Merge pull request #646 from sergeyvfx/mm_mul_ps_inline #272

Job	Run time
host-win-msvc	55s
coding-style	16s
host-arm (armv7, none, none, g++-10)	3m 41s
host-win (x86_64)	44s
host-arm (armv7, none, none, clang++-11)	3m 43s
host-x86 (x86_64, g++-10)	2m 23s
host-arm (aarch64, none, none, g++-10)	2m 51s
host-win (armv7)	38s
host-x86 (x86_64, clang++-11)	24s
host-arm (aarch64, none, none, clang++-11)	3m 28s
host-win (aarch64)	45s
host-arm (aarch64, crypto+crc, none, g++-10)	2m 55s
host-arm (aarch64, crypto+crc, none, clang++-11)	3m 32s
host-arm (armv7, none, -mcpu=cortex-a32 -mfpu=neon-fp-armv8, g++-10)	3m 10s
host-arm (armv7, none, -mcpu=cortex-a32 -mfpu=neon-fp-armv8, clang++-11)	3m 25s
test-win-msvc	47s
	33m 37s

Provide feedback