The definition of Shufps is wrong, we are incorrectly passing 0 as the
immediate in all cases. No tests broke because we only used Shufps for
splats, which has imm8 == 0 anyway.

Also, it was using movss, which only moves a single 32-bit. Because we
were using it only for f32x4 splat, this ended up being enough (imm8 ==
0 meant that we only shuffled the low 32-bit). This is fixed to use
movaps, which moves the entire 128-bit register.

Also tweak the definition of Shufps to take 4 arguments. `vshufps dst,
src1, src2, imm8` shuffles src1 and src2 into dst. `shufps dst, src,
imm8`, shuffles dst and src into dst.

So `Shufps(dst, src, imm8)` is ambiguous in the AVX case, it could be:
1. vshufps(dst, src, src, imm8), or
2. vshufps(dst, dst, src, imm8)

2. is more likely to be the intended behavior, but it introduces a false
dependency on the value of dst.

With `Shufps(dst, src1, src2, imm8)`, it is clearer what the behavior
should be:
1. shufps(dst, src2, imm8) matches the AVX behavior IFF dst == src1.

Change-Id: I60dc4ec868023d28d00f2b09d2c53b82a729bc4d
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2591849Reviewed-by: Clemens Backes <clemensb@chromium.org>
Commit-Queue: Zhi An Ng <zhin@chromium.org>
Cr-Commit-Position: refs/heads/master@{#71775}