Travis recently appears unable to find a matching homebrew package for 32bit gfortran,
and the IOS crossbuild suffered from excessive output due to the known problem with "ASMNAME redefined"
warnings when CFLAGS is set in the environment

rebase

Fix PPC970 big-endian support

The altivec versions of SGEMM and CGEMM fail most test in LAPACK-TESTING when compiled for big endian, STRSM/CTRSM even cause segfaults. The rot kernels either fail the corresponding utest or lead to failures in LAPACK-TESTING.

as the respective PPC970 "altivec" kernels give wrong results when compiled for big endian

Fix potential issue in the c/z blas3 ctests

AVX512 CGEMM & ZGEMM kernels

96-99% 1-thread performance of MKL2018

rebase

Optimize SGEMM on SKYLAKEX CPUs

Disable three-operand DCBT on PPC970 regardless of operating system

Disable IDAMIN/MAX and IZAMIN/MAX optimizations on big-endian POWER8

Remove obsolete workarounds for IOS on ARMV8

There seems to be no advantage to the three-operand form used in the earliest GotoBLAS kernels, and it causes compilation problems  on other than the previously special-cased platforms as well

resync with upstream

Fixed a minor cmake problem, occuring when DYNAMIC_ARCH=ON and CMAKE_C_FLAGS was empty

Add support for NetBSD by adding it to the existing xBSD conditionals

Both forms are seen on NetBSD (#2288)

Improve support for g95 and non-GNU ld

Fix netlib 3.7/3.8 function enumeration for linktest

Optimize RPCC function on ARM64

Fixup x86 cpuid changes from #2283

Auto-add "-fno-second-underscore" option to make LAPACKE compile (as it calls LAPACK functions that may have gotten a second underscore added otherwise). Also support -R for rpath when parsing compiler directives in f_check

to allow linktest to pass with a compiler that adds a second underscore to such names

as I find conflicting information on accessibility from non-priviledged processes

* Fix source typo

Found via `codespell -q 3 -L amin,als,ba,dum,mone,nd,nto,orign -S Changelog.txt,./lapack*`

* Remove beta-thread function per request

#2283 had inadvertently removed Goldmont+, and cpuid was reporting a mix of Core2 and Pentium2 for some QEMU configurations

resync with upstream

AVX512 DGEMM kernel

90% MKL 1-thread performance.