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

508 lines
13 KiB
Go
Raw Normal View History

// Copyright 2018 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package wasm
import (
"cmd/compile/internal/base"
"cmd/compile/internal/gc"
[dev.regabi] cmd/compile: introduce cmd/compile/internal/ir [generated] If we want to break up package gc at all, we will need to move the compiler IR it defines into a separate package that can be imported by packages that gc itself imports. This CL does that. It also removes the TINT8 etc aliases so that all code is clear about which package things are coming from. This CL is automatically generated by the script below. See the comments in the script for details about the changes. [git-generate] cd src/cmd/compile/internal/gc rf ' # These names were never fully qualified # when the types package was added. # Do it now, to avoid confusion about where they live. inline -rm \ Txxx \ TINT8 \ TUINT8 \ TINT16 \ TUINT16 \ TINT32 \ TUINT32 \ TINT64 \ TUINT64 \ TINT \ TUINT \ TUINTPTR \ TCOMPLEX64 \ TCOMPLEX128 \ TFLOAT32 \ TFLOAT64 \ TBOOL \ TPTR \ TFUNC \ TSLICE \ TARRAY \ TSTRUCT \ TCHAN \ TMAP \ TINTER \ TFORW \ TANY \ TSTRING \ TUNSAFEPTR \ TIDEAL \ TNIL \ TBLANK \ TFUNCARGS \ TCHANARGS \ NTYPE \ BADWIDTH # esc.go and escape.go do not need to be split. # Append esc.go onto the end of escape.go. mv esc.go escape.go # Pull out the type format installation from func Main, # so it can be carried into package ir. mv Main:/Sconv.=/-0,/TypeLinkSym/-1 InstallTypeFormats # Names that need to be exported for use by code left in gc. mv Isconst IsConst mv asNode AsNode mv asNodes AsNodes mv asTypesNode AsTypesNode mv basicnames BasicTypeNames mv builtinpkg BuiltinPkg mv consttype ConstType mv dumplist DumpList mv fdumplist FDumpList mv fmtMode FmtMode mv goopnames OpNames mv inspect Inspect mv inspectList InspectList mv localpkg LocalPkg mv nblank BlankNode mv numImport NumImport mv opprec OpPrec mv origSym OrigSym mv stmtwithinit StmtWithInit mv dump DumpAny mv fdump FDumpAny mv nod Nod mv nodl NodAt mv newname NewName mv newnamel NewNameAt mv assertRepresents AssertValidTypeForConst mv represents ValidTypeForConst mv nodlit NewLiteral # Types and fields that need to be exported for use by gc. mv nowritebarrierrecCallSym SymAndPos mv SymAndPos.lineno SymAndPos.Pos mv SymAndPos.target SymAndPos.Sym mv Func.lsym Func.LSym mv Func.setWBPos Func.SetWBPos mv Func.numReturns Func.NumReturns mv Func.numDefers Func.NumDefers mv Func.nwbrCalls Func.NWBRCalls # initLSym is an algorithm left behind in gc, # not an operation on Func itself. mv Func.initLSym initLSym mv nodeQueue NodeQueue mv NodeQueue.empty NodeQueue.Empty mv NodeQueue.popLeft NodeQueue.PopLeft mv NodeQueue.pushRight NodeQueue.PushRight # Many methods on Node are actually algorithms that # would apply to any node implementation. # Those become plain functions. mv Node.funcname FuncName mv Node.isBlank IsBlank mv Node.isGoConst isGoConst mv Node.isNil IsNil mv Node.isParamHeapCopy isParamHeapCopy mv Node.isParamStackCopy isParamStackCopy mv Node.isSimpleName isSimpleName mv Node.mayBeShared MayBeShared mv Node.pkgFuncName PkgFuncName mv Node.backingArrayPtrLen backingArrayPtrLen mv Node.isterminating isTermNode mv Node.labeledControl labeledControl mv Nodes.isterminating isTermNodes mv Nodes.sigerr fmtSignature mv Node.MethodName methodExprName mv Node.MethodFunc methodExprFunc mv Node.IsMethod IsMethod # Every node will need to implement RawCopy; # Copy and SepCopy algorithms will use it. mv Node.rawcopy Node.RawCopy mv Node.copy Copy mv Node.sepcopy SepCopy # Extract Node.Format method body into func FmtNode, # but leave method wrapper behind. mv Node.Format:0,$ FmtNode # Formatting helpers that will apply to all node implementations. mv Node.Line Line mv Node.exprfmt exprFmt mv Node.jconv jconvFmt mv Node.modeString modeString mv Node.nconv nconvFmt mv Node.nodedump nodeDumpFmt mv Node.nodefmt nodeFmt mv Node.stmtfmt stmtFmt # Constant support needed for code moving to ir. mv okforconst OKForConst mv vconv FmtConst mv int64Val Int64Val mv float64Val Float64Val mv Node.ValueInterface ConstValue # Organize code into files. mv LocalPkg BuiltinPkg ir.go mv NumImport InstallTypeFormats Line fmt.go mv syntax.go Nod NodAt NewNameAt Class Pxxx PragmaFlag Nointerface SymAndPos \ AsNode AsTypesNode BlankNode OrigSym \ Node.SliceBounds Node.SetSliceBounds Op.IsSlice3 \ IsConst Node.Int64Val Node.CanInt64 Node.Uint64Val Node.BoolVal Node.StringVal \ Node.RawCopy SepCopy Copy \ IsNil IsBlank IsMethod \ Node.Typ Node.StorageClass node.go mv ConstType ConstValue Int64Val Float64Val AssertValidTypeForConst ValidTypeForConst NewLiteral idealType OKForConst val.go # Move files to new ir package. mv bitset.go class_string.go dump.go fmt.go \ ir.go node.go op_string.go val.go \ sizeof_test.go cmd/compile/internal/ir ' : # fix mkbuiltin.go to generate the changes made to builtin.go during rf sed -i '' ' s/\[T/[types.T/g s/\*Node/*ir.Node/g /internal\/types/c \ fmt.Fprintln(&b, `import (`) \ fmt.Fprintln(&b, ` "cmd/compile/internal/ir"`) \ fmt.Fprintln(&b, ` "cmd/compile/internal/types"`) \ fmt.Fprintln(&b, `)`) ' mkbuiltin.go gofmt -w mkbuiltin.go : # update cmd/dist to add internal/ir cd ../../../dist sed -i '' '/compile.internal.gc/a\ "cmd/compile/internal/ir", ' buildtool.go gofmt -w buildtool.go : # update cmd/compile TestFormats cd ../.. go install std cmd cd cmd/compile go test -u || go test # first one updates but fails; second passes Change-Id: I5f7caf6b20629b51970279e81231a3574d5b51db Reviewed-on: https://go-review.googlesource.com/c/go/+/273008 Trust: Russ Cox <rsc@golang.org> Reviewed-by: Matthew Dempsky <mdempsky@google.com>
2020-11-19 21:09:22 -05:00
"cmd/compile/internal/ir"
"cmd/compile/internal/logopt"
"cmd/compile/internal/ssa"
"cmd/compile/internal/types"
"cmd/internal/obj"
"cmd/internal/obj/wasm"
"cmd/internal/objabi"
)
func Init(arch *gc.Arch) {
arch.LinkArch = &wasm.Linkwasm
arch.REGSP = wasm.REG_SP
arch.MAXWIDTH = 1 << 50
arch.ZeroRange = zeroRange
arch.Ginsnop = ginsnop
arch.Ginsnopdefer = ginsnop
arch.SSAMarkMoves = ssaMarkMoves
arch.SSAGenValue = ssaGenValue
arch.SSAGenBlock = ssaGenBlock
}
func zeroRange(pp *gc.Progs, p *obj.Prog, off, cnt int64, state *uint32) *obj.Prog {
if cnt == 0 {
return p
}
if cnt%8 != 0 {
base.Fatalf("zerorange count not a multiple of widthptr %d", cnt)
}
for i := int64(0); i < cnt; i += 8 {
p = pp.Appendpp(p, wasm.AGet, obj.TYPE_REG, wasm.REG_SP, 0, 0, 0, 0)
p = pp.Appendpp(p, wasm.AI64Const, obj.TYPE_CONST, 0, 0, 0, 0, 0)
p = pp.Appendpp(p, wasm.AI64Store, 0, 0, 0, obj.TYPE_CONST, 0, off+i)
}
return p
}
func ginsnop(pp *gc.Progs) *obj.Prog {
return pp.Prog(wasm.ANop)
}
func ssaMarkMoves(s *gc.SSAGenState, b *ssa.Block) {
}
func ssaGenBlock(s *gc.SSAGenState, b, next *ssa.Block) {
switch b.Kind {
case ssa.BlockPlain:
if next != b.Succs[0].Block() {
s.Br(obj.AJMP, b.Succs[0].Block())
}
case ssa.BlockIf:
switch next {
case b.Succs[0].Block():
// if false, jump to b.Succs[1]
cmd/compile: allow multiple SSA block control values Control values are used to choose which successor of a block is jumped to. Typically a control value takes the form of a 'flags' value that represents the result of a comparison. Some architectures however use a variable in a register as a control value. Up until now we have managed with a single control value per block. However some architectures (e.g. s390x and riscv64) have combined compare-and-branch instructions that take two variables in registers as parameters. To generate these instructions we need to support 2 control values per block. This CL allows up to 2 control values to be used in a block in order to support the addition of compare-and-branch instructions. I have implemented s390x compare-and-branch instructions in a different CL. Passes toolstash-check -all. Results of compilebench: name old time/op new time/op delta Template 208ms ± 1% 209ms ± 1% ~ (p=0.289 n=20+20) Unicode 83.7ms ± 1% 83.3ms ± 3% -0.49% (p=0.017 n=18+18) GoTypes 748ms ± 1% 748ms ± 0% ~ (p=0.460 n=20+18) Compiler 3.47s ± 1% 3.48s ± 1% ~ (p=0.070 n=19+18) SSA 11.5s ± 1% 11.7s ± 1% +1.64% (p=0.000 n=19+18) Flate 130ms ± 1% 130ms ± 1% ~ (p=0.588 n=19+20) GoParser 160ms ± 1% 161ms ± 1% ~ (p=0.211 n=20+20) Reflect 465ms ± 1% 467ms ± 1% +0.42% (p=0.007 n=20+20) Tar 184ms ± 1% 185ms ± 2% ~ (p=0.087 n=18+20) XML 253ms ± 1% 253ms ± 1% ~ (p=0.377 n=20+18) LinkCompiler 769ms ± 2% 774ms ± 2% ~ (p=0.070 n=19+19) ExternalLinkCompiler 3.59s ±11% 3.68s ± 6% ~ (p=0.072 n=20+20) LinkWithoutDebugCompiler 446ms ± 5% 454ms ± 3% +1.79% (p=0.002 n=19+20) StdCmd 26.0s ± 2% 26.0s ± 2% ~ (p=0.799 n=20+20) name old user-time/op new user-time/op delta Template 238ms ± 5% 240ms ± 5% ~ (p=0.142 n=20+20) Unicode 105ms ±11% 106ms ±10% ~ (p=0.512 n=20+20) GoTypes 876ms ± 2% 873ms ± 4% ~ (p=0.647 n=20+19) Compiler 4.17s ± 2% 4.19s ± 1% ~ (p=0.093 n=20+18) SSA 13.9s ± 1% 14.1s ± 1% +1.45% (p=0.000 n=18+18) Flate 145ms ±13% 146ms ± 5% ~ (p=0.851 n=20+18) GoParser 185ms ± 5% 188ms ± 7% ~ (p=0.174 n=20+20) Reflect 534ms ± 3% 538ms ± 2% ~ (p=0.105 n=20+18) Tar 215ms ± 4% 211ms ± 9% ~ (p=0.079 n=19+20) XML 295ms ± 6% 295ms ± 5% ~ (p=0.968 n=20+20) LinkCompiler 832ms ± 4% 837ms ± 7% ~ (p=0.707 n=17+20) ExternalLinkCompiler 1.58s ± 8% 1.60s ± 4% ~ (p=0.296 n=20+19) LinkWithoutDebugCompiler 478ms ±12% 489ms ±10% ~ (p=0.429 n=20+20) name old object-bytes new object-bytes delta Template 559kB ± 0% 559kB ± 0% ~ (all equal) Unicode 216kB ± 0% 216kB ± 0% ~ (all equal) GoTypes 2.03MB ± 0% 2.03MB ± 0% ~ (all equal) Compiler 8.07MB ± 0% 8.07MB ± 0% -0.06% (p=0.000 n=20+20) SSA 27.1MB ± 0% 27.3MB ± 0% +0.89% (p=0.000 n=20+20) Flate 343kB ± 0% 343kB ± 0% ~ (all equal) GoParser 441kB ± 0% 441kB ± 0% ~ (all equal) Reflect 1.36MB ± 0% 1.36MB ± 0% ~ (all equal) Tar 487kB ± 0% 487kB ± 0% ~ (all equal) XML 632kB ± 0% 632kB ± 0% ~ (all equal) name old export-bytes new export-bytes delta Template 18.5kB ± 0% 18.5kB ± 0% ~ (all equal) Unicode 7.92kB ± 0% 7.92kB ± 0% ~ (all equal) GoTypes 35.0kB ± 0% 35.0kB ± 0% ~ (all equal) Compiler 109kB ± 0% 110kB ± 0% +0.72% (p=0.000 n=20+20) SSA 137kB ± 0% 138kB ± 0% +0.58% (p=0.000 n=20+20) Flate 4.89kB ± 0% 4.89kB ± 0% ~ (all equal) GoParser 8.49kB ± 0% 8.49kB ± 0% ~ (all equal) Reflect 11.4kB ± 0% 11.4kB ± 0% ~ (all equal) Tar 10.5kB ± 0% 10.5kB ± 0% ~ (all equal) XML 16.7kB ± 0% 16.7kB ± 0% ~ (all equal) name old text-bytes new text-bytes delta HelloSize 761kB ± 0% 761kB ± 0% ~ (all equal) CmdGoSize 10.8MB ± 0% 10.8MB ± 0% ~ (all equal) name old data-bytes new data-bytes delta HelloSize 10.7kB ± 0% 10.7kB ± 0% ~ (all equal) CmdGoSize 312kB ± 0% 312kB ± 0% ~ (all equal) name old bss-bytes new bss-bytes delta HelloSize 122kB ± 0% 122kB ± 0% ~ (all equal) CmdGoSize 146kB ± 0% 146kB ± 0% ~ (all equal) name old exe-bytes new exe-bytes delta HelloSize 1.13MB ± 0% 1.13MB ± 0% ~ (all equal) CmdGoSize 15.1MB ± 0% 15.1MB ± 0% ~ (all equal) Change-Id: I3cc2f9829a109543d9a68be4a21775d2d3e9801f Reviewed-on: https://go-review.googlesource.com/c/go/+/196557 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Daniel Martí <mvdan@mvdan.cc> Reviewed-by: Keith Randall <khr@golang.org>
2019-08-12 20:19:58 +01:00
getValue32(s, b.Controls[0])
s.Prog(wasm.AI32Eqz)
s.Prog(wasm.AIf)
s.Br(obj.AJMP, b.Succs[1].Block())
s.Prog(wasm.AEnd)
case b.Succs[1].Block():
// if true, jump to b.Succs[0]
cmd/compile: allow multiple SSA block control values Control values are used to choose which successor of a block is jumped to. Typically a control value takes the form of a 'flags' value that represents the result of a comparison. Some architectures however use a variable in a register as a control value. Up until now we have managed with a single control value per block. However some architectures (e.g. s390x and riscv64) have combined compare-and-branch instructions that take two variables in registers as parameters. To generate these instructions we need to support 2 control values per block. This CL allows up to 2 control values to be used in a block in order to support the addition of compare-and-branch instructions. I have implemented s390x compare-and-branch instructions in a different CL. Passes toolstash-check -all. Results of compilebench: name old time/op new time/op delta Template 208ms ± 1% 209ms ± 1% ~ (p=0.289 n=20+20) Unicode 83.7ms ± 1% 83.3ms ± 3% -0.49% (p=0.017 n=18+18) GoTypes 748ms ± 1% 748ms ± 0% ~ (p=0.460 n=20+18) Compiler 3.47s ± 1% 3.48s ± 1% ~ (p=0.070 n=19+18) SSA 11.5s ± 1% 11.7s ± 1% +1.64% (p=0.000 n=19+18) Flate 130ms ± 1% 130ms ± 1% ~ (p=0.588 n=19+20) GoParser 160ms ± 1% 161ms ± 1% ~ (p=0.211 n=20+20) Reflect 465ms ± 1% 467ms ± 1% +0.42% (p=0.007 n=20+20) Tar 184ms ± 1% 185ms ± 2% ~ (p=0.087 n=18+20) XML 253ms ± 1% 253ms ± 1% ~ (p=0.377 n=20+18) LinkCompiler 769ms ± 2% 774ms ± 2% ~ (p=0.070 n=19+19) ExternalLinkCompiler 3.59s ±11% 3.68s ± 6% ~ (p=0.072 n=20+20) LinkWithoutDebugCompiler 446ms ± 5% 454ms ± 3% +1.79% (p=0.002 n=19+20) StdCmd 26.0s ± 2% 26.0s ± 2% ~ (p=0.799 n=20+20) name old user-time/op new user-time/op delta Template 238ms ± 5% 240ms ± 5% ~ (p=0.142 n=20+20) Unicode 105ms ±11% 106ms ±10% ~ (p=0.512 n=20+20) GoTypes 876ms ± 2% 873ms ± 4% ~ (p=0.647 n=20+19) Compiler 4.17s ± 2% 4.19s ± 1% ~ (p=0.093 n=20+18) SSA 13.9s ± 1% 14.1s ± 1% +1.45% (p=0.000 n=18+18) Flate 145ms ±13% 146ms ± 5% ~ (p=0.851 n=20+18) GoParser 185ms ± 5% 188ms ± 7% ~ (p=0.174 n=20+20) Reflect 534ms ± 3% 538ms ± 2% ~ (p=0.105 n=20+18) Tar 215ms ± 4% 211ms ± 9% ~ (p=0.079 n=19+20) XML 295ms ± 6% 295ms ± 5% ~ (p=0.968 n=20+20) LinkCompiler 832ms ± 4% 837ms ± 7% ~ (p=0.707 n=17+20) ExternalLinkCompiler 1.58s ± 8% 1.60s ± 4% ~ (p=0.296 n=20+19) LinkWithoutDebugCompiler 478ms ±12% 489ms ±10% ~ (p=0.429 n=20+20) name old object-bytes new object-bytes delta Template 559kB ± 0% 559kB ± 0% ~ (all equal) Unicode 216kB ± 0% 216kB ± 0% ~ (all equal) GoTypes 2.03MB ± 0% 2.03MB ± 0% ~ (all equal) Compiler 8.07MB ± 0% 8.07MB ± 0% -0.06% (p=0.000 n=20+20) SSA 27.1MB ± 0% 27.3MB ± 0% +0.89% (p=0.000 n=20+20) Flate 343kB ± 0% 343kB ± 0% ~ (all equal) GoParser 441kB ± 0% 441kB ± 0% ~ (all equal) Reflect 1.36MB ± 0% 1.36MB ± 0% ~ (all equal) Tar 487kB ± 0% 487kB ± 0% ~ (all equal) XML 632kB ± 0% 632kB ± 0% ~ (all equal) name old export-bytes new export-bytes delta Template 18.5kB ± 0% 18.5kB ± 0% ~ (all equal) Unicode 7.92kB ± 0% 7.92kB ± 0% ~ (all equal) GoTypes 35.0kB ± 0% 35.0kB ± 0% ~ (all equal) Compiler 109kB ± 0% 110kB ± 0% +0.72% (p=0.000 n=20+20) SSA 137kB ± 0% 138kB ± 0% +0.58% (p=0.000 n=20+20) Flate 4.89kB ± 0% 4.89kB ± 0% ~ (all equal) GoParser 8.49kB ± 0% 8.49kB ± 0% ~ (all equal) Reflect 11.4kB ± 0% 11.4kB ± 0% ~ (all equal) Tar 10.5kB ± 0% 10.5kB ± 0% ~ (all equal) XML 16.7kB ± 0% 16.7kB ± 0% ~ (all equal) name old text-bytes new text-bytes delta HelloSize 761kB ± 0% 761kB ± 0% ~ (all equal) CmdGoSize 10.8MB ± 0% 10.8MB ± 0% ~ (all equal) name old data-bytes new data-bytes delta HelloSize 10.7kB ± 0% 10.7kB ± 0% ~ (all equal) CmdGoSize 312kB ± 0% 312kB ± 0% ~ (all equal) name old bss-bytes new bss-bytes delta HelloSize 122kB ± 0% 122kB ± 0% ~ (all equal) CmdGoSize 146kB ± 0% 146kB ± 0% ~ (all equal) name old exe-bytes new exe-bytes delta HelloSize 1.13MB ± 0% 1.13MB ± 0% ~ (all equal) CmdGoSize 15.1MB ± 0% 15.1MB ± 0% ~ (all equal) Change-Id: I3cc2f9829a109543d9a68be4a21775d2d3e9801f Reviewed-on: https://go-review.googlesource.com/c/go/+/196557 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Daniel Martí <mvdan@mvdan.cc> Reviewed-by: Keith Randall <khr@golang.org>
2019-08-12 20:19:58 +01:00
getValue32(s, b.Controls[0])
s.Prog(wasm.AIf)
s.Br(obj.AJMP, b.Succs[0].Block())
s.Prog(wasm.AEnd)
default:
// if true, jump to b.Succs[0], else jump to b.Succs[1]
cmd/compile: allow multiple SSA block control values Control values are used to choose which successor of a block is jumped to. Typically a control value takes the form of a 'flags' value that represents the result of a comparison. Some architectures however use a variable in a register as a control value. Up until now we have managed with a single control value per block. However some architectures (e.g. s390x and riscv64) have combined compare-and-branch instructions that take two variables in registers as parameters. To generate these instructions we need to support 2 control values per block. This CL allows up to 2 control values to be used in a block in order to support the addition of compare-and-branch instructions. I have implemented s390x compare-and-branch instructions in a different CL. Passes toolstash-check -all. Results of compilebench: name old time/op new time/op delta Template 208ms ± 1% 209ms ± 1% ~ (p=0.289 n=20+20) Unicode 83.7ms ± 1% 83.3ms ± 3% -0.49% (p=0.017 n=18+18) GoTypes 748ms ± 1% 748ms ± 0% ~ (p=0.460 n=20+18) Compiler 3.47s ± 1% 3.48s ± 1% ~ (p=0.070 n=19+18) SSA 11.5s ± 1% 11.7s ± 1% +1.64% (p=0.000 n=19+18) Flate 130ms ± 1% 130ms ± 1% ~ (p=0.588 n=19+20) GoParser 160ms ± 1% 161ms ± 1% ~ (p=0.211 n=20+20) Reflect 465ms ± 1% 467ms ± 1% +0.42% (p=0.007 n=20+20) Tar 184ms ± 1% 185ms ± 2% ~ (p=0.087 n=18+20) XML 253ms ± 1% 253ms ± 1% ~ (p=0.377 n=20+18) LinkCompiler 769ms ± 2% 774ms ± 2% ~ (p=0.070 n=19+19) ExternalLinkCompiler 3.59s ±11% 3.68s ± 6% ~ (p=0.072 n=20+20) LinkWithoutDebugCompiler 446ms ± 5% 454ms ± 3% +1.79% (p=0.002 n=19+20) StdCmd 26.0s ± 2% 26.0s ± 2% ~ (p=0.799 n=20+20) name old user-time/op new user-time/op delta Template 238ms ± 5% 240ms ± 5% ~ (p=0.142 n=20+20) Unicode 105ms ±11% 106ms ±10% ~ (p=0.512 n=20+20) GoTypes 876ms ± 2% 873ms ± 4% ~ (p=0.647 n=20+19) Compiler 4.17s ± 2% 4.19s ± 1% ~ (p=0.093 n=20+18) SSA 13.9s ± 1% 14.1s ± 1% +1.45% (p=0.000 n=18+18) Flate 145ms ±13% 146ms ± 5% ~ (p=0.851 n=20+18) GoParser 185ms ± 5% 188ms ± 7% ~ (p=0.174 n=20+20) Reflect 534ms ± 3% 538ms ± 2% ~ (p=0.105 n=20+18) Tar 215ms ± 4% 211ms ± 9% ~ (p=0.079 n=19+20) XML 295ms ± 6% 295ms ± 5% ~ (p=0.968 n=20+20) LinkCompiler 832ms ± 4% 837ms ± 7% ~ (p=0.707 n=17+20) ExternalLinkCompiler 1.58s ± 8% 1.60s ± 4% ~ (p=0.296 n=20+19) LinkWithoutDebugCompiler 478ms ±12% 489ms ±10% ~ (p=0.429 n=20+20) name old object-bytes new object-bytes delta Template 559kB ± 0% 559kB ± 0% ~ (all equal) Unicode 216kB ± 0% 216kB ± 0% ~ (all equal) GoTypes 2.03MB ± 0% 2.03MB ± 0% ~ (all equal) Compiler 8.07MB ± 0% 8.07MB ± 0% -0.06% (p=0.000 n=20+20) SSA 27.1MB ± 0% 27.3MB ± 0% +0.89% (p=0.000 n=20+20) Flate 343kB ± 0% 343kB ± 0% ~ (all equal) GoParser 441kB ± 0% 441kB ± 0% ~ (all equal) Reflect 1.36MB ± 0% 1.36MB ± 0% ~ (all equal) Tar 487kB ± 0% 487kB ± 0% ~ (all equal) XML 632kB ± 0% 632kB ± 0% ~ (all equal) name old export-bytes new export-bytes delta Template 18.5kB ± 0% 18.5kB ± 0% ~ (all equal) Unicode 7.92kB ± 0% 7.92kB ± 0% ~ (all equal) GoTypes 35.0kB ± 0% 35.0kB ± 0% ~ (all equal) Compiler 109kB ± 0% 110kB ± 0% +0.72% (p=0.000 n=20+20) SSA 137kB ± 0% 138kB ± 0% +0.58% (p=0.000 n=20+20) Flate 4.89kB ± 0% 4.89kB ± 0% ~ (all equal) GoParser 8.49kB ± 0% 8.49kB ± 0% ~ (all equal) Reflect 11.4kB ± 0% 11.4kB ± 0% ~ (all equal) Tar 10.5kB ± 0% 10.5kB ± 0% ~ (all equal) XML 16.7kB ± 0% 16.7kB ± 0% ~ (all equal) name old text-bytes new text-bytes delta HelloSize 761kB ± 0% 761kB ± 0% ~ (all equal) CmdGoSize 10.8MB ± 0% 10.8MB ± 0% ~ (all equal) name old data-bytes new data-bytes delta HelloSize 10.7kB ± 0% 10.7kB ± 0% ~ (all equal) CmdGoSize 312kB ± 0% 312kB ± 0% ~ (all equal) name old bss-bytes new bss-bytes delta HelloSize 122kB ± 0% 122kB ± 0% ~ (all equal) CmdGoSize 146kB ± 0% 146kB ± 0% ~ (all equal) name old exe-bytes new exe-bytes delta HelloSize 1.13MB ± 0% 1.13MB ± 0% ~ (all equal) CmdGoSize 15.1MB ± 0% 15.1MB ± 0% ~ (all equal) Change-Id: I3cc2f9829a109543d9a68be4a21775d2d3e9801f Reviewed-on: https://go-review.googlesource.com/c/go/+/196557 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Daniel Martí <mvdan@mvdan.cc> Reviewed-by: Keith Randall <khr@golang.org>
2019-08-12 20:19:58 +01:00
getValue32(s, b.Controls[0])
s.Prog(wasm.AIf)
s.Br(obj.AJMP, b.Succs[0].Block())
s.Prog(wasm.AEnd)
s.Br(obj.AJMP, b.Succs[1].Block())
}
case ssa.BlockRet:
s.Prog(obj.ARET)
case ssa.BlockRetJmp:
p := s.Prog(obj.ARET)
p.To.Type = obj.TYPE_MEM
p.To.Name = obj.NAME_EXTERN
p.To.Sym = b.Aux.(*obj.LSym)
case ssa.BlockExit:
case ssa.BlockDefer:
p := s.Prog(wasm.AGet)
p.From = obj.Addr{Type: obj.TYPE_REG, Reg: wasm.REG_RET0}
s.Prog(wasm.AI64Eqz)
s.Prog(wasm.AI32Eqz)
s.Prog(wasm.AIf)
s.Br(obj.AJMP, b.Succs[1].Block())
s.Prog(wasm.AEnd)
if next != b.Succs[0].Block() {
s.Br(obj.AJMP, b.Succs[0].Block())
}
default:
panic("unexpected block")
}
// Entry point for the next block. Used by the JMP in goToBlock.
s.Prog(wasm.ARESUMEPOINT)
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
if s.OnWasmStackSkipped != 0 {
panic("wasm: bad stack")
}
}
func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
switch v.Op {
case ssa.OpWasmLoweredStaticCall, ssa.OpWasmLoweredClosureCall, ssa.OpWasmLoweredInterCall:
s.PrepareCall(v)
if call, ok := v.Aux.(*ssa.AuxCall); ok && call.Fn == gc.Deferreturn {
// add a resume point before call to deferreturn so it can be called again via jmpdefer
s.Prog(wasm.ARESUMEPOINT)
}
if v.Op == ssa.OpWasmLoweredClosureCall {
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[1])
setReg(s, wasm.REG_CTXT)
}
if call, ok := v.Aux.(*ssa.AuxCall); ok && call.Fn != nil {
sym := call.Fn
p := s.Prog(obj.ACALL)
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: sym}
p.Pos = v.Pos
} else {
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
p := s.Prog(obj.ACALL)
p.To = obj.Addr{Type: obj.TYPE_NONE}
p.Pos = v.Pos
}
case ssa.OpWasmLoweredMove:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue32(s, v.Args[0])
getValue32(s, v.Args[1])
i32Const(s, int32(v.AuxInt))
p := s.Prog(wasm.ACall)
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: gc.WasmMove}
case ssa.OpWasmLoweredZero:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue32(s, v.Args[0])
i32Const(s, int32(v.AuxInt))
p := s.Prog(wasm.ACall)
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: gc.WasmZero}
case ssa.OpWasmLoweredNilCheck:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
s.Prog(wasm.AI64Eqz)
s.Prog(wasm.AIf)
p := s.Prog(wasm.ACALLNORESUME)
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: gc.SigPanic}
s.Prog(wasm.AEnd)
if logopt.Enabled() {
logopt.LogOpt(v.Pos, "nilcheck", "genssa", v.Block.Func.Name)
}
if base.Debug.Nil != 0 && v.Pos.Line() > 1 { // v.Pos.Line()==1 in generated wrappers
base.WarnfAt(v.Pos, "generated nil check")
}
case ssa.OpWasmLoweredWB:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
getValue64(s, v.Args[1])
p := s.Prog(wasm.ACALLNORESUME) // TODO(neelance): If possible, turn this into a simple wasm.ACall).
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: v.Aux.(*obj.LSym)}
case ssa.OpWasmI64Store8, ssa.OpWasmI64Store16, ssa.OpWasmI64Store32, ssa.OpWasmI64Store, ssa.OpWasmF32Store, ssa.OpWasmF64Store:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue32(s, v.Args[0])
getValue64(s, v.Args[1])
p := s.Prog(v.Op.Asm())
p.To = obj.Addr{Type: obj.TYPE_CONST, Offset: v.AuxInt}
case ssa.OpStoreReg:
getReg(s, wasm.REG_SP)
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
p := s.Prog(storeOp(v.Type))
gc.AddrAuto(&p.To, v)
default:
if v.Type.IsMemory() {
return
}
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
if v.OnWasmStack {
s.OnWasmStackSkipped++
// If a Value is marked OnWasmStack, we don't generate the value and store it to a register now.
// Instead, we delay the generation to when the value is used and then directly generate it on the WebAssembly stack.
return
}
ssaGenValueOnStack(s, v, true)
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
if s.OnWasmStackSkipped != 0 {
panic("wasm: bad stack")
}
setReg(s, v.Reg())
}
}
func ssaGenValueOnStack(s *gc.SSAGenState, v *ssa.Value, extend bool) {
switch v.Op {
case ssa.OpWasmLoweredGetClosurePtr:
getReg(s, wasm.REG_CTXT)
case ssa.OpWasmLoweredGetCallerPC:
p := s.Prog(wasm.AI64Load)
// Caller PC is stored 8 bytes below first parameter.
p.From = obj.Addr{
Type: obj.TYPE_MEM,
Name: obj.NAME_PARAM,
Offset: -8,
}
case ssa.OpWasmLoweredGetCallerSP:
p := s.Prog(wasm.AGet)
// Caller SP is the address of the first parameter.
p.From = obj.Addr{
Type: obj.TYPE_ADDR,
Name: obj.NAME_PARAM,
Reg: wasm.REG_SP,
Offset: 0,
}
case ssa.OpWasmLoweredAddr:
if v.Aux == nil { // address of off(SP), no symbol
getValue64(s, v.Args[0])
i64Const(s, v.AuxInt)
s.Prog(wasm.AI64Add)
break
}
p := s.Prog(wasm.AGet)
cmd/compile: fold offset into address on Wasm On Wasm, the offset was not folded into LoweredAddr, so it was not rematerializeable. This led to the address-taken operation in some cases generated too early, before the local variable becoming live. The liveness code thinks the variable live when the address is taken, then backs it up to live at function entry, then complains about it, because nothing other than arguments should be live on entry. This CL folds the offset into the address operation, so it is rematerializeable and so generated right before use, after the variable actually becomes live. It might be possible to relax the liveness code not to think a variable live when its address being taken, but until the address actually being used. But it would be quite complicated. As we're late in Go 1.11 freeze, it would be better not to do it. Also, I think the address operation is rematerializeable now on all architectures, so this is probably less necessary. This may also be a slight optimization, as the address+offset is now rematerializeable, which can be generated on the Wasm stack, without using any "registers" which are emulated by local variables on Wasm. I don't know how to do benchmarks on Wasm. At least, cmd/go binary size shrinks 9K. Fixes #25966. Change-Id: I01e5869515d6a3942fccdcb857f924a866876e57 Reviewed-on: https://go-review.googlesource.com/120599 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Richard Musiol <neelance@gmail.com>
2018-06-23 13:23:52 -04:00
p.From.Type = obj.TYPE_ADDR
switch v.Aux.(type) {
case *obj.LSym:
cmd/compile: fold offset into address on Wasm On Wasm, the offset was not folded into LoweredAddr, so it was not rematerializeable. This led to the address-taken operation in some cases generated too early, before the local variable becoming live. The liveness code thinks the variable live when the address is taken, then backs it up to live at function entry, then complains about it, because nothing other than arguments should be live on entry. This CL folds the offset into the address operation, so it is rematerializeable and so generated right before use, after the variable actually becomes live. It might be possible to relax the liveness code not to think a variable live when its address being taken, but until the address actually being used. But it would be quite complicated. As we're late in Go 1.11 freeze, it would be better not to do it. Also, I think the address operation is rematerializeable now on all architectures, so this is probably less necessary. This may also be a slight optimization, as the address+offset is now rematerializeable, which can be generated on the Wasm stack, without using any "registers" which are emulated by local variables on Wasm. I don't know how to do benchmarks on Wasm. At least, cmd/go binary size shrinks 9K. Fixes #25966. Change-Id: I01e5869515d6a3942fccdcb857f924a866876e57 Reviewed-on: https://go-review.googlesource.com/120599 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Richard Musiol <neelance@gmail.com>
2018-06-23 13:23:52 -04:00
gc.AddAux(&p.From, v)
case *ir.Name:
cmd/compile: fold offset into address on Wasm On Wasm, the offset was not folded into LoweredAddr, so it was not rematerializeable. This led to the address-taken operation in some cases generated too early, before the local variable becoming live. The liveness code thinks the variable live when the address is taken, then backs it up to live at function entry, then complains about it, because nothing other than arguments should be live on entry. This CL folds the offset into the address operation, so it is rematerializeable and so generated right before use, after the variable actually becomes live. It might be possible to relax the liveness code not to think a variable live when its address being taken, but until the address actually being used. But it would be quite complicated. As we're late in Go 1.11 freeze, it would be better not to do it. Also, I think the address operation is rematerializeable now on all architectures, so this is probably less necessary. This may also be a slight optimization, as the address+offset is now rematerializeable, which can be generated on the Wasm stack, without using any "registers" which are emulated by local variables on Wasm. I don't know how to do benchmarks on Wasm. At least, cmd/go binary size shrinks 9K. Fixes #25966. Change-Id: I01e5869515d6a3942fccdcb857f924a866876e57 Reviewed-on: https://go-review.googlesource.com/120599 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Richard Musiol <neelance@gmail.com>
2018-06-23 13:23:52 -04:00
p.From.Reg = v.Args[0].Reg()
gc.AddAux(&p.From, v)
default:
panic("wasm: bad LoweredAddr")
}
case ssa.OpWasmLoweredConvert:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
case ssa.OpWasmSelect:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
getValue64(s, v.Args[1])
getValue32(s, v.Args[2])
s.Prog(v.Op.Asm())
case ssa.OpWasmI64AddConst:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
i64Const(s, v.AuxInt)
s.Prog(v.Op.Asm())
case ssa.OpWasmI64Const:
i64Const(s, v.AuxInt)
case ssa.OpWasmF32Const:
f32Const(s, v.AuxFloat())
case ssa.OpWasmF64Const:
f64Const(s, v.AuxFloat())
case ssa.OpWasmI64Load8U, ssa.OpWasmI64Load8S, ssa.OpWasmI64Load16U, ssa.OpWasmI64Load16S, ssa.OpWasmI64Load32U, ssa.OpWasmI64Load32S, ssa.OpWasmI64Load, ssa.OpWasmF32Load, ssa.OpWasmF64Load:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue32(s, v.Args[0])
p := s.Prog(v.Op.Asm())
p.From = obj.Addr{Type: obj.TYPE_CONST, Offset: v.AuxInt}
case ssa.OpWasmI64Eqz:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
s.Prog(v.Op.Asm())
if extend {
s.Prog(wasm.AI64ExtendI32U)
}
case ssa.OpWasmI64Eq, ssa.OpWasmI64Ne, ssa.OpWasmI64LtS, ssa.OpWasmI64LtU, ssa.OpWasmI64GtS, ssa.OpWasmI64GtU, ssa.OpWasmI64LeS, ssa.OpWasmI64LeU, ssa.OpWasmI64GeS, ssa.OpWasmI64GeU,
ssa.OpWasmF32Eq, ssa.OpWasmF32Ne, ssa.OpWasmF32Lt, ssa.OpWasmF32Gt, ssa.OpWasmF32Le, ssa.OpWasmF32Ge,
ssa.OpWasmF64Eq, ssa.OpWasmF64Ne, ssa.OpWasmF64Lt, ssa.OpWasmF64Gt, ssa.OpWasmF64Le, ssa.OpWasmF64Ge:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
getValue64(s, v.Args[1])
s.Prog(v.Op.Asm())
if extend {
s.Prog(wasm.AI64ExtendI32U)
}
case ssa.OpWasmI64Add, ssa.OpWasmI64Sub, ssa.OpWasmI64Mul, ssa.OpWasmI64DivU, ssa.OpWasmI64RemS, ssa.OpWasmI64RemU, ssa.OpWasmI64And, ssa.OpWasmI64Or, ssa.OpWasmI64Xor, ssa.OpWasmI64Shl, ssa.OpWasmI64ShrS, ssa.OpWasmI64ShrU, ssa.OpWasmI64Rotl,
ssa.OpWasmF32Add, ssa.OpWasmF32Sub, ssa.OpWasmF32Mul, ssa.OpWasmF32Div, ssa.OpWasmF32Copysign,
ssa.OpWasmF64Add, ssa.OpWasmF64Sub, ssa.OpWasmF64Mul, ssa.OpWasmF64Div, ssa.OpWasmF64Copysign:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
getValue64(s, v.Args[1])
s.Prog(v.Op.Asm())
case ssa.OpWasmI32Rotl:
getValue32(s, v.Args[0])
getValue32(s, v.Args[1])
s.Prog(wasm.AI32Rotl)
s.Prog(wasm.AI64ExtendI32U)
case ssa.OpWasmI64DivS:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
getValue64(s, v.Args[1])
if v.Type.Size() == 8 {
// Division of int64 needs helper function wasmDiv to handle the MinInt64 / -1 case.
p := s.Prog(wasm.ACall)
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: gc.WasmDiv}
break
}
s.Prog(wasm.AI64DivS)
case ssa.OpWasmI64TruncSatF32S, ssa.OpWasmI64TruncSatF64S:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
if objabi.GOWASM.SatConv {
s.Prog(v.Op.Asm())
} else {
if v.Op == ssa.OpWasmI64TruncSatF32S {
s.Prog(wasm.AF64PromoteF32)
}
p := s.Prog(wasm.ACall)
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: gc.WasmTruncS}
}
case ssa.OpWasmI64TruncSatF32U, ssa.OpWasmI64TruncSatF64U:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
if objabi.GOWASM.SatConv {
s.Prog(v.Op.Asm())
} else {
if v.Op == ssa.OpWasmI64TruncSatF32U {
s.Prog(wasm.AF64PromoteF32)
}
p := s.Prog(wasm.ACall)
p.To = obj.Addr{Type: obj.TYPE_MEM, Name: obj.NAME_EXTERN, Sym: gc.WasmTruncU}
}
case ssa.OpWasmF32DemoteF64:
getValue64(s, v.Args[0])
s.Prog(v.Op.Asm())
case ssa.OpWasmF64PromoteF32:
getValue64(s, v.Args[0])
s.Prog(v.Op.Asm())
case ssa.OpWasmF32ConvertI64S, ssa.OpWasmF32ConvertI64U,
ssa.OpWasmF64ConvertI64S, ssa.OpWasmF64ConvertI64U,
ssa.OpWasmI64Extend8S, ssa.OpWasmI64Extend16S, ssa.OpWasmI64Extend32S,
ssa.OpWasmF32Neg, ssa.OpWasmF32Sqrt, ssa.OpWasmF32Trunc, ssa.OpWasmF32Ceil, ssa.OpWasmF32Floor, ssa.OpWasmF32Nearest, ssa.OpWasmF32Abs,
ssa.OpWasmF64Neg, ssa.OpWasmF64Sqrt, ssa.OpWasmF64Trunc, ssa.OpWasmF64Ceil, ssa.OpWasmF64Floor, ssa.OpWasmF64Nearest, ssa.OpWasmF64Abs,
ssa.OpWasmI64Ctz, ssa.OpWasmI64Clz, ssa.OpWasmI64Popcnt:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
s.Prog(v.Op.Asm())
case ssa.OpLoadReg:
p := s.Prog(loadOp(v.Type))
gc.AddrAuto(&p.From, v.Args[0])
case ssa.OpCopy:
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
getValue64(s, v.Args[0])
default:
v.Fatalf("unexpected op: %s", v.Op)
}
}
func isCmp(v *ssa.Value) bool {
switch v.Op {
case ssa.OpWasmI64Eqz, ssa.OpWasmI64Eq, ssa.OpWasmI64Ne, ssa.OpWasmI64LtS, ssa.OpWasmI64LtU, ssa.OpWasmI64GtS, ssa.OpWasmI64GtU, ssa.OpWasmI64LeS, ssa.OpWasmI64LeU, ssa.OpWasmI64GeS, ssa.OpWasmI64GeU,
ssa.OpWasmF32Eq, ssa.OpWasmF32Ne, ssa.OpWasmF32Lt, ssa.OpWasmF32Gt, ssa.OpWasmF32Le, ssa.OpWasmF32Ge,
ssa.OpWasmF64Eq, ssa.OpWasmF64Ne, ssa.OpWasmF64Lt, ssa.OpWasmF64Gt, ssa.OpWasmF64Le, ssa.OpWasmF64Ge:
return true
default:
return false
}
}
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
func getValue32(s *gc.SSAGenState, v *ssa.Value) {
if v.OnWasmStack {
s.OnWasmStackSkipped--
ssaGenValueOnStack(s, v, false)
if !isCmp(v) {
s.Prog(wasm.AI32WrapI64)
}
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
return
}
reg := v.Reg()
getReg(s, reg)
if reg != wasm.REG_SP {
s.Prog(wasm.AI32WrapI64)
}
}
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
func getValue64(s *gc.SSAGenState, v *ssa.Value) {
if v.OnWasmStack {
s.OnWasmStackSkipped--
ssaGenValueOnStack(s, v, true)
cmd/compile: add wasm stack optimization Go's SSA instructions only operate on registers. For example, an add instruction would read two registers, do the addition and then write to a register. WebAssembly's instructions, on the other hand, operate on the stack. The add instruction first pops two values from the stack, does the addition, then pushes the result to the stack. To fulfill Go's semantics, one needs to map Go's single add instruction to 4 WebAssembly instructions: - Push the value of local variable A to the stack - Push the value of local variable B to the stack - Do addition - Write value from stack to local variable C Now consider that B was set to the constant 42 before the addition: - Push constant 42 to the stack - Write value from stack to local variable B This works, but is inefficient. Instead, the stack is used directly by inlining instructions if possible. With inlining it becomes: - Push the value of local variable A to the stack (add) - Push constant 42 to the stack (constant) - Do addition (add) - Write value from stack to local variable C (add) Note that the two SSA instructions can not be generated sequentially anymore, because their WebAssembly instructions are interleaved. Design doc: https://docs.google.com/document/d/131vjr4DH6JFnb-blm_uRdaC0_Nv3OUwjEY5qVCxCup4 Updates #18892 Change-Id: Ie35e1c0bebf4985fddda0d6330eb2066f9ad6dec Reviewed-on: https://go-review.googlesource.com/103535 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2018-03-09 00:14:58 +01:00
return
}
reg := v.Reg()
getReg(s, reg)
if reg == wasm.REG_SP {
s.Prog(wasm.AI64ExtendI32U)
}
}
func i32Const(s *gc.SSAGenState, val int32) {
p := s.Prog(wasm.AI32Const)
p.From = obj.Addr{Type: obj.TYPE_CONST, Offset: int64(val)}
}
func i64Const(s *gc.SSAGenState, val int64) {
p := s.Prog(wasm.AI64Const)
p.From = obj.Addr{Type: obj.TYPE_CONST, Offset: val}
}
func f32Const(s *gc.SSAGenState, val float64) {
p := s.Prog(wasm.AF32Const)
p.From = obj.Addr{Type: obj.TYPE_FCONST, Val: val}
}
func f64Const(s *gc.SSAGenState, val float64) {
p := s.Prog(wasm.AF64Const)
p.From = obj.Addr{Type: obj.TYPE_FCONST, Val: val}
}
func getReg(s *gc.SSAGenState, reg int16) {
p := s.Prog(wasm.AGet)
p.From = obj.Addr{Type: obj.TYPE_REG, Reg: reg}
}
func setReg(s *gc.SSAGenState, reg int16) {
p := s.Prog(wasm.ASet)
p.To = obj.Addr{Type: obj.TYPE_REG, Reg: reg}
}
func loadOp(t *types.Type) obj.As {
if t.IsFloat() {
switch t.Size() {
case 4:
return wasm.AF32Load
case 8:
return wasm.AF64Load
default:
panic("bad load type")
}
}
switch t.Size() {
case 1:
if t.IsSigned() {
return wasm.AI64Load8S
}
return wasm.AI64Load8U
case 2:
if t.IsSigned() {
return wasm.AI64Load16S
}
return wasm.AI64Load16U
case 4:
if t.IsSigned() {
return wasm.AI64Load32S
}
return wasm.AI64Load32U
case 8:
return wasm.AI64Load
default:
panic("bad load type")
}
}
func storeOp(t *types.Type) obj.As {
if t.IsFloat() {
switch t.Size() {
case 4:
return wasm.AF32Store
case 8:
return wasm.AF64Store
default:
panic("bad store type")
}
}
switch t.Size() {
case 1:
return wasm.AI64Store8
case 2:
return wasm.AI64Store16
case 4:
return wasm.AI64Store32
case 8:
return wasm.AI64Store
default:
panic("bad store type")
}
}