cmd/compile: optimize AMD64 with more read-modify-write operations

6 more operations which do read-modify-write with a constant source operand are added. 1. The total size of pkg/linux_amd64 decreases about 3KB, excluding cmd/compile. 2. The go1 benckmark shows a slight improvement. name old time/op new time/op delta BinaryTree17-4 2.61s ± 4% 2.67s ± 2% +2.26% (p=0.000 n=30+29) Fannkuch11-4 2.39s ± 2% 2.32s ± 2% -2.67% (p=0.000 n=30+30) FmtFprintfEmpty-4 44.0ns ± 4% 41.7ns ± 4% -5.15% (p=0.000 n=30+30) FmtFprintfString-4 74.2ns ± 4% 72.3ns ± 4% -2.59% (p=0.000 n=30+30) FmtFprintfInt-4 81.7ns ± 3% 78.8ns ± 4% -3.54% (p=0.000 n=27+30) FmtFprintfIntInt-4 130ns ± 4% 124ns ± 5% -4.60% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 154ns ± 3% 152ns ± 3% -1.13% (p=0.012 n=30+30) FmtFprintfFloat-4 215ns ± 4% 212ns ± 5% -1.56% (p=0.002 n=30+30) FmtManyArgs-4 522ns ± 3% 512ns ± 3% -1.84% (p=0.001 n=30+30) GobDecode-4 6.42ms ± 5% 6.49ms ± 7% ~ (p=0.070 n=30+30) GobEncode-4 6.07ms ± 8% 5.98ms ± 8% ~ (p=0.150 n=30+30) Gzip-4 236ms ± 4% 223ms ± 4% -5.57% (p=0.000 n=30+30) Gunzip-4 37.4ms ± 3% 36.7ms ± 4% -2.03% (p=0.000 n=30+30) HTTPClientServer-4 58.7µs ± 1% 58.5µs ± 2% -0.37% (p=0.018 n=30+29) JSONEncode-4 12.0ms ± 4% 12.1ms ± 3% ~ (p=0.112 n=30+30) JSONDecode-4 54.5ms ± 3% 55.5ms ± 4% +1.80% (p=0.006 n=30+30) Mandelbrot200-4 3.78ms ± 4% 3.78ms ± 4% ~ (p=0.173 n=30+30) GoParse-4 3.16ms ± 5% 3.22ms ± 5% +1.75% (p=0.010 n=30+30) RegexpMatchEasy0_32-4 76.6ns ± 1% 75.9ns ± 3% ~ (p=0.672 n=25+30) RegexpMatchEasy0_1K-4 252ns ± 3% 253ns ± 3% +0.57% (p=0.027 n=30+30) RegexpMatchEasy1_32-4 69.8ns ± 4% 70.2ns ± 6% ~ (p=0.539 n=30+30) RegexpMatchEasy1_1K-4 374ns ± 3% 373ns ± 5% ~ (p=0.263 n=30+30) RegexpMatchMedium_32-4 107ns ± 4% 109ns ± 3% ~ (p=0.067 n=30+30) RegexpMatchMedium_1K-4 33.9µs ± 5% 34.1µs ± 4% ~ (p=0.297 n=30+30) RegexpMatchHard_32-4 1.54µs ± 3% 1.56µs ± 4% +1.43% (p=0.002 n=30+30) RegexpMatchHard_1K-4 46.6µs ± 3% 47.0µs ± 3% ~ (p=0.055 n=30+30) Revcomp-4 411ms ± 6% 407ms ± 6% ~ (p=0.219 n=30+30) Template-4 66.8ms ± 3% 64.8ms ± 5% -3.01% (p=0.000 n=30+30) TimeParse-4 312ns ± 2% 319ns ± 3% +2.50% (p=0.000 n=30+30) TimeFormat-4 296ns ± 5% 299ns ± 3% +0.93% (p=0.005 n=30+30) [Geo mean] 47.5µs 47.1µs -0.75% name old speed new speed delta GobDecode-4 120MB/s ± 5% 118MB/s ± 6% ~ (p=0.072 n=30+30) GobEncode-4 127MB/s ± 8% 129MB/s ± 8% ~ (p=0.150 n=30+30) Gzip-4 82.1MB/s ± 4% 87.0MB/s ± 4% +5.90% (p=0.000 n=30+30) Gunzip-4 519MB/s ± 4% 529MB/s ± 4% +2.07% (p=0.001 n=30+30) JSONEncode-4 162MB/s ± 4% 161MB/s ± 3% ~ (p=0.110 n=30+30) JSONDecode-4 35.6MB/s ± 3% 35.0MB/s ± 4% -1.77% (p=0.007 n=30+30) GoParse-4 18.3MB/s ± 4% 18.0MB/s ± 4% -1.72% (p=0.009 n=30+30) RegexpMatchEasy0_32-4 418MB/s ± 1% 422MB/s ± 3% ~ (p=0.645 n=25+30) RegexpMatchEasy0_1K-4 4.06GB/s ± 3% 4.04GB/s ± 3% -0.57% (p=0.033 n=30+30) RegexpMatchEasy1_32-4 459MB/s ± 4% 456MB/s ± 6% ~ (p=0.530 n=30+30) RegexpMatchEasy1_1K-4 2.73GB/s ± 3% 2.75GB/s ± 5% ~ (p=0.279 n=30+30) RegexpMatchMedium_32-4 9.28MB/s ± 5% 9.18MB/s ± 4% ~ (p=0.086 n=30+30) RegexpMatchMedium_1K-4 30.2MB/s ± 4% 30.0MB/s ± 4% ~ (p=0.300 n=30+30) RegexpMatchHard_32-4 20.8MB/s ± 3% 20.5MB/s ± 4% -1.41% (p=0.002 n=30+30) RegexpMatchHard_1K-4 22.0MB/s ± 3% 21.8MB/s ± 3% ~ (p=0.051 n=30+30) Revcomp-4 619MB/s ± 7% 625MB/s ± 7% ~ (p=0.219 n=30+30) Template-4 29.0MB/s ± 3% 29.9MB/s ± 4% +3.11% (p=0.000 n=30+30) [Geo mean] 123MB/s 123MB/s +0.28% Change-Id: I850652cfd53329c1af804b7f57f4393d8097bb0d Reviewed-on: https://go-review.googlesource.com/121135 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>

cmd/compile: optimize AMD64 with more read-modify-write operations
6 more operations which do read-modify-write with a constant source operand are added. 1. The total size of pkg/linux_amd64 decreases about 3KB, excluding cmd/compile. 2. The go1 benckmark shows a slight improvement. name old time/op new time/op delta BinaryTree17-4 2.61s ± 4% 2.67s ± 2% +2.26% (p=0.000 n=30+29) Fannkuch11-4 2.39s ± 2% 2.32s ± 2% -2.67% (p=0.000 n=30+30) FmtFprintfEmpty-4 44.0ns ± 4% 41.7ns ± 4% -5.15% (p=0.000 n=30+30) FmtFprintfString-4 74.2ns ± 4% 72.3ns ± 4% -2.59% (p=0.000 n=30+30) FmtFprintfInt-4 81.7ns ± 3% 78.8ns ± 4% -3.54% (p=0.000 n=27+30) FmtFprintfIntInt-4 130ns ± 4% 124ns ± 5% -4.60% (p=0.000 n=30+30) FmtFprintfPrefixedInt-4 154ns ± 3% 152ns ± 3% -1.13% (p=0.012 n=30+30) FmtFprintfFloat-4 215ns ± 4% 212ns ± 5% -1.56% (p=0.002 n=30+30) FmtManyArgs-4 522ns ± 3% 512ns ± 3% -1.84% (p=0.001 n=30+30) GobDecode-4 6.42ms ± 5% 6.49ms ± 7% ~ (p=0.070 n=30+30) GobEncode-4 6.07ms ± 8% 5.98ms ± 8% ~ (p=0.150 n=30+30) Gzip-4 236ms ± 4% 223ms ± 4% -5.57% (p=0.000 n=30+30) Gunzip-4 37.4ms ± 3% 36.7ms ± 4% -2.03% (p=0.000 n=30+30) HTTPClientServer-4 58.7µs ± 1% 58.5µs ± 2% -0.37% (p=0.018 n=30+29) JSONEncode-4 12.0ms ± 4% 12.1ms ± 3% ~ (p=0.112 n=30+30) JSONDecode-4 54.5ms ± 3% 55.5ms ± 4% +1.80% (p=0.006 n=30+30) Mandelbrot200-4 3.78ms ± 4% 3.78ms ± 4% ~ (p=0.173 n=30+30) GoParse-4 3.16ms ± 5% 3.22ms ± 5% +1.75% (p=0.010 n=30+30) RegexpMatchEasy0_32-4 76.6ns ± 1% 75.9ns ± 3% ~ (p=0.672 n=25+30) RegexpMatchEasy0_1K-4 252ns ± 3% 253ns ± 3% +0.57% (p=0.027 n=30+30) RegexpMatchEasy1_32-4 69.8ns ± 4% 70.2ns ± 6% ~ (p=0.539 n=30+30) RegexpMatchEasy1_1K-4 374ns ± 3% 373ns ± 5% ~ (p=0.263 n=30+30) RegexpMatchMedium_32-4 107ns ± 4% 109ns ± 3% ~ (p=0.067 n=30+30) RegexpMatchMedium_1K-4 33.9µs ± 5% 34.1µs ± 4% ~ (p=0.297 n=30+30) RegexpMatchHard_32-4 1.54µs ± 3% 1.56µs ± 4% +1.43% (p=0.002 n=30+30) RegexpMatchHard_1K-4 46.6µs ± 3% 47.0µs ± 3% ~ (p=0.055 n=30+30) Revcomp-4 411ms ± 6% 407ms ± 6% ~ (p=0.219 n=30+30) Template-4 66.8ms ± 3% 64.8ms ± 5% -3.01% (p=0.000 n=30+30) TimeParse-4 312ns ± 2% 319ns ± 3% +2.50% (p=0.000 n=30+30) TimeFormat-4 296ns ± 5% 299ns ± 3% +0.93% (p=0.005 n=30+30) [Geo mean] 47.5µs 47.1µs -0.75% name old speed new speed delta GobDecode-4 120MB/s ± 5% 118MB/s ± 6% ~ (p=0.072 n=30+30) GobEncode-4 127MB/s ± 8% 129MB/s ± 8% ~ (p=0.150 n=30+30) Gzip-4 82.1MB/s ± 4% 87.0MB/s ± 4% +5.90% (p=0.000 n=30+30) Gunzip-4 519MB/s ± 4% 529MB/s ± 4% +2.07% (p=0.001 n=30+30) JSONEncode-4 162MB/s ± 4% 161MB/s ± 3% ~ (p=0.110 n=30+30) JSONDecode-4 35.6MB/s ± 3% 35.0MB/s ± 4% -1.77% (p=0.007 n=30+30) GoParse-4 18.3MB/s ± 4% 18.0MB/s ± 4% -1.72% (p=0.009 n=30+30) RegexpMatchEasy0_32-4 418MB/s ± 1% 422MB/s ± 3% ~ (p=0.645 n=25+30) RegexpMatchEasy0_1K-4 4.06GB/s ± 3% 4.04GB/s ± 3% -0.57% (p=0.033 n=30+30) RegexpMatchEasy1_32-4 459MB/s ± 4% 456MB/s ± 6% ~ (p=0.530 n=30+30) RegexpMatchEasy1_1K-4 2.73GB/s ± 3% 2.75GB/s ± 5% ~ (p=0.279 n=30+30) RegexpMatchMedium_32-4 9.28MB/s ± 5% 9.18MB/s ± 4% ~ (p=0.086 n=30+30) RegexpMatchMedium_1K-4 30.2MB/s ± 4% 30.0MB/s ± 4% ~ (p=0.300 n=30+30) RegexpMatchHard_32-4 20.8MB/s ± 3% 20.5MB/s ± 4% -1.41% (p=0.002 n=30+30) RegexpMatchHard_1K-4 22.0MB/s ± 3% 21.8MB/s ± 3% ~ (p=0.051 n=30+30) Revcomp-4 619MB/s ± 7% 625MB/s ± 7% ~ (p=0.219 n=30+30) Template-4 29.0MB/s ± 3% 29.9MB/s ± 4% +3.11% (p=0.000 n=30+30) [Geo mean] 123MB/s 123MB/s +0.28% Change-Id: I850652cfd53329c1af804b7f57f4393d8097bb0d Reviewed-on: https://go-review.googlesource.com/121135 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
b75c5c59 · Ben Shi · b40db514 · b75c5c59 · b75c5c59 · b75c5c59
Commit b75c5c59 authored Jun 27, 2018 by Ben Shi
6 changed files
--- a/src/cmd/compile/internal/amd64/ssa.go
+++ b/src/cmd/compile/internal/amd64/ssa.go
@@ -770,6 +770,17 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 			p.To.Reg = v.Args[0].Reg()
 			gc.AddAux2(&p.To, v, off)
 		}
+	case ssa.OpAMD64ANDQconstmodify, ssa.OpAMD64ANDLconstmodify, ssa.OpAMD64ORQconstmodify, ssa.OpAMD64ORLconstmodify,
+		ssa.OpAMD64XORQconstmodify, ssa.OpAMD64XORLconstmodify:
+		sc := v.AuxValAndOff()
+		off := sc.Off()
+		val := sc.Val()
+		p := s.Prog(v.Op.Asm())
+		p.From.Type = obj.TYPE_CONST
+		p.From.Offset = val
+		p.To.Type = obj.TYPE_MEM
+		p.To.Reg = v.Args[0].Reg()
+		gc.AddAux2(&p.To, v, off)
 	case ssa.OpAMD64MOVQstoreconst, ssa.OpAMD64MOVLstoreconst, ssa.OpAMD64MOVWstoreconst, ssa.OpAMD64MOVBstoreconst:
 		p := s.Prog(v.Op.Asm())
 		p.From.Type = obj.TYPE_CONST

--- a/src/cmd/compile/internal/ssa/gen/AMD64.rules
+++ b/src/cmd/compile/internal/ssa/gen/AMD64.rules
@@ -1039,8 +1039,10 @@
 	((ADD|SUB|MUL)SSload [off1+off2] {sym} val base mem)
 ((ADD|SUB|MUL)SDload [off1] {sym} val (ADDQconst [off2] base) mem) && is32Bit(off1+off2) ->
 	((ADD|SUB|MUL)SDload [off1+off2] {sym} val base mem)
-(ADD(L|Q)constmodify [valoff1] {sym} (ADDQconst [off2] base) mem) && ValAndOff(valoff1).canAdd(off2) ->
-	(ADD(L|Q)constmodify [ValAndOff(valoff1).add(off2)] {sym} base mem)
+((ADD|AND|OR|XOR)Qconstmodify [valoff1] {sym} (ADDQconst [off2] base) mem) && ValAndOff(valoff1).canAdd(off2) ->
+	((ADD|AND|OR|XOR)Qconstmodify [ValAndOff(valoff1).add(off2)] {sym} base mem)
+((ADD|AND|OR|XOR)Lconstmodify [valoff1] {sym} (ADDQconst [off2] base) mem) && ValAndOff(valoff1).canAdd(off2) ->
+	((ADD|AND|OR|XOR)Lconstmodify [ValAndOff(valoff1).add(off2)] {sym} base mem)

 // Fold constants into stores.
 (MOVQstore [off] {sym} ptr (MOVQconst [c]) mem) && validValAndOff(c,off) ->
@@ -1081,9 +1083,12 @@
 ((ADD|SUB|MUL)SDload [off1] {sym1} val (LEAQ [off2] {sym2} base) mem)
 	&& is32Bit(off1+off2) && canMergeSym(sym1, sym2) ->
 	((ADD|SUB|MUL)SDload [off1+off2] {mergeSym(sym1,sym2)} val base mem)
-(ADD(L|Q)constmodify [valoff1] {sym1} (LEAQ [off2] {sym2} base) mem)
+((ADD|AND|OR|XOR)Qconstmodify [valoff1] {sym1} (LEAQ [off2] {sym2} base) mem)
 	&& ValAndOff(valoff1).canAdd(off2) && canMergeSym(sym1, sym2) ->
-	(ADD(L|Q)constmodify [ValAndOff(valoff1).add(off2)] {mergeSym(sym1,sym2)} base mem)
+	((ADD|AND|OR|XOR)Qconstmodify [ValAndOff(valoff1).add(off2)] {mergeSym(sym1,sym2)} base mem)
+((ADD|AND|OR|XOR)Lconstmodify [valoff1] {sym1} (LEAQ [off2] {sym2} base) mem)
+	&& ValAndOff(valoff1).canAdd(off2) && canMergeSym(sym1, sym2) ->
+	((ADD|AND|OR|XOR)Lconstmodify [ValAndOff(valoff1).add(off2)] {mergeSym(sym1,sym2)} base mem)

 // generating indexed loads and stores
 (MOV(B|W|L|Q|SS|SD)load [off1] {sym1} (LEAQ1 [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) ->
@@ -2352,12 +2357,12 @@
 (MOVWQZX (MOVBQZX x)) -> (MOVBQZX x)
 (MOVBQZX (MOVBQZX x)) -> (MOVBQZX x)

-(MOVQstore [off] {sym} ptr a:(ADDQconst [c] l:(MOVQload [off] {sym} ptr2 mem)) mem)
+(MOVQstore [off] {sym} ptr a:((ADD|AND|OR|XOR)Qconst [c] l:(MOVQload [off] {sym} ptr2 mem)) mem)
 	&& isSamePtr(ptr, ptr2) && a.Uses == 1 && l.Uses == 1 && validValAndOff(c,off) ->
-	(ADDQconstmodify {sym} [makeValAndOff(c,off)] ptr mem)
-(MOVLstore [off] {sym} ptr a:(ADDLconst [c] l:(MOVLload [off] {sym} ptr2 mem)) mem)
+	((ADD|AND|OR|XOR)Qconstmodify {sym} [makeValAndOff(c,off)] ptr mem)
+(MOVLstore [off] {sym} ptr a:((ADD|AND|OR|XOR)Lconst [c] l:(MOVLload [off] {sym} ptr2 mem)) mem)
 	&& isSamePtr(ptr, ptr2) && a.Uses == 1 && l.Uses == 1 && validValAndOff(c,off) ->
-	(ADDLconstmodify {sym} [makeValAndOff(c,off)] ptr mem)
+	((ADD|AND|OR|XOR)Lconstmodify {sym} [makeValAndOff(c,off)] ptr mem)

 // float <-> int register moves, with no conversion.
 // These come up when compiling math.{Float{32,64}bits,Float{32,64}frombits}.

--- a/src/cmd/compile/internal/ssa/gen/AMD64Ops.go
+++ b/src/cmd/compile/internal/ssa/gen/AMD64Ops.go
@@ -225,20 +225,26 @@ func init() {
 		{name: "MULQU2", argLength: 2, reg: regInfo{inputs: []regMask{ax, gpsp}, outputs: []regMask{dx, ax}}, commutative: true, asm: "MULQ", clobberFlags: true}, // arg0 * arg1, returns (hi, lo)
 		{name: "DIVQU2", argLength: 3, reg: regInfo{inputs: []regMask{dx, ax, gpsp}, outputs: []regMask{ax, dx}}, asm: "DIVQ", clobberFlags: true},                // arg0:arg1 / arg2 (128-bit divided by 64-bit), returns (q, r)

-		{name: "ANDQ", argLength: 2, reg: gp21, asm: "ANDQ", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 & arg1
-		{name: "ANDL", argLength: 2, reg: gp21, asm: "ANDL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 & arg1
-		{name: "ANDQconst", argLength: 1, reg: gp11, asm: "ANDQ", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 & auxint
-		{name: "ANDLconst", argLength: 1, reg: gp11, asm: "ANDL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 & auxint
-
-		{name: "ORQ", argLength: 2, reg: gp21, asm: "ORQ", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 | arg1
-		{name: "ORL", argLength: 2, reg: gp21, asm: "ORL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 | arg1
-		{name: "ORQconst", argLength: 1, reg: gp11, asm: "ORQ", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 | auxint
-		{name: "ORLconst", argLength: 1, reg: gp11, asm: "ORL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 | auxint
-
-		{name: "XORQ", argLength: 2, reg: gp21, asm: "XORQ", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 ^ arg1
-		{name: "XORL", argLength: 2, reg: gp21, asm: "XORL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 ^ arg1
-		{name: "XORQconst", argLength: 1, reg: gp11, asm: "XORQ", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 ^ auxint
-		{name: "XORLconst", argLength: 1, reg: gp11, asm: "XORL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 ^ auxint
+		{name: "ANDQ", argLength: 2, reg: gp21, asm: "ANDQ", commutative: true, resultInArg0: true, clobberFlags: true},                                                 // arg0 & arg1
+		{name: "ANDL", argLength: 2, reg: gp21, asm: "ANDL", commutative: true, resultInArg0: true, clobberFlags: true},                                                 // arg0 & arg1
+		{name: "ANDQconst", argLength: 1, reg: gp11, asm: "ANDQ", aux: "Int32", resultInArg0: true, clobberFlags: true},                                                 // arg0 & auxint
+		{name: "ANDLconst", argLength: 1, reg: gp11, asm: "ANDL", aux: "Int32", resultInArg0: true, clobberFlags: true},                                                 // arg0 & auxint
+		{name: "ANDQconstmodify", argLength: 2, reg: gpstoreconst, asm: "ANDQ", aux: "SymValAndOff", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // and ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
+		{name: "ANDLconstmodify", argLength: 2, reg: gpstoreconst, asm: "ANDL", aux: "SymValAndOff", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // and ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
+
+		{name: "ORQ", argLength: 2, reg: gp21, asm: "ORQ", commutative: true, resultInArg0: true, clobberFlags: true},                                                 // arg0 | arg1
+		{name: "ORL", argLength: 2, reg: gp21, asm: "ORL", commutative: true, resultInArg0: true, clobberFlags: true},                                                 // arg0 | arg1
+		{name: "ORQconst", argLength: 1, reg: gp11, asm: "ORQ", aux: "Int32", resultInArg0: true, clobberFlags: true},                                                 // arg0 | auxint
+		{name: "ORLconst", argLength: 1, reg: gp11, asm: "ORL", aux: "Int32", resultInArg0: true, clobberFlags: true},                                                 // arg0 | auxint
+		{name: "ORQconstmodify", argLength: 2, reg: gpstoreconst, asm: "ORQ", aux: "SymValAndOff", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // or ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
+		{name: "ORLconstmodify", argLength: 2, reg: gpstoreconst, asm: "ORL", aux: "SymValAndOff", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // or ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
+
+		{name: "XORQ", argLength: 2, reg: gp21, asm: "XORQ", commutative: true, resultInArg0: true, clobberFlags: true},                                                 // arg0 ^ arg1
+		{name: "XORL", argLength: 2, reg: gp21, asm: "XORL", commutative: true, resultInArg0: true, clobberFlags: true},                                                 // arg0 ^ arg1
+		{name: "XORQconst", argLength: 1, reg: gp11, asm: "XORQ", aux: "Int32", resultInArg0: true, clobberFlags: true},                                                 // arg0 ^ auxint
+		{name: "XORLconst", argLength: 1, reg: gp11, asm: "XORL", aux: "Int32", resultInArg0: true, clobberFlags: true},                                                 // arg0 ^ auxint
+		{name: "XORQconstmodify", argLength: 2, reg: gpstoreconst, asm: "XORQ", aux: "SymValAndOff", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // xor ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
+		{name: "XORLconstmodify", argLength: 2, reg: gpstoreconst, asm: "XORL", aux: "SymValAndOff", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // xor ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem

 		{name: "CMPQ", argLength: 2, reg: gp2flags, asm: "CMPQ", typ: "Flags"},                    // arg0 compare to arg1
 		{name: "CMPL", argLength: 2, reg: gp2flags, asm: "CMPL", typ: "Flags"},                    // arg0 compare to arg1

--- a/src/cmd/compile/internal/ssa/opGen.go
+++ b/src/cmd/compile/internal/ssa/opGen.go
@@ -487,14 +487,20 @@ const (
 	OpAMD64ANDL
 	OpAMD64ANDQconst
 	OpAMD64ANDLconst
+	OpAMD64ANDQconstmodify
+	OpAMD64ANDLconstmodify
 	OpAMD64ORQ
 	OpAMD64ORL
 	OpAMD64ORQconst
 	OpAMD64ORLconst
+	OpAMD64ORQconstmodify
+	OpAMD64ORLconstmodify
 	OpAMD64XORQ
 	OpAMD64XORL
 	OpAMD64XORQconst
 	OpAMD64XORLconst
+	OpAMD64XORQconstmodify
+	OpAMD64XORLconstmodify
 	OpAMD64CMPQ
 	OpAMD64CMPL
 	OpAMD64CMPW
@@ -5948,6 +5954,34 @@ var opcodeTable = [...]opInfo{
 			},
 		},
 	},
+	{
+		name:           "ANDQconstmodify",
+		auxType:        auxSymValAndOff,
+		argLen:         2,
+		clobberFlags:   true,
+		faultOnNilArg0: true,
+		symEffect:      SymRead | SymWrite,
+		asm:            x86.AANDQ,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{0, 4295032831}, // AX CX DX BX SP BP SI DI R8 R9 R10 R11 R12 R13 R14 R15 SB
+			},
+		},
+	},
+	{
+		name:           "ANDLconstmodify",
+		auxType:        auxSymValAndOff,
+		argLen:         2,
+		clobberFlags:   true,
+		faultOnNilArg0: true,
+		symEffect:      SymRead | SymWrite,
+		asm:            x86.AANDL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{0, 4295032831}, // AX CX DX BX SP BP SI DI R8 R9 R10 R11 R12 R13 R14 R15 SB
+			},
+		},
+	},
 	{
 		name:         "ORQ",
 		argLen:       2,
@@ -6014,6 +6048,34 @@ var opcodeTable = [...]opInfo{
 			},
 		},
 	},
+	{
+		name:           "ORQconstmodify",
+		auxType:        auxSymValAndOff,
+		argLen:         2,
+		clobberFlags:   true,
+		faultOnNilArg0: true,
+		symEffect:      SymRead | SymWrite,
+		asm:            x86.AORQ,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{0, 4295032831}, // AX CX DX BX SP BP SI DI R8 R9 R10 R11 R12 R13 R14 R15 SB
+			},
+		},
+	},
+	{
+		name:           "ORLconstmodify",
+		auxType:        auxSymValAndOff,
+		argLen:         2,
+		clobberFlags:   true,
+		faultOnNilArg0: true,
+		symEffect:      SymRead | SymWrite,
+		asm:            x86.AORL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{0, 4295032831}, // AX CX DX BX SP BP SI DI R8 R9 R10 R11 R12 R13 R14 R15 SB
+			},
+		},
+	},
 	{
 		name:         "XORQ",
 		argLen:       2,
@@ -6080,6 +6142,34 @@ var opcodeTable = [...]opInfo{
 			},
 		},
 	},
+	{
+		name:           "XORQconstmodify",
+		auxType:        auxSymValAndOff,
+		argLen:         2,
+		clobberFlags:   true,
+		faultOnNilArg0: true,
+		symEffect:      SymRead | SymWrite,
+		asm:            x86.AXORQ,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{0, 4295032831}, // AX CX DX BX SP BP SI DI R8 R9 R10 R11 R12 R13 R14 R15 SB
+			},
+		},
+	},
+	{
+		name:           "XORLconstmodify",
+		auxType:        auxSymValAndOff,
+		argLen:         2,
+		clobberFlags:   true,
+		faultOnNilArg0: true,
+		symEffect:      SymRead | SymWrite,
+		asm:            x86.AXORL,
+		reg: regInfo{
+			inputs: []inputInfo{
+				{0, 4295032831}, // AX CX DX BX SP BP SI DI R8 R9 R10 R11 R12 R13 R14 R15 SB
+			},
+		},
+	},
 	{
 		name:   "CMPQ",
 		argLen: 2,

--- a/src/cmd/compile/internal/ssa/rewriteAMD64.go
+++ b/src/cmd/compile/internal/ssa/rewriteAMD64.go
--- a/test/codegen/bits.go
+++ b/test/codegen/bits.go
@@ -262,6 +262,16 @@ func bitcompl32(a, b uint32) (n uint32) {
 	return n
 }

+// check direct operation on memory with constant source
+func bitOpOnMem(a []uint32) {
+	// amd64:`ANDL\s[$]200,\s\([A-Z]+\)`
+	a[0] &= 200
+	// amd64:`ORL\s[$]220,\s4\([A-Z]+\)`
+	a[1] |= 220
+	// amd64:`XORL\s[$]240,\s8\([A-Z]+\)`
+	a[2] ^= 240
+}
+
 // Check AND masking on arm64 (Issue #19857)

 func and_mask_1(a uint64) uint64 {