math/big: rewrite subVW to use fast path on s390x

math/big: rewrite subVW to use fast path on s390x

This CL replaces the original subVW implementation with a implementation
that uses a similar idea as CL 164968.

When we know the borrow bit is zero, we can copy the rest of words as
they will not be updated. Also, since we are copying vector of a words,
a faster implementation of copy is written in this CL to copy a word or
multiple words at a time.

Benchmarks:
name             old time/op    new time/op     delta
SubVW/1-18         4.43ns ± 0%     3.82ns ± 0%   -13.85%  (p=0.000 n=20+20)
SubVW/2-18         5.39ns ± 0%     4.25ns ± 0%   -21.23%  (p=0.000 n=20+20)
SubVW/3-18         6.29ns ± 0%     4.65ns ± 0%   -26.07%  (p=0.000 n=16+19)
SubVW/4-18         6.08ns ± 2%     4.84ns ± 0%   -20.43%  (p=0.000 n=20+20)
SubVW/5-18         7.06ns ± 1%     4.93ns ± 0%   -30.18%  (p=0.000 n=20+20)
SubVW/10-18        10.3ns ± 2%      7.2ns ± 0%   -30.35%  (p=0.000 n=20+19)
SubVW/100-18       48.0ns ± 4%     17.6ns ± 0%   -63.32%  (p=0.000 n=18+19)
SubVW/1000-18       448ns ±10%      236ns ± 1%   -47.24%  (p=0.000 n=20+20)
SubVW/10000-18     4.83µs ± 5%     2.96µs ± 0%   -38.73%  (p=0.000 n=20+19)
SubVW/100000-18    46.6µs ± 3%     30.6µs ± 1%   -34.30%  (p=0.000 n=20+20)
[Geo mean]         56.3ns          37.0ns        -34.24%

name             old speed      new speed       delta
SubVW/1-18       1.80GB/s ± 0%   2.10GB/s ± 0%   +16.16%  (p=0.000 n=20+20)
SubVW/2-18       2.97GB/s ± 0%   3.77GB/s ± 0%   +26.95%  (p=0.000 n=20+20)
SubVW/3-18       3.82GB/s ± 0%   5.16GB/s ± 0%   +35.26%  (p=0.000 n=20+19)
SubVW/4-18       5.26GB/s ± 1%   6.61GB/s ± 0%   +25.59%  (p=0.000 n=20+20)
SubVW/5-18       5.67GB/s ± 1%   8.11GB/s ± 0%   +43.12%  (p=0.000 n=20+20)
SubVW/10-18      7.79GB/s ± 2%  11.17GB/s ± 0%   +43.52%  (p=0.000 n=20+19)
SubVW/100-18     16.7GB/s ± 4%   45.5GB/s ± 0%  +172.61%  (p=0.000 n=18+20)
SubVW/1000-18    17.9GB/s ± 9%   33.9GB/s ± 1%   +89.25%  (p=0.000 n=20+20)
SubVW/10000-18   16.6GB/s ± 5%   27.0GB/s ± 0%   +63.08%  (p=0.000 n=20+19)
SubVW/100000-18  17.2GB/s ± 2%   26.1GB/s ± 1%   +52.18%  (p=0.000 n=20+20)
[Geo mean]       7.25GB/s       11.03GB/s        +52.01%

Change-Id: I32e99cbab3260054a96231d02b87049c833ab77e
Reviewed-on: https://go-review.googlesource.com/c/go/+/227297
Reviewed-by: Michael Munday <mike.munday@ibm.com>
Run-TryBot: Michael Munday <mike.munday@ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>