internal/bytealg: improve asm for memequal on ppc64x

This includes two changes to the memequal function.

Previously the asm implementation on ppc64x for Equal called the internal
function memequal using a BL, whereas the other asm implementations for
bytes functions on ppc64x used BR. The BR is preferred because the BL
causes the calling function to stack a frame. This changes Equal so it
uses BR and is consistent with the others.

This also uses vsx instructions where possible to improve performance
of the compares for sizes over 32.

Here are results from the sizes affected:

Equal/32             8.40ns ± 0%     7.66ns ± 0%    -8.81%  (p=0.029 n=4+4)
Equal/4K              193ns ± 0%      144ns ± 0%   -25.39%  (p=0.029 n=4+4)
Equal/4M              346µs ± 0%      277µs ± 0%   -20.08%  (p=0.029 n=4+4)
Equal/64M            7.66ms ± 1%     7.27ms ± 0%    -5.10%  (p=0.029 n=4+4)

Change-Id: Ib6ee2cdc3e5d146e2705e3338858b8e965d25420
Reviewed-on: https://go-review.googlesource.com/c/143060
Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com>
Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
Reviewed-by: David Chase <drchase@google.com>

0 files changed, 0 insertions, 0 deletions