On top of the previous vec_merge simplifications [1] we can add this pattern to perform
a store of a vec_concat of two 64-bit values in distinct registers as an STP.
This avoids constructing such a vector explicitly in a register and storing it as
a Q register.
This way for the code in the testcase we can generate:

construct_lane_1:
        ldp     d1, d0, [x0]
        fmov    d3, 1.0e+0
        fmov    d2, 2.0e+0
        fadd    d4, d1, d3
        fadd    d5, d0, d2
        stp     d4, d5, [x1, 32]
        ret

construct_lane_2:
        ldp     x2, x0, [x0]
        add     x3, x2, 1
        add     x4, x0, 2
        stp     x3, x4, [x1, 32]
        ret

instead of the current:
construct_lane_1:
        ldp     d0, d1, [x0]
        fmov    d3, 1.0e+0
        fmov    d2, 2.0e+0
        fadd    d0, d0, d3
        fadd    d1, d1, d2
        dup     v0.2d, v0.d[0]
        ins     v0.d[1], v1.d[0]
        str     q0, [x1, 32]
        ret

construct_lane_2:
        ldp     x2, x3, [x0]
        add     x0, x2, 1
        add     x2, x3, 2
        dup     v0.2d, x0
        ins     v0.d[1], x2
        str     q0, [x1, 32]
        ret

Bootstrapped and tested on aarch64-none-linux-gnu.

[1] https://gcc.gnu.org/ml/gcc-patches/2017-06/msg00272.html
    https://gcc.gnu.org/ml/gcc-patches/2017-06/msg00273.html
    https://gcc.gnu.org/ml/gcc-patches/2017-06/msg00274.html

	* config/aarch64/aarch64-simd.md (store_pair_lanes<mode>):
	New pattern.
	* config/aarch64/constraints.md (Uml): New constraint.
	* config/aarch64/predicates.md (aarch64_mem_pair_lanes_operand): New
	predicate.

	* gcc.target/aarch64/store_v2vec_lanes.c: New test.

From-SVN: r254551