Support 32/64-bit vectorization for conversion between _Float16 and integer/float.

Support 32/64-bit vectorization for conversion between _Float16 and integer/float.

gcc/ChangeLog:

	* config/i386/mmx.md (V2FI_32): New mode iterator
	(movd_v2hf_to_sse): Rename to ..
	(movd_<mode>_to_sse): .. this.
	(movd_v2hf_to_sse_reg): Rename to ..
	(movd_<mode>_to_sse_reg): .. this.
	(fix<fixunssuffix>_trunc<mode><mmxintvecmodelower>2): New
	expander.
	(fix<fixunssuffix>_truncv2hfv2si2): Ditto.
	(float<floatunssuffix><mmxintvecmodelower><mode>2): Ditto.
	(float<floatunssuffix>v2siv2hf2): Ditto.
	(extendv2hfv2sf2): Ditto.
	(truncv2sfv2hf2): Ditto.
	* config/i386/sse.md (*vec_concatv8hf_movss): Rename to ..
	(*vec_concat<mode>_movss): .. this.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/part-vect-hf-convert-1.c: New test.