Commit Graph

67 Commits

Author SHA256 Message Date
5a47826ff0 Accepting request 839300 from home:eeich:branches:science
- Set DYNAMIC_ARCH everywhere, use a base CPU model for non-dynamic
  bits to have a reproducible base line:
  x86_64: CORE2
  aarch64: ARMV8
  ppc: POWER8
  s390: ZARCH_GENERIC
- Remove workaround for build failure on aarch64 (boo#1128794).

OBS-URL: https://build.opensuse.org/request/show/839300
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=100
2020-10-03 13:51:01 +00:00
Ismail Dönmez
b8f59c01fc Accepting request 837203 from home:eeich:branches:science
- For s390/s390x add TARGET=ZARCH_GENERIC (jsc#SLE-13773).

OBS-URL: https://build.opensuse.org/request/show/837203
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=98
2020-09-25 08:36:13 +00:00
f391c4cf63 Accepting request 833599 from home:eeich:branches:science
- Add build support for gcc10 to HPC build (bsc#1174439).

OBS-URL: https://build.opensuse.org/request/show/833599
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=96
2020-09-11 08:25:52 +00:00
Ismail Dönmez
ff51291708 Accepting request 825866 from home:bmwiedemann:branches:science
Avoid compile-time CPU-detection (boo#1100677)

the docs in GotoBLAS_02QuickInstall.txt say
3. Specifying target architecture

   If you need library for different architecture, you can use TARGET
   option. You can find current available options in top of getarch.c.
   For example, if you need library for Intel core2 architecture,
   you'll find FORCE_CORE2 option in getarch.c. Therefore you can
   specify TARGET=CORE2 (get rid of FORCE_) with make.

   $shell> make TARGET=CORE2

This is rather unspecific, but my tests show it helps to get reproducible binaries and compilation still happens with -DDYNAMIC_ARCH -march=skylake-avx512

OBS-URL: https://build.opensuse.org/request/show/825866
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=94
2020-08-12 07:31:08 +00:00
Ismail Dönmez
e731315c9d Accepting request 814610 from home:namtrac:branches:science
- Update to version 0.3.10
  common:
  * Improved thread locking behaviour in blas_server and parallel getrf
  * Imported bugfix 394 from LAPACK (spurious reference to "XERBL"
    due to overlong lines)
  * Imported bugfix 403 from LAPACK (compile option "recursive" required
    for correctness with Intel and PGI)
  * Imported bugfix 408 from LAPACK (wrong scaling in ZHEEQUB)
  * Imported bugfix 411 from LAPACK (infinite loop in LARGV/LARTG/LARTGP)
  * Fixed mismatches between BUFFERSIZE and GEMM_UNROLL parameters that
    could lead to crashes at large matrix sizes
  * Restored internal soname in dynamic libraries on FreeBSD and Dragonfly
  * Added API (openblas_setaffinity) to set thread affinity
    programmatically on Linux
  * Added initial infrastructure for half-precision floating point
    (bfloat16) support with a generic implementation of SHGEMM
  * Added CMAKE build system support for building the cblas_Xgemm3m
    functions
  * Fixed CMAKE support for building in a path with embedded spaces
  * Fixed CMAKE (non)handling of NO_EXPRECISION and MAX_STACK_ALLOC
  * Fixed GCC version detection in the Makefiles
  * Allowed overriding the names of AR, AS and LD in Makefile builds
  POWER:
  * fixed big-endian POWER8 ELFv2 builds on FreeBSD
  * Fixed GCC version checks and DYNAMIC_ARCH builds on POWER9
  * Fixed CMAKE build support for POWER9
  * fixed a potential race condition in the thread buffer allocation
  * Worked around LAPACK test failures on PPC G4
  MIPS:
  * fixed a potential race condition in the thread buffer allocation

OBS-URL: https://build.opensuse.org/request/show/814610
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=92
2020-06-15 05:33:39 +00:00
Ismail Dönmez
4cea3d1493 Accepting request 780848 from home:marxin:branches:science
- Update to version 0.3.9
  common:
  * Fixed a miscompilation of the GETRF functions with CMAKE
    The size of the memory buffer used for splitting GEMM tasks across
    multiple threads can now be configured in the build system.
    Imported bugfix 390 from LAPACK (missing NaN propagation in xCOMBSSQ)
  POWER:
  * fixed several compilation problems related to endianness and
    ELF version support on POWER8 and POWER9.
  * fixed misuse of the absolute value IAMIN/IAMAX in place of IMIN/IMAX
  * fixed a race condition in the level3 blas code
  MIPS64:
  * fixed misuse of the absolute value IAMIN/IAMAX in place of IMIN/IMAX
  ARMV7:
  * fixed a race condition in the level3 blas code
  * fixed a compilation problem on Android
  ARMV8:
  * Added support for Ampere EMAG8180
  * Added support for Neoverse N1
    improved performance of the blas_lock function
    fixed a race condition in the level3 blas code
  * Fixed a performance regression on TSV110 servers
  x86_64:
  * Fixed a long-standing error with undeclared register clobbers in
    the DSCAL microkernel for Haswell,SkylakeX and Zen exposed by gcc9.2
  *  Fixed a long-standing bug in the SSE implementation of the IAMAX functions
  *  Fixed a cmake build failure with DYNAMIC_ARCH on x86_64
  *  Fixed an oversight in the cpu detection code for Intel Goldmont+,
     Cannon Lake and Ice Lake
  * Fixed compile failure on OSX when the compiler name contains a dash

OBS-URL: https://build.opensuse.org/request/show/780848
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=90
2020-03-11 05:24:37 +00:00
3202080ce8 Accepting request 779439 from home:eeich:branches:science
- Add support for gcc8/9 building (jsc#SLE-8604).

OBS-URL: https://build.opensuse.org/request/show/779439
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=88
2020-02-26 14:56:25 +00:00
Ismail Dönmez
ad5e4348bc Accepting request 772619 from home:namtrac:branches:science
- Update to version 0.3.8
  common:
  * LAPACK has been updated to 3.9.0 (plus patches up to January 2nd, 2020)
  * CMAKE support has been improved in several areas including cross-compilation
  * A thread race condition in the GEMM3M kernels was resolved
  * The "generic" (plain C) gemm beta kernel used by many targets has been sped up
  * An optimized version of the LAPACK trtrs functions has been added
  * An incompatibilty between the LAPACK tests and the OpenBLAS implementation of XERBLA
    was resolved, removing the numerous warnings about wrong error exits in the former
  * Support for NetBSD has been added
  * Support for compilation with g95 and non-GNU versions of ld has been improved
  * Compilation with (upcoming) gcc 10 is now supported
  power:
  * Worked around miscompilation of several POWER8 and POWER9 kernels by
    older versions of gcc
  * Added support for big-endian POWER8 and for compilation on AIX
  * Corrected bugs in the big-endian support for PPC440 and PPC970
  * DYNAMIC_ARCH support is now available in CMAKE builds as well
  armv8:
  * Performance of DGEMM_BETA and SGEMM_NCOPY has been improved
  * Compilation for 32bit works again 
  * Performance of the RPCC function has been improved
  * Improved performance on small systems
  * DYNAMIC_ARCH support is now available in CMAKE builds as well
  * Cross-compilation from OSX to IOS was simplified
  x86-64:
  * A new AVX512 DGEMM kernel was added and the AVX512 SGEMM kernel was
    significantly improved
  * Optimized AVX512 kernels for CGEMM and ZGEMM have been added
  * AVX2 kernels for STRMM, SGEMM, and CGEMM have been significantly

OBS-URL: https://build.opensuse.org/request/show/772619
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=87
2020-02-25 06:31:34 +00:00
Dmitry Roshchin
91d3d1b815 Accepting request 755043 from home:marxin:branches:science
- Add gcc10-Support-two-digit-version-numbers-in-gcc-version-che.patch
  in order to fix boo#1158727.

OBS-URL: https://build.opensuse.org/request/show/755043
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=85
2019-12-12 15:56:56 +00:00
Ana Guerrero
3880fb2eef OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=83 2019-09-30 07:20:43 +00:00
Dmitry Roshchin
95aab13929 Accepting request 722576 from home:marxin:branches:science
- Update to version 0.3.7
  common:
    * having the gmake special variables TARGET_ARCH or TARGET_MACH
      defined no longer causes build failures in ctest or utest
    * defining NO_AFFINITY or USE_TLS to zero in gmake builds
      no longer has the same effect as setting them to one
    * a new test program was added to allow checking the library for thread safety
    * a new option USE_LOCKING was added to ensure thread safety
      when OpenBLAS itself is built without multithreading but
    * will be called from multiple threads.
    * a build failure on Linux with glibc versions earlier than 2.5 was fixed
    * a runtime error with CPU enumeration (and NO_AFFINITY not set)
      on glibc 2.6 was fixed
    * NO_AFFINITY was added to the CMAKE options
      (and defaults to being active on Linux, as in the gmake builds)
  x86_64
    * the build-time logic for detection of AVX512 availability
      in the processor and compiler was fixed
    * gmake builds on OSX now set the internal name
      of the library to libopenblas.0.dylib (consistent with CMAKE)
    * the Haswell DGEMM kernel received a significant speedup
      through improved prefetch and load instructions
    * performance of DGEMM, DTRMM, DTRSM and ZDOT on Zen/Zen2
      was markedly increased by avoiding vpermpd instructions
    * the SKYLAKEX (AVX512) DGEMM helper functions have now been
      disabled to fix remaining errors in DGEMM, DSYMM and DTRMM
  POWER:
    * added support for building on FreeBSD/powerpc64 and FreeBSD/ppc970
    * added optimized kernels for POWER9 single and double precision complex BLAS3
    * added optimized kernels for POWER9 SGEMM and STRMM

OBS-URL: https://build.opensuse.org/request/show/722576
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=81
2019-08-12 14:13:38 +00:00
Dmitry Roshchin
f01ba9789b Accepting request 699559 from home:marxin:branches:science
- Update to version 0.3.6 (boo#1122186)
  common:
    * the build tools now check that a given cpu TARGET is actually valid
    * the build-time check of system features (c_check) has been made
      less dependent on particular perl features (this should mainly
      benefit building on Windows)
    * several problems with ReLAPACK and its integration were fixed,
      including INTERFACE64 support and building a shared library
    * building with CMAKE on BSD systems was improved
    * a non-absolute SUM function was added based on the
      existing optimized code for ASUM
    * CBLAS interfaces to the IxMIN and IxMAX functions were added
    * a name clash between LAPACKE and BOOST headers was resolved
    * CMAKE builds with OpenMP failed to include the appropriate getrf_parallel
      kernels
    * a crash on thread (key) deletion with the USE_TLS=1 memory management
      option was fixed
    * restored several earlier fixes, in particular for OpenMP performance,
      building on BSD, and calling fork on CYGWIN, which had inadvertently
      been dropped in the 0.3.3 rewrite of the memory management code.
  POWER:
    * single precision BLAS1/2 functions have received optimized POWER8 kernels
    * POWER9 is now a separate target, with an optimized DGEMM/DTRMM kernel
    * building on PPC970 systems under OSX Leopard or Tiger is now supported
    * out-of-bounds memory accesses in the gemm_beta microkernels were fixed
    * building a shared library on AIX is now supported for POWER6
    * DYNAMIC_ARCH support has been added for POWER6 and newer
  ARMV7:
    * corrected xDOT behaviour with zero INC_X or INC_Y 
    * a bug in the IMIN implementation made it return the result of IMAX
  ARMV8:
    * added support for HiSilicon TSV110 cpus
    * the CMAKE build system now recognizes 32bit userspace on 64bit hardware 
    * cross-compilation with CMAKE now works again
    * a bug in the IMIN implementation made it return the result of IMAX
    * ARMV8 builds with the BINARY=32 option are now automatically handled as ARMV7
  x86_64:
    * the AVX512 DGEMM kernel has been disabled again due to unsolved problems
    * building with old versions of MSVC was fixed
    * it is now possible to build a static library on Windows with CMAKE
    * accessing environment variables on CYGWIN at run time was fixed
    * the CMAKE build system now recognizes 32bit userspace on 64bit hardware
    * Intel "Denverton" atom and Hygon "Dhyana" zen CPUs are now autodetected
    * building for DYNAMIC_ARCH with a DYNAMIC_LIST of targets is now supported
      with CMAKE as well
    * building for DYNAMIC_ARCH with GENERIC as the default target is now supported
    * a buffer overflow in the SSE GEMM kernel for Intel Nano targets was fixed
    * assembly bugs involving undeclared modification of input operands were fixed
      in the AXPY, DOT, GEMV, GER, SCAL, SYMV and TRSM microkernels for Nehalem, 
      Sandybridge, Haswell, Bulldozer and Piledriver. These would typically cause
      test failures or segfaults when compiled with recent versions of gcc from 8 onward.
    * a similar bug was fixed in the blas_quickdivide code used to split workloads
      in most functions
    * a bug in the IxMIN implementation for the GENERIC target made it return the result of IxMAX
    * fixed building on SkylakeX systems when either the compiler or the (emulated) operating 
      environment does not support AVX512
    * improved GEMM performance on ZEN targets
  x86:
    * build failures caused by the recently added checks for AVX512 were fixed
    * an inline assembly bug involving undeclared modification of an input argument was
      fixed in the blas_quickdivide code used to split workloads in most functions
    * a bug in the IMIN implementation for the GENERIC target made it return the result of IMAX
  MIPS32:
    * a bug in the IMIN implementation made it return the result of IMAX
  IBM Z:
    * optimized microkernels for single precicion BLAS1/2 functions have been added for Z13 and Z14
  - Rebase openblas-noexecstack.patch and openblas-s390.patch patches.
  - Remove 0001-Add-a-register-to-the-clobber-list-for-the-mul-instr.patch.

OBS-URL: https://build.opensuse.org/request/show/699559
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=79
2019-05-04 08:29:45 +00:00
Dmitry Roshchin
a70faf2d20 Accepting request 684134 from home:StefanBruens:branches:science
- Reduce _constraints to a reasonable size, the old constraints
  were probably necessary pre multibuild.
- Enable DYNAMIC_ARCH for aarch64, available since 0.3.4

OBS-URL: https://build.opensuse.org/request/show/684134
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=77
2019-03-12 17:39:07 +00:00
fe2899268f Accepting request 677189 from home:eeich:branches:science
- Add OPENBLAS_INC and OPENBLAS_DIR to HPC environment (bsc#1125547).

OBS-URL: https://build.opensuse.org/request/show/677189
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=75
2019-02-19 13:34:27 +00:00
Stefan Brüns
a55e92ab2d Accepting request 674767 from home:StefanBruens:branches:science
Fix openblas error, leading to failing octave testsuite on i586

- Fix https://github.com/xianyi/OpenBLAS/issues/2014
  Add 0001-Add-a-register-to-the-clobber-list-for-the-mul-instr.patch

OBS-URL: https://build.opensuse.org/request/show/674767
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=74
2019-02-18 17:19:19 +00:00
Dmitry Roshchin
7498fdfdf4 Accepting request 663321 from home:namtrac:branches:science
- Update to versiom 0.3.5
  common:
    * Loop unrolling in TRMV has been enabled again.
    * A domain error in the thread workload distribution for SYRK
      has been fixed.
    * gmake builds will now automatically add -fPIC to the build
      options if the platform requires it.
    * A pthreads key leakage (and associate crash on dlclose) in
      the USE_TLS codepath was fixed.
    * Building of the utest cases on systems that do not provide
      an implementation of complex.h was fixed.
  x86_64:
    * The SkylakeX code was changed to compile on OSX.
    * Unwanted application of the -march=skylake-avx512 option
      to the common code parts of a DYNAMIC_ARCH build was fixed.
    * Improved performance of SGEMM for small workloads on Skylake X.
    * Performance of SGEMM and DGEMM was improved on Haswell.
  armv8:
    * A configuration error that broke the CNRM2 kernel was corrected.
    * Compilation of the GEMM kernels with CMAKE was fixed.
    * DYNAMIC_ARCH builds are now available with CMAKE as well.
    * Using CMAKE for cross-compilation to the new cpu TARGETs
      introduced in 0.3.4 now works.
  power:
    * A problem in cpu autodetection for AIX has been corrected.

OBS-URL: https://build.opensuse.org/request/show/663321
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=72
2019-01-27 09:00:38 +00:00
Dmitry Roshchin
f70e95f316 Accepting request 656046 from home:namtrac:branches:science
- Update to version 0.3.4
  common:
    * The new, experimental thread-local memory allocation had
      inadvertently been left enabled for gmake builds in 0.3.3
      despite the announcement. It is now disabled by default,
      and single-threaded builds will keep using the old
      allocator even if the USE_TLS option is turned on.
    * OpenBLAS will now provide enough buffer space for at least
      50 threads by default.
    * The output of openblas_get_config() now contains the version
      number.
    * A serious thread safety bug in GEMV operation with small M and
      large N size has been fixed.
    * The code will now automatically call blas_thread_init after
      a fork if needed before handling a call to
      openblas_set_num_threads
    * Accesses to parallelized level3 functions from multiple
      callers are now serialized to avoid thread races
      (unless using OpenMP).
    * This should provide better performance than the
      known-threadsafe (but non-default)
      USE_SIMPLE_THREADED_LEVEL3 option.
    * When building LAPACK with gfortran, -frecursive is now
      (again) enabled by default to ensure correct behaviour.
    * The OpenBLAS version cblas.h now supports both CBLAS_ORDER
      and CBLAS_LAYOUT as the name of the matrix row/column order
      option.
    * Externally set LDFLAGS are now passed through to the final
      compile/link
    * steps to facilitate setting platform-specific linker flags.

OBS-URL: https://build.opensuse.org/request/show/656046
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=70
2018-12-07 19:31:33 +00:00
Dmitry Roshchin
0737842b18 Accepting request 640892 from home:Dmitry_R:branches:science
- Update to version 0.3.3 
  common:
    * thread memory allocation has been switched back to the method used before version 0.3.1 due to unexpected problems caused by the new code under some circumstances.
    * LAPACK PR272 has been integrated, which fixes spurious errors in DSYEVR and related functions caused by missing conversion from ILAENV to ILAENV_2STAGE in several _2stage routines.
  x86_64
    * added AVX512 implementations of SDOT, DDOT, SAXPY, DAXPY, DSCAL, DGEMVN and DSYMVL
    * added a workaround for a cygwin issue that prevented compilation of AVX512 code

OBS-URL: https://build.opensuse.org/request/show/640892
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=68
2018-10-09 21:01:55 +00:00
Dmitry Roshchin
868106f937 Accepting request 629943 from home:namtrac:branches:science
- Update to version 0.3.2
  common:
    * Fixes for regressions caused by the rewrite of the thread
      initialization code in 0.3.1
  x86_64:
    * Added autodetection of AMD Ryzen 2
    * Fixed build with older versions of MSVC
  power:
    * Fixed cpu autodetection for the BSDs
  mips64:
    * Fixed utest errors in AXPY, DSDOT, ROT and SWAP
- Version 0.3.1
  common:
    * Rewritten thread initialization code with significantly
      reduced overhead
    * Added CBLAS interfaces to the IxAMIN BLAS extension functions
    * Fixed the lapack-test target
    * CMAKE builds now create an OpenBLASConfig.cmake file
    * ZAXPY now uses a single thread for small input sizes
    * The LAPACK code was updated from Reference-LAPACK/lapack#253
  power:
    * Corrected CROT and ZROT behaviour with zero INC_X
  armv7:
    * Corrected xDOT behaviour with zero INC_X or INC_Y
  x86_64:
    * Retired some older targets of DYNAMIC_ARCH builds to a
      new option DYNAMIC_OLDER, this affects PENRYN,DUNNINGTON,
      OPTERON,OPTERON_SSE3,BOBCAT,ATOM and NANO (which will still
      be supported via the slower PRESCOTT kernels when this option
      is not set)

OBS-URL: https://build.opensuse.org/request/show/629943
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=67
2018-08-17 20:04:11 +00:00
0deb6f1a78 - add openblas-s390.patch to build on s390 (bsc#1079513).
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=65
2018-02-07 16:25:42 +00:00
7e03e03396 Accepting request 571250 from home:oertel:branches:science
- add openblas-s390.patch to build on s390

OBS-URL: https://build.opensuse.org/request/show/571250
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=64
2018-02-07 16:13:12 +00:00
Dmitry Roshchin
eeb9603ad7 Accepting request 573243 from home:eeich:branches:science
- OpenBLAS doesn't support s390: do not build it there (bsc#1079513).

OBS-URL: https://build.opensuse.org/request/show/573243
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=63
2018-02-06 09:34:52 +00:00
2a92468570 Accepting request 562259 from home:eeich:branches:fix-compilers-hpc
- Switch from gcc6 to gcc7 as additional compiler flavor for HPC on SLES.
- Fix library package requires - use HPC macro (boo#1074890).
- Fix unexpanded rpm macro in environment module file for HPC (boo#1074897).

OBS-URL: https://build.opensuse.org/request/show/562259
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=61
2018-01-07 21:00:47 +00:00
Dmitry Roshchin
c628de499b Accepting request 546005 from home:michel_mno:branches:science
- Add -mvsx option for ppc64 archi (not required for ppc64le)
  to avoid ./kernel/power/sasum_microk_power8.c:41:3: error:
  '__vector' undeclared (first use in this function); ...

OBS-URL: https://build.opensuse.org/request/show/546005
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=59
2017-11-30 09:57:24 +00:00
3fa5455661 Accepting request 534889 from home:eeich:branches:science
- Still tuning parameters for the build in the OBS ring.

OBS-URL: https://build.opensuse.org/request/show/534889
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=57
2017-10-18 08:10:36 +00:00
fcc6124211 - Add magic to limit the number of flavors built in the
in the OBS ring.

OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=56
2017-10-17 13:39:15 +00:00
Dmitry Roshchin
48de63cb9e Accepting request 533655 from home:eeich:hpc_alt
- Generate baselib.conf dynamically and only for the non-HPC
  builds: this avoids issues with the source validator.

- Convert openblas to multibuild.
- Add HPC build using environment modules.
  (FATE#321708).
- fix-arm64-cpuid-return.patch
  Fix CPUID detection on ARM (From OHPC).

OBS-URL: https://build.opensuse.org/request/show/533655
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=55
2017-10-16 15:00:39 +00:00
Dmitry Roshchin
2dc7521b9a Accepting request 515927 from home:Dmitry_R:branches:science
OBS-URL: https://build.opensuse.org/request/show/515927
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=53
2017-08-10 14:07:44 +00:00
Dmitry Roshchin
e2a59c91a4 Accepting request 513093 from home:badshah400:branches:science
- Update to version 0.2.20:
  * common:
    - Improved CMake support
    - Fixed several thread race and locking bugs
    - Fixed default LAPACK optimization level
    - Updated LAPACK to 3.7.0
    - Added ReLAPACK (https://github.com/HPAC/ReLAPACK), make
      BUILD_RELAPACK=1
  * POWER:
    - Optimizations for Power9
    - Fixed several Power8 assembly bugs
  * ARM:
    - New optimized Vulcan and ThunderX2T99 targets
    - Support for ARMV7 SOFT_FP ABI  (make ARM_SOFTFP_ABI=1)
    - Detect all cpu cores including offline ones
    - Fix compilation with CLANG
    - Support building a shared library for Android
  * MIPS:
    - Fixed several threading issues
    - Fix compilation with CLANG
  * x86_64:
    - Detect Intel Bay Trail and Apollo Lake
    - Detect Intel Sky Lake and Kaby Lake
    - Detect Intel Knights Landing
    - Detect AMD A8, A10, A12 and Ryzen
    - Support 64bit builds with Visual Studio
    - Fix building with Intel and PGI compilers
    - Fix building with MINGW and TDM-GCC
    - Fix cmake builds for Haswell and related cpus
    - Fix building for Sandybridge with CLANG 3.9

OBS-URL: https://build.opensuse.org/request/show/513093
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=52
2017-08-02 19:43:10 +00:00
Dmitry Roshchin
82ccf7a9ca Accepting request 495825 from home:msmeissn:branches:science
- 0001-Fix-power8-asm.patch: fixed power8 assembly (bsc#1039397)

OBS-URL: https://build.opensuse.org/request/show/495825
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=50
2017-05-19 07:51:55 +00:00
Ismail Dönmez
8491339a4b - Update to version 0.2.19
POWER:
    * Optimize BLAS on Power8
    * Fixed Julia+OpenBLAS bugs on Power8
  MIPS:
    * Optimize BLAS on MIPS P5600 and I6400
  ARM:
    * Improved on ARM Cortex-A57

OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=48
2016-09-07 16:20:26 +00:00
Dmitry Roshchin
ef43c5c10b Accepting request 389139 from home:Dmitry_R:branches:science
- Update to version 0.2.18
  ARM:
    * Provide DGEMM 8x4 kernel for Cortex-A57
  POWER:
    * Optimize S and C BLAS3 on Power8
    * Optimize BLAS2/1 on Power8

OBS-URL: https://build.opensuse.org/request/show/389139
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=46
2016-04-13 09:42:05 +00:00
Dmitry Roshchin
a35b003df1 Accepting request 377040 from home:Dmitry_R:branches:science
OBS-URL: https://build.opensuse.org/request/show/377040
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=44
2016-03-21 22:35:54 +00:00
Dmitry Roshchin
b830f494d3 Accepting request 374076 from home:namtrac:branches:science
- Update to version 0.2.16
  * Upgrade LAPACK to 3.6.0 version.
  * Disable multi-threading for small size swap and ger.
  * Improve small zger, zgemv, ztrmv using stack alloction.
  * Let openblas_get_num_threads return the number of active threads.
  * Fix LAPACK Dormbr, Dormlq bug.
  * Avoid potential getenv segfault.
  * Import LAPACK svn bugfix #142-#147,#150-#155
  * Optimize trsm kernels for AMD Bulldozer, Piledriver, Steamroller.
  * Detect Intel Avoton.
  * Detect AMD Trinity, Richland, E2-3200.
  * Optimize c/zgemv for AMD Bulldozer, Piledriver, Steamroller
  * Fix bug with scipy linalg test.
  * Support and optimize Cortex-A57 AArch64.
  * Update ARMV6 kernels.
  * Improve DGEMM for ARM Cortex-A57.
  * Fix detection of POWER architecture.
  * Optimize D and Z BLAS3 functions for Power8.
- Remove openblas-libs.patch, not needed.

OBS-URL: https://build.opensuse.org/request/show/374076
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=42
2016-03-17 07:56:09 +00:00
Dmitry Roshchin
435f704e97 Accepting request 341265 from home:Dmitry_R:branches:science
- Update to version 0.2.15
  * Enable MAX_STACK_ALLOC flags by default.
  * Improve ger and gemv for small matrices.
  * Improve gemv parallel with small m and large n case.
  * Improve ?imatcopy when lda==ldb
  * Add vecLib benchmarks
  * Fix LAPACK lantr for row major matrices
  * Fix LAPACKE lansy
  * Import bug fixes for LAPACKE s/dormlq, c/zunmlq
  * Raise the signal when pthread_create fails
  * Drop obsolete openblas-arm64-build.patch
  x86/x86-64:
    * Support pure C generic kernels for x86/x86-64.
    * Support Intel Boardwell and Skylake by Haswell kernels.
    * Support AMD Excavator by Steamroller kernels.
    * Optimize s/d/c/zdot for Intel SandyBridge and Haswell.
    * Optimize s/d/c/zdot for AMD Piledriver and Steamroller.
    * Optimize s/d/c/zapxy for Intel SandyBridge and Haswell.
    * Optimize s/d/c/zapxy for AMD Piledriver and Steamroller.
    * Optimize d/c/zscal for Intel Haswell, dscal for Intel SandyBridge.
    * Optimize d/c/zscal for AMD Bulldozer, Piledriver and Steamroller.
    * Optimize s/dger for Intel SandyBridge.
    * Optimize s/dsymv for Intel SandyBridge.
    * Optimize ssymv for Intel Haswell.
    * Optimize dgemv for Intel Nehalem and Haswell.
    * Optimize dtrmm for Intel Haswell.
  ARM:
    * Support Android NDK armeabi-v7a-hard ABI (-mfloat-abi=hard)
    * Fix lock, rpcc bugs
  POWER:

OBS-URL: https://build.opensuse.org/request/show/341265
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=40
2015-10-28 07:50:54 +00:00
Dmitry Roshchin
9e74d420ec - Change library name suffix
* drop openblas-soname.patch
- Add RPM %post script for manual BLAS/LAPACK update-alternatives
  configuration update
- Use update-alternatives mechanism for OpenBLAS variants (serial,
  openmp, pthreads). pthreads variant is default for x86 and x86_64,
  OpenMP for other architectures.
- Fix build on ARM64
  * openblas-arm64-build.patch
- Add update-alternatives mechanism for CBLAS
- Provide cmake module
- Delete info about host cpu from openblas_config.h for dynamic arch
- Add update-alternatives to 'preup' and 'post' requires list for 
  libraries
- Add README.SUSE

OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=38
2015-08-12 08:12:08 +00:00
Dmitry Roshchin
d541b436fe Accepting request 305140 from home:Dmitry_R:branches:science
- Update to version 0.2.14
  * Improve ger and gemv for small matrices by stack allocation.
    e.g. make -DMAX_STACK_ALLOC=2048
  * Introduce openblas_get_num_threads and openblas_get_num_procs.
  * Add ATLAS-style ?geadd function.
  * Fix c/zsyr bug with negative incx.
  * Fix race condition during shutdown causing a crash in
    gotoblas_set_affinity().
  x86/x86-64:
  * Support AMD Streamroller.
  ARM:
  * Add Cortex-A9 and Cortex-A15 targets.

OBS-URL: https://build.opensuse.org/request/show/305140
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=36
2015-05-03 07:25:46 +00:00
Dmitry Roshchin
c6f985351a - Update to version 0.2.13
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=34
2014-12-04 08:50:14 +00:00
Dmitry Roshchin
465538538d Accepting request 263945 from home:Dmitry_R:branches:science
OBS-URL: https://build.opensuse.org/request/show/263945
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=33
2014-12-04 08:48:36 +00:00
Dmitry Roshchin
bbf55ca159 Accepting request 257419 from home:Dmitry_R:branches:science
- Update to version 0.2.12
  * Added CBLAS interface for ?omatcopy and ?imatcopy.
  * Enable ?gemm3m functions.
  * Added benchmark for ?gemm3m.
  * Optimized multithreading lower limits.
  * Disabled SYMM3M and HEMM3M functions because of segment violations.
  x86/x86-64:
  * Improved axpy and symv performance on AMD Bulldozer.
  * Improved gemv performance on modern Intel and AMD CPUs.

OBS-URL: https://build.opensuse.org/request/show/257419
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=31
2014-10-17 16:18:42 +00:00
Dmitry Roshchin
0198eb424b Accepting request 245137 from home:Dmitry_R:branches:science
OBS-URL: https://build.opensuse.org/request/show/245137
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=29
2014-08-18 21:35:30 +00:00
Dmitry Roshchin
ecffa8bd76 Accepting request 241394 from home:Dmitry_R:branches:science
- Update to version 0.2.10
  * Added BLAS extensions as following.
    s/d/c/zaxpby, s/d/c/zimatcopy, s/d/c/zomatcopy.
  * Added OPENBLAS_CORETYPE environment for dynamic_arch. (a86d34)
  * Support outputing the CPU corename on runtime.(#407)
  * Patched LAPACK to fix bug 114, 117, 118. 
   (http://www.netlib.org/lapack/bug_list.html)
  * Disabled ?gemm3m for a work-around fix. (#400)
  * Fixed lots of bugs for optimized kernels on sandybridge,Haswell, 
    bulldozer, and piledriver.
  * Remove obsolete openblas-0.2.9-gcc-warnings.patch

OBS-URL: https://build.opensuse.org/request/show/241394
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=27
2014-07-17 23:21:38 +00:00
Dmitry Roshchin
861eea5119 Fix patch name
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=25
2014-06-12 20:06:06 +00:00
Dmitry Roshchin
31685c8f35 Fix changes file
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=24
2014-06-12 19:52:20 +00:00
Dmitry Roshchin
8c6de3157c Accepting request 237012 from home:Dmitry_R:branches:science
- Update to version 0.2.9
  * Update LAPACK to 3.5.0 version
  * Fixed compatiable issues with Clang and Pathscale compilers.
  * Added OPENBLAS_VERBOSE environment variable.(#338)
  * Make OpenBLAS thread-pool resilient to fork via pthread_atfork.
    (#294)
  * Rewrote rotmg
  * Fixed sdsdot bug.
  * Improved the result for LAPACK testing. (#372)
  x86/x86-64:
  * Optimization on Intel Haswell.
  * Enable optimization kernels on AMD Bulldozer and Piledriver.
  * Detect Intel Haswell for new Macbook.
  * To improve LAPACK testing, we fallback some kernels. (#372)
    https://github.com/xianyi/OpenBLAS/wiki/Fixed-optimized-kernels-To-do-List
  ARM:
  * Support ARMv6 and ARMv7 ISA.
  * Optimization on ARM Cortex-A9.
- Update patches:
  * openblas-0.2.8-libs.patch
  * openblas-0.2.8-noexecstack.patch
- Fix gcc warnings (#385)
  * openblas-0.2.9-gcc-warnings.patch

OBS-URL: https://build.opensuse.org/request/show/237012
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=23
2014-06-12 19:46:26 +00:00
Stephan Kulow
49b1747350 Accepting request 229830 from science
Replace of SR#229085

OBS-URL: https://build.opensuse.org/request/show/229830
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/openblas?expand=0&rev=1
2014-04-16 05:28:50 +00:00
Dmitry Roshchin
93dab2c628 Accepting request 229825 from home:Dmitry_R:branches:science
- Remove files with problematic licenses

OBS-URL: https://build.opensuse.org/request/show/229825
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=21
2014-04-12 10:03:38 +00:00
Dmitry Roshchin
8c0cd20a46 Accepting request 229075 from home:Dmitry_R:branches:science
- Update to version 0.2.8
  * Add executable stack markings.
  * Respect user's LDFLAGS
  * Rollback bulldozer and piledriver kernels to barcelona kernels  
  * update openblas-0.2.6-libs.patch
  * update c_xerbla_no-void-return.patch
  * update openblas-0.2.7-noexecstack.patch

OBS-URL: https://build.opensuse.org/request/show/229075
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=20
2014-04-05 06:32:53 +00:00
Corot Sebastien
32b43ec6cc Accepting request 184489 from home:scorot:branches:science
- version 0.2.7
  * Support LSB (Linux Standard Base) 4.1.
    e.g. make CC=lsbcc
  * Include LAPACK 3.4.2 source codes to the repo. 
    Avoid downloading at compile time.
  * Add NO_PARALLEL_MAKE flag to disable parallel make.
  * Create openblas_get_parallel to retrieve information which parallelization model is used by OpenBLAS. (Thank grisuthedragon)
  * Detect LLVM/Clang compiler.
  * A walk round for dtrti_U single thread bug. Replace it with LAPACK codes. (#191)
  * Optimize c/zgemm, trsm, dgemv_n, ddot, daxpy, dcopy on AMD Bulldozer. (Thank Werner Saar)
  * Add Intel Haswell support (using Sandybridge optimizations). (Thank Dan Luu)
  * Add AMD Piledriver support (using Bulldozer optimizations).
  * Fix the computational error in zgemm avx kernel on Sandybridge. (#237)
  * Fix the overflow bug in gemv.
  * Fix the overflow bug in multi-threaded BLAS3, getrf when NUM_THREADS is very large.(#214, #221, #246).
- rebase patch noexecstack.patch
- remove lapack source tarball since lapack sources are included in openblas sources
- increase NUM_THREAD from 32 to 64

OBS-URL: https://build.opensuse.org/request/show/184489
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=19
2013-07-27 13:48:56 +00:00
Corot Sebastien
1218b58a91 Accepting request 157145 from home:scorot:branches:science
- version 0.2.6
  * Improved OpenMP performance slightly. (d744c9)
  * Improved cblas.h compatibility with Intel MKL.(#185)
  * Fixed the overflowing bug in single thread cholesky factorization.
  * Fixed the overflowing buffer bug of multithreading hbmv and sbmv.(#174)
  * Added AMD Bulldozer x86-64 S/DGEMM AVX kernels. (Thank Werner Saar) We will tune the performance in future.
  * Auto-detect Intel Xeon E7540.
  * Fixed the overflowing buffer bug of gemv. (#173)
  * Fixed the bug of s/cdot about invalid reading NAN on x86_64. (#189)
- rebase patch0 openblas-0.2.6-libs.patch

OBS-URL: https://build.opensuse.org/request/show/157145
OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=18
2013-03-03 10:23:31 +00:00