rebase

[WIP] fix compilation on AIX

Add flang build to Github Actions

Fix OpenMP builds defaulting to singlethreading with OMP_PLACES or OMP_PROC_BIND set

Add LAPACK-TESTING to the cmake build

Change minimum gcc version for POWER10

As the MMA patches for POWER10 are backported to gcc10.2, changing
the minimum gcc version needed to build OpenBLAS for POWER10.

Changing mcpu option as power10

As compiler enabled mcpu option as power10, changing it from future.

Always obey omp_get_max_threads() when build with USE_OPENMP

RFC: Use -dumpfullversion to get minor version on gcc-7 and newer

Compatibility fix for gcc < 4.7

rebase

AIX build on POWER8 32bits

Add autodetection of Intel Comet Lake H and S models

rebase

Strip UTF8 byte order marker from source files

powerpc: Optimized SHGEMM kernel for POWER10

Add cpu detection support for comet lake U

Fix for #2671

This patch introduces new optimized version of SHGEMM kernel
using power10 Matrix-Multiply Assist (MMA) feature introduced in
POWER ISA v3.1. This patch makes use of new POWER10 compute instructions
for matrix multiplication operation.

Tested on simulator and there are no new test failures.

Comet Lake U CPUs have family: 6, model: 6, extended family: 0, and
extended model: 10 were not being correctly detected by GETARCH during
openblas builds and would show CORE=UNKNOWN and LIBCORE=unknown. This
commit adds the necessary information to cpuid_x86 to detect extended
family 10 model 6 and return the proper core information. It's
essentially just a skylake cpu, not skylake x, so I just took the used
the same return fields as skylake.

1. macro preprocessing for POWER8 and later kernels only
2. default buffer size used by AIX version of m4 is too small

rebase

POWER10 Optimized GEMM kernels

address vs2019 C4293 warning

This patch introduces new optimized version of ZGEMM kernel
using power10 Matrix-Multiply Assist (MMA) feature introduced in
POWER ISA v3.1. This patch makes use of new POWER10 compute instructions
for matrix multiplication operation.

Tested on simulator and there are no new test failures.
Cycles count reduced by 30-50%  compared to POWER9 version depending on
M/N/K sizes.