NBMAX=4096 for gemvn, added sgemvn 8x8 for future

sgemv cgemv pairs

part of PR #1993 that was inadvertently misplaced into the toplevel directory

from #1993 , file should have gone into kernel/zarch

Various fixes for the new Z14 target

from patch provided by aarnez in #991

from patch provided by aarnez in #991

from patch provided by aarnez in #991

from patch provided by aarnez in #991

from patch provided by aarnez in #991

from patch provided by aarnez in #991

from patch provided by aarnez in #991

from patch provided by aarnez in #991

[ZARCH] Z14 Support, BLAS 1/2 single precision implementations

as reported by aarnez in #1990

as suggested in #1990

Correct naming of getrf_parallel object

Fix include directory of exported targets

Better support for MSVC/Windows in CMake (v0.3.x)

Modrenize R benchmarks slightly

Change ARMV8 target with BINARY=32 to ARMV7 automatically

fixes #1961

fixes #1984

Shift transition to multithreading towards larger matrix sizes

Report SkylakeX as Haswell if compiler does not support AVX512

... or make was invoked with NO_AVX512=1

Increase Zen SWITCH_RATIO to 16

fixes #1974

following GEMM benchmarks on Ryzen2700X. For #1464

See #1886 and JuliaRobotics issue 500. trsm benchmarks on Haswell and Zen showed that with these values performance is roughly doubled for matrix sizes between 8x8 and 14x14, and still 10 to 20 percent better near the new cutoff at 32x32.