cmd/compile: intrinsify math/big.mulWW on ARM64

Performance numbers on amberwing:

pkg: math/big
name                            old time/op    new time/op    delta
QuoRem                            3.08µs ± 0%    2.93µs ± 1%   -4.89%  (p=0.008 n=5+5)
ModSqrt225_Tonelli                 721µs ± 0%     718µs ± 0%   -0.46%  (p=0.008 n=5+5)
ModSqrt224_3Mod4                   218µs ± 0%     217µs ± 0%   -0.27%  (p=0.008 n=5+5)
ModSqrt5430_Tonelli                2.91s ± 0%     2.91s ± 0%     ~     (p=0.222 n=5+5)
ModSqrt5430_3Mod4                  970ms ± 0%     970ms ± 0%     ~     (p=0.151 n=5+5)
Sqrt                              45.9µs ± 0%    43.8µs ± 0%   -4.63%  (p=0.008 n=5+5)
IntSqr/1                          19.9ns ± 0%    17.3ns ± 0%  -13.07%  (p=0.008 n=5+5)
IntSqr/2                          52.6ns ± 0%    50.8ns ± 0%   -3.35%  (p=0.008 n=5+5)
IntSqr/3                          70.4ns ± 0%    69.4ns ± 0%     ~     (p=0.079 n=4+5)
IntSqr/5                           103ns ± 0%      99ns ± 0%   -3.98%  (p=0.008 n=5+5)
IntSqr/8                           179ns ± 0%     178ns ± 0%   -0.56%  (p=0.008 n=5+5)
IntSqr/10                          272ns ± 0%     272ns ± 0%     ~     (all equal)
IntSqr/20                          763ns ± 0%     787ns ± 0%   +3.15%  (p=0.016 n=5+4)
IntSqr/30                         1.25µs ± 1%    1.29µs ± 1%   +3.27%  (p=0.008 n=5+5)
IntSqr/50                         2.64µs ± 0%    2.71µs ± 0%   +2.61%  (p=0.008 n=5+5)
IntSqr/80                         5.67µs ± 0%    5.72µs ± 0%   +0.88%  (p=0.008 n=5+5)
IntSqr/100                        8.05µs ± 0%    8.09µs ± 0%   +0.45%  (p=0.008 n=5+5)
IntSqr/200                        28.0µs ± 0%    28.1µs ± 0%     ~     (p=0.151 n=5+5)
IntSqr/300                        59.4µs ± 0%    59.6µs ± 0%   +0.36%  (p=0.008 n=5+5)
IntSqr/500                         141µs ± 0%     141µs ± 0%   +0.08%  (p=0.008 n=5+5)
IntSqr/800                         280µs ± 0%     280µs ± 0%   -0.12%  (p=0.008 n=5+5)
IntSqr/1000                        429µs ± 0%     428µs ± 0%   -0.27%  (p=0.008 n=5+5)

pkg: crypto-ecdsa
name      old time/op    new time/op    delta
SignP384    7.85ms ± 1%    7.61ms ± 1%  -3.12%  (p=0.008 n=5+5)

Change-Id: I1ab30856cc0e570f6312f0bd8914779b55adbc16
Reviewed-on: https://go-review.googlesource.com/104135
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>

Author: bmakam-qdt

src/cmd/compile/internal/arm64/ssa.go

@@ -413,6 +413,21 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 		p.Reg = v.Args[0].Reg()
 		p.To.Type = obj.TYPE_REG
 		p.To.Reg = v.Reg()
+	case ssa.OpARM64LoweredMuluhilo:
+		r0 := v.Args[0].Reg()
+		r1 := v.Args[1].Reg()
+		p := s.Prog(arm64.AUMULH)
+		p.From.Type = obj.TYPE_REG
+		p.From.Reg = r1
+		p.Reg = r0
+		p.To.Type = obj.TYPE_REG
+		p.To.Reg = v.Reg0()
+		p1 := s.Prog(arm64.AMUL)
+		p1.From.Type = obj.TYPE_REG
+		p1.From.Reg = r1
+		p1.Reg = r0
+		p1.To.Type = obj.TYPE_REG
+		p1.To.Reg = v.Reg1()
 	case ssa.OpARM64LoweredAtomicExchange64,
 		ssa.OpARM64LoweredAtomicExchange32:
 		// LDAXR	(Rarg0), Rout

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

@@ -3207,7 +3207,7 @@ func init() {
 		func(s *state, n *Node, args []*ssa.Value) *ssa.Value {
 			return s.newValue2(ssa.OpMul64uhilo, types.NewTuple(types.Types[TUINT64], types.Types[TUINT64]), args[0], args[1])
 		},
-		sys.ArchAMD64)
+		sys.ArchAMD64, sys.ArchARM64)
 	add("math/big", "divWW",
 		func(s *state, n *Node, args []*ssa.Value) *ssa.Value {
 			return s.newValue3(ssa.OpDiv128u, types.NewTuple(types.Types[TUINT64], types.Types[TUINT64]), args[0], args[1], args[2])

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

@@ -29,6 +29,7 @@
 (Hmul64u x y) -> (UMULH x y)
 (Hmul32 x y) -> (SRAconst (MULL <typ.Int64> x y) [32])
 (Hmul32u x y) -> (SRAconst (UMULL <typ.UInt64> x y) [32])
+(Mul64uhilo x y) -> (LoweredMuluhilo x y)
 
 (Div64 x y) -> (DIV x y)
 (Div64u x y) -> (UDIV x y)
@@ -1791,4 +1792,4 @@
 (FSUBS a (FNMULS x y)) -> (FMADDS a x y)
 (FSUBD a (FNMULD x y)) -> (FMADDD a x y)
 (FSUBS (FNMULS x y) a) -> (FNMADDS a x y)
-(FSUBD (FNMULD x y) a) -> (FNMADDD a x y)
+(FSUBD (FNMULD x y) a) -> (FNMADDD a x y)

src/cmd/compile/internal/ssa/gen/ARM64Ops.go

@@ -142,6 +142,7 @@ func init() {
 		gp21nog   = regInfo{inputs: []regMask{gp, gp}, outputs: []regMask{gp}}
 		gp2flags  = regInfo{inputs: []regMask{gpg, gpg}}
 		gp2flags1 = regInfo{inputs: []regMask{gp, gp}, outputs: []regMask{gp}}
+		gp22      = regInfo{inputs: []regMask{gpg, gpg}, outputs: []regMask{gp, gp}}
 		gpload    = regInfo{inputs: []regMask{gpspsbg}, outputs: []regMask{gp}}
 		gpstore   = regInfo{inputs: []regMask{gpspsbg, gpg}}
 		gpstore0  = regInfo{inputs: []regMask{gpspsbg}}
@@ -203,6 +204,7 @@ func init() {
 		{name: "EON", argLength: 2, reg: gp21, asm: "EON"},                    // arg0 ^ ^arg1
 		{name: "ORN", argLength: 2, reg: gp21, asm: "ORN"},                    // arg0 | ^arg1
 
+		{name: "LoweredMuluhilo", argLength: 2, reg: gp22, resultNotInArgs: true}, // arg0 * arg1, returns (hi, lo)
 		// unary ops
 		{name: "MVN", argLength: 1, reg: gp11, asm: "MVN"},         // ^arg0
 		{name: "NEG", argLength: 1, reg: gp11, asm: "NEG"},         // -arg0