Use unaligned data types for unaligned intrinsics #112

Job	Run time
host-x86 (x86_64, g++-10)	1m 54s
host-arm (armv7, none, none, g++-10)	3m 10s
host-x86 (x86_64, clang++-11)	17s
coding-style	14s
host-arm (armv7, none, none, clang++-11)	3m 30s
host-win (x86_64)	59s
host-arm (aarch64, none, none, g++-10)	3m 3s
host-win (armv7)	50s
host-arm (aarch64, none, none, clang++-11)	3m 39s
host-win-msvc	2m 48s
host-win (aarch64)	49s
host-arm (aarch64, crypto+crc, none, g++-10)	3m 15s
host-arm (aarch64, crypto+crc, none, clang++-11)	3m 39s
host-arm (armv7, none, -mcpu=cortex-a32 -mfpu=neon-fp-armv8, g++-10)	3m 34s
host-arm (armv7, none, -mcpu=cortex-a32 -mfpu=neon-fp-armv8, clang++-11)	4m 2s
test-win-msvc	53s
	36m 36s

Provide feedback