blas_server_avail was read without holding server_lock. If multiple threads call blas_thread_shutdown simultaneously, for example, by calling fork(), then they can attempt to shut down multiple times. This can lead to a segmentation fault.

Fix get_num_procs()  in the USE_TLS branch for non-glibc systems

Recognize Intel Tiger Lake CPUID as SkylakeX

Fix build issue on POWER8 with DYNAMIC_ARCH

Running make DYNAMIC_ARCH=1 on POWER 8 BE with gcc10.2 version, gives
the following error due to the difference in UNROLL_M/N.
'No rule to make target 'dgemm_incopy_POWER10.o', needed by kernel'

Enable optimized Haswell/AVX2 kernels for sasum/dasum and srot/drot on Ryzen

Addressed issue #3100 - removing an unnecessary write to the include directory

Strip pkgversion info from compiler version string before comparing

rebase

build openmp on appveyor

Fix Cooperlake/DYNAMIC_ARCH builds with clang on Windows

Co-authored-by: xoviat <49173759+xoviat@users.noreply.github.com>

add embedded option

fix copy-paste error in build rules for cblas_crotg and cblas_zrotg

Optimize cscal function for POWER10

This patch makes use of new POWER10 vector pair instructions for
loads and stores.

Fix calculation of the non-exceptional shift values in LAPACK complex QZ

rebase

Apply Reference-LAPACK PR 477 for convergence problems in CHGEQZ/ZHGEQZ

rebase

Add Ci job for ARM64/gcc10 DYNAMIC_ARCH

Fix null pointer check in blas_memory_alloc

Add DYNAMIC_LIST support for ARM64

rebase

Optimize s/dscal function for POWER10

This patch makes use of new POWER10 vector pair instructions for
loads and stores.