From f5d2341b5717c2c56f8a2753d47d88332b640eca7cb813ecb025c832ad141240 Mon Sep 17 00:00:00 2001 From: Christian Goll Date: Mon, 10 Jun 2024 06:46:37 +0000 Subject: [PATCH] Accepting request 1179598 from home:eeich:branches:science - Update to version 0.3.27 (boo#1225869): General: * Added initial (generic) support for the `CSKY` architecture. * Capped the maximum number of threads used in `GEMM`, `GETRF` and `POTRF` to avoid creating underutilized or idle threads. * Sped up multithreaded `POTRF` on all platforms. * Added extension `openblas_set_num_threads_local()` that returns the previous thread count. * Re-evaluated the `SGEMV` and `DGEMV` load thresholds to avoid activating multithreading for too small workloads. * Improved the fallback code used when the precompiled number of threads is exceeded, and made it callable multiple times during the lifetime of an instance. * Added CBLAS interfaces for the BLAS extensions `?AMIN`,`?AMAX`, `CAXPYC` and `ZAXPYC`. * Fixed a potential buffer overflow in the interface to the `GEMMT` kernels. * Fixed use of incompatible pointer types in `GEMMT` and `C`/`ZAXPBY` as flagged by GCC-14. * Fixed unwanted case sensitivity of the character parameters in `?TRTRS` sped up the OpenMP thread management code. * Fixed sizing of logical variables in `INTERFACE64` builds of the C version of LAPACK. * Fixed inclusion of new LAPACK and LAPACKE functions from LAPACK 3.11 in the shared library. * Modified the error thresholds for `SGS`/`DGS` functions in the LAPACK testsuite to suppress spurious errors. * Added support for calling ?NRM2 with a negative increment value on all architectures. * Fixed handling of the `OPENBLAS_LOOPS` variable in several OBS-URL: https://build.opensuse.org/request/show/1179598 OBS-URL: https://build.opensuse.org/package/show/science/openblas?expand=0&rev=175 --- OpenBLAS-0.3.26.tar.gz | 3 -- OpenBLAS-0.3.27.tar.gz | 3 ++ openblas.changes | 64 ++++++++++++++++++++++++++++++++++++++++++ openblas.spec | 6 ++-- 4 files changed, 70 insertions(+), 6 deletions(-) delete mode 100644 OpenBLAS-0.3.26.tar.gz create mode 100644 OpenBLAS-0.3.27.tar.gz diff --git a/OpenBLAS-0.3.26.tar.gz b/OpenBLAS-0.3.26.tar.gz deleted file mode 100644 index c5ae4eb..0000000 --- a/OpenBLAS-0.3.26.tar.gz +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4e6e4f5cb14c209262e33e6816d70221a2fe49eb69eaf0a06f065598ac602c68 -size 24404912 diff --git a/OpenBLAS-0.3.27.tar.gz b/OpenBLAS-0.3.27.tar.gz new file mode 100644 index 0000000..c9a2ea8 --- /dev/null +++ b/OpenBLAS-0.3.27.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2d68b1564fe2b13bc292672608e9cdeeeb6dc34995512e65c3b10f4599e897 +size 24493704 diff --git a/openblas.changes b/openblas.changes index c64a00f..5524c62 100644 --- a/openblas.changes +++ b/openblas.changes @@ -1,3 +1,67 @@ +------------------------------------------------------------------- +Sun Jun 9 07:07:51 UTC 2024 - Egbert Eich + +- Update to version 0.3.27 (boo#1225869): + General: + * Added initial (generic) support for the `CSKY` architecture. + * Capped the maximum number of threads used in `GEMM`, `GETRF` + and `POTRF` to avoid creating underutilized or idle threads. + * Sped up multithreaded `POTRF` on all platforms. + * Added extension `openblas_set_num_threads_local()` that returns + the previous thread count. + * Re-evaluated the `SGEMV` and `DGEMV` load thresholds to avoid + activating multithreading for too small workloads. + * Improved the fallback code used when the precompiled number of + threads is exceeded, and made it callable multiple times + during the lifetime of an instance. + * Added CBLAS interfaces for the BLAS extensions `?AMIN`,`?AMAX`, + `CAXPYC` and `ZAXPYC`. + * Fixed a potential buffer overflow in the interface to the + `GEMMT` kernels. + * Fixed use of incompatible pointer types in `GEMMT` and + `C`/`ZAXPBY` as flagged by GCC-14. + * Fixed unwanted case sensitivity of the character parameters in + `?TRTRS` sped up the OpenMP thread management code. + * Fixed sizing of logical variables in `INTERFACE64` builds of + the C version of LAPACK. + * Fixed inclusion of new LAPACK and LAPACKE functions from + LAPACK 3.11 in the shared library. + * Modified the error thresholds for `SGS`/`DGS` functions in + the LAPACK testsuite to suppress spurious errors. + * Added support for calling ?NRM2 with a negative increment value + on all architectures. + * Fixed handling of the `OPENBLAS_LOOPS` variable in several + benchmarks. + * Integrated fixes from the Reference-LAPACK project: + Increased accuracy in `C`/`ZLARFGP` (Reference-LAPACK PR 981). + x86: + * Fixed handling of `NaN` and `Inf` arguments in `ZSCAL`. + x86-64: + * Removed all instances of `sched_yield()` on Linux and BSD. + * Fixed handling of `NaN` and `Inf` arguments in `ZSCAL`. + * Added compiler checks for `AVX512BF16` compatibility. + * Fixed cpu handling fallbacks for Sapphire Rapids with disabled + AVX2 in `DYNAMIC_ARCH` mode. + * Fixed extensions `SCSUM` and `DZSUM`. + * Improved `GEMM` performance for ZEN targets. + arm64: + * Added initial support for the Cortex-A76 cpu. + * Fixed handling of `NaN` and `Inf` arguments in `ZSCAL`. + * Fixed default compiler options for gcc (-march and -mtune). + * Added support for the NeoverseV2 cpu in `DYNAMIC_ARCH` builds. + * Corrected `SCSUM` kernels (erroneously duplicating `SCASUM` + behaviour). + * Added SVE-enabled kernels for `CSUM`/`ZSUM`. + * Worked around an inaccuracy in the `NRM2` kernels for NeoverseN1. + power: + * Improved performance of `SGEMM` on POWER8/9/10. + * Improved performance of `DGEMM` on POWER10. + zarch: + * Fixed handling of `NaN` and `Inf` arguments in `ZSCAL`. + * Fixed calculation of `?SUM` on Z13. +- LIBNAMESUFFIX semantics have changed: no separator will be added. + Adjusted in spec file. + ------------------------------------------------------------------- Thu Feb 15 08:27:33 UTC 2024 - Egbert Eich diff --git a/openblas.spec b/openblas.spec index 49b0790..2d540db 100644 --- a/openblas.spec +++ b/openblas.spec @@ -18,8 +18,8 @@ %global flavor @BUILD_FLAVOR@%{nil} -%define _vers 0_3_26 -%define vers 0.3.26 +%define _vers 0_3_27 +%define vers 0.3.27 %define so_v 0 %define pname openblas @@ -421,7 +421,7 @@ EOF # Do not use LIBNAMESUFFIX for new builds as it will not allow # the different flavors to be plugin replacements of each other %if 0%{?suse_version} <= 1500 && %{without hpc} -%define libnamesuffix LIBNAMESUFFIX=%flavor +%define libnamesuffix LIBNAMESUFFIX=_%{flavor} %endif make MAKE_NB_JOBS=$jobs %{?openblas_target} %{?build_flags} \ %{?openblas_opt} \