Changelog for
libatlas3-basic-3.10.3-2.238.x86_64.rpm :
* Fri Jul 29 2016 normandAATTlinux.vnet.ibm.com- temporarily change basic flavor build do not set -V -A and let ATLAS build to analyse architecture. (would need more work to be compatible with new 3.10.3)
* Fri Jul 29 2016 normandAATTlinux.vnet.ibm.com- update to 3.10.3 (copy from changelog) ATLAS 3.10.3 released 07/28/16, highlights of changes from 3.10.2
* Updated F77 L1BLAS testers to those used LAPACK3.6.1
* Fixed bug in rotmg revealed by LAPACK3.6.1 testers
* Fixed bug in hprk/sprk that could cause NaN propogation in HERK/SYRK due to reading uninitialized memory in BETA=0 case
* Fixed bug in threaded SYR2K/HER2K that could cause NaN propogation due to reading uninitialized memory
* Extended matrix/vector norm functions to detect NaNs
* Extended configure: + --force-clang=/path/to/clang : will use clang for all C compilers, even goodgcc (assumes gcc flag & inline-assembly compatibility) + --cripple-atlas-performance: install despite failing throttle check + Can now use arch string rather than enum # for -A arg + --force-tids now affects ATLrun.sh as well as threaded build + ARM32 autodetects SOFTFP/HARDFP ABI
* backport of config & archdefs for: + POWER[7,8]le, IBMz[10,13,19], Corei[3,4], ARM[7,9,15,17], ARM64[xgene,a53,a57] + archdefs for NEON ARMa[7,15] + config support for IBM Z[9,196,12]
* backport & extension of atlas_simd.h & atlas_cplxsimd.h + New SIMD kernels for: VSX, VXZ, AVX2, AdvancedSIMD, NEON
* Fixed mflop test of PrintMMLine, that sometimes failed to print valid mflop due to negative values from prior runs
* Removed ATL_dmm6x1x60_sse2_32.c from z index files (not valid cplx kern)
* Forced MinGW comps to be ignored unless -Si nocygwin 1 is set
* Added support for WOW64 detection & basic use, numerous changes to make work on cygwin64
* Fixed uninit nM in s[1,2]nxtune.c\'s RecDoubleNX- update atlas-suse-shared.patch- remove all related ppc64/ppc64le patches useless for 3.10.3 atlas-new_archdef_for_ppc64le.patch atlas.3.10.2-add_power8_cpu.patch atlas.3.10.2-ppc64le_abiv2.patch atlas.3.10.2-ppc64le_do_not_use_files_with_lvx.patch issue_64.patch getdoublearr.stripwhite.patch initialize_malloc_memory.invtrsm.wms.oct23.patch- add %check pragma but do not fail on error.
* Mon Jun 06 2016 normandAATTlinux.vnet.ibm.com- modify last build rework to avoid build error for ppc64/ppc64le
* Fri May 20 2016 jengelhAATTinai.de- Rework the build of flavors, by splitting to separate .spec files because the build time of target \"ptshared\" is quite long already (>6000s).- Make sure the flavor builds are only built with the extensions they should have. This resolves a build failure in the fflas-ffpack package because libatlas was built with AVX when it should not have.
* Fri Dec 18 2015 jengelhAATTinai.de- disable nonfunctional parallel build [boo#959154]
* Tue Aug 11 2015 normandAATTlinux.vnet.ibm.com- For ppc64/ppc64le architectures: Update the related patches to new version 3.10.2 deleted patches: issue_64.patch is embeded in 3.10.2 atlas.3.10.1-ppc64le_abiv2.patch atlas.3.10.1-add_power8_cpu.patch new patches: atlas.3.10.2-ppc64le_abiv2.patch atlas.3.10.2-add_power8_cpu.patch
* Sun Aug 09 2015 p.drouandAATTgmail.com- Update to version 3.10.2
* Fixed all errataed bugs: + Failure to init workspace can cause NaNs in SYRK + Complex row-major Q-type factorizations produce bad TAU + Failure to cast causes integer overflow on 64-byt platforms + Missing IBM S390 assembly file
* Fixed Make.bin to have threaded latime built to do parallel cache flushing
* Extended extract string lengths as patched by SAGE folks
* Backported fixes & some arch support to configure framework, including host of Itanium and UST1 stuff provided by SAGE folks NOTE: 3.10.2 is terribly out of date, and was released only because the threading rewrite it taking too long. If possible, you should use a developer release after testing that it works for your particular platform. In particular, developer releases are
*much
* faster for any x86 that uses AVX or later SIMD ISA, or any machine with ncores >= 8. The developer release also supports ARM architectures better (though performance is not hugely better if you can get stable installed).
* Wed Aug 05 2015 normandAATTlinux.vnet.ibm.com- For ppc64/ppc64le architectures: Add support of Power8 cpu Do not support lvx files for ppc64le (temporarily) In spec create power8 archives files if do not exist yet POWER864VSX from POWER764VSX and POWER864LEVSX from POWER764LEVSX removed patch: xlf.command.not.found.patch libatlas.ppc64le-abiv2.patch new patches: issue_64.patch atlas.3.10.1-ppc64le_abiv2.patch atlas-new_archdef_for_ppc64le.patch atlas.3.10.1-add_power8_cpu.patch atlas.3.10.2-ppc64le_do_not_use_files_with_lvx.patch
* Sun Jun 07 2015 dmitry_rAATTopensuse.org- Move all headers to /usr/include/atlas directory to avoid conflicts
* Thu Jun 26 2014 dvaleevAATTsuse.com- Enable build for ppc and ppc64le see http://sourceforge.net/p/math-atlas/mailman/message/32471499/ POWER332.tar.bz2 POWER764LEVSX.tar.bz2 libatlas.ppc64le-abiv2.patch initialize_malloc_memory.invtrsm.wms.oct23.patch xlf.command.not.found.patch getdoublearr.stripwhite.patch
