Add GEMM optimization for small matrix and single/double kernel for skylakex

skylakex sgemv_t kernel fix

Add support for windows/arm64 targets with clang

* Add OSX build job with Homebrew OpenMP in a CMAKE build
* Check install step on OSX/gcc to make sure all include files are generated and installed as intended
* Add mixed clang/gfortran build with cmake on OSX
* move IOS ARMV7/ARMV8 crossbuilds from travis to azure

Delete the macro instruction "li" and use "li.d" instead

Change-Id: Icff7981e2eb7df29ba5af1f8eb5be8443c67450f

Fix undefined behavior checking the size of ARGC

POWER10: Improving dasum performance

Unrolling a loop in dasum micro code to help in improving
POWER10 performance.

Disable all x86 jobs on Travis

Update Travis badge in README

Add all SBGEMM kernels for IA AVX512-BF16 based platforms

Added all SBGEMM kernels including NN/NT/TN/TT for both ColMajor and
RowMajor, based on AVX512-BF16 ISA set on IA.

Signed-off-by: Chen, Guobing <guobing.chen@intel.com>

If no customized GEMM_SMALL_M_PERMIT kernel defined, it will just by pass to normal path.

Improve the "tried to allocate too many buffers" error message