Add half precision gemm for bfloat16 in OpenBLAS

Add a Windows/CL build job to the Azure CI

Revert "Add Windows build job on Azure CI"

This reverts commit e1e543b145.

* Add Windows-CL build job on Azure

rebase

[OpenBLAS]: benchmark error of potrf

[description]: when the matrix size goes higher than 5800 during the cpotrf test, error info, such as "Potrf info = 5679", will be returned on ARM64 and x86 machines. Uplo = L & F.
[solution]: changed the func for building the matrix so that the complex Hermitian matrix can stay positive definite during the computation.
[dts]:

Update and reformat README

Add a drone.io multithread test for x86_64

This patch adds support for bfloat16 data type matrix multiplication kernel.
For architectures that don't support bfloat16, it is defined as unsigned short
(2 bytes).  Default unroll sizes can be changed as per architecture as done for
SGEMM and for now 8 and 4 are used for M and N.  Size of ncopy/tcopy can be
changed as per architecture requirement and for now, size 2 is used.

Added shgemm in kernel/power/KERNEL.POWER9 and tested in powerpc64le and
powerpc64.  For reference, added a small test compare_sgemm_shgemm.c to compare
sgemm and shgemm output.

This patch does not cover OpenBLAS test, benchmark and lapack tests for shgemm.
Complex type implementation can be discussed and added once this is approved.

Add a read memory barrier to the traversal of the buffer slot list

Handle unaligned data in the SSE2 copy kernel

should have no performance impact on reasonably modern cpus and fixes occasional crashes in actual user code.

Needed on systems with weak memory ordering - the inferior, partially working fix from #2544 was already removed in #2551

rebase

Increase BUFFER_SIZEs and add a safeguard; supply GEMM_R for POWER8/9