libstdc++: Add masked ++/-- implementation for sizeof < 16

libstdc++: Add masked ++/-- implementation for sizeof < 16

This resolves further failures (-Wreturn-type warnings) and test
failures for where-* tests targeting AVX-512.

Signed-off-by: Matthias Kretz <m.kretz@gsi.de>
libstdc++-v3/ChangeLog:

	* include/experimental/bits/simd_x86.h (_S_masked_unary):
	Cast inputs < 16 bytes to 16 byte vectors before calling the
	right subtraction builtin. Before returning, truncate to the
	return vector type.

(cherry picked from commit a6c630c314b099f64d79055964d88b257459cf13)