cmd/compile: emit more compact 386 instructions

ADDL/SUBL/ANDL/ORL/XORL can have a memory operand as destination,
and this CL optimize the compiler to emit such instructions on
386 for more compact binary.

Here is test report:
1. The total size of pkg/linux_386/ and pkg/tool/linux_386/ decreases
about 14KB.
(pkg/linux_386/cmd/compile/ and pkg/tool/linux_386/compile are excluded)

2. The go1 benchmark shows little change, excluding ±2% noise.
name                     old time/op    new time/op    delta
BinaryTree17-4              3.34s ± 2%     3.38s ± 2%  +1.27%  (p=0.000 n=40+39)
Fannkuch11-4                3.55s ± 1%     3.51s ± 1%  -1.33%  (p=0.000 n=40+40)
FmtFprintfEmpty-4          46.3ns ± 3%    46.9ns ± 4%  +1.41%  (p=0.002 n=40+40)
FmtFprintfString-4         80.8ns ± 3%    80.4ns ± 6%  -0.54%  (p=0.044 n=40+40)
FmtFprintfInt-4            93.0ns ± 3%    92.2ns ± 4%  -0.88%  (p=0.007 n=39+40)
FmtFprintfIntInt-4          144ns ± 5%     145ns ± 2%  +0.78%  (p=0.015 n=40+40)
FmtFprintfPrefixedInt-4     184ns ± 2%     182ns ± 2%  -1.06%  (p=0.004 n=40+40)
FmtFprintfFloat-4           415ns ± 4%     419ns ± 4%    ~     (p=0.434 n=40+40)
FmtManyArgs-4               615ns ± 3%     619ns ± 3%    ~     (p=0.100 n=40+40)
GobDecode-4                7.30ms ± 6%    7.36ms ± 6%    ~     (p=0.074 n=40+40)
GobEncode-4                7.10ms ± 6%    7.21ms ± 5%    ~     (p=0.082 n=40+39)
Gzip-4                      364ms ± 3%     362ms ± 6%  -0.71%  (p=0.020 n=40+40)
Gunzip-4                   42.4ms ± 3%    42.2ms ± 3%    ~     (p=0.303 n=40+40)
HTTPClientServer-4         62.9µs ± 1%    62.9µs ± 1%    ~     (p=0.768 n=38+39)
JSONEncode-4               21.4ms ± 4%    21.5ms ± 5%    ~     (p=0.210 n=40+40)
JSONDecode-4               67.7ms ± 3%    67.9ms ± 4%    ~     (p=0.713 n=40+40)
Mandelbrot200-4            5.18ms ± 3%    5.21ms ± 3%  +0.59%  (p=0.021 n=40+40)
GoParse-4                  3.35ms ± 3%    3.34ms ± 2%    ~     (p=0.996 n=40+40)
RegexpMatchEasy0_32-4      98.5ns ± 5%    96.3ns ± 4%  -2.15%  (p=0.001 n=40+40)
RegexpMatchEasy0_1K-4       851ns ± 4%     850ns ± 5%    ~     (p=0.700 n=40+40)
RegexpMatchEasy1_32-4       105ns ± 7%     107ns ± 4%  +1.50%  (p=0.017 n=40+40)
RegexpMatchEasy1_1K-4      1.03µs ± 5%    1.03µs ± 4%    ~     (p=0.992 n=40+40)
RegexpMatchMedium_32-4      130ns ± 6%     128ns ± 4%  -1.66%  (p=0.012 n=40+40)
RegexpMatchMedium_1K-4     44.0µs ± 5%    43.6µs ± 3%    ~     (p=0.704 n=40+40)
RegexpMatchHard_32-4       2.29µs ± 3%    2.23µs ± 4%  -2.38%  (p=0.000 n=40+40)
RegexpMatchHard_1K-4       69.0µs ± 3%    68.1µs ± 3%  -1.28%  (p=0.003 n=40+40)
Revcomp-4                   1.85s ± 2%     1.87s ± 3%  +1.11%  (p=0.000 n=40+40)
Template-4                 69.8ms ± 3%    69.6ms ± 3%    ~     (p=0.125 n=40+40)
TimeParse-4                 442ns ± 5%     440ns ± 3%    ~     (p=0.585 n=40+40)
TimeFormat-4                419ns ± 3%     420ns ± 3%    ~     (p=0.824 n=40+40)
[Geo mean]                 67.3µs         67.2µs       -0.11%

name                     old speed      new speed      delta
GobDecode-4               105MB/s ± 6%   104MB/s ± 6%    ~     (p=0.074 n=40+40)
GobEncode-4               108MB/s ± 7%   107MB/s ± 5%    ~     (p=0.080 n=40+39)
Gzip-4                   53.3MB/s ± 3%  53.7MB/s ± 6%  +0.73%  (p=0.021 n=40+40)
Gunzip-4                  458MB/s ± 3%   460MB/s ± 3%    ~     (p=0.301 n=40+40)
JSONEncode-4             90.8MB/s ± 4%  90.3MB/s ± 4%    ~     (p=0.213 n=40+40)
JSONDecode-4             28.7MB/s ± 3%  28.6MB/s ± 4%    ~     (p=0.679 n=40+40)
GoParse-4                17.3MB/s ± 3%  17.3MB/s ± 2%    ~     (p=1.000 n=40+40)
RegexpMatchEasy0_32-4     325MB/s ± 5%   333MB/s ± 4%  +2.44%  (p=0.000 n=40+38)
RegexpMatchEasy0_1K-4    1.20GB/s ± 4%  1.21GB/s ± 5%    ~     (p=0.684 n=40+40)
RegexpMatchEasy1_32-4     303MB/s ± 7%   298MB/s ± 4%  -1.52%  (p=0.022 n=40+40)
RegexpMatchEasy1_1K-4     995MB/s ± 5%   996MB/s ± 4%    ~     (p=0.996 n=40+40)
RegexpMatchMedium_32-4   7.67MB/s ± 6%  7.80MB/s ± 4%  +1.68%  (p=0.011 n=40+40)
RegexpMatchMedium_1K-4   23.3MB/s ± 5%  23.5MB/s ± 3%    ~     (p=0.697 n=40+40)
RegexpMatchHard_32-4     14.0MB/s ± 3%  14.3MB/s ± 4%  +2.43%  (p=0.000 n=40+40)
RegexpMatchHard_1K-4     14.8MB/s ± 3%  15.0MB/s ± 3%  +1.30%  (p=0.003 n=40+40)
Revcomp-4                 137MB/s ± 2%   136MB/s ± 3%  -1.10%  (p=0.000 n=40+40)
Template-4               27.8MB/s ± 3%  27.9MB/s ± 3%    ~     (p=0.128 n=40+40)
[Geo mean]               79.6MB/s       79.9MB/s       +0.28%

Change-Id: I02a3efc125dc81e18fc8495eb2bf1bba59ab8733
Reviewed-on: https://go-review.googlesource.com/110157
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>

src/cmd/compile/internal/ssa/gen/386.rules

@@ -641,6 +641,8 @@
 	((ADD|SUB|MUL)SSmem [off1+off2] {sym} val base mem)
 ((ADD|SUB|MUL)SDmem [off1] {sym} val (ADDLconst [off2] base) mem) && is32Bit(off1+off2) ->
 	((ADD|SUB|MUL)SDmem [off1+off2] {sym} val base mem)
+((ADD|SUB|AND|OR|XOR)Lmodify [off1] {sym} (ADDLconst [off2] base) val mem) && is32Bit(off1+off2) ->
+	((ADD|SUB|AND|OR|XOR)Lmodify [off1+off2] {sym} base val mem)
 
 // Fold constants into stores.
 (MOVLstore [off] {sym} ptr (MOVLconst [c]) mem) && validOff(off) ->
@@ -763,6 +765,9 @@
 ((ADD|SUB|MUL)SDmem [off1] {sym1} val (LEAL [off2] {sym2} base) mem)
 	&& is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || !config.ctxt.Flag_shared) ->
 	((ADD|SUB|MUL)SDmem [off1+off2] {mergeSym(sym1,sym2)} val base mem)
+((ADD|SUB|AND|OR|XOR)Lmodify [off1] {sym1} (LEAL [off2] {sym2} base) val mem)
+	&& is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || !config.ctxt.Flag_shared) ->
+	((ADD|SUB|AND|OR|XOR)Lmodify [off1+off2] {mergeSym(sym1,sym2)} base val mem)
 
 (MOVBload [off] {sym} (ADDL ptr idx) mem) && ptr.Op != OpSB -> (MOVBloadidx1 [off] {sym} ptr idx mem)
 (MOVWload [off] {sym} (ADDL ptr idx) mem) && ptr.Op != OpSB -> (MOVWloadidx1 [off] {sym} ptr idx mem)
@@ -839,10 +844,13 @@
 (MOVSDstoreidx1 [c] {sym} ptr (ADDLconst [d] idx) val mem) -> (MOVSDstoreidx1 [int64(int32(c+d))]   {sym} ptr idx val mem)
 (MOVSDstoreidx8 [c] {sym} ptr (ADDLconst [d] idx) val mem) -> (MOVSDstoreidx8 [int64(int32(c+8*d))] {sym} ptr idx val mem)
 
-// Merge load to op
+// Merge load/store to op
 ((ADD|AND|OR|XOR|SUB)L x l:(MOVLload [off] {sym} ptr mem)) && canMergeLoad(v, l, x) && clobber(l) -> ((ADD|AND|OR|XOR|SUB)Lmem x [off] {sym} ptr mem)
 ((ADD|SUB|MUL)SD x l:(MOVSDload [off] {sym} ptr mem)) && canMergeLoad(v, l, x) && !config.use387 && clobber(l) -> ((ADD|SUB|MUL)SDmem x [off] {sym} ptr mem)
 ((ADD|SUB|MUL)SS x l:(MOVSSload [off] {sym} ptr mem)) && canMergeLoad(v, l, x) && !config.use387 && clobber(l) -> ((ADD|SUB|MUL)SSmem x [off] {sym} ptr mem)
+(MOVLstore {sym} [off] ptr y:((ADD|AND|OR|XOR)Lmem x [off] {sym} ptr mem) mem) && y.Uses==1 && clobber(y) -> ((ADD|AND|OR|XOR)Lmodify [off] {sym} ptr x mem)
+(MOVLstore {sym} [off] ptr y:((ADD|SUB|AND|OR|XOR)L l:(MOVLload [off] {sym} ptr mem) x) mem) && y.Uses==1 && l.Uses==1 && clobber(y) && clobber(l) ->
+	((ADD|SUB|AND|OR|XOR)Lmodify [off] {sym} ptr x mem)
 
 (MOVBstoreconstidx1 [x] {sym} (ADDLconst [c] ptr) idx mem) ->
 	(MOVBstoreconstidx1 [ValAndOff(x).add(c)] {sym} ptr idx mem)

src/cmd/compile/internal/ssa/gen/386Ops.go

@@ -345,6 +345,13 @@ func init() {
 		{name: "MOVWstore", argLength: 3, reg: gpstore, asm: "MOVW", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"},    // store 2 bytes in arg1 to arg0+auxint+aux. arg2=mem
 		{name: "MOVLstore", argLength: 3, reg: gpstore, asm: "MOVL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"},    // store 4 bytes in arg1 to arg0+auxint+aux. arg2=mem
 
+		// direct binary-op on memory (read-modify-write)
+		{name: "ADDLmodify", argLength: 3, reg: gpstore, asm: "ADDL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // *(arg0+auxint+aux) += arg1, arg2=mem
+		{name: "SUBLmodify", argLength: 3, reg: gpstore, asm: "SUBL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // *(arg0+auxint+aux) -= arg1, arg2=mem
+		{name: "ANDLmodify", argLength: 3, reg: gpstore, asm: "ANDL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // *(arg0+auxint+aux) &= arg1, arg2=mem
+		{name: "ORLmodify", argLength: 3, reg: gpstore, asm: "ORL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"},   // *(arg0+auxint+aux) |= arg1, arg2=mem
+		{name: "XORLmodify", argLength: 3, reg: gpstore, asm: "XORL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // *(arg0+auxint+aux) ^= arg1, arg2=mem
+
 		// indexed loads/stores
 		{name: "MOVBloadidx1", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVBLZX", aux: "SymOff", symEffect: "Read"}, // load a byte from arg0+arg1+auxint+aux. arg2=mem
 		{name: "MOVWloadidx1", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVWLZX", aux: "SymOff", symEffect: "Read"}, // load 2 bytes from arg0+arg1+auxint+aux. arg2=mem

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

@@ -380,6 +380,11 @@ const (
 	Op386MOVBstore
 	Op386MOVWstore
 	Op386MOVLstore
+	Op386ADDLmodify
+	Op386SUBLmodify
+	Op386ANDLmodify
+	Op386ORLmodify
+	Op386XORLmodify
 	Op386MOVBloadidx1
 	Op386MOVWloadidx1
 	Op386MOVWloadidx2
@@ -4418,6 +4423,76 @@ var opcodeTable = [...]opInfo{
 			},
 		},
 	},
+	{
+		name:           "ADDLmodify",
+		auxType:        auxSymOff,
+		argLen:         3,
+		faultOnNilArg0: true,
+		symEffect:      SymWrite,
+		asm:            x86.AADDL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 255},   // AX CX DX BX SP BP SI DI
+				{0, 65791}, // AX CX DX BX SP BP SI DI SB
+			},
+		},
+	},
+	{
+		name:           "SUBLmodify",
+		auxType:        auxSymOff,
+		argLen:         3,
+		faultOnNilArg0: true,
+		symEffect:      SymWrite,
+		asm:            x86.ASUBL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 255},   // AX CX DX BX SP BP SI DI
+				{0, 65791}, // AX CX DX BX SP BP SI DI SB
+			},
+		},
+	},
+	{
+		name:           "ANDLmodify",
+		auxType:        auxSymOff,
+		argLen:         3,
+		faultOnNilArg0: true,
+		symEffect:      SymWrite,
+		asm:            x86.AANDL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 255},   // AX CX DX BX SP BP SI DI
+				{0, 65791}, // AX CX DX BX SP BP SI DI SB
+			},
+		},
+	},
+	{
+		name:           "ORLmodify",
+		auxType:        auxSymOff,
+		argLen:         3,
+		faultOnNilArg0: true,
+		symEffect:      SymWrite,
+		asm:            x86.AORL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 255},   // AX CX DX BX SP BP SI DI
+				{0, 65791}, // AX CX DX BX SP BP SI DI SB
+			},
+		},
+	},
+	{
+		name:           "XORLmodify",
+		auxType:        auxSymOff,
+		argLen:         3,
+		faultOnNilArg0: true,
+		symEffect:      SymWrite,
+		asm:            x86.AXORL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{1, 255},   // AX CX DX BX SP BP SI DI
+				{0, 65791}, // AX CX DX BX SP BP SI DI SB
+			},
+		},
+	},
 	{
 		name:        "MOVBloadidx1",
 		auxType:     auxSymOff,

src/cmd/compile/internal/x86/ssa.go

@@ -521,7 +521,8 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 		if v.Reg() != v.Args[0].Reg() {
 			v.Fatalf("input[0] and output not in same register %s", v.LongString())
 		}
-	case ssa.Op386MOVSSstore, ssa.Op386MOVSDstore, ssa.Op386MOVLstore, ssa.Op386MOVWstore, ssa.Op386MOVBstore:
+	case ssa.Op386MOVSSstore, ssa.Op386MOVSDstore, ssa.Op386MOVLstore, ssa.Op386MOVWstore, ssa.Op386MOVBstore,
+		ssa.Op386ADDLmodify, ssa.Op386SUBLmodify, ssa.Op386ANDLmodify, ssa.Op386ORLmodify, ssa.Op386XORLmodify:
 		p := s.Prog(v.Op.Asm())
 		p.From.Type = obj.TYPE_REG
 		p.From.Reg = v.Args[1].Reg()

test/codegen/arithmetic.go

@@ -14,7 +14,11 @@ package codegen
 //    Subtraction    //
 // ----------------- //
 
-func SubMem(arr []int) int {
+func SubMem(arr []int, b int) int {
+	// 386:`SUBL\s[A-Z]+,\s8\([A-Z]+\)`
+	arr[2] -= b
+	// 386:`SUBL\s[A-Z]+,\s12\([A-Z]+\)`
+	arr[3] -= b
 	// 386:"SUBL\t4"
 	// amd64:"SUBQ\t8"
 	return arr[0] - arr[1]