to avoid surprises from defining either as zero. Fixes #2035 by addressing some concerns from #1422

Make sure that AVX512 is disabled in 32bit builds

for #2033

Make x86_32 imply NO_AVX2, NO_AVX512 in addition to NO_AVX

as xcode10 deprecated i386

fixes #2033

Move one of clobber fixes to right place

to make compilation complete reliably within the 1h limit again

revert workaround introduced for issue #1332 as the actual cause appears to be my incorrect fix from #1262 (see #1388)

same bug as seen in #1388, somehow missed in corresponding PR #1389

Fix inline assembly constraints in Bulldozer TRSM kernels

Fix inline assembly constraints in various x86_64 GEMVN kernels

Reword/expand comments in Makefile.rule

rework indices to allow marking i,as and bs as both input and output (marked operand n1 as well for simplicity). For #2009

rework indices to allow marking argument lda as input and output.

rework indices to allow marking argument lda4 as input and output. For #2009

Fix wrong constraints in inline assembly of Haswell DTRSM kernel

add note about NUM_THREADS for package maintainers, add examples of programs that cause affinity troubles

for #2009

Fix unannounced modification of input operand 8 (lda4) in Haswell GEMVN microkernel

With the Intel compiler on Linux, prefer ifort for the final link step

icc has known problems with mixed-language builds that ifort can handle just fine. Fixes #1956

Fixes miscompilation with gcc9 -ftree-vectorize (related to issue #2009)

dgemv_kernel_4x4(Haswell): add missing clobbers for xmm0,xmm1,xmm2,xmm3

This fixes a crash in dblat2 when OpenBLAS is compiled using
-march=znver1 -ftree-vectorize -O2

See also:
https://github.com/easybuilders/easybuild-easyconfigs/issues/7180

* Fix missing clobber in blas_quickdivide assembly

Fix invalid memory access in PPC gemm_beta

Fixes #2011 (as suggested by davemq), assuming typo by K.Goto

Fixes #2011 (as suggested by davemq) presuming typo by K.Goto

[ZARCH] Many improvements

Fix declaration of input arguments in x86_64 GEMV, SYMV and DSCAL

Argument 0 is modified so should be input and output

Arguments 0 and 1 are both input and output

Argument 0 is modified as it doubles as a counter

Arguments 0 and 1 need to be tagged as both input and output

* Fix potential memory leak in cpu enumeration with glibc

An early return after a failed call to sched_getaffinity would leak the previously allocated cpu_set_t. Wrong calculation of the size argument in that call increased the likelyhood of that failure. Fixes #2003

* Restore dropped patches in the non-TLS branch of memory.c

As discovered in #2002, the reintroduction of the "original" non-TLS version of memory.c as an alternate branch had inadvertently used ba1f91f rather than a8002e2 , thereby dropping the commits for #1450, #1468, #1501, #1504 and #1520.