cmd/compile: optimize RotateLeft8/16 on loong64

cmd/compile: optimize RotateLeft8/16 on loong64

goos: linux
goarch: loong64
pkg: math/bits
cpu: Loongson-3A6000 @ 2500.00MHz
             │  bench.old   │              bench.new               │
             │    sec/op    │    sec/op     vs base                │
RotateLeft8     1.401n ± 0%    1.201n ± 0%  -14.28% (p=0.000 n=20)
RotateLeft16   1.4010n ± 0%   0.8032n ± 0%  -42.67% (p=0.000 n=20)
geomean         1.401n        0.9822n       -29.90%

goos: linux
goarch: loong64
pkg: math/bits
cpu: Loongson-3A5000 @ 2500.00MHz
             │  bench.old  │              bench.new              │
             │   sec/op    │   sec/op     vs base                │
RotateLeft8    1.576n ± 0%   1.310n ± 0%  -16.88% (p=0.000 n=20)
RotateLeft16   1.576n ± 0%   1.166n ± 0%  -26.02% (p=0.000 n=20)
geomean        1.576n        1.236n       -21.58%

Change-Id: I39c18306be0b8fd31b57bd0911714abd1783b50e
Reviewed-on: https://go-review.googlesource.com/c/go/+/604738
Auto-Submit: abner chenc <chenguoqi@loongson.cn>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Tim King <taking@google.com>