Ref #731

Fixes for old outstanding bugs in CBLAS test programs

The NTRA argument can be equal to -1 if one does not want a snapshot file
(and this is the case with sample data {s,d,c,z}in3).
The routines {S,D,C,Z}PRCN3 will try to use their first argument as an output
unit number, so we avoid calling them when NTRA < 0.

Patch originally written by Camm Maguire.

The SNAME variable contains names of C functions like "cblas_dgemv".
Apparently the code was not taking into account the 6-letter "cblas_"
prefix when determining the task to be done.

The issue does not affect c_{s,d,c}blat2.f, which use the correct
offsetting.

Patch originally written by Camm Maguire.

* Fix commit 87a2ccc
* Close #736

Factorize MAX_STACK_ALLOC code to common_stackalloc.h

Ref #727

Do not use vsub to clear the register values

added optimized trsm_kernels

Fix make MAX_STACK_ALLOC=0

Close #722

It's no longer required to modify Makefile.rule to disable
stack allocation. It's now possible to run:

make MAX_STACK_ALLOC=0

Fix detection of AMD E2-3200

Allow to force the number of parallel make job

This is particularly useful when using distcc

Fix Dormbr to perform the correct size operations with RowMajor

Fix Dormlq to perform the correct size operations with RowMajor

Fixes issue #712

Fixes issue #615.

fix makefile warning when renaming symbols

use different names for `openblas*.renamed` between osx and other unices, fixes
```
Makefile:121: warning: overriding commands for target `../libopenblas64_p-r0.2.15.a.renamed'
Makefile:100: warning: ignoring old commands for target `../libopenblas64_p-r0.2.15.a.renamed'
```

also clean `*.renamed`

Thank matzeri's patch.

(Visual Studio) Don't use C99 complex numbers when building C++ code.

Cortex A57 fixes and Lapack 3.6.0