Before this commit, the "position < NUM_BUFFERS" loop condition from
blas_memory_free will be completely optimized away by GCC. This is
because the condition can only be false after undefined behavior has
already been invoked (reading past the end of an array). As a
consequence of this bug, GCC also removes the subsequent if statement
and all the code after the error label because all of it is dead.

This commit switches the loop condition around so it works as intended.

Optimized Implementations for ThunderX2T99

Add new targets for ARM64

prepared driver/level3 functions for UNROLL values, that are not a po…

Ref. #995, may possibly help solve issues seen in 660,883

USE NPROCESSOR_CONF instaed of NPORCESSOR_ONLN

Add Bay Trail "Pentium N3520" atom

to determine the number of CPU. In ARM platform,
online CPU will increasing when there is more workload.
while configure cpu is the max number of CPU.

Add Braswell (extended model 4, model 12) N3150 as Nehalem

If OpenBLAS is built using add_subdirectory(OpenBlas) as part of another project
then the paths set by CMAKE_XXX_DIR are relative to the parent project
and not the OpenBLAS project.

When the number of process can all be
accommodated within the current node,
then use cores from the current node only.

Fix #786

I cannot reproduce SEGFAULT of lapack-test with default stack size
on ARM Linux.

* Use stack allocation
* Disable multi-threading
* Ref #727

Second part of "support Intel Avoton via Nehalem kernel"

Let openblas_get_num_threads return the number of active threads

illumos fixes