128 in gcc 4.6 or later (on x86.
x86-64, and Itanium). The new routines use the fftwq_ prefix.
* New convenience functions fftw_alloc_real and fftw_alloc_complex to use
fftw_malloc for real and complex arrays without typecasts or sizeof.
* New convenience functions fftw_export_wisdom_to_filename and
fftw_import_wisdom_from_filename that export/import wisdom to a file, which
don't require you to open/close the file yourself.
* New function fftw_cost to return FFTW's internal cost metric for a given plan
* Remove --enable-portable-binary flag: we new produce portable binaries by default.
* Fixed build problem failure when srand48 declaration is missing
* Fixed bug in fftw_set_timelimit: ensure that a negative timelimit is equivalent
to no timelimit in all cases
* Fixed stack-overflow problem on OpenBSD caused by using alloca with too
large a buffer.
- added openmp library support
- added mpi library support
-------------------------------------------------------------------
Sun Apr 24 12:59:34 UTC 2011 - toddrme2178@gmail.com
- Add 32bit compatibility libraries
- Changed -devel package groups to Development/Libraries/C and C++ (fix for RPMLINT warning)
-------------------------------------------------------------------
Thu Apr 22 18:59:44 UTC 2010 - davejplater@gmail.com
- Added provides fftw-devel
-------------------------------------------------------------------
Thu Jul 16 15:27:24 CEST 2009 - tiwai@suse.de
- updated to version 3.2.2:
* Improve performance of some copy operations of complex arrays
* Add configure flag to disable alloca()
* Planning in FFTW_ESTIMATE mode for r2r transforms became slower
between fftw-3.1.3 and 3.2. This regression has now been fixed.
-------------------------------------------------------------------
Thu Apr 23 17:36:12 CEST 2009 - tiwai@suse.de
- remove obsolste fdupes check in spec file
- avoid unnecessary autoreconf
-------------------------------------------------------------------
Mon Feb 16 12:24:16 CET 2009 - tiwai@suse.de
- updated to version 3.2:
* major version up, performance improvements and SIMD support
* Worked around apparent glibc bug that leads to rare hangs
* Fixed segfault due to unaligned access
* MPI transforms not included, as they are still in alpha
- updated to version 3.2.1:
* Performance improvements for some multidimensional r2c/c2r
transforms
* Compile with icc on MacOS X, use better icc compiler flags.
* Compilation fixes for systems where snprintf is defined as a
macro
* Fortran documentation now recommends not using dfftw_execute,
because of reports of problems with various Fortran compilers
* Some documentation clarifications
* FAQ was accidentally omitted from 3.2 tarball.
* Remove some extraneous (harmless) files accidentally included
in a subdirectory of the 3.2 tarball.
-------------------------------------------------------------------
Sat Aug 2 10:46:31 CEST 2008 - tiwai@suse.de
- Reduce dependency without release number.
This allows to install packages on different media with
different release numbers.
-------------------------------------------------------------------
Mon Apr 16 17:07:05 CEST 2007 - tiwai@suse.de
- follow library packaging policy
* move docs to devel package
* remove static libraries
-------------------------------------------------------------------
Sat Oct 21 15:50:52 CEST 2006 - schwab@suse.de
- Fix broken macro.
-------------------------------------------------------------------
Tue Aug 22 13:09:41 CEST 2006 - tiwai@suse.de
- updated to version 3.1.2:
* correct bug in configure script
* updated FAQ
* use -maltivec when checking for altivec.h.
- clean up spec file, using %configure macro.
-------------------------------------------------------------------
Thu May 18 16:33:14 CEST 2006 - tiwai@suse.de
- major update to version 3.1.1:
* fixed texi files
* lots of configure fixes
* clean up and optimizations
see ChangeLog for details
- added missing glibc-devel to Requires of devel subpackages
- removed -fno-strict-aliasing option
-------------------------------------------------------------------
Wed Jan 25 21:35:52 CET 2006 - mls@suse.de
- converted neededforbuild to BuildRequires
-------------------------------------------------------------------
Wed Apr 13 14:19:35 CEST 2005 - tiwai@suse.de
- fixed neededforbuild.
-------------------------------------------------------------------
Tue Apr 27 01:27:36 CEST 2004 - ro@suse.de
- add -fno-strict-aliasing
-------------------------------------------------------------------
Sat Jan 10 14:45:42 CET 2004 - adrian@suse.de
- add missing %defattr and %run_ldconfig
-------------------------------------------------------------------
Fri Aug 29 05:38:19 CEST 2003 - nashif@suse.de
- #29586: info file installation in wrong post segment
-------------------------------------------------------------------
Wed Jul 30 18:00:20 CEST 2003 - nashif@suse.de
- Initial release