For 128/256-bit vec_cond_expr, When mask operands is lt reg const0_rtx, blendv...

For 128/256-bit vec_cond_expr, When mask operands is lt reg const0_rtx, blendv can be used instead of avx512 mask.

gcc/ChangeLog:

	PR target/100648
	* config/i386/sse.md (*avx_cmp<mode>3_lt): New
	define_insn_and_split.
	(*avx_cmp<mode>3_ltint): Ditto.
	(*avx2_pcmp<mode>3_3): Ditto.
	(*avx2_pcmp<mode>3_4): Ditto.
	(*avx2_pcmp<mode>3_5): Ditto.

gcc/testsuite/ChangeLog:

	PR target/100648
	* g++.target/i386/avx2-pr54700-2.C: Adjust testcase.
	* g++.target/i386/avx512vl-pr54700-1a.C: New test.
	* g++.target/i386/avx512vl-pr54700-1b.C: New test.
	* g++.target/i386/avx512vl-pr54700-2a.C: New test.
	* g++.target/i386/avx512vl-pr54700-2b.C: New test.
	* gcc.target/i386/avx512vl-pr100648.c: New test.
	* gcc.target/i386/avx512vl-blendv-1.c: New test.
	* gcc.target/i386/avx512vl-blendv-2.c: New test.