cmd/compile/internal/ssa: optimize if control flow rule of loong64

goos: linux
goarch: loong64
pkg: cmd/compile/internal/test
cpu: Loongson-3A6000 @ 2500.00MHz
                                 │     old     │                 new                 │
                                 │   sec/op    │   sec/op     vs base                │
Switch8Predictable                 2.908n ± 0%   2.702n ± 2%   -7.10% (p=0.000 n=10)
Switch8Unpredictable               13.29n ± 0%   12.45n ± 0%   -6.32% (p=0.000 n=10)
Switch32Predictable                3.069n ± 0%   3.137n ± 0%   +2.23% (p=0.000 n=10)
Switch32Unpredictable              15.11n ± 0%   13.21n ± 0%  -12.57% (p=0.000 n=10)
SwitchStringPredictable            5.165n ± 0%   4.447n ± 0%  -13.90% (p=0.000 n=10)
SwitchStringUnpredictable          18.26n ± 0%   16.86n ± 0%   -7.67% (p=0.000 n=10)
SwitchTypePredictable              3.961n ± 0%   3.405n ± 0%  -14.04% (p=0.000 n=10)
SwitchTypeUnpredictable            17.92n ± 0%   16.17n ± 0%   -9.77% (p=0.000 n=10)
SwitchInterfaceTypePredictable     8.463n ± 0%   8.492n ± 0%   +0.34% (p=0.001 n=10)
SwitchInterfaceTypeUnpredictable   23.70n ± 0%   22.48n ± 0%   -5.15% (p=0.000 n=10)
geomean                            8.672n        8.018n        -7.54%

Change-Id: Iefbf8e9e784905779f1ebc9fd6a9b7a28cf2f6f4
Reviewed-on: https://go-review.googlesource.com/c/go/+/620815
Reviewed-by: abner chenc <[email protected]>
LUCI-TryBot-Result: Go LUCI <[email protected]>
Reviewed-by: Michael Pratt <[email protected]>
Reviewed-by: Dmitri Shuralyov <[email protected]>

Author: limeidan

src/cmd/compile/internal/ssa/_gen/LOONG64.rules

@@ -453,6 +453,7 @@
 (GetCallerPC ...) => (LoweredGetCallerPC ...)
 
 (If cond yes no) => (NE (MOVBUreg <typ.UInt64> cond) yes no)
+(MOVBUreg x:(XOR (MOVVconst [1]) ((SGT|SGTU) _ _))) => x
 
 // Write barrier.
 (WB ...) => (LoweredWB ...)