cmd/compile: add missing s390x load with index operations

Prior to this CL loads with sign extension could not be replaced with
indexed loads (only loads with zero extension).

This CL also prevents large offsets (more than 20-bits) from being
merged into indexed loads. It is better to keep such offsets
separate.

Gives a small improvement in binary size, ~1.5KB from .text in cmd/go.

Change-Id: Ib848ffc2b05de6660c5ce2394ae1d1d144273e29
Reviewed-on: https://go-review.googlesource.com/36845
Run-TryBot: Michael Munday <mike.munday@ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

src/cmd/compile/internal/s390x/ssa.go

@@ -384,7 +384,8 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 		gc.AddAux(&p.From, v)
 		p.To.Type = obj.TYPE_REG
 		p.To.Reg = v.Reg()
-	case ssa.OpS390XMOVBZloadidx, ssa.OpS390XMOVHZloadidx, ssa.OpS390XMOVWZloadidx, ssa.OpS390XMOVDloadidx,
+	case ssa.OpS390XMOVBZloadidx, ssa.OpS390XMOVHZloadidx, ssa.OpS390XMOVWZloadidx,
+		ssa.OpS390XMOVBloadidx, ssa.OpS390XMOVHloadidx, ssa.OpS390XMOVWloadidx, ssa.OpS390XMOVDloadidx,
 		ssa.OpS390XMOVHBRloadidx, ssa.OpS390XMOVWBRloadidx, ssa.OpS390XMOVDBRloadidx,
 		ssa.OpS390XFMOVSloadidx, ssa.OpS390XFMOVDloadidx:
 		r := v.Args[0].Reg()

src/cmd/compile/internal/ssa/gen/S390XOps.go

@@ -403,10 +403,12 @@ func init() {
 		{name: "MVC", argLength: 3, reg: gpmvc, asm: "MVC", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, faultOnNilArg0: true, faultOnNilArg1: true, symEffect: "None"}, // arg0=destptr, arg1=srcptr, arg2=mem, auxint=size,off
 
 		// indexed loads/stores
-		// TODO(mundaym): add sign-extended indexed loads
-		{name: "MOVBZloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVBZ", aux: "SymOff", typ: "UInt8", clobberFlags: true, symEffect: "Read"},   // load a byte from arg0+arg1+auxint+aux. arg2=mem
-		{name: "MOVHZloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVHZ", aux: "SymOff", typ: "UInt16", clobberFlags: true, symEffect: "Read"},  // load 2 bytes from arg0+arg1+auxint+aux. arg2=mem
-		{name: "MOVWZloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVWZ", aux: "SymOff", typ: "UInt32", clobberFlags: true, symEffect: "Read"},  // load 4 bytes from arg0+arg1+auxint+aux. arg2=mem
+		{name: "MOVBZloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVBZ", aux: "SymOff", typ: "UInt8", clobberFlags: true, symEffect: "Read"},   // load a byte from arg0+arg1+auxint+aux. arg2=mem. Zero extend.
+		{name: "MOVBloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVB", aux: "SymOff", typ: "Int8", clobberFlags: true, symEffect: "Read"},      // load a byte from arg0+arg1+auxint+aux. arg2=mem. Sign extend.
+		{name: "MOVHZloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVHZ", aux: "SymOff", typ: "UInt16", clobberFlags: true, symEffect: "Read"},  // load 2 bytes from arg0+arg1+auxint+aux. arg2=mem. Zero extend.
+		{name: "MOVHloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVH", aux: "SymOff", typ: "Int16", clobberFlags: true, symEffect: "Read"},     // load 2 bytes from arg0+arg1+auxint+aux. arg2=mem. Sign extend.
+		{name: "MOVWZloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVWZ", aux: "SymOff", typ: "UInt32", clobberFlags: true, symEffect: "Read"},  // load 4 bytes from arg0+arg1+auxint+aux. arg2=mem. Zero extend.
+		{name: "MOVWloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVW", aux: "SymOff", typ: "Int32", clobberFlags: true, symEffect: "Read"},     // load 4 bytes from arg0+arg1+auxint+aux. arg2=mem. Sign extend.
 		{name: "MOVDloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVD", aux: "SymOff", typ: "UInt64", clobberFlags: true, symEffect: "Read"},    // load 8 bytes from arg0+arg1+auxint+aux. arg2=mem
 		{name: "MOVHBRloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVHBR", aux: "SymOff", typ: "Int16", clobberFlags: true, symEffect: "Read"}, // load 2 bytes from arg0+arg1+auxint+aux. arg2=mem. Reverse bytes.
 		{name: "MOVWBRloadidx", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVWBR", aux: "SymOff", typ: "Int32", clobberFlags: true, symEffect: "Read"}, // load 4 bytes from arg0+arg1+auxint+aux. arg2=mem. Reverse bytes.

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

@@ -1649,8 +1649,11 @@ const (
 	OpS390XMOVDBRstore
 	OpS390XMVC
 	OpS390XMOVBZloadidx
+	OpS390XMOVBloadidx
 	OpS390XMOVHZloadidx
+	OpS390XMOVHloadidx
 	OpS390XMOVWZloadidx
+	OpS390XMOVWloadidx
 	OpS390XMOVDloadidx
 	OpS390XMOVHBRloadidx
 	OpS390XMOVWBRloadidx
@@ -21532,6 +21535,24 @@ var opcodeTable = [...]opInfo{
 			},
 		},
 	},
+	{
+		name:         "MOVBloadidx",
+		auxType:      auxSymOff,
+		argLen:       3,
+		commutative:  true,
+		clobberFlags: true,
+		symEffect:    SymRead,
+		asm:          s390x.AMOVB,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 54270},      // R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14 SP
+				{0, 4295021566}, // R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14 SP SB
+			},
+			outputs: []outputInfo{
+				{0, 21503}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14
+			},
+		},
+	},
 	{
 		name:         "MOVHZloadidx",
 		auxType:      auxSymOff,
@@ -21550,6 +21571,24 @@ var opcodeTable = [...]opInfo{
 			},
 		},
 	},
+	{
+		name:         "MOVHloadidx",
+		auxType:      auxSymOff,
+		argLen:       3,
+		commutative:  true,
+		clobberFlags: true,
+		symEffect:    SymRead,
+		asm:          s390x.AMOVH,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 54270},      // R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14 SP
+				{0, 4295021566}, // R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14 SP SB
+			},
+			outputs: []outputInfo{
+				{0, 21503}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14
+			},
+		},
+	},
 	{
 		name:         "MOVWZloadidx",
 		auxType:      auxSymOff,
@@ -21568,6 +21607,24 @@ var opcodeTable = [...]opInfo{
 			},
 		},
 	},
+	{
+		name:         "MOVWloadidx",
+		auxType:      auxSymOff,
+		argLen:       3,
+		commutative:  true,
+		clobberFlags: true,
+		symEffect:    SymRead,
+		asm:          s390x.AMOVW,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 54270},      // R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14 SP
+				{0, 4295021566}, // R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14 SP SB
+			},
+			outputs: []outputInfo{
+				{0, 21503}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R12 R14
+			},
+		},
+	},
 	{
 		name:         "MOVDloadidx",
 		auxType:      auxSymOff,