Movddup can take a memory operand, so we can save a move from gp reg to
xmm reg in that case. No problem with unaligned memory since we are
loading 64 bits (not 128 bits).

Also drive-by comment on i32x4.splat, it uses pshufd, which can also take
a memory operand (saving a mov), but we need aligned memory for that
first.

Bug: v8:9198
Change-Id: I55969888db1debb6ed4d193f767589d0da598386
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2567538Reviewed-by: Bill Budge <bbudge@chromium.org>
Commit-Queue: Zhi An Ng <zhin@chromium.org>
Cr-Commit-Position: refs/heads/master@{#71580}