runtime: improve memmove for short moves on ppc64

runtime: improve memmove for short moves on ppc64

This improves the performance of memmove for almost all moves <= 16 bytes
for the ppc64 assembler, improving linux/ppc64le, linux/ppc64, aix/ppc64.

Only the forward moves were changed, the backward moves were left as is.
Additional macro defines were added to improve the readability of the asm.

Results from power8:
name                      old time/op    new time/op    delta
Memmove/0                   5.70ns ± 0%    5.69ns ± 0%    -0.18%  (p=0.029 n=4+4)
Memmove/1                   5.54ns ± 0%    5.39ns ± 0%    -2.71%  (p=0.029 n=4+4)
Memmove/2                   6.31ns ± 0%    5.55ns ± 0%   -12.08%  (p=0.029 n=4+4)
Memmove/3                   7.41ns ± 0%    5.54ns ± 0%   -25.24%  (p=0.029 n=4+4)
Memmove/4                   8.41ns ± 0%    5.56ns ± 0%   -33.87%  (p=0.029 n=4+4)
Memmove/5                   10.1ns ± 5%     5.5ns ± 0%   -45.30%  (p=0.029 n=4+4)
Memmove/6                   10.3ns ± 0%     5.6ns ± 0%   -45.92%  (p=0.029 n=4+4)
Memmove/7                   11.4ns ± 0%     5.7ns ± 0%   -50.33%  (p=0.029 n=4+4)
Memmove/8                   5.66ns ± 0%    5.54ns ± 0%    -2.12%  (p=0.029 n=4+4)
Memmove/9                   5.66ns ± 0%    6.47ns ± 0%   +14.31%  (p=0.029 n=4+4)
Memmove/10                  6.67ns ± 0%    6.22ns ± 0%    -6.82%  (p=0.029 n=4+4)
Memmove/11                  7.83ns ± 0%    6.45ns ± 0%   -17.60%  (p=0.029 n=4+4)
Memmove/12                  8.91ns ± 0%    6.25ns ± 0%   -29.85%  (p=0.029 n=4+4)
Memmove/13                  9.81ns ± 0%    6.48ns ± 0%   -33.94%  (p=0.029 n=4+4)
Memmove/14                  10.7ns ± 1%     6.4ns ± 0%   -40.00%  (p=0.029 n=4+4)
Memmove/15                  11.8ns ± 0%     6.7ns ± 0%   -42.84%  (p=0.029 n=4+4)
Memmove/16                  5.63ns ± 0%    5.56ns ± 0%    -1.20%  (p=0.029 n=4+4)

Change-Id: I2de434f543c5a017395e0850fb9b9f7219583bbb
Reviewed-on: https://go-review.googlesource.com/c/go/+/223317
Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com>
Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>