make SMALL_MATRIX_OPT=1

Power10: Fix for SBGEMM

While testing bfloat16 sbgemm kernel, there are some failures for odd value inputs due to updating result for
additional bytes.

Refs. numpy/numpy#18422

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

Remove spurious casts from PPC parameters and fix compilation for older targets

Optimized sgemv_t for small N based on AVX512

While testing bfloat16 sbgemm kernel, there are some failures
for odd value inputs due to array access beyond the boundary.

The implementation in `riscv64/dot.c` fails the `test_dsdot` test, and
the generic kernel seems to have better precision. Tested on SiFive
FU740 (HiFive Unmatched) and QEMU.

Also see #1469.

Same as #1990.

GEMM: skylake: improve the performance when m is small

optimize on sgemv_n for small n

filter out -mavx flag on Sandybridge zgemm/ztrmm kernels

Support compilation with pre-C99 versions of MSVC

Update the intrinsic api to the offical name.

This patch uses vector pair pointer for input load operation
which helps to generate power10 lxvp instructions.

This patch makes use of Matrix-Multiply Assist (MMA)
feature introduced in POWER ISA v3.1 for zgemv_n and zgemv_t.

Remove Unnecessary/Erroneous Adds/Reads In sgemm_tcopy_16.S COPY1x8 Macro

This patch makes sure that recent POWER10 patches are used
only for little endian.

There appears to have been some code leak when copying from the COPY2x8
macro above where we're reading 8 bytes into d4-d7 directly after
reading 4 bytes into s4-s7. These 32 bytes in d4-7 are unused and can
possibly overrun the boundary of allocated memory -- Valgrind detected
this which is what dragged my attention to it for a 128,1 copy.

Additionally, there is no need to update the addresses stored in A0-A7
as the only possible paths after running this macro will overwrite A0-7
if looping to the next 8 rows, or overwrite A0-3 if moving to 4 rows --
in which case A4-7 are unused.

Add workaround for LAPACK testsuite failures with the NVIDIA HPC compiler on PPC

Move x86_64 DOMATCOPY_RT back to the C implementation