VSHF_B2_SB(e0, r0, e1, r1, mask, mask, d0, d1);
VSHF_B2_SB(e2, r2, e3, r3, mask, mask, d2, d3);
VSHF_B2_SB(e4, r4, e5, r5, mask, mask, d4, d5);
VSHF_B2_SB(e6, r6, e7, r7, mask, mask, d6, d7);
/* Final sequence of operations over-write original dst */
VSHF_B2_SB(e0, r0, e1, r1, mask, mask, d0, d1);
VSHF_B2_SB(e2, r2, e3, r3, mask, mask, d2, d3);
VSHF_B2_SB(e4, r4, e5, r5, mask, mask, d4, d5);
VSHF_B2_SB(e6, r6, e7, r7, mask, mask, d6, d7);
/* Final sequence of operations over-write original dst */