cmd/compile: optimize math.Copysign on arm64

Add rewrite rules to optimize math.Copysign() when the second
argument is negative floating point constant.

For example, math.Copysign(c, -2): The previous compile output is
"AND $9223372036854775807, R0, R0; ORR $-9223372036854775808, R0, R0".
The optimized compile output is "ORR $-9223372036854775808, R0, R0"

Math package benchmark results.
name                   old time/op  new time/op  delta
Copysign-8             2.61ns ± 2%  2.49ns ± 0%  -4.55%  (p=0.000 n=10+10)
Cos-8                  43.0ns ± 0%  41.5ns ± 0%  -3.49%  (p=0.000 n=10+10)
Cosh-8                 98.6ns ± 0%  98.1ns ± 0%  -0.51%  (p=0.000 n=10+10)
ExpGo-8                 107ns ± 0%   105ns ± 0%  -1.87%  (p=0.000 n=10+10)
Exp2Go-8                100ns ± 0%   100ns ± 0%  +0.39%  (p=0.000 n=10+8)
Max-8                  6.56ns ± 2%  6.45ns ± 1%  -1.63%  (p=0.002 n=10+10)
Min-8                  6.66ns ± 3%  6.47ns ± 2%  -2.82%  (p=0.006 n=10+10)
Mod-8                   107ns ± 1%   104ns ± 1%  -2.72%  (p=0.000 n=10+10)
Frexp-8                11.5ns ± 1%  11.0ns ± 0%  -4.56%  (p=0.000 n=8+10)
HypotGo-8              19.4ns ± 0%  19.4ns ± 0%  +0.36%  (p=0.019 n=10+10)
Ilogb-8                8.63ns ± 0%  8.51ns ± 0%  -1.36%  (p=0.000 n=10+10)
Jn-8                    584ns ± 0%   585ns ± 0%  +0.17%  (p=0.000 n=7+8)
Ldexp-8                13.8ns ± 0%  13.5ns ± 0%  -2.17%  (p=0.002 n=8+10)
Logb-8                 10.2ns ± 0%   9.9ns ± 0%  -2.65%  (p=0.000 n=10+7)
Nextafter64-8          7.54ns ± 0%  7.51ns ± 0%  -0.37%  (p=0.000 n=10+10)
Remainder-8            73.5ns ± 1%  70.4ns ± 1%  -4.27%  (p=0.000 n=10+10)
SqrtGoLatency-8        79.6ns ± 0%  76.2ns ± 0%  -4.30%  (p=0.000 n=9+10)
Yn-8                    582ns ± 0%   579ns ± 0%  -0.52%  (p=0.000 n=10+10)

Change-Id: I0c9cd1ea87435e7b8bab94b4e79e6e29785f25b1
Reviewed-on: https://go-review.googlesource.com/132915
Reviewed-by: Cherry Zhang <[email protected]>
Run-TryBot: Cherry Zhang <[email protected]>
TryBot-Result: Gobot Gobot <[email protected]>

Author: zhangfannie

src/cmd/compile/internal/ssa/gen/ARM64.rules

@@ -101,6 +101,8 @@
 
 // Load args directly into the register class where it will be used.
 (FMOVDgpfp <t> (Arg [off] {sym})) -> @b.Func.Entry (Arg <t> [off] {sym})
+(FMOVDfpgp <t> (Arg [off] {sym})) -> @b.Func.Entry (Arg <t> [off] {sym})
+
 // Similarly for stores, if we see a store after FPR <-> GPR move, then redirect store to use the other register set.
 (MOVDstore ptr (FMOVDfpgp val) mem) -> (FMOVDstore ptr val mem)
 (FMOVDstore ptr (FMOVDgpfp val) mem) -> (MOVDstore ptr val mem)
@@ -1626,6 +1628,9 @@
 (SRLconst [c] (SLLconst [c] x)) && 0 < c && c < 64 -> (ANDconst [1<<uint(64-c)-1] x) // mask out high bits
 (SLLconst [c] (SRLconst [c] x)) && 0 < c && c < 64 -> (ANDconst [^(1<<uint(c)-1)] x) // mask out low bits
 
+// Special case setting bit as 1. An example is math.Copysign(c,-1)
+(ORconst [c1] (ANDconst [c2] x)) && c2|c1 == ^0  -> (ORconst [c1] x)
+
 // bitfield ops
 
 // sbfiz

src/cmd/compile/internal/ssa/rewriteARM64.go

@@ -74,6 +74,7 @@ func copysign(a, b, c float64) {
 	// amd64:"BTSQ\t[$]63"
 	// s390x:"LNDFR\t",-"MOVD\t"     (no integer load/store)
 	// ppc64le:"FCPSGN"
+	// arm64:"ORR\t[$]-9223372036854775808"
 	sink64[1] = math.Copysign(c, -1)
 
 	// Like math.Copysign(c, -1), but with integer operations. Useful